Search results for: forecasting

Authors: Giovanni Masala, Stefania Marica

Abstract:

Forecasting electricity load plays a crucial role regards decision making and planning for economical purposes. Besides, in the light of the recent privatization and deregulation of the power industry, the forecasting of future electricity load turned out to be a very challenging problem. Empirical data about electricity load highlights a clear seasonal behavior (higher load during the winter season), which is partly due to climatic effects. We also emphasize the presence of load periodicity at a weekly basis (electricity load is usually lower on weekends or holidays) and at daily basis (electricity load is clearly influenced by the hour). Finally, a long-term trend may depend on the general economic situation (for example, industrial production affects electricity load). All these features must be captured by the model. The purpose of this paper is then to build an hourly electricity load model. The deterministic component of the model requires non-linear regression and Fourier series while we will investigate the stochastic component through econometrical tools. The calibration of the parameters’ model will be performed by using data coming from the Italian market in a 6 year period (2007- 2012). Then, we will perform a Monte Carlo simulation in order to compare the simulated data respect to the real data (both in-sample and out-of-sample inspection). The reliability of the model will be deduced thanks to standard tests which highlight a good fitting of the simulated values.

Keywords: ARMA-GARCH process, electricity load, fitting tests, Fourier series, Monte Carlo simulation, non-linear regression

Procedia PDF Downloads 369

Authors: E. A. Krasikov

Abstract:

Dependence of the materials properties on neutron irradiation intensity (flux) is a key problem while usage data of the accelerated materials irradiation in test reactors for forecasting of their capacity for work in realistic (practical) circumstances of operation. Investigations of the reactor pressure vessel steel radiation degradation dependence on fast neutron fluence (embrittlement kinetics) at low flux reveal the instability in the form of the scatter of the experimental data and wave-like sections of embrittlement kinetics appearance. Disclosure of the steel degradation oscillating is a sign of the steel structure cyclic self-recovery transformation as it take place in self-organization processes. This assumption has received support through the discovery of the similar ‘anomalous’ data in scientific publications and by means of own additional experiments. Data obtained stimulate looking-for ways to management of the structural steel radiation stability (for example, by means of nano - structure modification for radiation defects annihilation intensification) for creation of the intelligent self-recovering material. Expected results: - radiation degradation theory and mechanisms development, - more adequate models of the radiation embrittlement elaboration, - surveillance specimen programs improvement, - methods and facility development for usage data of the accelerated materials irradiation for forecasting of their capacity for work in realistic (practical) circumstances of operation, - search of the ways for creating of the radiation stable self-recovery intelligent materials.

Keywords: degradation, radiation, steel, wave-like kinetics

Procedia PDF Downloads 278

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 41

Authors: Lukas Reznak, Maria Reznakova

Abstract:

Recession of an economy has a profound negative effect on all involved stakeholders. It follows that timely prediction of recessions has been of utmost interest both in the theoretical research and in practical macroeconomic modelling. Current mainstream of recession prediction is based on standard OLS models of continuous GDP using macroeconomic data. This approach is not suitable for two reasons: the standard continuous models are proving to be obsolete and the macroeconomic data are unreliable, often revised many years retroactively. The aim of the paper is to explore a different branch of recession forecasting research theory and verify the findings on real data of the Czech Republic and Germany. In the paper, the authors present a family of discrete choice probit models with parameters estimated by the method of maximum likelihood. In the basic form, the probits model a univariate series of recessions and expansions in the economic cycle for a given country. The majority of the paper deals with more complex model structures, namely dynamic and bivariate extensions. The dynamic structure models the autoregressive nature of recessions, taking into consideration previous economic activity to predict the development in subsequent periods. Bivariate extensions utilize information from a foreign economy by incorporating correlation of error terms and thus modelling the dependencies of the two countries. Bivariate models predict a bivariate time series of economic states in both economies and thus enhance the predictive performance. A vital enabler of timely and successful recession forecasting are reliable and readily available data. Leading indicators, namely the yield curve and the stock market indices, represent an ideal data base, as the pieces of information is available in advance and do not undergo any retroactive revisions. As importantly, the combination of yield curve and stock market indices reflect a range of macroeconomic and financial market investors’ trends which influence the economic cycle. These theoretical approaches are applied on real data of Czech Republic and Germany. Two models for each country were identified – each for in-sample and out-of-sample predictive purposes. All four followed a bivariate structure, while three contained a dynamic component.

Keywords: bivariate probit, leading indicators, recession forecasting, Czech Republic, Germany

Procedia PDF Downloads 225

Authors: Thabo M. Bafitlhile, Adewole Oladele

Abstract:

Botswana has been affected by floods since long ago and is still experiencing this tragic event. Flooding occurs mostly in the North-West, North-East, and parts of Central district due to heavy rainfalls experienced in these areas. The torrential rains destroyed homes, roads, flooded dams, fields and destroyed livestock and livelihoods. Palapye is one area in the central district that has been experiencing floods ever since 1995 when its greatest flood on record occurred. Heavy storms result in floods and inundation; this has been exacerbated by poor and absence of drainage structures. Since floods are a part of nature, they have existed and will to continue to exist, hence more destruction. Furthermore floods and highway plays major role in erosion and destruction of roads structures. Already today, many culverts, trenches, and other drainage facilities lack the capacity to deal with current frequency for extreme flows. Future changes in the pattern of hydro climatic events will have implications for the design and maintenance costs of roads. Increase in rainfall and severe weather events can affect the demand for emergent responses. Therefore flood forecasting and warning is a prerequisite for successful mitigation of flood damage. In flood prone areas like Palapye, preventive measures should be taken to reduce possible adverse effects of floods on the environment including road structures. Therefore this paper attempts to estimate return periods associated with huge storms of different magnitude from recorded historical rainfall depth using statistical method. The method of annual maxima was used to select data sets for the rainfall analysis. In the statistical method, the Type 1 extreme value (Gumbel), Log Normal, Log Pearson 3 distributions were all applied to the annual maximum series for Palapye area to produce IDF curves. The Kolmogorov-Smirnov test and Chi Squared were used to confirm the appropriateness of fitted distributions for the location and the data do fit the distributions used to predict expected frequencies. This will be a beneficial tool for urgent flood forecasting and water resource administration as proper drainage design will be design based on the estimated flood events and will help to reclaim and protect the road structures from adverse impacts of flood.

Keywords: drainage, estimate, evaluation, floods, flood forecasting

Procedia PDF Downloads 333

Authors: V. Jagadeesh, K. Venkata Subbaiah, P. Govinda Rao

Abstract:

This paper explaining about the significance of information technology tools and software packages in supply chain management (SCM) in order to manage the entire supply chain. Managing materials flow and financial flow and information flow effectively and efficiently with the aid of information technology tools and packages in order to deliver right quantity with right quality of goods at right time by using right methods and technology. Information technology plays a vital role in streamlining the sales forecasting and demand planning and Inventory control and transportation in supply networks and finally deals with production planning and scheduling. It achieves the objectives by streamlining the business process and integrates within the enterprise and its extended enterprise. SCM starts with customer and it involves sequence of activities from customer, retailer, distributor, manufacturer and supplier within the supply chain framework. It is the process of integrating demand planning and supply network planning and production planning and control. Forecasting indicates the direction for planning raw materials in order to meet the production planning requirements. Inventory control and transportation planning allocate the optimal or economic order quantity by utilizing shortest possible routes to deliver the goods to the customer. Production planning and control utilize the optimal resources mix in order to meet the capacity requirement planning. The above operations can be achieved by using appropriate information technology tools and software packages for the supply chain management.

Keywords: supply chain management, information technology, business process, extended enterprise

Procedia PDF Downloads 336

Authors: M. Zayoud, S. Oueida, S. Ionescu, P. AbiChar

Abstract:

Background: Wireless sensor network is encompassed of diversified tools of information technology, which is widely applied in a range of domains, including military surveillance, weather forecasting, and earthquake forecasting. Strengthened grounds are always developed for wireless sensor networks, which usually emerges security issues during professional application. Thus, essential technological tools are necessary to be assessed for secure aggregation of data. Moreover, such practices have to be incorporated in the healthcare practices that shall be serving in the best of the mutual interest Objective: Aggregation of encrypted data has been assessed through homomorphic stream cipher to assure its effectiveness along with providing the optimum solutions to the field of healthcare. Methods: An experimental design has been incorporated, which utilized newly developed cipher along with CPU-constrained devices. Modular additions have also been employed to evaluate the nature of aggregated data. The processes of homomorphic stream cipher have been highlighted through different sensors and modular additions. Results: Homomorphic stream cipher has been recognized as simple and secure process, which has allowed efficient aggregation of encrypted data. In addition, the application has led its way to the improvisation of the healthcare practices. Statistical values can be easily computed through the aggregation on the basis of selected cipher. Sensed data in accordance with variance, mean, and standard deviation has also been computed through the selected tool. Conclusion: It can be concluded that homomorphic stream cipher can be an ideal tool for appropriate aggregation of data. Alongside, it shall also provide the best solutions to the healthcare sector.

Keywords: aggregation, cipher, homomorphic stream, encryption

Procedia PDF Downloads 220

Authors: Jacky Liu, Dulani Jayasuriya, Ryan Elmore

Abstract:

Match fixing and anomalous sports events have increasingly threatened the integrity of professional sports, prompting concerns about existing detection methods. This study addresses prior research limitations in match fixing detection, improving the identification of potential fraudulent matches by incorporating advanced anomaly detection techniques. We develop a novel method to identify anomalous matches and player performances by examining series of matches, such as playoffs. Additionally, we investigate bettors' potential profits when avoiding anomaly matches and explore factors behind unusual player performances. Our literature review covers match fixing detection, match outcome forecasting models, and anomaly detection methods, underscoring current limitations and proposing a new sports anomaly detection method. Our findings reveal anomalous series in the 2022 NBA playoffs, with the Phoenix Suns vs Dallas Mavericks series having the lowest natural occurrence probability. We identify abnormal player performances and bettors' profits significantly decrease when post-season matches are included. This study contributes by developing a new approach to detect anomalous matches and player performances, and assisting investigators in identifying responsible parties. While we cannot conclusively establish reasons behind unusual player performances, our findings suggest factors such as team financial difficulties, executive mismanagement, and individual player contract issues.

Keywords: anomaly match detection, match fixing, match outcome forecasting, problematic players identification

Procedia PDF Downloads 49

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 74

Authors: Hui Hsin Huang

Abstract:

The downstream manufactures will order their materials from different upstream suppliers to maintain a certain level of the demand. This paper proposes a bivariate model to portray this phenomenon of material demand. We use empirical data to estimate the parameters of model and evaluate the RMSD of model calibration. The results show that the model has better fitness.

Keywords: recency, ordering time, materials demand quantity, multi-source ordering

Procedia PDF Downloads 501

Authors: Vahid Nourani, Atefeh Ashrafi

Abstract:

Prediction of treated wastewater quality is a matter of growing importance in water treatment procedure. In this way artificial neural network (ANN), as a robust data-driven approach, has been widely used for forecasting the effluent quality of wastewater treatment. However, developing ANN model based on appropriate input variables is a major concern due to the numerous parameters which are collected from treatment process and the number of them are increasing in the light of electronic sensors development. Various studies have been conducted, using different clustering methods, in order to classify most related and effective input variables. This issue has been overlooked in the selecting dominant input variables among wastewater treatment parameters which could effectively lead to more accurate prediction of water quality. In the presented study two ANN models were developed with the aim of forecasting effluent quality of Tabriz city’s wastewater treatment plant. Biochemical oxygen demand (BOD) was utilized to determine water quality as a target parameter. Model A used Principal Component Analysis (PCA) for input selection as a linear variance-based clustering method. Model B used those variables identified by the mutual information (MI) measure. Therefore, the optimal ANN structure when the result of model B compared with model A showed up to 15% percent increment in Determination Coefficient (DC). Thus, this study highlights the advantage of PCA method in selecting dominant input variables for ANN modeling of wastewater plant efficiency performance.

Keywords: Artificial Neural Networks, biochemical oxygen demand, principal component analysis, mutual information, Tabriz wastewater treatment plant, wastewater treatment plant

Procedia PDF Downloads 95

Authors: V. Churkin, M. Lopatin

Abstract:

The purpose of the paper is to estimate the US small wind turbines market potential and forecast the small wind turbines sales in the US. The forecasting method is based on the application of the Bass model and the generalized Bass model of innovations diffusion under replacement purchases. In the work an exponential distribution is used for modeling of replacement purchases. Only one parameter of such distribution is determined by average lifetime of small wind turbines. The identification of the model parameters is based on nonlinear regression analysis on the basis of the annual sales statistics which has been published by the American Wind Energy Association (AWEA) since 2001 up to 2012. The estimation of the US average market potential of small wind turbines (for adoption purchases) without account of price changes is 57080 (confidence interval from 49294 to 64866 at P = 0.95) under average lifetime of wind turbines 15 years, and 62402 (confidence interval from 54154 to 70648 at P = 0.95) under average lifetime of wind turbines 20 years. In the first case the explained variance is 90,7%, while in the second - 91,8%. The effect of the wind turbines price changes on their sales was estimated using generalized Bass model. This required a price forecast. To do this, the polynomial regression function, which is based on the Berkeley Lab statistics, was used. The estimation of the US average market potential of small wind turbines (for adoption purchases) in that case is 42542 (confidence interval from 32863 to 52221 at P = 0.95) under average lifetime of wind turbines 15 years, and 47426 (confidence interval from 36092 to 58760 at P = 0.95) under average lifetime of wind turbines 20 years. In the first case the explained variance is 95,3%, while in the second –95,3%.

Keywords: bass model, generalized bass model, replacement purchases, sales forecasting of innovations, statistics of sales of small wind turbines in the United States

Procedia PDF Downloads 322

Authors: M. Mulumpwa, W. W. L. Jere, M. Lazaro, A. H. N. Mtethiwa

Abstract:

The study considered Seasonal Autoregressive Integrated Moving Average (SARIMA) processes to select an appropriate stochastic model to forecast the monthly data from the Lake Malawi water levels for the period 1986 through 2015. The appropriate model was chosen based on SARIMA (p, d, q) (P, D, Q)S. The Autocorrelation function (ACF), Partial autocorrelation (PACF), Akaike Information Criteria (AIC), Bayesian Information Criterion (BIC), Box–Ljung statistics, correlogram and distribution of residual errors were estimated. The SARIMA (1, 1, 0) (1, 1, 1)12 was selected to forecast the monthly data of the Lake Malawi water levels from August, 2015 to December, 2021. The plotted time series showed that the Lake Malawi water levels are decreasing since 2010 to date but not as much as was the case in 1995 through 1997. The future forecast of the Lake Malawi water levels until 2021 showed a mean of 474.47 m ranging from 473.93 to 475.02 meters with a confidence interval of 80% and 90% against registered mean of 473.398 m in 1997 and 475.475 m in 1989 which was the lowest and highest water levels in the lake respectively since 1986. The forecast also showed that the water levels of Lake Malawi will drop by 0.57 meters as compared to the mean water levels recorded in the previous years. These results suggest that the Lake Malawi water level may not likely go lower than that recorded in 1997. Therefore, utilisation and management of water-related activities and programs among others on the lake should provide room for such scenarios. The findings suggest a need to manage the Lake Malawi jointly and prudently with other stakeholders starting from the catchment area. This will reduce impacts of anthropogenic activities on the lake’s water quality, water level, aquatic and adjacent terrestrial ecosystems thereby ensuring its resilience to climate change impacts.

Keywords: forecasting, Lake Malawi, water levels, water level fluctuation, climate change, anthropogenic activities

Procedia PDF Downloads 195

Authors: S. Chuenchooklin, S. Taweepong, U. Pangnakorn

Abstract:

This research was conducted in the Mae Sot Watershed whereas located in the Moei River Basin at the Upper Salween River Basin in Tak Province, Thailand. The Mae Sot Municipality is the largest urbanized in Tak Province and situated in the midstream of the Mae Sot Watershed. It usually faces flash flood problem after heavy rain due to poor flood management has been reported since economic rapidly bloom up in recently years. Its catchment can be classified as ungauged basin with lack of rainfall data and no any stream gaging station was reported. It was attached by most severely flood event in 2013 as the worst studied case for those all communities in this municipality. Moreover, other problems are also faced in this watershed such shortage water supply for domestic consumption and agriculture utilizations including deterioration of water quality and landslide as well. The research aimed to increase capability building and strengthening the participation of those local community leaders and related agencies to conduct better water management in urban area was started by mean of the data collection and illustration of appropriated application of some short period rainfall forecasting model as the aim for better flood relief plan and management through the hydrologic model system and river analysis system programs. The authors intended to apply the global rainfall data via the integrated data viewer (IDV) program from the Unidata with the aim for rainfall forecasting in short period of 7 - 10 days in advance during rainy season instead of real time record. The IDV product can be present in advance period of rainfall with time step of 3 - 6 hours was introduced to the communities. The result can be used to input to either the hydrologic modeling system model (HEC-HMS) or the soil water assessment tool model (SWAT) for synthesizing flood hydrographs and use for flood forecasting as well. The authors applied the river analysis system model (HEC-RAS) to present flood flow behaviors in the reach of the Mae Sot stream via the downtown of the Mae Sot City as flood extents as water surface level at every cross-sectional profiles of the stream. Both models of HMS and RAS were tested in 2013 with observed rainfall and inflow-outflow data from the Mae Sot Dam. The result of HMS showed fit to the observed data at dam and applied at upstream boundary discharge to RAS in order to simulate flood extents and tested in the field, and the result found satisfied. The result of IDV’s rainfall forecast data was compared to observed data and found fair. However, it is an appropriate tool to use in the ungauged catchment to use with flood hydrograph and river analysis models for future efficient flood relief plan and management.

Keywords: global rainfall, flood forecast, hydrologic modeling system, river analysis system

Procedia PDF Downloads 317

Authors: Redvan Ghasemlounia, Elham Ansari, Hikmet Kerem Cigizoglu

Abstract:

Hydrological modeling in arid and semi-arid regions is very important. Iran has many regions with these climate conditions such as Chaharmahal and Bakhtiari province that needs lots of attention with an appropriate management. Forecasting of hydrological parameters and estimation of hydrological events of catchments, provide important information that used for design, management and operation of water resources such as river systems, and dams, widely. Discharge in rivers is one of these parameters. This study presents the application and comparison of some estimation methods such as Feed-Forward Back Propagation Neural Network (FFBPNN), Multi Linear Regression (MLR), Gene Expression Programming (GEP) and Bayesian Network (BN) to predict the daily flow discharge of the Soolegan River, located at Chaharmahal and Bakhtiari province, in Iran. In this study, Soolegan, station was considered. This Station is located in Soolegan River at 51° 14՜ Latitude 31° 38՜ longitude at North Karoon basin. The Soolegan station is 2086 meters higher than sea level. The data used in this study are daily discharge and daily precipitation of Soolegan station. Feed Forward Back Propagation Neural Network(FFBPNN), Multi Linear Regression (MLR), Gene Expression Programming (GEP) and Bayesian Network (BN) models were developed using the same input parameters for Soolegan's daily discharge estimation. The results of estimation models were compared with observed discharge values to evaluate performance of the developed models. Results of all methods were compared and shown in tables and charts.

Keywords: ANN, multi linear regression, Bayesian network, forecasting, discharge, gene expression programming

Procedia PDF Downloads 529

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 113

Authors: Dmytro Zubov, Francesco Volponi

Abstract:

In this paper, D-Wave quantum computing Ising model is used for the forecasting of positive extremes of daily mean air temperature. Forecast models are designed with two to five qubits, which represent 2-, 3-, 4-, and 5-day historical data respectively. Ising model’s real-valued weights and dimensionless coefficients are calculated using daily mean air temperatures from 119 places around the world, as well as sea level (Aburatsu, Japan). In comparison with current methods, this approach is better suited to predict heat wave values because it does not require the estimation of a probability distribution from scarce observations. Proposed forecast quantum computing algorithm is simulated based on traditional computer architecture and combinatorial optimization of Ising model parameters for the Ronald Reagan Washington National Airport dataset with 1-day lead-time on learning sample (1975-2010 yr). Analysis of the forecast accuracy (ratio of successful predictions to total number of predictions) on the validation sample (2011-2014 yr) shows that Ising model with three qubits has 100 % accuracy, which is quite significant as compared to other methods. However, number of identified heat waves is small (only one out of nineteen in this case). Other models with 2, 4, and 5 qubits have 20 %, 3.8 %, and 3.8 % accuracy respectively. Presented three-qubit forecast model is applied for prediction of heat waves at other five locations: Aurel Vlaicu, Romania – accuracy is 28.6 %; Bratislava, Slovakia – accuracy is 21.7 %; Brussels, Belgium – accuracy is 33.3 %; Sofia, Bulgaria – accuracy is 50 %; Akhisar, Turkey – accuracy is 21.4 %. These predictions are not ideal, but not zeros. They can be used independently or together with other predictions generated by different method(s). The loss of human life, as well as environmental, economic, and material damage, from extreme air temperatures could be reduced if some of heat waves are predicted. Even a small success rate implies a large socio-economic benefit.

Keywords: heat wave, D-wave, forecast, Ising model, quantum computing

Procedia PDF Downloads 463

Authors: Jonathan J. Burson

Abstract:

With the rise of virtually costless, mobile-based trading platforms, stock market trading activity has increased significantly over the past decade, particularly for the millennial generation. This increased stock market attention, combined with the recent market turmoil due to the economic upset caused by COVID-19, make the topics of market-timing and forecasting particularly relevant. While the overall stock market saw an unprecedented, historically-long bull market from March 2009 to February 2020, the end of that bull market reignited a search by investors for a way to reduce risk and increase return. Similar searches for outperformance occurred in the early, and late 2000’s as the Dotcom bubble burst and the Great Recession led to years of negative returns for mean-variance, index investors. Extensive research has been conducted on fundamental analysis, technical analysis, macroeconomic indicators, microeconomic indicators, and other techniques—all using different methodologies and investment periods—in pursuit of higher returns with lower risk. The enormous variety of timeframes, data, and methodologies used by the diverse forecasting methods makes it difficult to compare the outcome of each method directly to other methods. This paper establishes a process to evaluate the market-timing methods in an apples-to-apples manner based on simplicity, performance, and feasibility. Preliminary findings show that certain technical analysis models provide a higher return with lower risk when compared to the buy-and-hold method and to other market-timing strategies. Furthermore, technical analysis models tend to be easier for individual investors both in terms of acquiring the data and in analyzing it, making technical analysis-based market-timing methods the preferred choice for retail investors.

Keywords: buy-and-hold, forecast, market-timing, probit, technical analysis

Procedia PDF Downloads 66

Authors: Anucha Wittayakorn-Puripunpinyoo

Abstract:

The research objectives were 1) to study the situation and its trend of agricultural product export of Thailand 2) to study the impact of agricultural product export on income of Thai economy 3) the impact of agricultural product export on employment of Thai economy and 4) to find out the recommendations of agricultural product export policy of Thailand. In this research, secondary data were collected as yearly time series data from 1990 to 2016 accounted for 27 years. Data were collected from the Bank of Thailand database. Primary data were collected from the steakholders of agricultural product export policy of Thailand. Data analysis was applied descriptive statistics such as arithmetic mean, standard deviation. The forecasting of agricultural product was applied Mote Carlo Simulation technique as well as time trend analysis. In addition, the impact of agricultural product export on income and employment by applying econometric model while the estimated parameters were utilized the ordinary least square technique. The research results revealed that 1) agricultural product export value of Thailand from 1990 to 2016 was 338,959.5 Million Thai baht with its growth rate of 4.984 percent yearly, in addition, the forecasting of agricultural product export value of Thailand has increased but its growth rate has been declined 2) the impact of agricultural product export has positive impact on income in Thai economy, increasing in agricultural product export of Thailand by 1 percent would lead income increased by 0.0051 percent 3) the impact of agricultural product export has positive impact on employment in Thai economy, increasing in agricultural product export of Thailand by 1 percent would lead income increased by 0.079 percent and 4) in the future, agricultural product export policy would focused on finished or semi-finished agricultural product instead of raw material by applying technology and innovation in to make value added of agricultural product export. The public agricultural product export policy would support exporters in private sector in order to encourage them as agricultural exporters in Thailand.

Keywords: agricultural product export, income, employment, Thai economy

Procedia PDF Downloads 269

Authors: Bryan Low

Abstract:

In the coming decades, the global maritime industry will face a most formidable environmental challenge -achieving net zero carbon emissions by 2050. To meet this target, the Maritime Port Authority of Singapore (MPA) has worked to establish green shipping and digital corridors with ports of several other countries around the world where ships will use low-carbon alternative fuels such as ammonia for power generation. While this paradigm shift to the bunkering of greener fuels is encouraging, fuels like ammonia will also introduce a new and unique type of environmental risk in the unlikely scenario of a spill. While numerous modelling studies have been conducted for oil spills and their associated environmental impact on coastal and marine ecosystems, ammonia spills are comparatively less well understood. For example, there is a knowledge gap regarding how the complex hydrodynamic conditions of the Singapore Straits may influence the dispersion of a hypothetical ammonia plume, which has different physical and chemical properties compared to an oil slick. Chemically, ammonia can be absorbed by phytoplankton, thus altering the balance of the marine nitrogen cycle. Biologically, ammonia generally serves the role of a nutrient in coastal ecosystems at lower concentrations. However, at higher concentrations, it has been found to be toxic to many local species. It may also have the potential to trigger eutrophication and harmful algal blooms (HABs) in coastal waters, depending on local hydrodynamic conditions. Thus, the key objective of this research paper is to support the development of a model-based forecasting system that can predict ammonia plume behaviour in coastal waters, given prevailing hydrodynamic conditions and their environmental impact. This will be essential as ammonia bunkering becomes more commonplace in Singapore’s ports and around the world. Specifically, this system must be able to assess the HAB-triggering potential of an ammonia plume, as well as its lethal and sub-lethal toxic effects on local species. This will allow the relevant authorities to better plan risk mitigation measures or choose a time window with the ideal hydrodynamic conditions to conduct ammonia bunkering operations with minimal risk. In this paper, we present the first part of such a forecasting system: a jointly coupled hydrodynamic-water quality model that can capture how advection-diffusion processes driven by ocean currents influence plume behaviour and how the plume interacts with the marine nitrogen cycle. The model is then applied to various ammonia spill scenarios where the results are discussed in the context of current ammonia toxicity guidelines, impact on local ecosystems, and mitigation measures for future bunkering operations conducted in the Singapore Straits.

Keywords: ammonia bunkering, forecasting, harmful algal blooms, hydrodynamics, marine nitrogen cycle, oceanography, water quality modeling

Procedia PDF Downloads 35

Authors: Manish Pandey, Gurinderjit Kaur, Meenu Talwar, Sachin Chauhan, Jagbir Gill

Abstract:

Health-care management systems are a unit of nice connection as a result of the supply a straightforward and fast management of all aspects relating to a patient, not essentially medical. What is more, there are unit additional and additional cases of pathologies during which diagnosing and treatment may be solely allotted by victimization medical imaging techniques. With associate ever-increasing prevalence, medical pictures area unit directly acquired in or regenerate into digital type, for his or her storage additionally as sequent retrieval and process. Data Mining is the process of extracting information from large data sets through using algorithms and Techniques drawn from the field of Statistics, Machine Learning and Data Base Management Systems. Forecasting may be a prediction of what's going to occur within the future, associated it's an unsure method. Owing to the uncertainty, the accuracy of a forecast is as vital because the outcome foretold by foretelling the freelance variables. A forecast management should be wont to establish if the accuracy of the forecast is within satisfactory limits. Fuzzy regression strategies have normally been wont to develop shopper preferences models that correlate the engineering characteristics with shopper preferences relating to a replacement product; the patron preference models offer a platform, wherever by product developers will decide the engineering characteristics so as to satisfy shopper preferences before developing the merchandise. Recent analysis shows that these fuzzy regression strategies area units normally will not to model client preferences. We tend to propose a Testing the strength of Exponential Regression Model over regression toward the mean Model.

Keywords: health-care management systems, fuzzy regression, data mining, forecasting, fuzzy membership function

Procedia PDF Downloads 249

Authors: Amel Oueslati, Olfa Benouda

Abstract:

New Value at Risk (VaR) estimation is proposed and investigated. The well-known two stages Garch-EVT approach uses conditional volatility to generate one step ahead forecasts of VaR. With daily data for twelve stocks that decompose the Dow Jones Industrial Average (DJIA) index, this paper incorporates the volume in the first stage volatility estimation. Afterwards, the forecasting ability of this conditional volatility concerning the VaR estimation is compared to that of a basic volatility model without considering any trading component. The results are significant and bring out the importance of the trading volume in the VaR measure.

Keywords: Garch-EVT, value at risk, volume, volatility

Procedia PDF Downloads 251

Authors: Elena Collino, Dario A. Ronzio, Goffredo Decimi, Maurizio Riva

Abstract:

The rapid increase of renewable energy in Italy is led by wind and solar installations. The 2017 Italian energy strategy foresees a further development of these sustainable technologies, especially solar. This fact has resulted in new opportunities, challenges, and different problems to deal with. The growth of renewables allows to meet the European requirements regarding energy and environmental policy, but these types of sources are difficult to manage because they are intermittent and non-programmable. Operationally, these characteristics can lead to instability on the voltage profile and increasing uncertainty on energy reserve scheduling. The increasing renewable production must be considered with more and more attention especially by the Transmission System Operator (TSO). The TSO, in fact, every day provides orders on energy dispatch, once the market outcome has been determined, on extended areas, defined mainly on the basis of power transmission limitations. In Italy, six market zone are defined: Northern-Italy, Central-Northern Italy, Central-Southern Italy, Southern Italy, Sardinia, and Sicily. An accurate hourly renewable power forecasting for the day-ahead on these extended areas brings an improvement both in terms of dispatching and reserve management. In this study, an operational forecasting tool of the hourly solar output for the six Italian market zones is presented, and the performance is analysed. The implementation is carried out by means of a numerical weather prediction model, coupled with a statistical post-processing in order to derive the power forecast on the basis of the meteorological projection. The weather forecast is obtained from the limited area model RAMS on the Italian territory, initialized with IFS-ECMWF boundary conditions. The post-processing calculates the solar power production with the Analog Ensemble technique (AN). This statistical approach forecasts the production using a probability distribution of the measured production registered in the past when the weather scenario looked very similar to the forecasted one. The similarity is evaluated for the components of the solar radiation: global (GHI), diffuse (DIF) and direct normal (DNI) irradiation, together with the corresponding azimuth and zenith solar angles. These are, in fact, the main factors that affect the solar production. Considering that the AN performance is strictly related to the length and quality of the historical data a training period of more than one year has been used. The training set is made by historical Numerical Weather Prediction (NWP) forecasts at 12 UTC for the GHI, DIF and DNI variables over the Italian territory together with corresponding hourly measured production for each of the six zones. The AN technique makes it possible to estimate the aggregate solar production in the area, without information about the technologic characteristics of the all solar parks present in each area. Besides, this information is often only partially available. Every day, the hourly solar power forecast for the six Italian market zones is made publicly available through a website.

Keywords: analog ensemble, electricity market, PV forecast, solar energy

Procedia PDF Downloads 123

Authors: Muhammad Ahnaf Zahin, Yaw Adu-Gyamfi

Abstract:

Bus transit is a crucial component of transportation networks, especially in urban areas. Any intelligent transportation system must have accurate real-time information on bus travel times since it minimizes waiting times for passengers at different stations along a route, improves service reliability, and significantly optimizes travel patterns. Bus agencies must enhance the quality of their information service to serve their passengers better and draw in more travelers since people waiting at bus stops are frequently anxious about when the bus will arrive at their starting point and when it will reach their destination. For solving this issue, different models have been developed for predicting bus travel times recently, but most of them are focused on smaller road networks due to their relatively subpar performance in high-density urban areas on a vast network. This paper develops a deep learning-based architecture using a single-step multi-station forecasting approach to predict average bus travel times for numerous routes, stops, and trips on a large-scale network using heterogeneous bus transit data collected from the GTFS database. Over one week, data was gathered from multiple bus routes in Saint Louis, Missouri. In this study, Gated Recurrent Unit (GRU) neural network was followed to predict the mean vehicle travel times for different hours of the day for multiple stations along multiple routes. Historical time steps and prediction horizon were set up to 5 and 1, respectively, which means that five hours of historical average travel time data were used to predict average travel time for the following hour. The spatial and temporal information and the historical average travel times were captured from the dataset for model input parameters. As adjacency matrices for the spatial input parameters, the station distances and sequence numbers were used, and the time of day (hour) was considered for the temporal inputs. Other inputs, including volatility information such as standard deviation and variance of journey durations, were also included in the model to make it more robust. The model's performance was evaluated based on a metric called mean absolute percentage error (MAPE). The observed prediction errors for various routes, trips, and stations remained consistent throughout the day. The results showed that the developed model could predict travel times more accurately during peak traffic hours, having a MAPE of around 14%, and performed less accurately during the latter part of the day. In the context of a complicated transportation network in high-density urban areas, the model showed its applicability for real-time travel time prediction of public transportation and ensured the high quality of the predictions generated by the model.

Keywords: gated recurrent unit, mean absolute percentage error, single-step forecasting, travel time prediction.

Procedia PDF Downloads 46

Authors: R. Premasiri, W. A. H. A. Abeygunasekara, S. M. Hewavidana, T. Jananthan, R. M. S. Madawala, K. Vaheeshan

Abstract:

Forecasting the potential for disastrous events such as landslides has become one of the major necessities in the current world. Most of all, the landslides occurred in Sri Lanka are found to be triggered mostly by intense rainfall events. The study area is the landslide near Gerandiella waterfall which is located by the 41st kilometer post on Nuwara Eliya-Gampala main road in Kotmale Division in Sri Lanka. The landslide endangers the entire Kotmale town beneath the slope. Geographic Information System (GIS) platform is very much useful when it comes to the need of emulating the real-world processes. The models are used in a wide array of applications ranging from simple evaluations to the levels of forecast future events. This project investigates the possibility of developing a dynamic model to map the spatial distribution of the slope stability. The model incorporates several theoretical models including the infinite slope model, Green Ampt infiltration model and Perched ground water flow model. A series of rainfall values can be fed to the model as the main input to simulate the dynamics of slope stability. Hydrological model developed using GIS is used to quantify the perched water table height, which is one of the most critical parameters affecting the slope stability. Infinite slope stability model is used to quantify the degree of slope stability in terms of factor of safety. DEM was built with the use of digitized contour data. Stratigraphy was modeled in Surfer using borehole data and resistivity images. Data available from rainfall gauges and piezometers were used in calibrating the model. During the calibration, the parameters were adjusted until a good fit between the simulated ground water levels and the piezometer readings was obtained. This model equipped with the predicted rainfall values can be used to forecast of the slope dynamics of the area of interest. Therefore it can be investigated the slope stability of rainfall induced landslides by adjusting temporal dimensions.

Keywords: factor of safety, geographic information system, hydrological model, slope stability

Procedia PDF Downloads 388

Authors: Jiun-Horng Tsai, Shi-Jie, Nieh

Abstract:

Fine particulate matter (PM₂.₅) has become an important issue all over the world over the last decade. Annual mean PM₂.₅ concentration has been over the ambient air quality standard of PM₂.₅ (annual average concentration as 15μg/m³) which adapted by Taiwan Environmental Protection Administration (TEPA). TEPA, therefore, has developed a number of air pollution control measures to improve the ambient concentration by reducing the emissions of primary fine particulate matter and the precursors of secondary PM₂.₅. This study investigated the potential improvement of ambient PM₂.₅ concentration by the TEPA program and the other scenario for further emission reduction on various sources. Four scenarios had been evaluated in this study, including a basic case and three reduction scenarios (A to C). The ambient PM₂.₅ concentration was evaluated by Community Multi-scale Air Quality modelling system (CMAQ) ver. 4.7.1 along with the Weather Research and Forecasting Model (WRF) ver. 3.4.1. The grid resolutions in the modelling work are 81 km × 81 km for domain 1 (covers East Asia), 27 km × 27 km for domain 2 (covers Southeast China and Taiwan), and 9 km × 9 km for domain 3 (covers Taiwan). The result of PM₂.₅ concentration simulation in different regions of Taiwan shows that the annual average concentration of basic case is 24.9 μg/m³, and are 22.6, 18.8, and 11.3 μg/m³, respectively, for scenarios A to C. The annual average concentration of PM₂.₅ would be reduced by 9-55 % for those control scenarios. The result of scenario C (the emissions of precursors reduce to allowance levels) could improve effectively the airborne PM₂.₅ concentration to attain the air quality standard. According to the results of unit precursor reduction contribution, the allowance emissions of PM₂.₅, SOₓ, and NOₓ are 16.8, 39, and 62 thousand tons per year, respectively. In the Kao-Ping air basin, the priority for reducing precursor emissions is PM₂.₅ > NOₓ > SOₓ, whereas the priority for reducing precursor emissions is PM₂.₅ > SOₓ > NOₓ in others area. The result indicates that the target pollutants that need to be reduced in different air basin are different, and the control measures need to be adapted to local conditions.

Keywords: airborne PM₂.₅, community multi-scale air quality modelling system, control measures, weather research and forecasting model

Procedia PDF Downloads 109

Authors: Yichao Liu, Peter Fransson, Julian Heidecke, Jonas Wallin, Joacim Rockloev

Abstract:

Dengue, a mosquito-borne viral disease, poses a significant public health challenge in endemic tropical or subtropical countries, including Sri Lanka. To reveal insights into the complexity of the dynamics of this disease and study the drivers, a comprehensive model capable of both robust forecasting and insightful inference of drivers while capturing the co-circulating of several virus strains is essential. However, existing studies mostly focus on only one aspect at a time and do not integrate and carry insights across the siloed approach. While mechanistic models are developed to capture immunity dynamics, they are often oversimplified and lack integration of all the diverse drivers of disease transmission. On the other hand, purely data-driven methods lack constraints imposed by immuno-epidemiological processes, making them prone to overfitting and inference bias. This research presents a hybrid model that combines machine learning techniques with mechanistic modelling to overcome the limitations of existing approaches. Leveraging eight years of newly reported dengue case data, along with socioeconomic factors, such as human mobility, weekly climate data from 2011 to 2018, genetic data detecting the introduction and presence of new strains, and estimates of seropositivity for different districts in Sri Lanka, we derive a data-driven vector (SEI) to human (SEIR) model across 16 regions in Sri Lanka at the weekly time scale. By conducting ablation studies, the lag effects allowing delays up to 12 weeks of time-varying climate factors were determined. The model demonstrates superior predictive performance over a pure machine learning approach when considering lead times of 5 and 10 weeks on data withheld from model fitting. It further reveals several interesting interpretable findings of drivers while adjusting for the dynamics and influences of immunity and introduction of a new strain. The study uncovers strong influences of socioeconomic variables: population density, mobility, household income and rural vs. urban population. The study reveals substantial sensitivity to the diurnal temperature range and precipitation, while mean temperature and humidity appear less important in the study location. Additionally, the model indicated sensitivity to vegetation index, both max and average. Predictions on testing data reveal high model accuracy. Overall, this study advances the knowledge of dengue transmission in Sri Lanka and demonstrates the importance of incorporating hybrid modelling techniques to use biologically informed model structures with flexible data-driven estimates of model parameters. The findings show the potential to both inference of drivers in situations of complex disease dynamics and robust forecasting models.

Keywords: compartmental model, climate, dengue, machine learning, social-economic

Procedia PDF Downloads 39

Authors: Jeonghwan Jeon, Mintak Han, Youngjun Kim

Abstract:

Due to the rapid development of information and communication technology (ICT), a substantial transformation is currently happening in the society. As the range of intelligent technologies and services is continuously expanding, ‘things’ are becoming capable of communicating one another and even with people. However, such “Internet of Things” has the technical weakness so that a great amount of such information transferred in real-time may be widely exposed to the threat of security. User’s personal data are a typical example which is faced with a serious security threat. The threats of security will be diversified and arose more frequently because next generation of unfamiliar technology develops. Moreover, as the society is becoming increasingly complex, security vulnerability will be increased as well. In the existing literature, a considerable number of private and public reports that forecast future society have been published as a precedent step of the selection of future technology and the establishment of strategies for competitiveness. Although there are previous studies that forecast security technology, they have focused only on technical issues and overlooked the interrelationships between security technology and social factors are. Therefore, investigations of security threats in the future and security technology that is able to protect people from various threats are required. In response, this study aims to derive potential security threats associated with the development of technology and to explore the security technology that can protect against them. To do this, first of all, private and public reports that forecast future and online documents from technology-related communities are collected. By analyzing the data, future issues are extracted and categorized in terms of STEEP (Society, Technology, Economy, Environment, and Politics), as well as security. Second, the components of potential security threats are developed based on classified future issues. Then, points that the security threats may occur –for example, mobile payment system based on a finger scan technology– are identified. Lastly, alternatives that prevent potential security threats are proposed by matching security threats with points and investigating related security technologies from patent data. Proposed approach can identify the ICT-related latent security menaces and provide the guidelines in the ‘problem – alternative’ form by linking the threat point with security technologies.

Keywords: future society, information and communication technology, security technology, technology forecasting

Procedia PDF Downloads 438

Authors: Timothy Kayode Samson, Adedoyin Isola Lawal

Abstract:

The past five years have shown a sharp increase in public interest in the crypto market, with its market capitalization growing from $100 billion in June 2017 to $2158.42 billion on April 5, 2022. Despite the outrageous nature of the volatility of cryptocurrencies, the use of skewed error innovation distributions in modelling the volatility behaviour of these digital currencies has not been given much research attention. Hence, this study models the volatility of 5 largest cryptocurrencies by market capitalization (Bitcoin, Ethereum, Tether, Binance coin, and USD Coin) using four variants of GARCH models (GJR-GARCH, sGARCH, EGARCH, and APARCH) estimated using three skewed error innovation distributions (skewed normal, skewed student- t and skewed generalized error innovation distributions). Daily closing prices of these currencies were obtained from Yahoo Finance website. Finding reveals that the Binance coin reported higher mean returns compared to other digital currencies, while the skewness indicates that the Binance coin, Tether, and USD coin increased more than they decreased in values within the period of study. For both Bitcoin and Ethereum, negative skewness was obtained, meaning that within the period of study, the returns of these currencies decreased more than they increased in value. Returns from these cryptocurrencies were found to be stationary but not normality distributed with evidence of the ARCH effect. The skewness parameters in all best forecasting models were all significant (p<.05), justifying of use of skewed error innovation distributions with a fatter tail than normal, Student-t, and generalized error innovation distributions. For Binance coin, EGARCH-sstd outperformed other volatility models, while for Bitcoin, Ethereum, Tether, and USD coin, the best forecasting models were EGARCH-sstd, APARCH-sstd, EGARCH-sged, and GJR-GARCH-sstd, respectively. This suggests the superiority of skewed Student t- distribution and skewed generalized error distribution over the skewed normal distribution.

Keywords: skewed generalized error distribution, skewed normal distribution, skewed student t- distribution, APARCH, EGARCH, sGARCH, GJR-GARCH

Procedia PDF Downloads 64

Authors: Pinel Sebastien, Bourrin François, De Madron Du Rieu Xavier, Ludwig Wolfgang, Arnau Pedro

Abstract:

Heavy precipitation constitutes a major meteorological threat in the western Mediterranean. Research has investigated the relationship between the states of the Mediterranean Sea and the atmosphere with the precipitation for short temporal windows. However, at a larger temporal scale, the precursor signals of heavy rainfall in the sea and atmosphere have drawn little attention. Moreover, despite ongoing improvements in numerical weather prediction, the medium-term forecasting of rainfall events remains a difficult task. Here, we aim to investigate the influence of early-spring environmental parameters on the following autumnal heavy precipitations. Hence, we develop a machine learning model to predict extreme autumnal rainfall with a 6-month lead time over the Spanish Catalan coastal area, based on i) the sea pattern (main current-LPC and Sea Surface Temperature-SST) at the mesoscale scale, ii) 4 European weather teleconnection patterns (NAO, WeMo, SCAND, MO) at synoptic scale, and iii) the hydrological regime of the main local river (Rhône River). The accuracy of the developed model classifier is evaluated via statistical analysis based on classification accuracy, logarithmic and confusion matrix by comparing with rainfall estimates from rain gauges and satellite observations (CHIRPS-2.0). Sensitivity tests are carried out by changing the model configuration, such as sea SST, sea LPC, river regime, and synoptic atmosphere configuration. The sensitivity analysis suggests a negligible influence from the hydrological regime, unlike SST, LPC, and specific teleconnection weather patterns. At last, this study illustrates how public datasets can be integrated into a machine learning model for heavy rainfall prediction and can interest local policies for management purposes.

Keywords: extreme hazards, sensitivity analysis, heavy rainfall, machine learning, sea-atmosphere modeling, precipitation forecasting

Procedia PDF Downloads 99