Search results for: Time-series forecasting

Authors: Oluwaseun K. Oyebode, Josiah A. Adeyemo

Abstract:

Hydrological modelling plays a crucial role in the planning and management of water resources, most especially in water stressed regions where the need to effectively manage the available water resources is of critical importance. However, due to the complex, nonlinear and dynamic behaviour of hydro-climatic interactions, achieving reliable modelling of water resource systems and accurate projection of hydrological parameters are extremely challenging. Although a significant number of modelling techniques (process-based and data-driven) have been developed and adopted in that regard, the field of hydrological modelling is still considered as one that has sluggishly progressed over the past decades. This is majorly as a result of the identification of some degree of uncertainty in the methodologies and results of techniques adopted. In recent times, evolutionary computation (EC) techniques have been developed and introduced in response to the search for efficient and reliable means of providing accurate solutions to hydrological related problems. This paper presents a comprehensive review of the underlying principles, methodological needs and applications of a promising evolutionary computation modelling technique – genetic programming (GP). It examines the specific characteristics of the technique which makes it suitable to solving hydrological modelling problems. It discusses the opportunities inherent in the application of GP in water related-studies such as rainfall estimation, rainfall-runoff modelling, streamflow forecasting, sediment transport modelling, water quality modelling and groundwater modelling among others. Furthermore, the means by which such opportunities could be harnessed in the near future are discussed. In all, a case for total embracement of GP and its variants in hydrological modelling studies is made so as to put in place strategies that would translate into achieving meaningful progress as it relates to modelling of water resource systems, and also positively influence decision-making by relevant stakeholders.

Keywords: Computational modelling, evolutionary algorithms, genetic programming, hydrological modelling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3329

Authors: Rawaa H. El-Bidweihy, Hisham M. Abdelsalam, Ihab A. El-Khodary

Abstract:

Bayesian networks are now considered to be a promising tool in the field of energy with different applications. In this study, the aim was to indicate the states of a previous constructed Bayesian network related to the solar energy in Egypt and the factors affecting its market share, depending on the followed data distribution type for each factor, and using either the Z-distribution approach or the Chebyshev’s inequality theorem. Later on, the separate and the conditional probabilities of the states of each factor in the Bayesian network were derived, either from the collected and scrapped historical data or from estimations and past studies. Results showed that we could use the constructed model for scenario and decision analysis concerning forecasting the total percentage of the market share of the solar energy in Egypt by 2035 and using it as a stable renewable source for generating any type of energy needed. Also, it proved that whenever the use of the solar energy increases, the total costs decreases. Furthermore, we have identified different scenarios, such as the best, worst, 50/50, and most likely one, in terms of the expected changes in the percentage of the solar energy market share. The best scenario showed an 85% probability that the market share of the solar energy in Egypt will exceed 10% of the total energy market, while the worst scenario showed only a 24% probability that the market share of the solar energy in Egypt will exceed 10% of the total energy market. Furthermore, we applied policy analysis to check the effect of changing the controllable (decision) variable’s states acting as different scenarios, to show how it would affect the target nodes in the model. Additionally, the best environmental and economical scenarios were developed to show how other factors are expected to be, in order to affect the model positively. Additional evidence and derived probabilities were added for the weather dynamic nodes whose states depend on time, during the process of converting the Bayesian network into a dynamic Bayesian network.

Keywords: Bayesian network, Chebyshev, decision variable, dynamic Bayesian network, Z-distribution

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 504

Authors: Satyendra Nath Mandal, J. Pal Choudhury, Dilip De, S. R. Bhadra Chaudhuri

Abstract:

The selection for plantation of a particular type of mustard plant depending on its productivity (pod yield) at the stage of maturity. The growth of mustard plant dependent on some parameters of that plant, these are shoot length, number of leaves, number of roots and roots length etc. As the plant is growing, some leaves may be fall down and some new leaves may come, so it can not gives the idea to develop the relationship with the seeds weight at mature stage of that plant. It is not possible to find the number of roots and root length of mustard plant at growing stage that will be harmful of this plant as roots goes deeper to deeper inside the land. Only the value of shoot length which increases in course of time can be measured at different time instances. Weather parameters are maximum and minimum humidity, rain fall, maximum and minimum temperature may effect the growth of the plant. The parameters of pollution, water, soil, distance and crop management may be dominant factors of growth of plant and its productivity. Considering all parameters, the growth of the plant is very uncertain, fuzzy environment can be considered for the prediction of shoot length at maturity of the plant. Fuzzification plays a greater role for fuzzification of data, which is based on certain membership functions. Here an effort has been made to fuzzify the original data based on gaussian function, triangular function, s-function, Trapezoidal and L –function. After that all fuzzified data are defuzzified to get normal form. Finally the error analysis (calculation of forecasting error and average error) indicates the membership function appropriate for fuzzification of data and use to predict the shoot length at maturity. The result is also verified using residual (Absolute Residual, Maximum of Absolute Residual, Mean Absolute Residual, Mean of Mean Absolute Residual, Median of Absolute Residual and Standard Deviation) analysis.

Keywords: Fuzzification, defuzzification, gaussian function, triangular function, trapezoidal function, s-function, , membership function, residual analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2319

Authors: S. Mahalakshmi, B. Senthil Arasu

Abstract:

As per the recent changes happening in the global policies, climate related changes and the impact it causes across every sector are viewed as green swan events – in essence, climate related changes can happen often and lead to risk and lot of uncertainty, but need to be mitigated instead of considering them as black swan events. This brings about a question on how this risk can be computed, so that the financial institutions can plan to mitigate it. Climate related changes impact all risk types – credit risk, market risk, operational risk, liquidity risk, reputational risk and others. And the models required to compute this have to consider the different industrial needs of the counterparty, as well as the factors that are contributing to this – be it in the form of different risk drivers, or the different transmission channels or the different approaches and the granular form of data availability. This brings out to the suggestion that the climate related changes, though it affects Pillar I risks, will be a Pillar II risk. This has to be modeled specifically based on the financial institution’s actual exposure to different industries, instead of generalizing the risk charge. And this will have to be considered as the additional capital to be met by the financial institution in addition to their Pillar I risks, as well as the existing Pillar II risks. In this paper, we present a risk assessment framework to model and assess climate change risks - for both credit and market risks. This framework helps in assessing the different scenarios, and how the different transition risks affect the risk associated with the different parties. This research paper delves on the topic of increase in concentration of greenhouse gases, that in turn causing global warming. It then considers the various scenarios of having the different risk drivers impacting credit and market risk of an institution, by understanding the transmission channels, and also considering the transition risk. The paper then focuses on the industry that’s fast seeing a disruption: automobile industry. The paper uses the framework to show how the climate changes and the change to the relevant policies have impacted the entire financial institution. Appropriate statistical models for forecasting, anomaly detection and scenario modeling are built to demonstrate how the framework can be used by the relevant agencies to understand their financial risks. The paper also focuses on the climate risk calculation for the Pillar II capital calculations, and how it will make sense for the bank to maintain this in addition to their regular Pillar I and Pillar II capital.

Keywords: Capital calculation, climate risk, credit risk, pillar II risk, scenario modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 423

Authors: Satyendra Nath Mandal, J. Pal Choudhury, Dilip De, S. R. Bhadra Chaudhuri

Abstract:

The production of a plant can be measured in terms of seeds. The generation of seeds plays a critical role in our social and daily life. The fruit production which generates seeds, depends on the various parameters of the plant, such as shoot length, leaf number, root length, root number, etc When the plant is growing, some leaves may be lost and some new leaves may appear. It is very difficult to use the number of leaves of the tree to calculate the growth of the plant.. It is also cumbersome to measure the number of roots and length of growth of root in several time instances continuously after certain initial period of time, because roots grow deeper and deeper under ground in course of time. On the contrary, the shoot length of the tree grows in course of time which can be measured in different time instances. So the growth of the plant can be measured using the data of shoot length which are measured at different time instances after plantation. The environmental parameters like temperature, rain fall, humidity and pollution are also play some role in production of yield. The soil, crop and distance management are taken care to produce maximum amount of yields of plant. The data of the growth of shoot length of some mustard plant at the initial stage (7,14,21 & 28 days after plantation) is available from the statistical survey by a group of scientists under the supervision of Prof. Dilip De. In this paper, initial shoot length of Ken( one type of mustard plant) has been used as an initial data. The statistical models, the methods of fuzzy logic and neural network have been tested on this mustard plant and based on error analysis (calculation of average error) that model with minimum error has been selected and can be used for the assessment of shoot length at maturity. Finally, all these methods have been tested with other type of mustard plants and the particular soft computing model with the minimum error of all types has been selected for calculating the predicted data of growth of shoot length. The shoot length at the stage of maturity of all types of mustard plants has been calculated using the statistical method on the predicted data of shoot length.

Keywords: Fuzzy time series, neural network, forecasting error, average error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1591

Authors: Wan-Yu Liu

Abstract:

To respond to the Kyoto Protocol, the policy of Payment for Environmental Service (PES), which was entitled “Plain Landscape Afforestation Program (PLAP)", was certified by Executive Yuan in Taiwan on 31 August 2001 and has been implementing for six years since 1 January 2002. Although the PLAP has received a lot of positive comments, there are still many difficulties during the process of implementation, such as insufficient technology for afforestation, private landowners- low interests in participating in PLAP, insufficient subsidies, and so on, which are potential threats that hinder the PLAP from moving forward in future. In this paper, selecting Ping-Tung County in Taiwan as a sample region and targeting those private landowners with and without intention to participate in the PLAP, respectively, we conduct an empirical analysis based on the Logit model to investigate the factors that determine whether those private landowners join the PLAP, so as to realize the incentive effects of the PLAP upon the personal decision on afforestation. The possible factors that might determine private landowner-s participation in the PLAP include landowner-s characteristics, cropland characteristics, as well as policy factors. Among them, the policy factors include afforestation subsidy amount (+), duration of afforestation subsidy (+), the rules on adjoining and adjacent areas (+), and so on, which do not reach the remarkable level in statistics though, but the directions of variable signs are consistent with the intuition behind the policy. As for the landowners- characteristics, each of age (+), education level (–), and annual household income (+) variables reaches 10% of the remarkable level in statistics; as for the cropland characteristics, each of cropland area (+), cropland price (–), and the number of cropland parcels (–) reaches 1% of the remarkable level in statistics. In light of the above, the cropland characteristics are the dominate factor that determines the probability of landowner-s participation in the PLAP. In the Logit model established by this paper, the probability of correctly estimating nonparticipants is 98%, the probability of correctly estimating the participants is 71.8%, and the probability for the overall estimation is 95%. In addition, Hosmer-Lemeshow test and omnibus test also revealed that the Logit model in this paper may provide fine goodness of fit and good predictive power in forecasting private landowners- participation in this program. The empirical result of this paper expects to help the implementation of the afforestation programs in Taiwan.

Keywords: Forestry policy, logit, afforestation subsidy, afforestation policy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1605

Authors: Dhruvit S. Berawala, Jann R. Ursin, Obrad Slijepcevic

Abstract:

Shale gas is one of the most rapidly growing forms of natural gas. Unconventional natural gas deposits are difficult to characterize overall, but in general are often lower in resource concentration and dispersed over large areas. Moreover, gas is densely packed into the matrix through adsorption which accounts for large volume of gas reserves. Gas production from tight shale deposits are made possible by extensive and deep well fracturing which contacts large fractions of the formation. The conventional reservoir modelling and production forecasting methods, which rely on fluid-flow processes dominated by viscous forces, have proved to be very pessimistic and inaccurate. This paper presents a new approach to forecast shale gas production by detailed modeling of gas desorption, diffusion and non-linear flow mechanisms in combination with statistical representation of these processes. The representation of the model involves a cube as a porous media where free gas is present and a sphere (SiC: Sphere in Cube model) inside it where gas is adsorbed on to the kerogen or organic matter. Further, the sphere is considered consisting of many layers of adsorbed gas in an onion-like structure. With pressure decline, the gas desorbs first from the outer most layer of sphere causing decrease in its molecular concentration. The new available surface area and change in concentration triggers the diffusion of gas from kerogen. The process continues until all the gas present internally diffuses out of the kerogen, gets adsorbs onto available surface area and then desorbs into the nanopores and micro-fractures in the cube. Each SiC idealizes a gas pathway and is characterized by sphere diameter and length of the cube. The diameter allows to model gas storage, diffusion and desorption; the cube length takes into account the pathway for flow in nanopores and micro-fractures. Many of these representative but general cells of the reservoir are put together and linked to a well or hydraulic fracture. The paper quantitatively describes these processes as well as clarifies the geological conditions under which a successful shale gas production could be expected. A numerical model has been derived which is then compiled on FORTRAN to develop a simulator for the production of shale gas by considering the spheres as a source term in each of the grid blocks. By applying SiC to field data, we demonstrate that the model provides an effective way to quickly access gas production rates from shale formations. We also examine the effect of model input properties on gas production.

Keywords: Sphere in Cube Grid Approach to Modelling of Shale Gas Production Using Non-Linear Flow Mechanisms

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 822

Authors: D. Tedesco, G. Feletti, P. Trucco

Abstract:

The present study aims to develop a Decision Support System (DSS) to support operational decisions in Emergency Medical Service (EMS) systems regarding the assignment of medical emergency requests to Emergency Departments (ED). This problem is called “hospital selection” and concerns the definition of policies for the selection of the ED to which patients who require further treatment are transported by ambulance. The employed research methodology consists of a first phase of review of the technical-scientific literature concerning DSSs to support the EMS management and, in particular, the hospital selection decision. From the literature analysis, it emerged that current studies mainly focused on the EMS phases related to the ambulance service and consider a process that ends when the ambulance is available after completing a mission. Therefore, all the ED-related issues are excluded and considered as part of a separate process. Indeed, the most studied hospital selection policy turned out to be proximity, thus allowing to minimize the travelling time and to free-up the ambulance in the shortest possible time. The purpose of the present study consists in developing an optimization model for assigning medical emergency requests to the EDs also considering the expected time performance in the subsequent phases of the process, such as the case mix, the expected service throughput times, and the operational capacity of different EDs in hospitals. To this end, a Discrete Event Simulation (DES) model was created to compare different hospital selection policies. The model was implemented with the AnyLogic software and finally validated on a realistic case. The hospital selection policy that returned the best results was the minimization of the Time To Provider (TTP), considered as the time from the beginning of the ambulance journey to the ED at the beginning of the clinical evaluation by the doctor. Finally, two approaches were further compared: a static approach, based on a retrospective estimation of the TTP, and a dynamic approach, focused on a predictive estimation of the TTP which is determined with a constantly updated Winters forecasting model. Findings reveal that considering the minimization of TTP is the best hospital selection policy. It allows to significantly reducing service throughput times in the ED with a negligible increase in travel time. Furthermore, an immediate view of the saturation state of the ED is produced and the case mix present in the ED structures (i.e., the different triage codes) is considered, as different severity codes correspond to different service throughput times. Besides, the use of a predictive approach is certainly more reliable in terms on TTP estimation, than a retrospective approach. These considerations can support decision-makers in introducing different hospital selection policies to enhance EMSs performance.

Keywords: Emergency medical services, hospital selection, discrete event simulation, forecast model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 233

Authors: C. Silveira, A. Ascenso, J. Ferreira, A. I. Miranda, P. Tuccella, G. Curci

Abstract:

Poor air quality is one of the main environmental causes of premature deaths worldwide, and mainly in cities, where the majority of the population lives. It is a consequence of successive land cover (LC) and use changes, as a result of the intensification of human activities. Knowing these landscape modifications in a comprehensive spatiotemporal dimension is, therefore, essential for understanding variations in air pollutant concentrations. In this sense, the use of air quality models is very useful to simulate the physical and chemical processes that affect the dispersion and reaction of chemical species into the atmosphere. However, the modelling performance should always be evaluated since the resolution of the input datasets largely dictates the reliability of the air quality outcomes. Among these data, the updated LC is an important parameter to be considered in atmospheric models, since it takes into account the Earth’s surface changes due to natural and anthropic actions, and regulates the exchanges of fluxes (emissions, heat, moisture, etc.) between the soil and the air. This work aims to evaluate the performance of the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem), when different LC classifications are used as an input. The influence of two LC classifications was tested: i) the 24-classes USGS (United States Geological Survey) LC database included by default in the model, and the ii) CLC (Corine Land Cover) and specific high-resolution LC data for Portugal, reclassified according to the new USGS nomenclature (33-classes). Two distinct WRF-Chem simulations were carried out to assess the influence of the LC on air quality over Europe and Portugal, as a case study, for the year 2015, using the nesting technique over three simulation domains (25 km², 5 km² and 1 km² horizontal resolution). Based on the 33-classes LC approach, particular emphasis was attributed to Portugal, given the detail and higher LC spatial resolution (100 m x 100 m) than the CLC data (5000 m x 5000 m). As regards to the air quality, only the LC impacts on tropospheric ozone concentrations were evaluated, because ozone pollution episodes typically occur in Portugal, in particular during the spring/summer, and there are few research works relating to this pollutant with LC changes. The WRF-Chem results were validated by season and station typology using background measurements from the Portuguese air quality monitoring network. As expected, a better model performance was achieved in rural stations: moderate correlation (0.4 – 0.7), BIAS (10 – 21µg.m^-3) and RMSE (20 – 30 µg.m^-3), and where higher average ozone concentrations were estimated. Comparing both simulations, small differences grounded on the Leaf Area Index and air temperature values were found, although the high-resolution LC approach shows a slight enhancement in the model evaluation. This highlights the role of the LC on the exchange of atmospheric fluxes, and stresses the need to consider a high-resolution LC characterization combined with other detailed model inputs, such as the emission inventory, to improve air quality assessment.

Keywords: Land cover, tropospheric ozone, WRF-Chem, air quality assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 796