Search results for: forest management certification
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 9985

Search results for: forest management certification

9535 Identification of Candidate Congenital Heart Defects Biomarkers by Applying a Random Forest Approach on DNA Methylation Data

Authors: Kan Yu, Khui Hung Lee, Eben Afrifa-Yamoah, Jing Guo, Katrina Harrison, Jack Goldblatt, Nicholas Pachter, Jitian Xiao, Guicheng Brad Zhang

Abstract:

Background and Significance of the Study: Congenital Heart Defects (CHDs) are the most common malformation at birth and one of the leading causes of infant death. Although the exact etiology remains a significant challenge, epigenetic modifications, such as DNA methylation, are thought to contribute to the pathogenesis of congenital heart defects. At present, no existing DNA methylation biomarkers are used for early detection of CHDs. The existing CHD diagnostic techniques are time-consuming and costly and can only be used to diagnose CHDs after an infant was born. The present study employed a machine learning technique to analyse genome-wide methylation data in children with and without CHDs with the aim to find methylation biomarkers for CHDs. Methods: The Illumina Human Methylation EPIC BeadChip was used to screen the genome‐wide DNA methylation profiles of 24 infants diagnosed with congenital heart defects and 24 healthy infants without congenital heart defects. Primary pre-processing was conducted by using RnBeads and limma packages. The methylation levels of top 600 genes with the lowest p-value were selected and further investigated by using a random forest approach. ROC curves were used to analyse the sensitivity and specificity of each biomarker in both training and test sample sets. The functionalities of selected genes with high sensitivity and specificity were then assessed in molecular processes. Major Findings of the Study: Three genes (MIR663, FGF3, and FAM64A) were identified from both training and validating data by random forests with an average sensitivity and specificity of 85% and 95%. GO analyses for the top 600 genes showed that these putative differentially methylated genes were primarily associated with regulation of lipid metabolic process, protein-containing complex localization, and Notch signalling pathway. The present findings highlight that aberrant DNA methylation may play a significant role in the pathogenesis of congenital heart defects.

Keywords: biomarker, congenital heart defects, DNA methylation, random forest

Procedia PDF Downloads 135
9534 Impact Factor Analysis for Spatially Varying Aerosol Optical Depth in Wuhan Agglomeration

Authors: Wenting Zhang, Shishi Liu, Peihong Fu

Abstract:

As an indicator of air quality and directly related to concentration of ground PM2.5, the spatial-temporal variation and impact factor analysis of Aerosol Optical Depth (AOD) have been a hot spot in air pollution. This paper concerns the non-stationarity and the autocorrelation (with Moran’s I index of 0.75) of the AOD in Wuhan agglomeration (WHA), in central China, uses the geographically weighted regression (GRW) to identify the spatial relationship of AOD and its impact factors. The 3 km AOD product of Moderate Resolution Imaging Spectrometer (MODIS) is used in this study. Beyond the economic-social factor, land use density factors, vegetable cover, and elevation, the landscape metric is also considered as one factor. The results suggest that the GWR model is capable of dealing with spatial varying relationship, with R square, corrected Akaike Information Criterion (AICc) and standard residual better than that of ordinary least square (OLS) model. The results of GWR suggest that the urban developing, forest, landscape metric, and elevation are the major driving factors of AOD. Generally, the higher AOD trends to located in the place with higher urban developing, less forest, and flat area.

Keywords: aerosol optical depth, geographically weighted regression, land use change, Wuhan agglomeration

Procedia PDF Downloads 335
9533 A Case Study of Wildlife Crime in Bangladesh

Authors: M. Golam Rabbi

Abstract:

Theme of wildlife crime is unique in Bangladesh. In earlier of 2010, wildlife crime was not designated as a crime, unlike other offenses. Forest Department and other enforcement agencies were not in full swing to find out the organized crime scene at that time and recorded few cases along with forest crime. However, after the establishment of Wildlife Crime Control Unitin 2012a, total of 374 offenses have been detected with 566 offenders and 37,039 wildlife and trophies were seized till November 2016. Most offenses seem to be committed outside the forests where the presence of the forest staff is minimal. Total detection percentage of offenses is not known, but offenders are not identified in 60% of detected cases (UDOR). Only 20% cases are decided by the courts even after eight years, conviction rate of the total disposal is 70.65%. Mostly six months imprisonment and BDT 5000 fine seems to be the modal penalty. The monetary value of wildlife crime in the country is approximate $0.72M per year and the maximum value counted for reptiles around $0.45M especially for high-level trafficking of geckos and turtles. The most common seizures of wildlife are birds (mynas, munias, parakeets, lorikeets, water birds, etc.) which have domestic demand for pet. Some other wildlife like turtles, lizards and small mammals are also on the list. Venison and migratory waterbirds often seized which has a large quantity demand for consuming at aristocratic level.Due to porous border and weak enforcement in border region poachers use the way for trafficking of geckos, turtles, and tortoises, snakes, venom, tiger and body parts, spotted deerskin, pangolinetc. Those have very high demand in East Asian countries for so-called medicinal purposes. The recent survey also demonstrates new route for illegal trade and trafficking for instance, after poaching of tiger and deer from the Sundarbans, the largest mangrove track of the planet to Thailand through the Bay of Bengal, sharks fins and ray fish through Chittagong seaport and directly by sea routes to Myanmar and Thailand. However, a good number of records of offense demonstrate the transition route from India to South and South East Asian countries. Star tortoises and Hamilton’s turtles are smuggled in from India which mostly seized at Benapole border of Jessore and Hazrat Shah Jajal International Airport of Dhaka, in very large numbers for transmission to East Asian countries. Most of the cases of wildlife trade routes leading to China, Thailand, Malaysia, and Myanmar. Most surprisingly African ivory was seized in Bangladesh recently, which was meant to be trafficked to the South-East Asia. However; forest department is working to fight against wildlife poaching, illegal trade and trafficking in collaboration with other law enforcement agencies. The department needs a clear mandate and to build technical capabilities for identifying, seizing and holding specimens. The department also needs to step out of the forests and must develop the capacity to surveillance and patrol all sensitive locations across the country.

Keywords: Bangladesh forest department, Sundarban, tiger, wildlife crime, wildlife trafficking

Procedia PDF Downloads 273
9532 Management of Theatre with Social and Culture

Authors: Chitsuphang Ungsvanonda

Abstract:

Objective of this research is to study the government’s theater management system regarding planning and operation. Also studying how the management associate with the change of an environment. This is to gather an appropriate model to develop a theater management system especially regarding all show performance. The research will be done by a Qualitative Research with an interview of 35 person by specify and unexpectedly group.

Keywords: management, theatre, social, culture

Procedia PDF Downloads 444
9531 Flood Hazard Assessment and Land Cover Dynamics of the Orai Khola Watershed, Bardiya, Nepal

Authors: Loonibha Manandhar, Rajendra Bhandari, Kumud Raj Kafle

Abstract:

Nepal’s Terai region is a part of the Ganges river basin which is one of the most disaster-prone areas of the world, with recurrent monsoon flooding causing millions in damage and the death and displacement of hundreds of people and households every year. The vulnerability of human settlements to natural disasters such as floods is increasing, and mapping changes in land use practices and hydro-geological parameters is essential in developing resilient communities and strong disaster management policies. The objective of this study was to develop a flood hazard zonation map of Orai Khola watershed and map the decadal land use/land cover dynamics of the watershed. The watershed area was delineated using SRTM DEM, and LANDSAT images were classified into five land use classes (forest, grassland, sediment and bare land, settlement area and cropland, and water body) using pixel-based semi-automated supervised maximum likelihood classification. Decadal changes in each class were then quantified using spatial modelling. Flood hazard mapping was performed by assigning weights to factors slope, rainfall distribution, distance from the river and land use/land cover on the basis of their estimated influence in causing flood hazard and performing weighed overlay analysis to identify areas that are highly vulnerable. The forest and grassland coverage increased by 11.53 km² (3.8%) and 1.43 km² (0.47%) from 1996 to 2016. The sediment and bare land areas decreased by 12.45 km² (4.12%) from 1996 to 2016 whereas settlement and cropland areas showed a consistent increase to 14.22 km² (4.7%). Waterbody coverage also increased to 0.3 km² (0.09%) from 1996-2016. 1.27% (3.65 km²) of total watershed area was categorized into very low hazard zone, 20.94% (60.31 km²) area into low hazard zone, 37.59% (108.3 km²) area into moderate hazard zone, 29.25% (84.27 km²) area into high hazard zone and 31 villages which comprised 10.95% (31.55 km²) were categorized into high hazard zone area.

Keywords: flood hazard, land use/land cover, Orai river, supervised maximum likelihood classification, weighed overlay analysis

Procedia PDF Downloads 320
9530 The Affect of Total Quality Management on Firm's Innovation Performance: A Literature Review

Authors: Omer Akkaya, Nurullah Ekmekcı, Muammer Zerenler

Abstract:

Innovation for businesses means a new product and service and sometimes a new implementation. Total Quality Management is a management philosophy which focus on customer, process and system.There is a certain relationship between principles of Total Quality Management and innovation performance. Main aim of this study is to show how the implementation and principles of Total Quality Management (TQM) affect a firm's innovation performance. Also, this paper discusses positive and negative affects of Total Quality Management on innovation performance and demonstrates some examples.

Keywords: innovation, innovation types, total quality management, principles of total quality management

Procedia PDF Downloads 598
9529 What Happens When We Try to Bridge the Science-Practice Gap? An Example from the Brazilian Native Vegetation Protection Law

Authors: Alice Brites, Gerd Sparovek, Jean Paul Metzger, Ricardo Rodrigues

Abstract:

The segregation between science and policy in decision making process hinders nature conservation efforts worldwide. Scientists have been criticized for not producing information that leads to effective solutions for environmental problems. In an attempt to bridge this gap between science and practice, we conducted a project aimed at supporting the implementation of the Brazilian Native Vegetation Protection Law (NVPL) implementation in São Paulo State (SP), Brazil. To do so, we conducted multiple open meetings with the stakeholders involved in this discussion. Throughout this process, we raised stakeholders' demands for scientific information and brought feedbacks about our findings. However, our main scientific advice was not taken into account during the NVPL implementation in SP. The NVPL has a mechanism that exempts landholders who converted native vegetation without offending the legislation in place at the time of the conversion from restoration requirements. We found out that there were no accurate spatialized data for native vegetation cover before the 1960s. Thus, the initial benchmark for the mechanism application should be the 1965 Brazilian Forest Act. Even so, SP kept the 1934 Brazilian Forest Act as the initial legal benchmark for the law application. This decision implies the use of a probabilistic native vegetation map that has uncertainty and subjectivity as its intrinsic characteristics, thus its use can lead to legal queries, corruption, and an unfair benefit application. But why this decision was made even after the scientific advice was vastly divulgated? We raised some possible reasons to explain it. First, the decision was made during a government transition, showing that circumstantial political events can overshadow scientific arguments. Second, the debate about the NVPL in SP was not pacified and powerful stakeholders could benefit from the confusion created by this decision. Finally, the native vegetation protection mechanism is a complex issue, with many technical aspects that can be hard to understand for a non-specialized courtroom, such as the one that made the final decision at SP. This example shows that science and decision-makers still have a long way ahead to improve their way to interact and that science needs to find its way to be heard above the political buzz.

Keywords: Brazil, forest act, science-based dialogue, science-policy interface

Procedia PDF Downloads 101
9528 Seafarers Safety, Watch-Keeping and Navigation

Authors: Sunday Moses Ojelabi

Abstract:

Safety is the protection of the crew, passenger and equipment itself, as well as those living and working near bodies of water, from hazardous situations. To assure safety, watch keeping is paramount because neglecting your watchkeeping can lead to hazardous situations. Navigation is the assignment of a sailor to a specific route on a vessel to operate. Navigation is the process of planning, managing, and directing a vessel safely to the desired destination with the aid of intense and efficient watch keeping. Safety, i,e, all measures done to preserve the welfare of marine life, maritime infrastructure, facilities, ships, offshore installations, crew, and passengers, as well as the preservation of navigation and the ease of maritime trade, are referred to as safety measures;. When it comes to health, the absence of a proper first aid kit will affect injured sailors and passengers. Not using goggles while shipping, ear muffs, etc., in the course of maintenance can be hazardous. Watchkeeping: i.e the specific dutiies assigned to a personnel in a vessel to see to its continous smooth functionality. Your lookout or watch officer [officer on navigational duty] must be active at all times in the course of duty. Navigation refers to the technique of precisely determining a craft or vehicle's position and directing its motion along a particular course. The seafarers are not being put through regular seminars, training, and orientations. In parts of West Africa, sailors go to school without being able to secure jobs until their papers expire. For that, they won’t go for another Standard Trainning Certification and Watch keeping for Seafarers to upgrade their certificate. In light of this, they are not familiar with the new vessels in the country, and for this, they can`t meet the safety, watch keeping, and navigation standards. Also, shipping companies and ship owners are being selfish by not putting the proper things needed onboard regarding safety, watchkeeping, and navigational equipment. The questions raised in these presentations are the breakdown of the safety activities, watch keeping effectiveness, and navigational accuracy. All safety and watch keeping regulations should be applied efficiently. The problem identified includes a lack of safety instruments onboard vessels in African waters. Also, inadequate proper watchkeeping due to the excess workload on the seafarers can lead to an improper lookout, which gives room to collision, hijacking, and piracy. The impact of this research is to inform African seafarers, shipping companies, and ship owners of the necessary information concerning the safety of their lives and that of their passengers, cargo, and equipment.

Keywords: standard of training, certification, watch keeping for seafarers, navigation, safety, watchkeeping

Procedia PDF Downloads 53
9527 Review of Innovation Management Frameworks and Assessment Tools

Authors: Qiang Fu, Abu Saleh

Abstract:

Research studies are highly fragmented when an innovation management framework is being discussed. With the aim to identify an innovation management framework/assessment tool suitable for small & medium enterprises (SMEs) in the service industry, this researcher critically reviewed existing innovation management frameworks and assessment models/tools and discovered a number of literature gaps. It is established that existing literature lacks generally agreed innovation management dimensions, commonly accepted knowledge creation through empirical studies on innovation management in SMEs, effective innovation management performance measurements, and studies on innovation management in the service industry, in particular in retail SMEs. As such, there is a dire need to develop an appropriate firm-level innovation management framework suitable for SMEs in the service industry for a future research project and further study. In addition, this researcher also discussed the significance of establishing such an innovation management framework.

Keywords: innovation management, innovation management framework, innovation management assessment tools, SMEs, service industry

Procedia PDF Downloads 166
9526 Genetic Parameters as Indicators of Sustainability and Diversity of Schinus terebinthifolius Populations in the Riparian Area of the São Francisco River

Authors: Renata Silva-Mann, Sheila Valéria Álvares Carvalho, Robério Anastácio Ferreira, Laura Jane Gomes

Abstract:

There is growing interest in defining indicators of sustainability, which are important for monitoring the conservation of native forests, particularly in areas of permanent protection. These indicators are references for assessing the state of the forest and the status of the depredated area and its ability to maintain species populations. The aim of the present study was to select genetic parameters as indicators of sustainability for Schinus terebinthifolius Raddi. Fragments located in riparian areas between the Sergipe and Alagoas States in Brazil. This species has been exploited for traditional communities, which represent 20% of the incoming. This study was carried out using the indicators suggested by the Organization for Economic Cooperation and Development, which were identified as Driving-Pressure-State-Impact-Response (DPSIR) factors. The genetic parameters were obtained in five populations located on the shores and islands of the São Francisco River, one of the most important rivers in Brazil. The framework for Schinus conservation suggests seventeen indicators of sustainability. In accordance with genetic parameters, the populations are isolated, and these genetic parameters can be used to monitor the sustainability of those populations in riparian area with the aim of defining strategies for forest restoration.

Keywords: alleles, molecular markers, genetic diversity, biodiversity

Procedia PDF Downloads 272
9525 Medical versus Non-Medical Students' Opinions about Academic Stress Management Using Unconventional Therapies

Authors: Ramona-Niculina Jurcau, Ioana-Marieta Jurcau, Dong Hun Kwak, Nicolae-Alexandru Colceriu

Abstract:

Background: Stress management (SM) is a topic of great academic interest and equally a task to accomplish. In addition, it is recognized the beneficial role of unconventional therapies (UCT) in stress modulation. Aims: The aim was to evaluate medical (MS) versus non-medical students’ (NMS) opinions about academic stress management (ASM) using UCT. Methods: MS (n=103, third year males and females) and NMS (n=112, males and females, from humanities faculties, different years of study), out of their academic program, voluntarily answered to a questionnaire concerning: a) Classification of the four most important academic stress factors; b) The extent to which their daily life influences academic stress; c) The most important SM methods they know; d) Which of these methods they are applying; e) the UCT they know or about which they have heard; f) Which of these they know to have stress modulation effects; g) Which of these UCT, participants are using or would like to use for modulating stress; and if participants use UTC for their own choose or following a specialist consultation in those therapies (SCT); h) If they heard about the following UCT and what opinion they have (using visual analogue scale) about their use (following CST) for the ASM: Phytotherapy (PT), apitherapy (AT), homeopathy (H), ayurvedic medicine (AM), traditional Chinese medicine (TCM), music therapy (MT), color therapy (CT), forest therapy (FT). Results: Among the four most important academic stress factors, for MS more than for NMS, are: busy schedule, large amount of information taught; high level of performance required, reduced time for relaxing. The most important methods for SM that MS and NMS know, hierarchically are: listen to music, meeting friends, playing sport, hiking, sleep, regularly breaks, seeing positive side, faith; of which, NMS more than MS, are partially applying to themselves. UCT about which MS and less NMS have heard, are phytotherapy, apitherapy, acupuncture, reiki. Of these UTC, participants know to have stress modulation effects: some plants, bee’s products and music; they use or would like to use for ASM (the majority without SCT) certain teas, honey and music. Most of MS and only some NMS heard about PT, AT, TCM, MT and much less about H, AM, CT, TT. NMS more than MS, would use these UCT, following CST. Conclusions: 1) Academic stress is similarly reflected in MS and NMS opinions. 2) MS and NMS apply similar but very few UCT for stress modulation. 3) Information that MS and NMS have about UCT and their ASM application is reduced. 4) It is remarkable that MS and especially NMS, are open to UCT use for ASM, following an SCT.

Keywords: academic stress, stress management, stress modulation, medical students, non-medical students, unconventional therapies

Procedia PDF Downloads 315
9524 Managing Virtual Teams in a Pandemic

Authors: M. Jafari Toosy, A. Zamani

Abstract:

This article, considering the result of pandemics at the international level and all activities and projects performed virtually and the need for resource management and virtual teams in this period identifies the components of virtual management after searching the available resources. Exploration of virtual management in the pandemic era is explored in 10 international articles. The results of research with this method and according to the tasks and topics related to management knowledge and definition of virtual teams can be divided into topics such as planning, decision making, control, organization, leadership, attention to growth and capability, resources and facilities, Communication, creativity, innovation and security. In order to explain the nature of virtual management, a definition of virtual management was provided.

Keywords: management, virtual, virtual team management, pandemic, team

Procedia PDF Downloads 156
9523 Wildfires Assessed By Remote Sensed Images And Burned Land Monitoring

Authors: Maria da Conceição Proença

Abstract:

This case study implements the evaluation of burned areas that suffered successive wildfires in Portugal mainland during the summer of 2017, killing more than 60 people. It’s intended to show that this evaluation can be done with remote sensing data free of charges in a simple laptop, with open-source software, describing the not-so-simple methodology step by step, to make it available for county workers in city halls of the areas attained, where the availability of information is essential for the immediate planning of mitigation measures, such as restoring road access, allocate funds for the recovery of human dwellings and assess further restoration of the ecological system. Wildfires also devastate forest ecosystems having a direct impact on vegetation cover and killing or driving away from the animal population. The economic interest is also attained, as the pinewood burned becomes useless for the noblest applications, so its value decreases, and resin extraction ends for several years. The tools described in this paper enable the location of the areas where took place the annihilation of natural habitats and establish a baseline for major changes in forest ecosystems recovery. Moreover, the result allows the follow up of the surface fuel loading, enabling the targeting and evaluation of restoration measures in a time basis planning.

Keywords: image processing, remote sensing, wildfires, burned areas evaluation, sentinel-2

Procedia PDF Downloads 177
9522 Tourism and Sustainability Example Projects in the EU

Authors: Renee Yi-Mond Yuan

Abstract:

The fast development of tourism industries around the world, has largely contributed to many cities, and countries economical and social progress. Past year Taiwan in particular was ranked among one of fastest raise growth country. Thanks to the prominent importance of this phenomenon; seasonal mobility or multipurpose trips have reached more than 1 Billion tourists crossing International borders and more than 4 billion intramural travelers that have nourished the economy and employment in the service sector in most attractive regions, representing about one tenth of World GDP amount, including trade, research, cultural or journalistic purposes. Then the increased activities are giving pressure to the consumption of energy, water, resources, and Greenhouse Gas emissions. The further concentration of tourists in most beautiful sites of the World with consistent supply and reduced pollutions and means for waste control and risks management are challenging the preservation and protection of the natural original environment, including species and their ecosystems, ethnics and their cultures or languages, protection of inherited landscapes and monuments for the future generations to come. In this article, few projects will be analyzed, methods and directions in the EU sustainable development scheme giving way to economical and social activities and preserve rural areas and remote countryside as well as smarter cities development. EU ETS forecasting escalation in the next few decades for road and air, and will reconsider investments and reliance on Biobased alternatives that may turn out solutions and contributions to sustain popularization of tourism development. Study of Examples of Stakeholders practices and Governments efforts, consumer’s attitude to bring new forms of more responsible holidays models: ecotourism, eco-certification, partnerships, investment in technologies and facilities, and possibly create greener perceptions and less impacting demands for the longer term through association, organizations and awards.

Keywords: tourism, sustainability, protection, risks management, change in rural/urban environment

Procedia PDF Downloads 312
9521 Grouping Pattern, Habitat Assessment and Overlap Analysis of Five Ungulates Species in Different Altitudinal Gradients of Western Himalaya, Uttarakhand, India

Authors: Kaleem Ahmed, Jamal A. Khan

Abstract:

Grouping patterns, habitat use, and overlap studies were conducted on five sympatric ungulate species sambar (Cervus unicolor), chital (Axis axis), muntjac (Muntiacus muntjac), goral (Nemorhaedus goral), and serow (Capricornis sumatraensis) in the Dabka watershed area within Indian West Himalayan range. Data on age, sex composition, group size, and various ecological and topographical factors governing the presence/absence of species within the study area were collected using a 250 km of a trail walk, 95 permanent circular plots of 10 m radius, and 3 vantage points with 58 scannings. The highest mean group size was recorded for chital (6.35 ± 0.50), followed by sambar (1.35 ± 0.10), goral (1.25 ±0.63), muntjac (1.12 ± 0.05), and serow (1.00 ± 0.00). Grouping pattern significantly varied among sympatric species (F = 85.10, df. = 6, P = 0.000). The highest mean pellet group density (/ha ± SE) was recorded for sambar (41.56 ± 3.51), followed by goral (23.31 ± 3.45), chital (19.21 ± 3.51), muntjac (7.43 ± 1.21), and serow (1.02 ± 0.10). Two-way variance analysis showed a significant difference in the density of the pellet group of all ungulate species across different study area habitats (F = 6.38, df = 4, P = 0.027). The availability-utilization (AU) analysis reveals that goral was mostly sighted in steep slopes, preferred > 2100 m altitudinal range with low shrub understory, avoided dense forest, and relatively more southern aspects were used. Chital had used a wide range of tree and shrub coverings with a preference towards moderate cover range (26-50%), preferred areas with low slope category ( < 25), avoided areas of high altitude > 900 m. Sambar avoided less tree cover (0-25), preferred slope category (26-500), altitudes between 1600-2100 m, and preferred dense forest with northern aspects. Muntjac used all elevation ranges in the study area with a preference towards the dense forest and northern aspects. Serow preferred high tree cover > 75%, avoided low shrub cover (0-25%), preferred high shrub cover 51-75%, utilized higher elevation > 2100 m, avoided low elevation range and northern aspects. All species occupied similar habitat types, forest or scrub, except for the goral, which preferred open spaces. Between muntjac and sambar, the highest overlap was found (65%), and there was no overlap between chital and serow, chital and goral. Aspect, slope, altitude, and vegetation characteristics were found to be important factors for the overlap of ungulate sympatric species. One major reason for their ecological separation at the fine-scale level is the differential use of altitude by ungulates in the present study. This is confirmed by the avoidance by chital of altitudes > 900 m and serow of < 2100 m.

Keywords: altitude, grouping pattern, Himalayas, overlap, ungulates

Procedia PDF Downloads 113
9520 An Examination of Changes on Natural Vegetation due to Charcoal Production Using Multi Temporal Land SAT Data

Authors: T. Garba, Y. Y. Babanyara, M. Isah, A. K. Muktari, R. Y. Abdullahi

Abstract:

The increased in demand of fuel wood for heating, cooking and sometimes bakery has continued to exert appreciable impact on natural vegetation. This study focus on the use of multi-temporal data from land sat TM of 1986, land sat EMT of 1999 and lands sat ETM of 2006 to investigate the changes of Natural Vegetation resulting from charcoal production activities. The three images were classified based on bare soil, built up areas, cultivated land, and natural vegetation, Rock out crop and water bodies. From the classified images Land sat TM of 1986 it shows natural vegetation of the study area to be 308,941.48 hectares equivalent to 50% of the area it then reduces to 278,061.21 which is 42.92% in 1999 it again depreciated to 199,647.81 in 2006 equivalent to 30.83% of the area. Consequently cultivated continue increasing from 259,346.80 hectares (42%) in 1986 to 312,966.27 hectares (48.3%) in 1999 and then to 341.719.92 hectares (52.78%). These show that within the span of 20 years (1986 to 2006) the natural vegetation is depreciated by 119,293.81 hectares. This implies that if the menace is not control the natural might likely be lost in another twenty years. This is because forest cleared for charcoal production is normally converted to farmland. The study therefore concluded that there is the need for alternatives source of domestic energy such as the use of biomass which can easily be accessible and affordable to people. In addition, the study recommended that there should be strong policies enforcement for the protection forest reserved.

Keywords: charcoal, classification, data, images, land use, natural vegetation

Procedia PDF Downloads 346
9519 Linking the Genetic Signature of Free-Living Soil Diazotrophs with Process Rates under Land Use Conversion in the Amazon Rainforest

Authors: Rachel Danielson, Brendan Bohannan, S.M. Tsai, Kyle Meyer, Jorge L.M. Rodrigues

Abstract:

The Amazon Rainforest is a global diversity hotspot and crucial carbon sink, but approximately 20% of its total extent has been deforested- primarily for the establishment of cattle pasture. Understanding the impact of this large-scale disturbance on soil microbial community composition and activity is crucial in understanding potentially consequential shifts in nutrient or greenhouse gas cycling, as well as adding to the body of knowledge concerning how these complex communities respond to human disturbance. In this study, surface soils (0-10cm) were collected from three forests and three 45-year-old pastures in Rondonia, Brazil (the Amazon state with the greatest rate of forest destruction) in order to determine the impact of forest conversion on microbial communities involved in nitrogen fixation. Soil chemical and physical parameters were paired with measurements of microbial activity and genetic profiles to determine how community composition and process rates relate to environmental conditions. Measuring both the natural abundance of 15N in total soil N, as well as incorporation of enriched 15N2 under incubation has revealed that conversion of primary forest to cattle pasture results in a significant increase in the rate of nitrogen fixation by free-living diazotrophs. Quantification of nifH gene copy numbers (an essential subunit encoding the nitrogenase enzyme) correspondingly reveals a significant increase of genes in pasture compared to forest soils. Additionally, genetic sequencing of both nifH genes and transcripts shows a significant increase in the diversity of the present and metabolically active diazotrophs within the soil community. Levels of both organic and inorganic nitrogen tend to be lower in pastures compared to forests, with ammonium rather than nitrate as the dominant inorganic form. However, no significant or consistent differences in total, extractable, permanganate-oxidizable, or loss-on-ignition carbon are present between the two land-use types. Forest conversion is associated with a 0.5- 1.0 unit pH increase, but concentrations of many biologically relevant nutrients such as phosphorus do not increase consistently. Increases in free-living diazotrophic community abundance and activity appear to be related to shifts in carbon to nitrogen pool ratios. Furthermore, there may be an important impact of transient, low molecular weight plant-root-derived organic carbon on free-living diazotroph communities not captured in this study. Preliminary analysis of nitrogenase gene variant composition using NovoSeq metagenomic sequencing indicates that conversion of forest to pasture may significantly enrich vanadium-based nitrogenases. This indication is complemented by a significant decrease in available soil molybdenum. Very little is known about the ecology of diazotrophs utilizing vanadium-based nitrogenases, so further analysis may reveal important environmental conditions favoring their abundance and diversity in soil systems. Taken together, the results of this study indicate a significant change in nitrogen cycling and diazotroph community composition with the conversion of the Amazon Rainforest. This may have important implications for the sustainability of cattle pastures once established since nitrogen is a crucial nutrient for forage grass productivity.

Keywords: free-living diazotrophs, land use change, metagenomic sequencing, nitrogen fixation

Procedia PDF Downloads 167
9518 Machine Learning Techniques in Seismic Risk Assessment of Structures

Authors: Farid Khosravikia, Patricia Clayton

Abstract:

The main objective of this work is to evaluate the advantages and disadvantages of various machine learning techniques in two key steps of seismic hazard and risk assessment of different types of structures. The first step is the development of ground-motion models, which are used for forecasting ground-motion intensity measures (IM) given source characteristics, source-to-site distance, and local site condition for future events. IMs such as peak ground acceleration and velocity (PGA and PGV, respectively) as well as 5% damped elastic pseudospectral accelerations at different periods (PSA), are indicators of the strength of shaking at the ground surface. Typically, linear regression-based models, with pre-defined equations and coefficients, are used in ground motion prediction. However, due to the restrictions of the linear regression methods, such models may not capture more complex nonlinear behaviors that exist in the data. Thus, this study comparatively investigates potential benefits from employing other machine learning techniques as statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring pre-defined equations or coefficients. Moreover, it is shown that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available. Second, it is investigated how machine learning techniques could be beneficial for developing probabilistic seismic demand models (PSDMs), which provide the relationship between the structural demand responses (e.g., component deformations, accelerations, internal forces, etc.) and the ground motion IMs. In the risk framework, such models are used to develop fragility curves estimating exceeding probability of damage for pre-defined limit states, and therefore, control the reliability of the predictions in the risk assessment. In this study, machine learning algorithms like artificial neural network, random forest, and support vector machine are adopted and trained on the demand parameters to derive PSDMs for them. It is observed that such models can provide more accurate estimates of prediction in relatively shorter about of time compared to conventional methods. Moreover, they can be used for sensitivity analysis of fragility curves with respect to many modeling parameters without necessarily requiring more intense numerical response-history analysis.

Keywords: artificial neural network, machine learning, random forest, seismic risk analysis, seismic hazard analysis, support vector machine

Procedia PDF Downloads 82
9517 Crack Growth Life Prediction of a Fighter Aircraft Wing Splice Joint Under Spectrum Loading Using Random Forest Regression and Artificial Neural Networks with Hyperparameter Optimization

Authors: Zafer Yüce, Paşa Yayla, Alev Taşkın

Abstract:

There are heaps of analytical methods to estimate the crack growth life of a component. Soft computing methods have an increasing trend in predicting fatigue life. Their ability to build complex relationships and capability to handle huge amounts of data are motivating researchers and industry professionals to employ them for challenging problems. This study focuses on soft computing methods, especially random forest regressors and artificial neural networks with hyperparameter optimization algorithms such as grid search and random grid search, to estimate the crack growth life of an aircraft wing splice joint under variable amplitude loading. TensorFlow and Scikit-learn libraries of Python are used to build the machine learning models for this study. The material considered in this work is 7050-T7451 aluminum, which is commonly preferred as a structural element in the aerospace industry, and regarding the crack type; corner crack is used. A finite element model is built for the joint to calculate fastener loads and stresses on the structure. Since finite element model results are validated with analytical calculations, findings of the finite element model are fed to AFGROW software to calculate analytical crack growth lives. Based on Fighter Aircraft Loading Standard for Fatigue (FALSTAFF), 90 unique fatigue loading spectra are developed for various load levels, and then, these spectrums are utilized as inputs to the artificial neural network and random forest regression models for predicting crack growth life. Finally, the crack growth life predictions of the machine learning models are compared with analytical calculations. According to the findings, a good correlation is observed between analytical and predicted crack growth lives.

Keywords: aircraft, fatigue, joint, life, optimization, prediction.

Procedia PDF Downloads 142
9516 The Relationship between Environmental Factors and Purchasing Decisions in the Residential Market in Sweden

Authors: Agnieszka Zalejska-Jonsson

Abstract:

The Swedish Green Building Council (SGBC) was established in 2009. Since then, over 1000 buildings have been certified, of which approximately 600 are newly produced and 340 are residential buildings. During that time, approximately 2000 apartment buildings have been built in Sweden. This means that over a five- year period 17% of residential buildings have been certified according to the environmental building scheme. The certification of the building is not a guarantee of environmental progress but it gives us an indication of the extent of the progress. The overarching aim of this study is to investigate the factors behind the relatively slow evolution of the green residential housing market in Sweden. The intention is to examine stated willingness to pay (WTP) for green and low energy apartments, and to explore which factors have a significant effect on stated WTP among apartment owners. A green building was defined as a building certified according to the environmental scheme and a low energy building as a building designed and constructed with high energy efficiency goals. Data for this study were collected through a survey conducted among occupants of comparable apartment buildings: two green and one conventional. The total number of received responses was 429: green A (N=160), response rate 42%; green B (N=138) response rate 35%, and conventional (N=131) response rate 43%. The study applied a quasi-experimental method. Survey responses regarding factors affecting purchase of apartment, stated WTP and environmental literacy have been analysed using descriptive statistics, the Mann–Whitney (rank sum) test and logistic models. Comments received from respondents have been used for further interpretation of results. Results indicate that environmental education has a significant effect on stated WTP. Occupants who declared higher WTP showed a higher level of environmental literacy and indicated that energy efficiency was one of the important factors that affected their decision to buy an apartment. Generally, the respondents were more likely to pay more for low energy buildings than for green buildings. This is to a great extent a consequence of rational customer behaviour and difficulty in apprehending the meaning of green building certification. The analysis shows that people living in green buildings indicate higher WTP for both green and low energy buildings, the difference being statistically significant. It is concluded that growth in the green housing market in Sweden might be achieved if policymakers and developers engage in active education in the environmental labelling system. The demand for green buildings is more likely to increase when the difference between green and conventional buildings is easily understood and information is not only delivered by the estate agent, but is part of an environmental education programme.

Keywords: consumer, environmental education, housing market, stated WTP, Sweden

Procedia PDF Downloads 215
9515 Distribution and Population Status of Canis spp. Threats and Conservation in Lehri Nature Park, Salt Range, District Jhelum

Authors: Muhammad Saad, AzherBaig, Anwar Maqsood, Muhammad Waseem

Abstract:

The grey wolf has been ranked endangered and Asiatic jackal as near threatened in Pakistan. Scientific data on population and threats to these species are not available in Pakistan, which is required for their proper management and conservation. The present study was conducted to collect data on distribution range, population status and threats to both of these Canis species in Lehri Nature Park. The data were collected using direct observations and indirect signs in the field. The population of grey wolf and Asiatic jackal were scattered into pocket of the study area and its surroundings. The current population of grey wolf was estimated 06 individuals and that of Asiatic jackal 28 individuals in the study area. The present study showed that grey wolf and Asiatic jackal were distributed in the northern and southern part of the study area having dense vegetation cover of tress and shrub between the altitudes of 330 m and 515 m. The research finding revealed that the scrub forest is the most preferred habitat of both the species but due to anthropogenic pressure the scrub forest is under severe threat. The dominant trees species were Acacia modesta, Zizyphus nummularia, and Prosopis juliflora and shrubs species of Dodonea-viscosa, Calotropis procera and Adhatoda vasica. Urial is one of the natural prey species: their population is low due to a number of reasons and therefore the maximum dependence of the wolves was on the livestock of the local and nomadic shepherds. The main prey species in the livestock was goats and sheep. The interviews were conducted with the eye witnesses of wolf attacks including livestock being killed by 5-6 numbers of wolves in different hamlets in the study area. The killing rate of the livestock by the wolves was greater when the nomadic shepherds were present in the area and decreased when they left the area. Presence of nomadic shepherds and killing rate has relation with the shifting of the wolves from the study area. It is further concluded that the population of the grey wolf and Asiatic jackal has decreased over time due to less availability of the natural prey species and habitat destruction.

Keywords: wildlife ecology, population conservation, rehabilitation, conservation

Procedia PDF Downloads 476
9514 Assessment of Land Use and Land Cover Change in Lake Ol Bolossat Catchment, Nyandarua County, Kenya

Authors: John Wangui, Charles Gachene, Stephen Mureithi, Boniface Kiteme

Abstract:

Land use changes caused by demographic, natural variability, economic, technological and policy factors affect the goods and services derived from an ecosystem. In the past few decades, Lake Ol Bolossat catchment in Nyandarua County Kenya has been facing challenges of land cover changes threatening its capacity to perform ecosystems functions and adversely affecting communities and ecosystems downstream. This study assessed land cover changes in the catchment for a period of twenty eight years (from 1986 to 2014). Analysis of three Landsat images i.e. L5 TM 1986, L5 TM 1995 and L8 OLI/TIRS 2014 was done using ERDAS 9.2 software. The results show that dense forest, cropland and area under water increased by 27%, 29% and 3% respectively. On the other hand, open forest, dense grassland, open grassland, bushland and shrubland decreased by 3%, 3%, 11%, 26% and 1% respectively during the period under assessment. The lake was noted to have increased due to siltation caused by soil erosion causing a reduction in Lake’s depth and consequently causing temporary flooding of the wetland. The study concludes that the catchment is under high demographic pressure which would lead to resource use conflicts and therefore formulation of mitigation measures is highly recommended.

Keywords: land cover, land use change, land degradation, Nyandarua, Remote sensing

Procedia PDF Downloads 337
9513 Predicting OpenStreetMap Coverage by Means of Remote Sensing: The Case of Haiti

Authors: Ran Goldblatt, Nicholas Jones, Jennifer Mannix, Brad Bottoms

Abstract:

Accurate, complete, and up-to-date geospatial information is the foundation of successful disaster management. When the 2010 Haiti Earthquake struck, accurate and timely information on the distribution of critical infrastructure was essential for the disaster response community for effective search and rescue operations. Existing geospatial datasets such as Google Maps did not have comprehensive coverage of these features. In the days following the earthquake, many organizations released high-resolution satellite imagery, catalyzing a worldwide effort to map Haiti and support the recovery operations. Of these organizations, OpenStreetMap (OSM), a collaborative project to create a free editable map of the world, used the imagery to support volunteers to digitize roads, buildings, and other features, creating the most detailed map of Haiti in existence in just a few weeks. However, large portions of the island are still not fully covered by OSM. There is an increasing need for a tool to automatically identify which areas in Haiti, as well as in other countries vulnerable to disasters, that are not fully mapped. The objective of this project is to leverage different types of remote sensing measurements, together with machine learning approaches, in order to identify geographical areas where OSM coverage of building footprints is incomplete. Several remote sensing measures and derived products were assessed as potential predictors of OSM building footprints coverage, including: intensity of light emitted at night (based on VIIRS measurements), spectral indices derived from Sentinel-2 satellite (normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), soil-adjusted vegetation index (SAVI), urban index (UI)), surface texture (based on Sentinel-1 SAR measurements)), elevation and slope. Additional remote sensing derived products, such as Hansen Global Forest Change, DLR`s Global Urban Footprint (GUF), and World Settlement Footprint (WSF), were also evaluated as predictors, as well as OSM street and road network (including junctions). Using a supervised classification with a random forest classifier resulted in the prediction of 89% of the variation of OSM building footprint area in a given cell. These predictions allowed for the identification of cells that are predicted to be covered but are actually not mapped yet. With these results, this methodology could be adapted to any location to assist with preparing for future disastrous events and assure that essential geospatial information is available to support the response and recovery efforts during and following major disasters.

Keywords: disaster management, Haiti, machine learning, OpenStreetMap, remote sensing

Procedia PDF Downloads 101
9512 Narrative Point of View in Nature Documentary Films: A Study of The Cove (2009), Tale of a Forest (2012), and Before the Flood (2016)

Authors: Sakshi Yadav, Sushila Shekhawat

Abstract:

This study addresses different types of points of view as seen in nature documentary films with the help of three eco documentaries, and it would be significant in understanding the role of the narrative point of view as a tool for showing and telling in documentaries. Narrative analysis of a film forms an essential aspect of the discourse of scholarship in film studies. Narration is the chain of events occurring in time and space. The notion of narrative provides the idea of coherence and wholeness to the story. There are various components that the narration carries, one of which is the perspective or point of view. The narrator plays the role of a mediator between the film and the audience; thus, his perspective influences the way the audience interprets the film. Feature films have been analyzed through narrative points of view; however, this research intends to conduct it from the angle of a nature documentary film. The study will examine narrative viewpoints unique to nature documentary films using three ecological documentary films-The Cove (2009), Tale of a forest (2012), and Before the flood (2016). This research will apply the framework of narrative theory and will investigate the impact of the different types of narrative points of view, as each portrays the human-nature relationship from a different standpoint, and it will also study the effect that the narrative point of view has on the mode of these eco documentaries.

Keywords: ecodocumentary, narrative, human-nature relationship, point of view

Procedia PDF Downloads 66
9511 Fraud Detection in Credit Cards with Machine Learning

Authors: Anjali Chouksey, Riya Nimje, Jahanvi Saraf

Abstract:

Online transactions have increased dramatically in this new ‘social-distancing’ era. With online transactions, Fraud in online payments has also increased significantly. Frauds are a significant problem in various industries like insurance companies, baking, etc. These frauds include leaking sensitive information related to the credit card, which can be easily misused. Due to the government also pushing online transactions, E-commerce is on a boom. But due to increasing frauds in online payments, these E-commerce industries are suffering a great loss of trust from their customers. These companies are finding credit card fraud to be a big problem. People have started using online payment options and thus are becoming easy targets of credit card fraud. In this research paper, we will be discussing machine learning algorithms. We have used a decision tree, XGBOOST, k-nearest neighbour, logistic-regression, random forest, and SVM on a dataset in which there are transactions done online mode using credit cards. We will test all these algorithms for detecting fraud cases using the confusion matrix, F1 score, and calculating the accuracy score for each model to identify which algorithm can be used in detecting frauds.

Keywords: machine learning, fraud detection, artificial intelligence, decision tree, k nearest neighbour, random forest, XGBOOST, logistic regression, support vector machine

Procedia PDF Downloads 120
9510 Comparison Study of Machine Learning Classifiers for Speech Emotion Recognition

Authors: Aishwarya Ravindra Fursule, Shruti Kshirsagar

Abstract:

In the intersection of artificial intelligence and human-centered computing, this paper delves into speech emotion recognition (SER). It presents a comparative analysis of machine learning models such as K-Nearest Neighbors (KNN),logistic regression, support vector machines (SVM), decision trees, ensemble classifiers, and random forests, applied to SER. The research employs four datasets: Crema D, SAVEE, TESS, and RAVDESS. It focuses on extracting salient audio signal features like Zero Crossing Rate (ZCR), Chroma_stft, Mel Frequency Cepstral Coefficients (MFCC), root mean square (RMS) value, and MelSpectogram. These features are used to train and evaluate the models’ ability to recognize eight types of emotions from speech: happy, sad, neutral, angry, calm, disgust, fear, and surprise. Among the models, the Random Forest algorithm demonstrated superior performance, achieving approximately 79% accuracy. This suggests its suitability for SER within the parameters of this study. The research contributes to SER by showcasing the effectiveness of various machine learning algorithms and feature extraction techniques. The findings hold promise for the development of more precise emotion recognition systems in the future. This abstract provides a succinct overview of the paper’s content, methods, and results.

Keywords: comparison, ML classifiers, KNN, decision tree, SVM, random forest, logistic regression, ensemble classifiers

Procedia PDF Downloads 19
9509 Influence of Settlements and Human Activities on Beetle Diversity and Assemblage Structure at Small Islands of the Kepulauan Seribu Marine National Park and Nearby Java

Authors: Shinta Holdsworth, Jan Axmacher, Darren J. Mann

Abstract:

Beetles represent the most diverse insect taxon, and they contribute significantly to a wide range of vital ecological functions. Examples include decomposition by bark beetles, nitrogen recycling and dung processing by dung beetles or pest control by predatory ground beetles. Nonetheless, research into the distribution patterns, species richness and functional diversity of beetles particularly from tropical regions remains extremely limited. In our research, we aim to investigate the distribution and diversity patterns of beetles and the roles they play in small tropical island ecosystems in the Kepulauan Seribu Marine National Park and on Java. Our research furthermore provides insights into the effects anthropogenic activities have on the assemblage composition and diversity of beetles on the small islands. We recorded a substantial number of highly abundant small island species, including a substantial number of unique small island species across the study area, highlighting these islands’ potential importance for the regional conservation of genetic resources. The highly varied patterns observed in relation to the use of different trapping types - pitfall traps and flight interception traps (FITs) - underscores the need for complementary trapping strategies that combine multiple methods for beetle community surveys in tropical islands. The significant impacts of human activities have on the small island beetle faunas were also highlighted in our research. More island beetle species encountered in settlement than forest areas shows clear trend of positive links between anthropogenic activities and the overall beetle species richness. However, undisturbed forests harboured a high number of unique species, also in comparison to disturbed forests. Finally, our study suggests that, with regards to different feeding guilds, the diversity of herbivorous beetles on islands is strongly affected by the different levels of forest cover encountered.

Keywords: beetle diversity, forest disturbance, island biogeography, island settlement

Procedia PDF Downloads 188
9508 Optimization of Hate Speech and Abusive Language Detection on Indonesian-language Twitter using Genetic Algorithms

Authors: Rikson Gultom

Abstract:

Hate Speech and Abusive language on social media is difficult to detect, usually, it is detected after it becomes viral in cyberspace, of course, it is too late for prevention. An early detection system that has a fairly good accuracy is needed so that it can reduce conflicts that occur in society caused by postings on social media that attack individuals, groups, and governments in Indonesia. The purpose of this study is to find an early detection model on Twitter social media using machine learning that has high accuracy from several machine learning methods studied. In this study, the support vector machine (SVM), Naïve Bayes (NB), and Random Forest Decision Tree (RFDT) methods were compared with the Support Vector machine with genetic algorithm (SVM-GA), Nave Bayes with genetic algorithm (NB-GA), and Random Forest Decision Tree with Genetic Algorithm (RFDT-GA). The study produced a comparison table for the accuracy of the hate speech and abusive language detection model, and presented it in the form of a graph of the accuracy of the six algorithms developed based on the Indonesian-language Twitter dataset, and concluded the best model with the highest accuracy.

Keywords: abusive language, hate speech, machine learning, optimization, social media

Procedia PDF Downloads 105
9507 Storm-water Management for Greenfield Area Using Low Impact Development Concept for Town Planning Scheme Mechanism

Authors: Sahil Patel

Abstract:

Increasing urbanization leads to a concrete forest. The effects of new development practices occur in the natural hydrologic cycle. Here the concerns have been raised about the groundwater recharge in sufficient quantity. With further development, porous surfaces reduce rapidly. A city like Ahmedabad, with a non-perennial river, is 100% dependent on groundwater. The Ahmedabad city receives its domestic use water from the Narmada river, located about 200 km away. The expenses to bring water is much higher. Ahmedabad city receives annually 800 mm rainfall, and mostly this water increases the local level waterlogging problems; after that, water goes to the Sabarmati river and merges into the sea. The existing developed area of Ahmedabad city is very dense, and does not offer many chances to change the built form and increase porous surfaces to absorb storm-water. Therefore, there is a need to plan upcoming areas with more effective solutions to manage storm-water. This paper is focusing on the management of stormwater for new development by retaining natural hydrology. The Low Impact Development (LID) concept is used to manage storm-water efficiently. Ahmedabad city has a tool called the “Town Planning Scheme,” which helps the local body drive new development by land pooling mechanism. This paper gives a detailed analysis of the selected area (proposed Town Planning Scheme area by the local authority) in Ahmedabad. Here the development control regulations for individual developers and some physical elements for public places are presented to manage storm-water. There is a different solution for the Town Planning scheme than that of the conventional way. A local authority can use it for any area, but it can be site-specific. In the end, there are benefits to locals with some financial analysis and comparisons.

Keywords: water management, green field development, low impact development, town planning scheme

Procedia PDF Downloads 100
9506 Reinforcement Learning for Classification of Low-Resolution Satellite Images

Authors: Khadija Bouzaachane, El Mahdi El Guarmah

Abstract:

The classification of low-resolution satellite images has been a worthwhile and fertile field that attracts plenty of researchers due to its importance in monitoring geographical areas. It could be used for several purposes such as disaster management, military surveillance, agricultural monitoring. The main objective of this work is to classify efficiently and accurately low-resolution satellite images by using novel technics of deep learning and reinforcement learning. The images include roads, residential areas, industrial areas, rivers, sea lakes, and vegetation. To achieve that goal, we carried out experiments on the sentinel-2 images considering both high accuracy and efficiency classification. Our proposed model achieved a 91% accuracy on the testing dataset besides a good classification for land cover. Focus on the parameter precision; we have obtained 93% for the river, 92% for residential, 97% for residential, 96% for the forest, 87% for annual crop, 84% for herbaceous vegetation, 85% for pasture, 78% highway and 100% for Sea Lake.

Keywords: classification, deep learning, reinforcement learning, satellite imagery

Procedia PDF Downloads 176