Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch042
L. Sharma, Suman Sinha
Ecological Footprint (EF) analysis is the spatial measurement of ecological load exerted by the humans on the earth that arises from the concept of sustainability and sustainable use of Earth's resources. A region-based EF study is conducted for Birla Institute of Technology, Mesra (India) campus to improve its sustainability. Highlight of the study is the explicitness of the methodology for determining the EF that incorporates analysis derived from conversion factors mentioned in the Ecological Footprint consultancy publications along with inputs from GIS domain. Questionnaire-based survey from the respondents regarding resource utilization and geospatial enumeration of land use land cover that harbors the population and their resources are the two integral parts of the analysis. Total EF of the institution campus is calculated to be 0.645 gha/ individual. This analysis provides a strong framework for combining efforts in a manner that can communicate the immediate priorities for improving the sustainability strategy of the campus area.
{"title":"Measuring Dynamics of Ecological Footprint as an Index of Environmental Sustainability at the Regional Level Using Geospatial Information Technology","authors":"L. Sharma, Suman Sinha","doi":"10.4018/978-1-5225-7033-2.ch042","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch042","url":null,"abstract":"Ecological Footprint (EF) analysis is the spatial measurement of ecological load exerted by the humans on the earth that arises from the concept of sustainability and sustainable use of Earth's resources. A region-based EF study is conducted for Birla Institute of Technology, Mesra (India) campus to improve its sustainability. Highlight of the study is the explicitness of the methodology for determining the EF that incorporates analysis derived from conversion factors mentioned in the Ecological Footprint consultancy publications along with inputs from GIS domain. Questionnaire-based survey from the respondents regarding resource utilization and geospatial enumeration of land use land cover that harbors the population and their resources are the two integral parts of the analysis. Total EF of the institution campus is calculated to be 0.645 gha/ individual. This analysis provides a strong framework for combining efforts in a manner that can communicate the immediate priorities for improving the sustainability strategy of the campus area.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78261622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch044
Jon M. Corbett, Samantha Brennan, Aidan Whitely
Communities in the Okanagan Valley, Canada are increasingly under threat from forest fires due to climate change and expanding urban development into fire interface zones. The effects of forest fires are not always quantifiable ‘hard' impacts. The fluid and chaotic ‘soft' impacts can have a profound effect on the collective consciousness of the people living close to the fires. To make sense of these impacts and understand where and when these forest fires have taken place, the authors have developed and implemented a Geoweb tool to support citizen-to-citizen dialogue and tell the stories of these impacts. This article will explore the interlinked ‘chaos' that exists between forest fires, GIS and volunteered geographic information, using a Geoweb focused case study from the Okanagan Valley, and argue that the Geoweb offers an unprecedented opportunity for citizen-citizen interaction and combines many types of dissimilar and unstructured data into a unified whole.
{"title":"Harnessing the Chaotic","authors":"Jon M. Corbett, Samantha Brennan, Aidan Whitely","doi":"10.4018/978-1-5225-7033-2.ch044","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch044","url":null,"abstract":"Communities in the Okanagan Valley, Canada are increasingly under threat from forest fires due to climate change and expanding urban development into fire interface zones. The effects of forest fires are not always quantifiable ‘hard' impacts. The fluid and chaotic ‘soft' impacts can have a profound effect on the collective consciousness of the people living close to the fires. To make sense of these impacts and understand where and when these forest fires have taken place, the authors have developed and implemented a Geoweb tool to support citizen-to-citizen dialogue and tell the stories of these impacts. This article will explore the interlinked ‘chaos' that exists between forest fires, GIS and volunteered geographic information, using a Geoweb focused case study from the Okanagan Valley, and argue that the Geoweb offers an unprecedented opportunity for citizen-citizen interaction and combines many types of dissimilar and unstructured data into a unified whole.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88752115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch057
Jenicka S.
Accuracy of land cover classification in remotely sensed images relies on the features extracted and the classifier used. Texture features are significant in land cover classification. Traditional texture models capture only patterns with discrete boundaries whereas fuzzy patterns need to be classified by assigning due weightage to uncertainty. When remotely sensed image contains noise, the image may have fuzzy patterns characterizing land covers and fuzzy boundaries separating land covers. So a fuzzy texture model is proposed for effective classification of land covers in remotely sensed images and the model uses Sugeno Fuzzy Inference System (FIS). Support Vector Machine (SVM) is used for precise and fast classification of image pixels. Hence it is proposed to use a hybrid of fuzzy texture model and SVM for land cover classification of remotely sensed images. In this chapter, land cover classification of IRS-P6, LISS-IV remotely sensed image is performed using multivariate version of the proposed texture model.
{"title":"Sugeno Fuzzy-Inference-System-Based Land Cover Classification of Remotely Sensed Images","authors":"Jenicka S.","doi":"10.4018/978-1-5225-7033-2.ch057","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch057","url":null,"abstract":"Accuracy of land cover classification in remotely sensed images relies on the features extracted and the classifier used. Texture features are significant in land cover classification. Traditional texture models capture only patterns with discrete boundaries whereas fuzzy patterns need to be classified by assigning due weightage to uncertainty. When remotely sensed image contains noise, the image may have fuzzy patterns characterizing land covers and fuzzy boundaries separating land covers. So a fuzzy texture model is proposed for effective classification of land covers in remotely sensed images and the model uses Sugeno Fuzzy Inference System (FIS). Support Vector Machine (SVM) is used for precise and fast classification of image pixels. Hence it is proposed to use a hybrid of fuzzy texture model and SVM for land cover classification of remotely sensed images. In this chapter, land cover classification of IRS-P6, LISS-IV remotely sensed image is performed using multivariate version of the proposed texture model.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86774532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch070
A. Santra
Earth's land surface temperature is considered to be very important for modeling the environment. Following the trend of increasing global population, urban areas are expanding in spatio-temporal domain. In this way it is affecting the urban climate and subsequently the global climate. Thus, scientific understanding is required to conceive the knowledge about interaction between urban land use/land cover and the atmospheric conditions prevailing in that area. In this chapter the land surface temperature estimation and urban heat island detection are perceived from remote sensing perspective. The chapter in this context highlights three major aspects, viz. the theoretical background, description about some of the common thermal sensors and widely used algorithms to retrieve surface temperature from these satellite sensors.
{"title":"Land Surface Temperature Estimation and Urban Heat Island Detection","authors":"A. Santra","doi":"10.4018/978-1-5225-7033-2.ch070","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch070","url":null,"abstract":"Earth's land surface temperature is considered to be very important for modeling the environment. Following the trend of increasing global population, urban areas are expanding in spatio-temporal domain. In this way it is affecting the urban climate and subsequently the global climate. Thus, scientific understanding is required to conceive the knowledge about interaction between urban land use/land cover and the atmospheric conditions prevailing in that area. In this chapter the land surface temperature estimation and urban heat island detection are perceived from remote sensing perspective. The chapter in this context highlights three major aspects, viz. the theoretical background, description about some of the common thermal sensors and widely used algorithms to retrieve surface temperature from these satellite sensors.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90539250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-3440-2.CH024
Mulalu I. Mulalu
Geographic Information Systems (GIS) are essentially concerned with fixing locations of features and attaching data to them. This geographic data is subsequently used in spatial analysis as a means to support problem analysis and solution modeling through exploratory data analysis and experimentation with various alternative solutions. Ultimately GIS is used for informed decision making. With the advent of technologies that support participation, digital mapping, Global Positioning System (GPS), the internet, Web Mapping, Web GIS, Web 2.0 and Web 3.0 technologies and smart phones, many people all over the world have become capacitated to collect and communicate geo-tagged multimedia information, a phenomenon that is known as crowdsourcing. One example of crowdsourcing is incorporating geotagged information collected by volunteers into a GIS. Consequently, crowdsourcing facilitates PGIS to become a powerful practice that can be leveraged to collect geographic data over extensive landscapes and often in near real time.
{"title":"Participatory Geographic Information Systems Within a Crowdsourcing Environment, With Special Reference to Volunteered Geographic Information","authors":"Mulalu I. Mulalu","doi":"10.4018/978-1-5225-3440-2.CH024","DOIUrl":"https://doi.org/10.4018/978-1-5225-3440-2.CH024","url":null,"abstract":"Geographic Information Systems (GIS) are essentially concerned with fixing locations of features and attaching data to them. This geographic data is subsequently used in spatial analysis as a means to support problem analysis and solution modeling through exploratory data analysis and experimentation with various alternative solutions. Ultimately GIS is used for informed decision making. With the advent of technologies that support participation, digital mapping, Global Positioning System (GPS), the internet, Web Mapping, Web GIS, Web 2.0 and Web 3.0 technologies and smart phones, many people all over the world have become capacitated to collect and communicate geo-tagged multimedia information, a phenomenon that is known as crowdsourcing. One example of crowdsourcing is incorporating geotagged information collected by volunteers into a GIS. Consequently, crowdsourcing facilitates PGIS to become a powerful practice that can be leveraged to collect geographic data over extensive landscapes and often in near real time.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86553785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch020
Y. Kostyuchenko, Yulia Stoyka, Iurii Negoda, Ivan Kopachevsky
Task of soft computing for decision support in field of risk management is analyzed in this chapter. Multi-model approach is described. Interrelations between models, remote sensing data and forecasting are described. Method of water quality assessment using satellite observation is described. Method is based on analysis of spectral reflectance of aquifers. Correlations between reflectance and pollutions are quantified. Fuzzy logic based approach for decision support in field of water quality degradation risk is discussed. Decision on water quality is making based on fuzzy algorithm using limited set of uncertain parameters. It is shown that this algorithm allows estimate water quality degradation rate and pollution risks. Using proposed approach, maps of surface water pollution risk from point and diffuse sources are calculated. Conclusions concerned soft computing in risk management are proposed and discussed. It was demonstrated, that basing on spatially distributed measurement data, proposed approach allows to calculate risk parameters with resolution close to observations.
{"title":"Decision Making Under Deep Uncertainty With Fuzzy Algorithm in Framework of Multi-Model Approach","authors":"Y. Kostyuchenko, Yulia Stoyka, Iurii Negoda, Ivan Kopachevsky","doi":"10.4018/978-1-5225-7033-2.ch020","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch020","url":null,"abstract":"Task of soft computing for decision support in field of risk management is analyzed in this chapter. Multi-model approach is described. Interrelations between models, remote sensing data and forecasting are described. Method of water quality assessment using satellite observation is described. Method is based on analysis of spectral reflectance of aquifers. Correlations between reflectance and pollutions are quantified. Fuzzy logic based approach for decision support in field of water quality degradation risk is discussed. Decision on water quality is making based on fuzzy algorithm using limited set of uncertain parameters. It is shown that this algorithm allows estimate water quality degradation rate and pollution risks. Using proposed approach, maps of surface water pollution risk from point and diffuse sources are calculated. Conclusions concerned soft computing in risk management are proposed and discussed. It was demonstrated, that basing on spatially distributed measurement data, proposed approach allows to calculate risk parameters with resolution close to observations.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79945293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch023
Balaguru Balakrishnan, Nagamurugan Nandakumar, Soosairaj Sebastin, Khaleel Ahamed Abdul Kareem
Conservation of the species in their native landscapes required understanding patterns of spatial distribution of species and their ecological connectivity through Species Distribution Models (SDM) by generation and integration of spatial data from different sources using Geographical Information System (GIS) tools. SDM is an ecological/spatial model which combines datasets and maps of occurrence of target species and their geographical and environmental variables by linking various algorithms together, that has been applied to either identify or predict the regions fulfilling the set conditions. This article is focused on comprehensive review of spatial data requirements, statistical algorithms and softwares used to generate the SDMs. This chapter also includes a case study predicting the suitable habitat distribution of Gnetum ula, an endemic and vulnerable plant species using maximum entropy (MaxEnt) species distribution model for species occurrences with inputs from environmental variables such as bioclimate and elevation.
{"title":"Species Distribution Models (SDM) – A Strategic Tool for Predicting Suitable Habitats for Conserving the Target Species","authors":"Balaguru Balakrishnan, Nagamurugan Nandakumar, Soosairaj Sebastin, Khaleel Ahamed Abdul Kareem","doi":"10.4018/978-1-5225-7033-2.ch023","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch023","url":null,"abstract":"Conservation of the species in their native landscapes required understanding patterns of spatial distribution of species and their ecological connectivity through Species Distribution Models (SDM) by generation and integration of spatial data from different sources using Geographical Information System (GIS) tools. SDM is an ecological/spatial model which combines datasets and maps of occurrence of target species and their geographical and environmental variables by linking various algorithms together, that has been applied to either identify or predict the regions fulfilling the set conditions. This article is focused on comprehensive review of spatial data requirements, statistical algorithms and softwares used to generate the SDMs. This chapter also includes a case study predicting the suitable habitat distribution of Gnetum ula, an endemic and vulnerable plant species using maximum entropy (MaxEnt) species distribution model for species occurrences with inputs from environmental variables such as bioclimate and elevation.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72451567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/IJAEIS.2019010101
A. Solomou, A. Sfougaris
The Mediterranean basin is a global hotspot of biodiversity. Woody plants are key components of ecosystems. This article explores the environmental impacts on woody plant species richness and diversity in maquis and abandoned olive groves in an important ecological area of central Greece. The results showed that woody plant species richness and diversity had increasing values in maquis compared to abandoned olive groves. According to Principal Component Analysis, woody plant species richness and diversity (Shannon diversity index) were positively correlated with soil organic matter, plant litter, N, P, K, slope and precipitation in maquis. Also, positive correlations among woody plant species richness and diversity, and soil organic matter, and slope were detected in abandoned olive groves. Conclusively, the present study is the first in the area and the results it will be utilized as a decision support tool for sustainability assessment of ecosystems with the help of the information systems.
{"title":"Predicting Woody Plant Diversity as Key Component of Ecosystems","authors":"A. Solomou, A. Sfougaris","doi":"10.4018/IJAEIS.2019010101","DOIUrl":"https://doi.org/10.4018/IJAEIS.2019010101","url":null,"abstract":"The Mediterranean basin is a global hotspot of biodiversity. Woody plants are key components of ecosystems. This article explores the environmental impacts on woody plant species richness and diversity in maquis and abandoned olive groves in an important ecological area of central Greece. The results showed that woody plant species richness and diversity had increasing values in maquis compared to abandoned olive groves. According to Principal Component Analysis, woody plant species richness and diversity (Shannon diversity index) were positively correlated with soil organic matter, plant litter, N, P, K, slope and precipitation in maquis. Also, positive correlations among woody plant species richness and diversity, and soil organic matter, and slope were detected in abandoned olive groves. Conclusively, the present study is the first in the area and the results it will be utilized as a decision support tool for sustainability assessment of ecosystems with the help of the information systems.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4018/IJAEIS.2019010101","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41310069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-5219-2.CH006
K. Mahata, R. Das, Subhasish Das, Anasua Sarkar
Computer science plays a major role in image segmentation and image processing applications. Despite the computational cost, PSO evaluated QCA approaches perform comparable to or better than their crisp counterparts. This novel approach, proposed in this chapter, has been found to enhance the functionality of the CA rule base and thus enhance the established potentiality of the fuzzy-based segmentation domain with the help of quantum cellular automata. This new unsupervised method is able to detect clusters using 2-dimensional quantum cellular automata model based on PSO evaluation. As a discrete, dynamical system, cellular automaton explores uniformly interconnected cells with states. In the second phase, it utilizes a 2-dimensional cellular automata to prioritize allocations of mixed pixels among overlapping land cover areas. The authors experiment on Tilaya Reservoir Catchment on Barakar River. The clustered regions are compared with well-known PSO, FCM, and k-means methods and also with the ground truth knowledge. The results show the superiority of the new method.
{"title":"Landcover Change Detection Using PSO-Evaluated Quantum CA Approach on Multi-Temporal Remote-Sensing Watershed Images","authors":"K. Mahata, R. Das, Subhasish Das, Anasua Sarkar","doi":"10.4018/978-1-5225-5219-2.CH006","DOIUrl":"https://doi.org/10.4018/978-1-5225-5219-2.CH006","url":null,"abstract":"Computer science plays a major role in image segmentation and image processing applications. Despite the computational cost, PSO evaluated QCA approaches perform comparable to or better than their crisp counterparts. This novel approach, proposed in this chapter, has been found to enhance the functionality of the CA rule base and thus enhance the established potentiality of the fuzzy-based segmentation domain with the help of quantum cellular automata. This new unsupervised method is able to detect clusters using 2-dimensional quantum cellular automata model based on PSO evaluation. As a discrete, dynamical system, cellular automaton explores uniformly interconnected cells with states. In the second phase, it utilizes a 2-dimensional cellular automata to prioritize allocations of mixed pixels among overlapping land cover areas. The authors experiment on Tilaya Reservoir Catchment on Barakar River. The clustered regions are compared with well-known PSO, FCM, and k-means methods and also with the ground truth knowledge. The results show the superiority of the new method.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78548710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.4018/978-1-5225-7033-2.ch050
J. C. Tomàs, F. Faria, J. Esquerdo, A. Coutinho, C. B. Medeiros
This paper presents a new approach to deal with agricultural crop recognition using SVM (Support Vector Machine), applied to time series of NDVI images. The presented method can be divided into two steps. First, the Timesat software package is used to extract a set of crop features from the NDVI time series. These features serve as descriptors that characterize each NDVI vegetation curve, i.e., the period comprised between sowing and harvesting dates. Then, it is used an SVM to learn the patterns that define each type of crop, and create a crop model that allows classifying new series. The authors present a set of experiments that show the effectiveness of this technique. They evaluated their algorithm with a collection of more than 3000 time series from the Brazilian State of Mato Grosso spanning 4 years (2009-2013). Such time series were annotated in the field by specialists from Embrapa (Brazilian Agricultural Research Corporation). This methodology is generic, and can be adapted to distinct regions and crop profiles.
{"title":"SiRCub, A Novel Approach to Recognize Agricultural Crops Using Supervised Classification","authors":"J. C. Tomàs, F. Faria, J. Esquerdo, A. Coutinho, C. B. Medeiros","doi":"10.4018/978-1-5225-7033-2.ch050","DOIUrl":"https://doi.org/10.4018/978-1-5225-7033-2.ch050","url":null,"abstract":"This paper presents a new approach to deal with agricultural crop recognition using SVM (Support Vector Machine), applied to time series of NDVI images. The presented method can be divided into two steps. First, the Timesat software package is used to extract a set of crop features from the NDVI time series. These features serve as descriptors that characterize each NDVI vegetation curve, i.e., the period comprised between sowing and harvesting dates. Then, it is used an SVM to learn the patterns that define each type of crop, and create a crop model that allows classifying new series. The authors present a set of experiments that show the effectiveness of this technique. They evaluated their algorithm with a collection of more than 3000 time series from the Brazilian State of Mato Grosso spanning 4 years (2009-2013). Such time series were annotated in the field by specialists from Embrapa (Brazilian Agricultural Research Corporation). This methodology is generic, and can be adapted to distinct regions and crop profiles.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79203001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：