Environmental and Pollution Spatial Data Classification with Support Vector Machines and Geostatistics
نویسنده
چکیده
The work deals with the application of Support Vector Machines (SVM) for environmental and pollution spatial data analysis and modeling. The main attention is paid to classification of spatially distributed data with SVM and comparison with probabilistic mapping using nonparametric geostatistical model (indicator kriging). SVMs with RBF kernels were used. It is shown that optimal bandwidth of kernel can be chosen by minimizing testing error. Real data on sediments pollution in the Geneva lake are used.
منابع مشابه
A comparative study of performance of K-nearest neighbors and support vector machines for classification of groundwater
The aim of this work is to examine the feasibilities of the support vector machines (SVMs) and K-nearest neighbor (K-NN) classifier methods for the classification of an aquifer in the Khuzestan Province, Iran. For this purpose, 17 groundwater quality variables including EC, TDS, turbidity, pH, total hardness, Ca, Mg, total alkalinity, sulfate, nitrate, nitrite, fluoride, phosphate, Fe, Mn, Cu, ...
متن کاملJune 2000 Submitted to ICONIP 2000 ENVIRONMENTAL DATA MAPPING WITH SUPPORT VECTOR REGRESSION AND GEOSTATISTICS Mikhail
The paper presents decision-oriented mapping of pollution using hybrid models based on statistical learning theory (support vector regression or SVR) and spatial statistics (geostatistics). Adaptive and robust SVR approach is used to model non-linear large scale trends in the region and geostatistical models – spatial predictions and spatial simulations – are used to prepare decisionoriented ma...
متن کاملEnvironmental Data Mapping with Support Vector Regression and Geostatistics
The paper presents decision-oriented mapping of pollution using hybrid models based on statistical learning theory (support vector regression or SVR) and spatial statistics (geostatistics). Adaptive and robust SVR approach is used to model non-linear large scale trends in the region and geostatistical models – spatial predictions and spatial simulations – are used to prepare decisionoriented ma...
متن کاملMachine Learning Algorithms for GeoSpatial Data. Applications and Software Tools
Nowadays machine learning (ML), including Artificial Neural Networks (ANN) of different architectures and Support Vector Machines (SVM), provides extremely important tools for intelligent geoand environmental data analysis, processing and visualisation. Machine learning is an important complement to the traditional techniques like geostatistics. This paper presents a review of several contempor...
متن کاملA prediction distribution of atmospheric pollutants using support vector machines, discriminant analysis and mapping tools (Case study: Tunisia)
Monitoring and controlling air quality parameters form an important subject of atmospheric and environmental research today due to the health impacts caused by the different pollutants present in the urban areas. The support vector machine (SVM), as a supervised learning analysis method, is considered an effective statistical tool for the prediction and analysis of air quality. The work present...
متن کامل