Multi-scale Support Vector Regression for Hot Spot Detection and Modeling
نویسندگان
چکیده
The algorithmic approach to data modelling has developed rapidly last years. It includes methods of data mining and machine learning. They follow the data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the recent success in application of Support Vector algorithms to geospatial data, this paper introduces an extension of the Support Vector Regression algorithm. This extension allows for simultaneous modelling environmental data at several spatial scales. The joint influence of different scales is tuned from data in automatic way, providing an optimum mixture of short and long scale models. The method is spatially adaptive to data. Particularly, it provides a way to model local anomalies in data which may emerge due to short-scale fallouts from anthropogenic accidents. For this approach to be successful, the prior knowledge of the existence of such short-scale patterns is important. The behaviour of the multi-scale Support Vector model is described in the paper both theoretically and experimentally. The method is applied to model the hot spots of Cs137 radioactivity after the Chernobyl fallout.
منابع مشابه
Machine learning algorithms in air quality modeling
Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...
متن کاملTehran Stock Price Modeling and Forecasting Using Support Vector Regression (SVR) and Its Comparison with the Classic Model ARIMA
متن کامل
Application of Support Vector Machine Regression for Predicting Critical Responses of Flexible Pavements
This paper aims to assess the application of Support Vector Machine (SVM) regression in order to analysis flexible pavements. To this end, 10000 Four-layer flexible pavement sections consisted of asphalt concrete layer, granular base layer, granular subbase layer, and subgrade soil were analyzed under the effect of standard axle loading using multi-layered elastic theory and pavement critical r...
متن کاملMonthly rainfall Forecasting using genetic programming and support vector machine
Rainfall and runoff estimation play a fundamental and effective role in the management and proper operation of the watershed, dams and reservoirs management, minimizing the damage caused by floods and droughts, and water resources management. The optimal performance of intelligent models has increased their use to predict various hydrological phenomena. Therefore, in this study, two intelligent...
متن کاملModeling and analysis of leishmaniasis distribution process using multilayer perceptron neural network and support vector regression (Case study: villages of Isfahan province)
Villages located in Isfahan province are one of the areas prone to the spread of cutaneous leishmaniasis, which is characterized by the occurrence of wounds on the skin. To predict the future prevalence of cutaneous leishmaniasis, Continuous monitoring of the spatial distribution of this disease is essential. Disease modeling was performed using two machine learning algorithms called support ve...
متن کامل