Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на этот ресурс: http://elar.urfu.ru/handle/10995/90155
Название: Topsoil pollution forecasting using artificial neural networks on the example of the abnormally distributed heavy metal at Russian subarctic
Авторы: Tarasov, D. A.
Buevich, A. G.
Sergeev, A. P.
Shichkin, A. V.
Baglaeva, E. M.
Дата публикации: 2017
Издатель: American Institute of Physics Inc.
Библиографическое описание: Topsoil pollution forecasting using artificial neural networks on the example of the abnormally distributed heavy metal at Russian subarctic / D. A. Tarasov, A. G. Buevich, A. P. Sergeev, A. V. Shichkin, et al. . — DOI 10.1063/1.4981964 // AIP Conference Proceedings. — 2017. — Iss. 1836. — 20024.
Аннотация: Forecasting the soil pollution is a considerable field of study in the light of the general concern of environmental protection issues. Due to the variation of content and spatial heterogeneity of pollutants distribution at urban areas, the conventional spatial interpolation models implemented in many GIS packages mostly cannot provide appreciate interpolation accuracy. Moreover, the problem of prediction the distribution of the element with high variability in the concentration at the study site is particularly difficult. The work presents two neural networks models forecasting a spatial content of the abnormally distributed soil pollutant (Cr) at a particular location of the subarctic Novy Urengoy, Russia. A method of generalized regression neural network (GRNN) was compared to a common multilayer perceptron (MLP) model. The proposed techniques have been built, implemented and tested using ArcGIS and MATLAB. To verify the models performances, 150 scattered input data points (pollutant concentrations) have been selected from 8.5 km2 area and then split into independent training data set (105 points) and validation data set (45 points). The training data set was generated for the interpolation using ordinary kriging while the validation data set was used to test their accuracies. The networks structures have been chosen during a computer simulation based on the minimization of the RMSE. The predictive accuracy of both models was confirmed to be significantly higher than those achieved by the geostatistical approach (kriging). It is shown that MLP could achieve better accuracy than both kriging and even GRNN for interpolating surfaces. © 2017 Author(s).
Ключевые слова: ARTIFICIAL NEURAL NETWORKS
CHROMIUM
KRIGING
POLLUTION
RESIDUAL KRIGING
URI: http://elar.urfu.ru/handle/10995/90155
Условия доступа: info:eu-repo/semantics/openAccess
Идентификатор SCOPUS: 85021313381
Идентификатор WOS: 000409539000024
Идентификатор PURE: 1931696
ISSN: 0094-243X
ISBN: 9780735415065
DOI: 10.1063/1.4981964
Располагается в коллекциях:Научные публикации ученых УрФУ, проиндексированные в SCOPUS и WoS CC

Файлы этого ресурса:
Файл Описание РазмерФормат 
10.1063-1.4981964.pdf818,36 kBAdobe PDFПросмотреть/Открыть


Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.