Mathematical models application for mapping soils spatial distribution on the example of the farm from the North of Udmurt Republic of Russia

3rd International Conference Environment and Sustainable Development of Territories: Ecological Challenges of the 21st Century

生态环境科学;地球科学;经济学

Dokuchaev, P.M.^1 ; Meshalkina, J.L.^1,2,3 ; Yaroslavtsev, A.M.^2,4,5

Soil Science Faculty, Lomonosov Moscow State University, Leninskye Gory, GSP-1, bld. 12, Moscow

119991, Russia^1

Department of Ecology, Russian Timiryazev State Agrarian University, Timiryazevskaya Str. 49, Moscow

127550, Russia^2

Dokuchaev Soil Science Institute, Pyzhyovskiy lane 7, Moscow

119017, Russia^3

RUDN University, Miklukho-Maklaya str.6, Moscow

117198, Russia^4

School of Natural Sciences, Far Eastern Federal University, Sukhanova St. 8, Vladivostok

690090, Russia^5

关键词: Automatic classification;    Comparative analysis;    Multinomial logistic regression;    Multiple logistic regression;    Quantitative assessments;    Support vector machines algorithms;    Support vector method;    Visual interpretation;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/107/1/012113/pdf
DOI  :  10.1088/1755-1315/107/1/012113

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Comparative analysis of soils geospatial modeling using multinomial logistic regression, decision trees, random forest, regression trees and support vector machines algorithms was conducted. The visual interpretation of the digital maps obtained and their comparison with the existing map, as well as the quantitative assessment of the individual soil groups detection overall accuracy and of the models kappa showed that multiple logistic regression, support vector method, and random forest models application with spatial prediction of the conditional soil groups distribution can be reliably used for mapping of the study area. It has shown the most accurate detection for sod-podzolics soils (Phaeozems Albic) lightly eroded and moderately eroded soils. In second place, according to the mean overall accuracy of the prediction, there are sod-podzolics soils - non-eroded and warp one, as well as sod-gley soils (Umbrisols Gleyic) and alluvial soils (Fluvisols Dystric, Umbric). Heavy eroded sod-podzolics and gray forest soils (Phaeozems Albic) were detected by methods of automatic classification worst of all.