Scholarlink

Abstract <p>Results of digital mapping of the humus horizon thickness (HHT) in the soils of the Cis-Salair Plain using the Random Forest (RF) machine learning algorithm implemented on the Google Earth Engine cloud online platform are reported. A total of 92 predictors are employed to characterize the soil formation factors, including climate, relief, vegetation, spatial position, and soil properties. Training (<i>n</i> = 718) and validation (<i>n</i> = 130) datasets are constructed based on the archive materials (1974–1984) of ZapSibNIIgiprozem (Western Siberian Research, Design, and Survey Institute for Land Use Planning). The following indicators of the HHT modeling efficacy using the RF algorithm are obtained: coefficient of determination for training dataset <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R_{{{\text{TD}}}}^{2}\)</EquationSource> <!--SoilSci2560156Gopp-m1--> </InlineEquation> = 0.88; coefficient of determination for validation dataset <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(R_{{{\text{VD}}}}^{2}\)</EquationSource> <!--SoilSci2560156Gopp-m2--> </InlineEquation> = 0.12; root mean square error RMSE<sub>VD</sub> = 9.7 cm; mean absolute percentage error MAPE<sub>VD</sub> = 24.3%; and mean absolute error MAE<sub>VD</sub> = 6.5 cm. The modeling accuracy estimated with MAPE<sub>VD</sub> is satisfactory. Actual data show that HHT varies from 3 to 110 cm with the trend of a decrease from northwest to southeast. The lowest (3 cm) average HHT values are typical of meadow–chernozemic solonetz (Solonetz (Salic)) and the highest (61 cm), of ordinary meadow soils (Mollic Gleysols).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Digital Mapping of the Humus Horizon Thickness in Soils of the Cis-Salair Plain Using the Random Forest Machine Learning Algorithm

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • N. V. Gopp

摘要

Abstract

Results of digital mapping of the humus horizon thickness (HHT) in the soils of the Cis-Salair Plain using the Random Forest (RF) machine learning algorithm implemented on the Google Earth Engine cloud online platform are reported. A total of 92 predictors are employed to characterize the soil formation factors, including climate, relief, vegetation, spatial position, and soil properties. Training (n = 718) and validation (n = 130) datasets are constructed based on the archive materials (1974–1984) of ZapSibNIIgiprozem (Western Siberian Research, Design, and Survey Institute for Land Use Planning). The following indicators of the HHT modeling efficacy using the RF algorithm are obtained: coefficient of determination for training dataset \(R_{{{\text{TD}}}}^{2}\) = 0.88; coefficient of determination for validation dataset \(R_{{{\text{VD}}}}^{2}\) = 0.12; root mean square error RMSEVD = 9.7 cm; mean absolute percentage error MAPEVD = 24.3%; and mean absolute error MAEVD = 6.5 cm. The modeling accuracy estimated with MAPEVD is satisfactory. Actual data show that HHT varies from 3 to 110 cm with the trend of a decrease from northwest to southeast. The lowest (3 cm) average HHT values are typical of meadow–chernozemic solonetz (Solonetz (Salic)) and the highest (61 cm), of ordinary meadow soils (Mollic Gleysols).