Mapping surface soil organic carbon density of cultivated land using machine learning in Zhengzhou DOI Creative Commons
Hengliang Guo,

Jinyang Wang,

Dujuan Zhang

и другие.

Environmental Geochemistry and Health, Год журнала: 2024, Номер 47(1)

Опубликована: Ноя. 28, 2024

Research on soil organic carbon (SOC) is crucial for improving sinks and achieving the "double-carbon" goal. This study introduces ten auxiliary variables based data from a 2021 land quality survey in Zhengzhou multi-objective regional geochemical survey. It uses geostatistical ordinary kriging (OK) interpolation, as well classical machine learning (ML) models, including random forest (RF) support vector (SVM), to map density (SOCD) topsoil layer (0 − 20 cm) of cultivated land. partitions sampling assess generalization capability with Zhongmu County designated an independent test set (dataset2) remaining training (dataset1). The three models are trained using dataset1, directly applied dataset2 evaluate compare their performance. distribution SOCD SOCS soils various types textures analyzed optimal interpolation method. results indicated that: (1) average SOC densities predicted by OK RF, SVM 3.70, 3.74, 3.63 kg/m2, precisions (R2) 0.34, 0.60, 0.81, respectively. (2) ML achieves significantly higher predictive precision than traditional interpolation. RF model's 0.21 model more precise estimating stock. (3) When dataset2, exhibited superior capabilities (R2 = 0.52, MSE 0.32) over 0.32, 0.45). (4) spatial surface area exhibits decreasing gradient west east south north. total stock estimated at approximately 10.76 × 106t. (5) integration attribute variables, climatic remote sensing data, techniques holds significant promise high-precision high-quality mapping agricultural soils.

Язык: Английский

Soil carbon storage under different types of arid land use in Algeria DOI Creative Commons
Abderraouf Benslama, Fouzi Benbrahim,

Lydia Rym-Gadoum

и другие.

Environmental Geochemistry and Health, Год журнала: 2024, Номер 46(9)

Опубликована: Июль 17, 2024

Abstract This study aims to assess the amount of organic carbon stored in soils, as it is an intention knowing sustainable soil management, by using two common methods for determining matter (SOM), namely oxidation with acidified wet dichromate (Walkley–Black method-WB) and loss on ignition (LOI). The was carried samples collected from a depth 0 30 cm Saharan arid region Ghardaïa (Algeria), different land uses: agricultural, forest pastoral. results obtained LOI WB were subjected statistical analysis, relations between both tested investigate their relationship. mean percentage SOM values 1.86, 2.42, 1.54 LOI, but, lower 0.34, 0.33, 0.36 determined method, pastoral soils respectively. A weak linear relationship analytical procedures (R 2 0.19 0.13 agricultural soils), while medium = 0.65) found when adjustment. However, opposite behaviour we use logarithmic outcomes indicated discrepancies measurements methods, been higher those estimated LOI. Finally, order identify best methodology measure more research required these extreme regions they are gap world maps.

Язык: Английский

Процитировано

1
Mapping surface soil organic carbon density of cultivated land using machine learning in Zhengzhou DOI Creative Commons
Hengliang Guo,

Jinyang Wang,

Dujuan Zhang

и другие.

Environmental Geochemistry and Health, Год журнала: 2024, Номер 47(1)

Опубликована: Ноя. 28, 2024

Research on soil organic carbon (SOC) is crucial for improving sinks and achieving the "double-carbon" goal. This study introduces ten auxiliary variables based data from a 2021 land quality survey in Zhengzhou multi-objective regional geochemical survey. It uses geostatistical ordinary kriging (OK) interpolation, as well classical machine learning (ML) models, including random forest (RF) support vector (SVM), to map density (SOCD) topsoil layer (0 − 20 cm) of cultivated land. partitions sampling assess generalization capability with Zhongmu County designated an independent test set (dataset2) remaining training (dataset1). The three models are trained using dataset1, directly applied dataset2 evaluate compare their performance. distribution SOCD SOCS soils various types textures analyzed optimal interpolation method. results indicated that: (1) average SOC densities predicted by OK RF, SVM 3.70, 3.74, 3.63 kg/m2, precisions (R2) 0.34, 0.60, 0.81, respectively. (2) ML achieves significantly higher predictive precision than traditional interpolation. RF model's 0.21 model more precise estimating stock. (3) When dataset2, exhibited superior capabilities (R2 = 0.52, MSE 0.32) over 0.32, 0.45). (4) spatial surface area exhibits decreasing gradient west east south north. total stock estimated at approximately 10.76 × 106t. (5) integration attribute variables, climatic remote sensing data, techniques holds significant promise high-precision high-quality mapping agricultural soils.

Язык: Английский

Процитировано

1