Your browser doesn't support javascript.
loading
Environmental variables improve the accuracy of remote sensing estimation of soil organic carbon content.
Xiao, Xiao; He, Qijin; Ma, Selimai; Liu, Jiahong; Sun, Weiwei; Lin, Yujing; Yi, Rui.
Afiliación
  • Xiao X; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China.
  • He Q; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China. heqijin@cau.edu.cn.
  • Ma S; Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters (CIC-FEMD), Nanjing University of Information Science and Technology, Nanjing, 210044, China. heqijin@cau.edu.cn.
  • Liu J; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China.
  • Sun W; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China.
  • Lin Y; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China.
  • Yi R; College of Resources and Environmental Sciences, China Agricultural University, Beijing, 100193, China.
Sci Rep ; 14(1): 18964, 2024 Aug 16.
Article en En | MEDLINE | ID: mdl-39152170
ABSTRACT
Accurately and quickly estimating the soil organic carbon (SOC) content is crucial in the monitoring of global carbon. Environmental variables play a significant role in improving the accuracy of the SOC content estimation model. This study focuses on modeling methodologies and environmental variables, which significantly influence the SOC content estimation model. The modeling methods used in this research comprise multiple linear regression (MLR), partial least squares regression (PLSR), random forest, and support vector machines (SVM). The analyzed environmental variables include terrain, climate, soil, and vegetation cover factors. The original spectral reflectance (OSR) of Landsat 5 TM images and the spectral reflectivity after the derivative processing were combined with the above environmental variables to estimate SOC content. The results showed that (1) The SOC content can be efficiently estimated using the OSR of Landsat 5 TM, however, the derived processing method cannot significantly improve the estimation accuracy. (2) Environmental variables can effectively improve the accuracy of SOC content estimation, with climate and soil factors producing the most significant improvements. (3) Machine learning modeling methods provide better estimation accuracy than MLR and PLSR, especially the SVM model which has the highest accuracy. According to our observations, the best estimation model in the study area was the "OSR + SVM" model (R2 = 0.9590, RMSE = 13.9887, MAE = 10.8075), which considered four environmental factors. This study highlights the significance of environmental variables in monitoring SOC content, offering insights for more precise future SOC assessments. It also provides crucial data support for soil health monitoring and sustainable agricultural development in the study area.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Sci Rep Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Sci Rep Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido