Soil Organic Matter Estimation Model Integrating Spectral and Profile Features

Shaofang He; Siqiao Tan; Luming Shen; Qing Zhou

doi:10.3390/s23249868

Soil Organic Matter Estimation Model Integrating Spectral and Profile Features

Sensors (Basel). 2023 Dec 16;23(24):9868. doi: 10.3390/s23249868.

Authors

Shaofang He¹, Siqiao Tan¹, Luming Shen¹, Qing Zhou²

Affiliations

¹ College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China.
² College of Resources, Hunan Agricultural University, Changsha 410128, China.

Abstract

The accurate measurement of soil organic matter (SOM) is vital for maintaining soil quality. We present an innovative model for SOM prediction by integrating spectral and profile features. We use PCA, Lasso, and SCARS methods to extract important spectral features and combine them with profile data. This hybrid approach significantly improves SOM prediction across various models, including Random Forest, ExtraTrees, and XGBoost, boosting the coefficient of determination (R²) by up to 26%. Notably, the ExtraTrees model, enriched with PCA-extracted features, achieves the highest accuracy with an R² of 0.931 and an RMSE of 0.068. Compared with single-feature models, this approach improves the R² by 17% and 26% for PCA features of full-band spectra and profile features, respectively. Our findings highlight the potential of feature integration, especially the ExtraTrees model with PCA-extracted features and profile features, as a stable and accurate tool for SOM prediction in extensive study areas.

Keywords: PCA; SCARS; fusion feature; lasso feature selection.

Grants and funding

This research was funded by the Natural Science Foundation of Hunan Province, grant number 2023JJ30304, the Scientific Research Program of Hunan Province Department of Education, grant number 23A0197, the National Science and Technology Basic Work Special Project, grant number 2014FY110200, and the Changsha Soft Science Research Program, grant number kh2302050.