Scholarlink

Background and aims <p>Accurate prediction of the vertical distribution of soil organic matter (SOM) is essential for assessing the carbon cycle in arid regions.</p> Methods <p>In this study, predictive models for SOM across depths of 0–100 cm were developed using 190 soil samples from 48 profiles in the Urumqi River Basin. The models integrate visible near‑infrared (VIS–NIR) with multi‑source environmental covariates. The random forest (RF) and convolutional neural network (CNN) approaches were compared, and the SHapley Additive exPlanations (SHAP) framework was employed to interpret the governing mechanisms within the optimal model.</p> Results <p>The results show that incorporating environmental covariates significantly improved model performance, especially in the surface layers (0–40 cm). The CNN model achieved its highest accuracy in the 0–20 cm layer (R² = 0.97) and the 80–100 cm layer (R² = 0.95). SHAP analysis further revealed a shift in the dominant drivers with depth: vegetation indices contributed cumulatively 39.1% in surface layers, whereas soil properties and topographic features became more influential in deeper horizons.&#xa0;</p> Conclusion <p>These findings empirically support the classical theory that SOM profile formation is co‑regulated by climate, biota, and parent material, and provide an effective framework for multi‑depth soil carbon estimation in arid landscapes.</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

Development and contribution analysis of a multi-depth soil organic matter prediction model integrating VIS–NIR spectroscopy and environmental covariates

  • 期刊论文

  • 发表日期：

    2026年2月12日

查看全文
  • Jiahui Dai,
  • Han Yang,
  • Aizemaitijiang Maimaitituersun,
  • Kamuran Maimaitiaili

摘要

Background and aims

Accurate prediction of the vertical distribution of soil organic matter (SOM) is essential for assessing the carbon cycle in arid regions.

Methods

In this study, predictive models for SOM across depths of 0–100 cm were developed using 190 soil samples from 48 profiles in the Urumqi River Basin. The models integrate visible near‑infrared (VIS–NIR) with multi‑source environmental covariates. The random forest (RF) and convolutional neural network (CNN) approaches were compared, and the SHapley Additive exPlanations (SHAP) framework was employed to interpret the governing mechanisms within the optimal model.

Results

The results show that incorporating environmental covariates significantly improved model performance, especially in the surface layers (0–40 cm). The CNN model achieved its highest accuracy in the 0–20 cm layer (R² = 0.97) and the 80–100 cm layer (R² = 0.95). SHAP analysis further revealed a shift in the dominant drivers with depth: vegetation indices contributed cumulatively 39.1% in surface layers, whereas soil properties and topographic features became more influential in deeper horizons. 

Conclusion

These findings empirically support the classical theory that SOM profile formation is co‑regulated by climate, biota, and parent material, and provide an effective framework for multi‑depth soil carbon estimation in arid landscapes.