Scholarlink

<p>Purpose</p><p>Crushing and spreading crop straw on the soil surface is a widely adopted agricultural management practice for preserving farmland and improving soil quality. However, satellite-based mapping of soil organic matter (SOM) typically requires exposed soil conditions. Persistent straw cover therefore poses a substantial challenge to conventional remote sensing-based SOM mapping. </p><p>Method</p><p>To address this issue, this study proposes a dual-driven SOM mapping framework (DDF) that integrates remote sensing estimation and spatial interpolation by distinguishing bare-soil and straw-covered areas. Within this framework, bare-soil areas are regarded as high-reliability observation areas, and their estimation results serve as conditioning information for spatial interpolation in observation-limited areas. In bare-soil areas, spectral variables were extracted from Sentinel-2 imagery, and sensitive features were identified using the Boruta–SHAP algorithm. A Random Forest model was then employed to map SOM in these high-reliability domains. In straw-covered areas, SOM was estimated through spatial interpolation constrained by the estimation results derived from bare-soil areas, enabling spatially continuous SOM mapping under heterogeneous surface conditions. </p><p>Results</p><p> The DDF achieved an R<sup>2</sup>of 0.82 (RMSE = 3.25 g/kg) in bare-soil areas and an R<sup>2</sup>of 0.76 (RMSE = 3.02 g/kg) in straw-covered areas. The DDF also outperformed RF, OK, and RFRK in estimation accuracy.</p><p>Conclusions</p><p>The results indicate that under spatially heterogeneous surface observation conditions, incorporating bare-soil estimation results as conditioning information into the spatial interpolation process effectively overcomes observation-induced mapping constraints and enables spatially continuous reconstruction of SOM at the regional scale.</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

A dual-driven framework integrating remote sensing and spatial interpolation for mapping soil organic matter under straw cover

  • 期刊论文

  • 发表日期：

    2026年7月23日

查看全文
  • Xuzhou Qu,
  • Zhitong Zhang,
  • Jianwei Wu,
  • Xiaohe Gu,
  • Jingping Zhou,
  • Chunjiang Zhao,
  • Yanglin Cui,
  • Dongfang Shan

摘要

Purpose

Crushing and spreading crop straw on the soil surface is a widely adopted agricultural management practice for preserving farmland and improving soil quality. However, satellite-based mapping of soil organic matter (SOM) typically requires exposed soil conditions. Persistent straw cover therefore poses a substantial challenge to conventional remote sensing-based SOM mapping.

Method

To address this issue, this study proposes a dual-driven SOM mapping framework (DDF) that integrates remote sensing estimation and spatial interpolation by distinguishing bare-soil and straw-covered areas. Within this framework, bare-soil areas are regarded as high-reliability observation areas, and their estimation results serve as conditioning information for spatial interpolation in observation-limited areas. In bare-soil areas, spectral variables were extracted from Sentinel-2 imagery, and sensitive features were identified using the Boruta–SHAP algorithm. A Random Forest model was then employed to map SOM in these high-reliability domains. In straw-covered areas, SOM was estimated through spatial interpolation constrained by the estimation results derived from bare-soil areas, enabling spatially continuous SOM mapping under heterogeneous surface conditions.

Results

The DDF achieved an R2of 0.82 (RMSE = 3.25 g/kg) in bare-soil areas and an R2of 0.76 (RMSE = 3.02 g/kg) in straw-covered areas. The DDF also outperformed RF, OK, and RFRK in estimation accuracy.

Conclusions

The results indicate that under spatially heterogeneous surface observation conditions, incorporating bare-soil estimation results as conditioning information into the spatial interpolation process effectively overcomes observation-induced mapping constraints and enables spatially continuous reconstruction of SOM at the regional scale.