Scholarlink

<p>Soil moisture is a key indicator of the global water cycle and terrestrial ecosystems, which is critical for drought monitoring and agricultural management for stronger scientific tone. Currently, soil moisture products obtained from remote sensing satellites have low spatial resolution, and soil moisture data derived using vegetation indices as downscaling factors exhibit significant temporal lag. Solar-induced chlorophyll fluorescence (SIF) provides direct information on vegetation physiology. Therefore, this paper reconstructs spatial-temporal SIF products. It proposes a downscaling method using multi-source remote sensing data that integrates vegetation physiological and structural characteristics. This method compares the downscaling performance of five machine learning approaches, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Networks (DNN), and a stacking ensemble. Multimodal data such as SIF, digital elevation models, soil properties, and albedo are used as predictor variables to select the optimal model for generating monthly Soil Moisture Active Passive (SMAP) soil moisture estimates at 1&#xa0;km resolution. The downscaling results are validated against high-resolution soil moisture datasets (SSM and SMCI1.0), with their temporal consistency assessed against CHIRPS precipitation data. As a result, the RF model with SIF performs optimally, with an R² of 0.92. The downscaled product achieved a superior accuracy (R= 0.864), outperforming both the non-SIF downscaling result and the SSM product. Across all sites, correlations with collocated high-resolution values ranged from 0.6 to 1.0, with a minimum ubRMSE of 0.015&#xa0;m³/m³. The downscaled SMAP soil moisture product exhibits enhanced spatial detail. The temporal correlation improved from 0.686 to 0.713 relative to vegetation index-based downscaling, indicating that SIF demonstrates superior applicability in SMAP soil moisture downscaling. This supports precise decision-making in agricultural drought monitoring and water resource management.</p> Graphical Abstract <p>This study proposes an SMAP soil moisture downscaling method based on Solar-induced chlorophyll fluorescence (SIF) and multi-source data fusion, aiming to downscale the coarse-resolution (9&#xa0;km) SMAP soil moisture data to a 1&#xa0;km spatial resolution monthly product. First, a Random Forest model was used to reconstruct the SIF data to both 1&#xa0;km and 9&#xa0;km resolutions, and the reconstructed SIF data were used as driving factors for soil moisture downscaling. The downscaling framework integrates multiple data sources, including Land Cover (LC), Normalized Difference Water Index (NDWI), Normalized Shortwave-Infrared Difference Soil Moisture Index (NSDSI), Apparent Thermal Inertia (ATI), Evapotranspiration (ET), Land Surface Temperature (LST), Albedo, soil properties (sand, silt, clay), Digital Elevation Model (DEM), slope, and precipitation data. During model training and evaluation, several machine learning algorithms, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Network (DNN), and Stacking ensemble model, were used. The results indicate that the RF model combined with SIF data performed the best, with an R² of 0.92, significantly outperforming the traditional vegetation index method (R² = 0.90). The high-resolution SMAP soil moisture product derived from the RF model showed significant improvements in spatial distribution and temporal dynamics capture.The innovation of this study lies in the introduction of SIF data to replace traditional vegetation indices, solving the time lag issue commonly associated with vegetation index methods. SIF provides a more direct and sensitive reflection of vegetation photosynthetic activity, enabling more accurate capture of soil moisture changes in dynamic processes. By integrating SIF with multi-source data, the study enhances the accuracy and timeliness of the soil moisture downscaling model, significantly improving the spatial resolution and temporal correlation of soil moisture products, providing more reliable monitoring tools for agricultural and water resource management.</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

SMAP Soil Moisture Downscaling Via Multimodal Data Fusion and Machine Learning

  • 期刊论文

  • 发表日期：

    2026年2月4日

查看全文
  • Xin Sang,
  • Xiaoping Lu,
  • Kailun Wang,
  • Junli Zhou,
  • Guosheng Cai,
  • Jinrui Fan

摘要

Soil moisture is a key indicator of the global water cycle and terrestrial ecosystems, which is critical for drought monitoring and agricultural management for stronger scientific tone. Currently, soil moisture products obtained from remote sensing satellites have low spatial resolution, and soil moisture data derived using vegetation indices as downscaling factors exhibit significant temporal lag. Solar-induced chlorophyll fluorescence (SIF) provides direct information on vegetation physiology. Therefore, this paper reconstructs spatial-temporal SIF products. It proposes a downscaling method using multi-source remote sensing data that integrates vegetation physiological and structural characteristics. This method compares the downscaling performance of five machine learning approaches, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Networks (DNN), and a stacking ensemble. Multimodal data such as SIF, digital elevation models, soil properties, and albedo are used as predictor variables to select the optimal model for generating monthly Soil Moisture Active Passive (SMAP) soil moisture estimates at 1 km resolution. The downscaling results are validated against high-resolution soil moisture datasets (SSM and SMCI1.0), with their temporal consistency assessed against CHIRPS precipitation data. As a result, the RF model with SIF performs optimally, with an R² of 0.92. The downscaled product achieved a superior accuracy (R= 0.864), outperforming both the non-SIF downscaling result and the SSM product. Across all sites, correlations with collocated high-resolution values ranged from 0.6 to 1.0, with a minimum ubRMSE of 0.015 m³/m³. The downscaled SMAP soil moisture product exhibits enhanced spatial detail. The temporal correlation improved from 0.686 to 0.713 relative to vegetation index-based downscaling, indicating that SIF demonstrates superior applicability in SMAP soil moisture downscaling. This supports precise decision-making in agricultural drought monitoring and water resource management.

Graphical Abstract

This study proposes an SMAP soil moisture downscaling method based on Solar-induced chlorophyll fluorescence (SIF) and multi-source data fusion, aiming to downscale the coarse-resolution (9 km) SMAP soil moisture data to a 1 km spatial resolution monthly product. First, a Random Forest model was used to reconstruct the SIF data to both 1 km and 9 km resolutions, and the reconstructed SIF data were used as driving factors for soil moisture downscaling. The downscaling framework integrates multiple data sources, including Land Cover (LC), Normalized Difference Water Index (NDWI), Normalized Shortwave-Infrared Difference Soil Moisture Index (NSDSI), Apparent Thermal Inertia (ATI), Evapotranspiration (ET), Land Surface Temperature (LST), Albedo, soil properties (sand, silt, clay), Digital Elevation Model (DEM), slope, and precipitation data. During model training and evaluation, several machine learning algorithms, including Support Vector Regression (SVR), XGBoost, Random Forest (RF), Deep Neural Network (DNN), and Stacking ensemble model, were used. The results indicate that the RF model combined with SIF data performed the best, with an R² of 0.92, significantly outperforming the traditional vegetation index method (R² = 0.90). The high-resolution SMAP soil moisture product derived from the RF model showed significant improvements in spatial distribution and temporal dynamics capture.The innovation of this study lies in the introduction of SIF data to replace traditional vegetation indices, solving the time lag issue commonly associated with vegetation index methods. SIF provides a more direct and sensitive reflection of vegetation photosynthetic activity, enabling more accurate capture of soil moisture changes in dynamic processes. By integrating SIF with multi-source data, the study enhances the accuracy and timeliness of the soil moisture downscaling model, significantly improving the spatial resolution and temporal correlation of soil moisture products, providing more reliable monitoring tools for agricultural and water resource management.