Shuaishuai Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Shuaishuai Shi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jiawen Wang
College of Life Sciences and Technology, Tarim University, Alar 843300, China
1 shared publication - Jibang Yang
College of Agriculture, Tarim University, Alar 843300, China
1 shared publication - Jie Peng
College of Agriculture, Tarim University, Alar 843300, China
1 shared publication - Yu Wang
College of Life Sciences and Technology, Tarim University, Alar 843300, China
1 shared publication - Zijin Bai
College of Horticulture and Forestry, Tarim University, Alar 843300, China
1 shared publication
Latest Publications
- Open Access
- 23 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 955
Soil Salinity Assessment and Cross-Regional Validation Based on Multiple Feature Optimization Methods and SHAP
Soil salinity severely threatens global ecosystems and agriculture, making accurate monitoring an ongoing priority. Currently, efficiently utilizing multi-source datasets to enhance monitoring accuracy while minimizing computational resources remains a critical challenge. This study evaluated several modeling strategies, including full-dataset modeling, variance inflation factor (VIF), Boruta, particle swarm optimization, ant colony optimization and recursive feature elimination (RFE), and validated results across diverse regions (Almaty, Kazakhstan; Shandong, China). We further validated the results using multiple algorithms, including linear regression, partial least squares regression, extreme gradient boosting, k-nearest neighbor and random forest (RF), with topsoil (0–20 cm) electrical conductivity inverted via the optimal method. Results indicate that input feature numbers substantially impact model performance: regional-scale feature selection is indispensable, with RFE outperforming full-dataset modeling (R2 improves by up to 0.28, while RMSE decreases by 2.21 dS m−1) and VIF performing the worst. Transferability is also demonstrated in Almaty and Shandong. Additionally, the RF algorithm shows superior performance in soil salinity mapping (overall accuracy = 0.73; kappa coefficient = 0.65). And, the RFE and SHAP results highlight CRSI, BI, and MSAVI2 as particularly important predictors for estimating soil salinity in our study area. Collectively, this study highlights the critical importance of feature optimization and interpretability in soil attribute mapping through the integration of multi-source remote sensing data.
- 23 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 955
Open AccessSoil Salinity Assessment and Cross-Regional Validation Based on Multiple Feature Optimization Methods and SHAP
Soil salinity severely threatens global ecosystems and agriculture, making accurate monitoring an ongoing priority. Currently, efficiently utilizing multi-source datasets to enhance monitoring accuracy while minimizing computational resources remains a critical challenge. This study evaluated several modeling strategies, including full-dataset modeling, variance inflation factor (VIF), Boruta, particle swarm optimization, ant colony optimization and recursive feature elimination (RFE), and validated results across diverse regions (Almaty, Kazakhstan; Shandong, China). We further validated the results using multiple algorithms, including linear regression, partial least squares regression, extreme gradient boosting, k-nearest neighbor and random forest (RF), with topsoil (0–20 cm) electrical conductivity inverted via the optimal method. Results indicate that input feature numbers substantially impact model performance: regional-scale feature selection is indispensable, with RFE outperforming full-dataset modeling (R2 improves by up to 0.28, while RMSE decreases by 2.21 dS m−1) and VIF performing the worst. Transferability is also demonstrated in Almaty and Shandong. Additionally, the RF algorithm shows superior performance in soil salinity mapping (overall accuracy = 0.73; kappa coefficient = 0.65). And, the RFE and SHAP results highlight CRSI, BI, and MSAVI2 as particularly important predictors for estimating soil salinity in our study area. Collectively, this study highlights the critical importance of feature optimization and interpretability in soil attribute mapping through the integration of multi-source remote sensing data.