FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features
Abstract Landslides are a frequent geohazard within the Himalayas, threatening human lives, infrastructure, and indigenous economies. Traditional subsidence velocity forecasting models, however, typically rely on either satellite remote sensing data or geotechnical parameters in isolation, which lim...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-12932-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849332984588533760 |
|---|---|
| author | Sahil Sankhyan Ajoy Kumar Praveen Kumar Aaditya Sharma K. V. Uday Varun Dutt |
| author_facet | Sahil Sankhyan Ajoy Kumar Praveen Kumar Aaditya Sharma K. V. Uday Varun Dutt |
| author_sort | Sahil Sankhyan |
| collection | DOAJ |
| description | Abstract Landslides are a frequent geohazard within the Himalayas, threatening human lives, infrastructure, and indigenous economies. Traditional subsidence velocity forecasting models, however, typically rely on either satellite remote sensing data or geotechnical parameters in isolation, which limits their predictive power and applicability. This work bridges this gap by suggesting an interpretable data-driven model that systematically integrates traditional soil information with geotechnical features for improved prediction. A stacking ensemble regression model called Forecasting Data-Driven Regression Learning (FDRL) was developed on the basis of the last machine learning breakthroughs, including feature selection techniques such as Pearson correlation and mutual information scores. The model combined both quantitative variables (e.g., specific gravity and plasticity index) and qualitative indicators based on conventional soil evaluation procedures (e.g., water retention, odor, and soil color). The FDRL model outperformed baseline regression models with a training Root Mean Squared Error (RMSE) of 1.11 mm/year and a test RMSE of 1.32 mm/year. Explainability analysis with SHAP showed that geotechnical as well as traditional soil characteristics significantly contributed to model predictions, confirming the utility of this hybrid combination. By demonstrating the explanatory potential of traditional soil indicators, typically excluded from scientific models, this study bridges local knowledge systems with modern data science. The method provides a scalable, interpretable, and locally implementable approach to early warning of slope creep and long-term deformation trends, facilitating proactive landslide risk management. |
| format | Article |
| id | doaj-art-9ed10b96ef6543c082f4743c85d595ce |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-9ed10b96ef6543c082f4743c85d595ce2025-08-20T03:46:01ZengNature PortfolioScientific Reports2045-23222025-08-0115111710.1038/s41598-025-12932-5FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil featuresSahil Sankhyan0Ajoy Kumar1Praveen Kumar2Aaditya Sharma3K. V. Uday4Varun Dutt5ACS Lab, Indian Institute of Technology MandiACS Lab, Indian Institute of Technology MandiACS Lab, Indian Institute of Technology MandiDepartment of Computer Science and Engineering, Punjab Engineering College School of Civil and Environmental Engineering, Indian Institute of Technology MandiACS Lab, Indian Institute of Technology MandiAbstract Landslides are a frequent geohazard within the Himalayas, threatening human lives, infrastructure, and indigenous economies. Traditional subsidence velocity forecasting models, however, typically rely on either satellite remote sensing data or geotechnical parameters in isolation, which limits their predictive power and applicability. This work bridges this gap by suggesting an interpretable data-driven model that systematically integrates traditional soil information with geotechnical features for improved prediction. A stacking ensemble regression model called Forecasting Data-Driven Regression Learning (FDRL) was developed on the basis of the last machine learning breakthroughs, including feature selection techniques such as Pearson correlation and mutual information scores. The model combined both quantitative variables (e.g., specific gravity and plasticity index) and qualitative indicators based on conventional soil evaluation procedures (e.g., water retention, odor, and soil color). The FDRL model outperformed baseline regression models with a training Root Mean Squared Error (RMSE) of 1.11 mm/year and a test RMSE of 1.32 mm/year. Explainability analysis with SHAP showed that geotechnical as well as traditional soil characteristics significantly contributed to model predictions, confirming the utility of this hybrid combination. By demonstrating the explanatory potential of traditional soil indicators, typically excluded from scientific models, this study bridges local knowledge systems with modern data science. The method provides a scalable, interpretable, and locally implementable approach to early warning of slope creep and long-term deformation trends, facilitating proactive landslide risk management.https://doi.org/10.1038/s41598-025-12932-5Subsidence velocity forecastingRainfall-Induced landslidesTraditional soil indicatorsInSAR deformation analysisMachine learning in geohazardsStacking ensemble regression |
| spellingShingle | Sahil Sankhyan Ajoy Kumar Praveen Kumar Aaditya Sharma K. V. Uday Varun Dutt FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features Scientific Reports Subsidence velocity forecasting Rainfall-Induced landslides Traditional soil indicators InSAR deformation analysis Machine learning in geohazards Stacking ensemble regression |
| title | FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features |
| title_full | FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features |
| title_fullStr | FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features |
| title_full_unstemmed | FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features |
| title_short | FDRL: a data-driven algorithm for forecasting subsidence velocities in Himalayas using conventional and traditional soil features |
| title_sort | fdrl a data driven algorithm for forecasting subsidence velocities in himalayas using conventional and traditional soil features |
| topic | Subsidence velocity forecasting Rainfall-Induced landslides Traditional soil indicators InSAR deformation analysis Machine learning in geohazards Stacking ensemble regression |
| url | https://doi.org/10.1038/s41598-025-12932-5 |
| work_keys_str_mv | AT sahilsankhyan fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures AT ajoykumar fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures AT praveenkumar fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures AT aadityasharma fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures AT kvuday fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures AT varundutt fdrladatadrivenalgorithmforforecastingsubsidencevelocitiesinhimalayasusingconventionalandtraditionalsoilfeatures |