Monthly soil temperature modelling across different depths using machine learning algorithms in northeast India
= 0.970; NSE = 0.970) accurately predicted 30 cm soil temperatures in the study region. Based on the analysis for determining the variable importance, air temperature (mean temperature, followed by minimum and maximum temperatures) was found to be the most influential variable for predicting soil temperature. The findings of the study will be beneficial in formulating future research directions, like soil temperature-based crop modelling in data-limited regions and beyond, especially in the absence of multi-depth soil temperature information.
Authors
- Ghanashyam Singh Yurembam (ORCID: https://orcid.org/0000-0003-1835-3149)
- Laishram Kanta Singh (ORCID: https://orcid.org/0000-0002-4340-9768)
- Abhaya Kumar Pradhan (ORCID: https://orcid.org/0000-0003-0617-7504)
- A. K. Mohanty (ORCID: https://orcid.org/0000-0002-6056-2983)
- Deepak Jhajharia (ORCID: https://orcid.org/0000-0003-1111-8648)
- Shoma Devi
- Muhammad Touseef (ORCID: https://orcid.org/0000-0002-6144-1358)
- T. Loidang Chanu
- Subhankar Ghosh (ORCID: https://orcid.org/0000-0001-7083-9555)
- Mainak Ghosh
- Kiran Bala Behura
- Shivam Gupta (ORCID: https://orcid.org/0000-0002-6026-1523)
- Ghanshyam T. Patle (ORCID: https://orcid.org/0000-0002-9175-8567)
Institutions
- National Institute of Technology Sikkim (IN)
- Odisha University of Agriculture and Technology (IN)
- Indian Institute of Technology Kharagpur (IN)
- Guangxi University (CN)
- Indian Council of Agricultural Research (IN)
- Jain Irrigation Systems (India) (IN)
- ICAR Research Complex for NEH Region (IN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-05-11
- DOI
- https://doi.org/10.1038/s41598-026-46856-5
- Primary Topic
- Soil Moisture and Remote Sensing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Indian Institute of Technology Kharagpur