Towards an Irrigation Decision Support System for Ragi in Karnataka: A Systematic Review of Satellite-Based Root-Zone Soil Moisture Estimation

Bhavya Chandrasan^1*and Solomon Jebaraj²

¹Department of CSIT, Centre for Research Excellence and Innovation, JAIN (Deemed-to-be University), Bengaluru, Karnataka, India.

²Department of CSIT, JAIN (Deemed-to-be University), Bengaluru, Karnataka, India.

Corresponding Author Email: bhavyac20.official@gmail.com

DOI : http://dx.doi.org/10.12944/CARJ.14.2.4

Article Publishing History

Received: 13 Jul 2026
Accepted: 26 Aug 2026
Published Online: 03 Sep 2026

Review Details

Reviewed by: Dr. Wandra Arrington
Second Review by: Dr. Meenakshi Kumari
Final Approval by: Dr. José Luis da Silva Nunes

Article Metrics

 

     PDF Downloads: 14

Abstract:

Proper estimation of Root-Zone Soil Moisture (RZSM) plays a vital role in effective irrigation management in rain-fed agriculture systems in drylands. Ragi (Eleusine coracana G.) is an important cereal grain crop grown in various lateritic districts of Karnataka, which is very sensitive to moisture stress during the crucial growth stages. However, there is no free-access Decision Support System (DSS) tool available for irrigating ragi. This systematic literature review study done following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and involving many peer-reviewed articles published between 2018 and 2025 from Google Scholar and IEEE Xplore provides a summary of various satellite-based and machine learning (ML) techniques to estimate RZSM, its relevance for Karnataka's semi-arid agro-climatic condition, and highlights five operational research gaps. Literature suggests that the ensemble ML models (Random Forest,eXtreme Gradient Boosting (XGBoost), LightGBM) using the fusion of multi-source satellite inputs (Soil Moisture Active Passive(SMAP), Sentinel-1/2, ERA5-Land, Climate Hazards Group InfraRed Precipitation with Station data(CHIRPS), SoilGrids) reliably predict the soil moisture with R² > 0.85. A well-designed research approach is proposed to fill the researchtopractice gap in estimating RZSM and ragi irrigation advice from free remote sensing data.

Keywords:

Decision Support Systems; Karnataka; Machine Learning; Ragi Irrigation; Remote Sensing; Root-Zone Soil Moisture; Sentinel-1; Soil Moisture Active Passive

Download this article as: 

[ HTML Full Text]