My current research addressed the complexity and interconnected linkages between critical soil-landscape parameters (i.e. below surface: soil moisture, at surface: soil class, above surface: crop cover) to provide smart solution for resource management. This work involves the development of an effective framework for retrieve of critical soil-landscape parameters using space based technologies: remote sensing and GIS. Six environmental covariates i.e. climate, organisms, topography, parent material, time or age, soil or soil properties, and relative position; are developed using different satellite data and climatic data. Effective statistical/machine learning approaches is optimized for predicting soil-landscape parameters. Developed modelling approach for digital soil mapping offers a quantitative approach as an alternative to traditional soil mapping and it will expedite the mapping process.

His study also provides insight into the use of prominent regression techniques, as a spatial surface soil moisture model over an agricultural land. I have published my some of the dissertation findings in reputed journals (SCI indexed) and research would benefit not only city planner (government bodies of BRICS nations) but also helps farmers for smart farming. By selecting the right crop for the given soil conditions, moisture condition and climate, farmers can optimise yields and save water requirements for irrigation. Mr Gaurav Shukla has peer reviewed 9 publications.