https://orcid.org/0000-0003-3829-4705
![Sample our Environment & Agriculture journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5934/TOC-Subject-Sample-2021-Environment-Agriculture.jpg"})
ABSTRACT
Reliable drought monitoring is a prerequisite for minimizing potential agricultural losses. Soil moisture is a key variable for monitoring agricultural drought assessment. This study conducted in the Bundelkhand region of Uttar Pradesh uses a macroscale variable infiltration capacity (VIC) hydrological model to simulate soil moisture and calculate soil moisture deficit index (SMDI) for agricultural drought assessment for the Rabi crop growing season, 1998–2016. Crop yield was linked with SMDI and other covariates using a random forest machine learning-based regression technique. The results show that the VIC model effectively simulated root zone soil moisture when compared with the reference data. Major droughts were identified in the years 2000–01, 2007–08, and 2015–16 in the study region. The RF-based crop yield prediction accuracy improved when irrigational factors were added. The study provides a noteworthy reference for drought assessment and prevention, water resource management, and ensuring food security.
Editor K. Soulis; Associate Editor M. Wens
Editor K. Soulis; Associate Editor M. Wens
Acknowledgements
The authors thank the Indian Meteorological Department (IMD), Pune and Central Water Commission, Agra, for providing the datasets for this research. The authors are grateful to Banaras Hindu University for all the necessary support throughout the programme.
Disclosure statement
No potential conflict of interest was reported by the author(s).