Semi physical and machine learning approach for yield estimation of pearl millet crop using SAR and optical data products

ABSTRACT

Pearl millet (Pennisetum glaucum L.R.Br.), is the most widely cultivated food crop after rice, wheat, and maize. The aim of the project is to determine the crop acreage of Pearl millet (Bajra) using Sentinel-1A SAR data and Machine Learning Algorithm to determine the yield estimation of the Pearl millet crop at the tehsil level using the Monteith approach. The classification overall accuracy is found to be 86.48% for Agra district and 80.15% for Firozabad district. The Relative Deviation of yield estimation for the Agra and Firozabad districts is found to be 10.14 and 6, respectively.

KEYWORDS:

• Crop acreage
• Sentinel-1A
• machine learning algorithm (random forest)
• yield estimation
• Monteith approach
• HI

Acknowledgments

The authors are thankful to the Directorate of Economics and Statistics (DES) for providing the statistics report. The authors would also like to thank ESA for providing the Sentinel datasets. The authors also sincerely thank the anonymous reviewers and members of the editorial team for their comments.

Disclosure statement

The authors of this paper declare that there are no conflicts of interest or financial disclosures to report in relation to the research presented in this manuscript.