Spatial mapping of winter wheat using C-band SAR (Sentinel-1A) data and yield prediction in Gorakhpur district, Uttar Pradesh (India)

ABSTRACT

Spatial depiction of wheat and predicting yields are crucial for national food security measures. This study has employed multi-temporal synthetic aperture radar (SAR) data for spatial mapping of winter wheat and estimating its acreage in the Gorakhpur district. Results showed that the estimated acreage of winter wheat based on SAR data was 189,740 hectares. Accordingly, the yield and production were predicted as 3.9 tonnes/ha and 740,000 tonnes, respectively, using a polynomial model. VH polarisation was effective in acreage mapping compared to VV. Thereby, the developed framework could support policymakers by giving advanced estimates of area and yield.

KEYWORDS:

• Backscatter coefficient
• polarisations
• random forest
• wheat acreage
• yield prediction

Acknowledgments

The authors thank Alaska Satellite facility (ASF) team for providing the Sentinel–1A SAR data. The authors also thank ESA/SNAP project team for providing the analysis software.

Author contributions

Conceived, designed research, analyzed data, and wrote the manuscript: BRP and SS.

CRediT authorship contribution statement

B.R. Parida and S. Singh: Conceptualisation, Investigation, Methodology, Software, Analysis, Writing & editing –original draft.

Disclosure statement

The authors declare no conflict of interest.

Ethical statement

The authors declare that all ethical aspects of publication have been followed and contributions of all possible interests are acknowledged.

Research fields

Remote sensing and GIS, Agriculture, Forestry and climate change.

Additional information

Funding

This research was supported by the University Grants Commission (UGC) under the start-up grant [F. 4-5(209-FRP)/2015/BSR].