Current Science

Open Access Open Access  Restricted Access Subscription Access

Automated kharif rice mapping using SAR data and machine learning techniques in GEE platform


Affiliations
1 College of Agricultural Information Technology, Anand Agricultural University, Anand 388 110, India
2 Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380 015, India

The present study employs temporal C-band Sentinel-1 synthetic aperture radar (SAR) data within the Google Earth Engine (GEE) platform to evaluate discriminabi­lity and estimate acreage of kharif rice across major Indian states. Utilizing multi-temporal Sentinel-1 C-band SAR data, including time-series cross-polariza­tion vertical–horizontal channels, the research spanned states such as Punjab, Haryana, Uttar Pradesh, Madhya Pradesh, Bihar, Jharkhand, Chhattisgarh, Telangana, Andhra Pradesh, West Bengal, Odisha and Assam. Employing five machine learning algorithms on GEE, with random forest demonstrating high performance, achieved 98.59% accuracy and 0.92 kappa coefficient (k) in Odisha. Subsequently, the RF algorithm was applied for kharif rice acreage estimation, yielding overall accuracies from 88.48% to 97.28% and k between 0.87 and 0.96 with deviations from reported acreage ranging from 0.95% to 12% across diverse states. The study underscores the efficacy of SAR data and machine learning within GEE for precise large-scale automated mapping of kharif rice

Keywords

Google earth engine, large-scale rice mapping, machine learning, multi-temporal, SAR
User
Notifications
Font Size

Abstract Views: 198




  • Automated kharif rice mapping using SAR data and machine learning techniques in GEE platform

Abstract Views: 198  | 

Authors

Saurabh P. Vyas
College of Agricultural Information Technology, Anand Agricultural University, Anand 388 110, India
Mukesh Kumar
Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380 015, India
Dhaval Kathiria
College of Agricultural Information Technology, Anand Agricultural University, Anand 388 110, India
Mandakini Jani
College of Agricultural Information Technology, Anand Agricultural University, Anand 388 110, India
Mehul R. Pandya
Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380 015, India
Bimal K. Bhattacharya
Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380 015, India

Abstract


The present study employs temporal C-band Sentinel-1 synthetic aperture radar (SAR) data within the Google Earth Engine (GEE) platform to evaluate discriminabi­lity and estimate acreage of kharif rice across major Indian states. Utilizing multi-temporal Sentinel-1 C-band SAR data, including time-series cross-polariza­tion vertical–horizontal channels, the research spanned states such as Punjab, Haryana, Uttar Pradesh, Madhya Pradesh, Bihar, Jharkhand, Chhattisgarh, Telangana, Andhra Pradesh, West Bengal, Odisha and Assam. Employing five machine learning algorithms on GEE, with random forest demonstrating high performance, achieved 98.59% accuracy and 0.92 kappa coefficient (k) in Odisha. Subsequently, the RF algorithm was applied for kharif rice acreage estimation, yielding overall accuracies from 88.48% to 97.28% and k between 0.87 and 0.96 with deviations from reported acreage ranging from 0.95% to 12% across diverse states. The study underscores the efficacy of SAR data and machine learning within GEE for precise large-scale automated mapping of kharif rice

Keywords


Google earth engine, large-scale rice mapping, machine learning, multi-temporal, SAR



DOI: https://doi.org/10.18520/cs%2Fv126%2Fi10%2F1265-1272