•  
  •  
 

Subject Area

Civil and Environmental Engineering

Article Type

Original Study

Abstract

Accurate rice mapping is challenging due to the lack of a simple, efficient approach and the complexity and limited ability of existing methods to distinguish rice fields from non-rice fields. This study proposes two novel indices: the Multispectral Rice Detection Index (MRDI), which utilises optical imagery, and the OptiRadar Rice Index (ORRI), which incorporates both optical and Synthetic Aperture Radar (SAR) data. Ground-truth data from the Cropland Cropping Systems (CROS) were used to assess the performance of both indices. The findings indicated that MRDI achieved an overall accuracy of 97.97% with perfect recall (100%) but lower precision (78.65%). However, the ORRI showed strong precision (89.55%) but lower recall (77.83%), with an overall accuracy of 96.89%. The results showed that integrating radar data into ORRI significantly reduced false positives and increased true negatives, thereby enhancing rice mapping accuracy. Both indices showed distinct advantages: MRDI excelled at detecting extensive rice cultivation areas, while ORRI demonstrated highly competitive performance in distinguishing rice from non-rice areas. While the proposed indices achieved competitive accuracy, they offer a practical alternative to machine learning approaches that require extensive training data and computational resources. The primary advantage lies in their operational simplicity and accessibility, as they can be implemented without machine learning expertise. These findings advance remote sensing applications in agriculture and provide valuable tools for real-time monitoring of rice cultivation, with potential applications in precision agriculture and global food security management

Keywords

Rice mapping, Remote sensing, Sentinel satellites, Multispectral imaging, Radar imagery, Agricultural monitoring

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS