Paddy characterization and yield estimation using optical and sar data

Abstract

Reliable and accurate monitoring of rice crop is vital for food security and the global newlineeconomy. This study aims to characterize rice types and provide an early yield estimation newlineusing optical and Synthetic Aperture Radar (SAR) data. Dense time series Sentinel-1 SAR newlinebackscatter data were analyzed for summer and kharif rice to discriminate between different newlinerice types and identify their optimum stages to represent crop growth profiles. Critical stages newlineof discrimination were determined statistically for all rice types. Knowledge-based decision newlinetree algorithm was employed to classify all major types of rice grown during both the newlineseasons. Savitzky-Golay fitted temporal profile of remotely sensed indices from Sentinel-1 newlineand Sentinel-2 satellite sensors were used to extract seasonality parameters using TIMESAT. newlineCorrelation analysis was performed at different phenophases to identify sensitive biophysical newlineand remote sensing parameters. Finally, machine learning models were used to predict yield newlineof rice at 45, 60 and 90 days after transplanting using remote sensing indices and biophysical newlineparameters as inputs. The performances of ML models for early yield estimation were newlineevaluated using standardized ranking performance index. newlineResults revealed significant differences between backscatter profiles of different rice newlinetypes especially in early vegetative stages with transplanting being the most critical stage. newlineTransplanting/seeding, tillering, panicle initiation, peak vegetative/flowering and maturity newlinewere identified to be the most important stages to represent the backscatter profile of entire newlinerice growth. Decision tree algorithm discriminated rice types with high overall accuracy and newlineKappa coefficient, viz., 94.74% and 0.94 for summer rice and 91.80% and 0.90 for kharif newlinerice, respectively. The extracted seasonality parameters revealed that start time derived from newlineSAR indices was found to accurately distinguish different types of rice. The correlation newlinestrength generally increased with the progress of crop growth in both seasons. All significant newlinecorrelations were positive except that with moisture content. NRPB was strongly correlated newlinewith VV and VV/VH ratio at all stages in both the seasons. LAI and dry biomass were found newlineto be the most sensitive biophysical parameters towards remote sensing data. Area under rice newlinecultivation in the study area was found to be 37.1%, using random forest classifier that newlineyielded an accuracy above 90% and kappa coefficient of 0.89. The machine learning models newlinewere able to achieve R2 and d-index values above 0.9 and RMSE below 0.5 t/ha. XGB was newlinethe best model for predicting rice yield using remote sensing and biophysical parameters. newlineThe findings of this study have the potential to contribute to the greater goal of sustainable newlineagriculture and food security. newline