High-resolution Sentinel-2 imagery combined with a deep learning (DL) segmentation model offers a promising approach for accurate mapping of small and fragmented agricultural burn areas. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, thereby achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy than the baseline Normalized Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirmed the effectiveness of DL approach. Challenges such as cloud interference, temporal gaps in satellite data, and limited reference data for training persist, but this study underscores the methodogical advancements and potential of DL models applied for small burn area detection in agricultural settings. The model achieved overall accuracy of 98.7%, a macro-F1 score of 97.6%, IoU 0.54, and a Dice coefficient of 0.64, demonstrating its capability for detailed burn area delineation. The model can capture burn area smaller than 250 m², but the model at present is less efficient at representing the full extent of the fires. Overall, outcomes demonstrate the model’s applicability to generalize to a new domain despite regional differences among research areas.

High-resolution Sentinel-2 imagery combined with a deep learning (DL) segmentation model offers a promising approach for accurate mapping of small and fragmented agricultural burn areas. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, thereby achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy than the baseline Normalized Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirmed the effectiveness of DL approach. Challenges such as cloud interference, temporal gaps in satellite data, and limited reference data for training persist, but this study underscores the methodogical advancements and potential of DL models applied for small burn area detection in agricultural settings. The model achieved overall accuracy of 98.7%, a macro-F1 score of 97.6%, IoU 0.54, and a Dice coefficient of 0.64, demonstrating its for detailed burn area delineation capability. The model can capture burn area smaller than 250m2, but the model at present is less efficient at representing the full extent of the fires. Overall, outcomes demonstrate the model’s applicability to generalize to a new domain despite regional differences among research areas.

This study investigates the capabilities of high-resolution Sentinel-2 observations and deep learning (DL) segmentation models, specifically convolutional neural networks (CNNs), for accurate mapping of small and fragmented agricultural burn areas in Punjab, India. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy and precision than the baseline Normalised Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirms the DL approach effectiveness. Cloud interference and temporal gaps in satellite data posed some challenges. Despite these limitations, the study highlights the methodological advancements and potential of using DL models for small burn area detection in agricultural settings. The model achieved overall testing accuracy of 0.64 in Dice score assessment. This report presents a promising approach for improved mapping of the burn area, which might engender better estimation of emissions and the management practices in regions with little available ground truth data.