HR-SR Net: Enhancing Wildfire Monitoring Through a Hybrid Residual Upscaling Approach of Super-Resolution and Weighting-Sum-Inject of Burned Area Indicators Into Remote Sensing Image Bands

The spatial resolution of multispectral satellite imagery often limits its utility for precise environmental monitoring applications, such as detailed mapping of burned areas after wildfires. To address this, we propose a novel hybrid deep learning architecture, the High-Resolution Super-Resolution Network (HR-SR Net), for 4x super-resolution of Sentinel-2 imagery. The HR-SR Net integrates a parallel encoder comprising a 3D depth-wise convolutional neural network (CNN) and a Swin Transformer block to synergistically extract both local spatial features and global contextual dependencies. A key innovation is the Weighted Sum Injection (WSI) of burned area indices, which guides the network to prioritize semantically relevant features during reconstruction. Furthermore, a Residual Cubic Gabor-Wavelet Filter (RCGWF) module is incorporated to enhance input data quality by suppressing noise and emphasizing critical textural details. The model was trained and evaluated on a benchmark dataset of Sentinel-2 imagery from a fire-affected region in Uzbekistan. Comprehensive experiments demonstrate that HR-SR Net sets a new state-of-the-art, achieving a Peak Signal-to-Noise Ratio (PSNR) of 45.72 dB and a Structural Similarity Index Measure (SSIM) of 95.63%, significantly outperforming a wide range of classical and deep learning-based super-resolution methods. The results confirm the model's robustness and its potential for generating high-fidelity, ultra-resolution imagery to support accurate post-fire assessment and monitoring.