🌟 Article of the Week 🌟 This week’s featured article from IEEE Geoscience and Remote Sensing Society Section within IEEE Access presents a deep learning approach for estimating building heights from single SAR images. 🔍 This Week's Highlight Title: A Pixel-Based Deep Learning Approach for Building Height Estimation From Single SAR Images Authors: Luigi Russo, Babak Memar, Silvia Liberata Ullo, Paolo Gamba 📖 🌍 Estimating building height from a single Synthetic Aperture Radar (SAR) image is a challenging problem due to geometric distortions such as layover and shadowing. This paper proposes a pixel-based deep learning framework using a modified Attention U-Net with dual decoders to separately model built-up and background regions. By leveraging a refined normalized Digital Surface Model (nDSM) for supervision and learning height-related SAR features, the approach produces continuous height maps and demonstrates strong performance across multiple cities, including robust cross-city generalization, outperforming several existing methods. 🔗 Read the full paper here: doi.org/10.1109/ACCESS.2026.… Stay tuned for more groundbreaking research every week as we celebrate excellence in geoscience and remote sensing! 🌍📡 #IEEEGRSS #RemoteSensing #Geoscience #SAR #BuildingHeight #DeepLearning #IEEEAccess #ieeexplore #AOTW