Flood studies are of paramount importance for several reasons, e.g., risk assessment, land use planning and management, and emergency preparedness. The increasing risks due to climate change require support for developing adaptation strategies, improved infrastruc- ture resilience, and sustainable land use practices. Remote sensing has proved its capacity to provide accurate and timely data for food studies. SAR remote sensing data has made signifcant advancements in food mapping, ofering unique capabilities to overcome cer- tain limitations associated with other types of remote sensing data. This study uses a time series of ASNARO-2 images that captured a mega-food event in Quang Nam province for food extent extraction. To address this challenge, we fne-tuned four deep learning (DL) models of U-Net, LinkNet, PSPNet, and DeepLabV3Plus confgured with four latest encoders of ResNet125, EfcientNet-b7, ResNeXt101_32 × 8d, and Timm-RegNetY_320 to segment the fooding water surface for mapping the food inundated areas. All the struc- tures performed well with the most accuracy above 95% of the DeepLabV3Plus + Efcient- Net-b7 and the most efciency of PSPNet + ResNeXt101_32 × 8d. The best inundation map agreed well with the United Nations Satellite Center reference data and some minor diferences were found. Although the contribution of SAR data is signifcantly important to food delineations, its limitations of trade-of resolution and repeated pass, wind, incident angle efects, and DL model accuracy and efciency are discussed.