DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation
This provides a scalable solution for wetland conservation by enabling water monitoring without ground truth data, though it is incremental in applying existing self-supervised techniques to a specific domain.
The paper tackles the problem of wetland water extent segmentation without manual annotations by introducing DeepAqua, a self-supervised model using knowledge distillation from NDWI to train a CNN on SAR images, resulting in improvements of 7% accuracy, 27% IoU, and 14% F1 score over other unsupervised methods.
Deep learning and remote sensing techniques have significantly advanced water monitoring abilities; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies over time and space, demanding multiple annotations for the same area. In this paper, we present DeepAqua, a self-supervised deep learning model that leverages knowledge distillation (a.k.a. teacher-student model) to eliminate the need for manual annotations during the training phase. We utilize the Normalized Difference Water Index (NDWI) as a teacher model to train a Convolutional Neural Network (CNN) for segmenting water from Synthetic Aperture Radar (SAR) images, and to train the student model, we exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. DeepAqua represents a significant advancement in computer vision techniques by effectively training semantic segmentation models without any manually annotated data. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%. This approach offers a practical solution for monitoring wetland water extent changes without needing ground truth data, making it highly adaptable and scalable for wetland conservation efforts.