Evaluation of Deep Learning-Based Water Bodies and Flooded Area Detection with Nanosatellites: The PlanetScope Satellite Imageries and HRNet Model
Wanyub Kim, Shinhyeon Cho, Junhyuk Jeong, Yeji Kim, Hyun Ok Kim, Minha Choi · 대한원격탐사학회지 · 2024
The continuous monitoring of water body is essential for efficient water resource management and the prevention of water-related disasters.Microsatellite and nanosatellite imageries provide a tool for continuous and accurate monitoring of water bodies at high spatial and temporal resolution.In this study, PlanetScope imagery with a resolution of 3.7 m and High-Resolution Network (HRNet) model were used to detect water bodies at dams and rivers in Korea, with the objective of evaluating the utility of water surface area monitoring.The HRNet model and the optimal band combinations of PlanetScope imagery which were R+G+B, R+G+B+NIR, Normalized Difference Water Index (NDWI), and Green+NIR+ NDWI, were initially evaluated.The Green+NIR+NDWI combination performed the best, with an accuracy of 0.91 and loss function of 0.05 for the validation set.Water body detection was performed using the HRNet model with the optimal band combination and models from previous studies (Otsu, K-means, U-net) The performance was evaluated through quantitative validation using labeled images.The HRNet model showed the best performance with an Intersection over Union (IoU) of 0.96, compared to models 는 픽셀들을 군집화 하는 K-means 클러스터링 기법이 수체 탐지에 주로 사용되었다(Krishna and Murty, 1999).하지만 임계값 및 클러 스터링 기법의 경우 수체와 비수체의 비율이 불균일할 경우 안정적 Korean Journal of Remote Sensing 2024, 40(5-1), 617-627 618 https://doi.org/10.7780/kjrs.2024.40.5.1.16in previous studies (Otsu: 0.90, K-means: 0.92, U-net: 0.95).Additionally, the HRNet model's flood detection performance showed an IoU of 0.93, indicating a high accuracy.However, there were limitations, as muddy and wet soil at the boundaries of flooded areas were false detected as water bodies.In the future, when a constellation of microsatellites is developed in Korea, the results of this study are expected to contribute to better management of water resources and water-related disasters through continuous monitoring of water bodies.