HASSDE-NAS: Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evolution for Hyperspectral Water Body Identification
Open Access
- 13 June 2025
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 16 (6) , 495
Abstract
The accurate identification of water bodies in hyperspectral images (HSIs) remains challenging due to hierarchical representation imbalances in deep learning models, where shallow layers overly focus on spectral features, boundary ambiguities caused by the relatively low spatial resolution of satellite imagery, and limited detection capability for small-scale aquatic features such as narrow rivers. To address these challenges, this study proposes Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evaluation (HASSDE-NAS). The architecture integrates three specialized units; a spectral-aware dynamic band selection cell suppresses redundant spectral bands, while a geometry-enhanced edge attention cell refines fragmented spatial boundaries. Additionally, a bidirectional fusion alignment cell jointly optimizes spectral and spatial dependencies. A heuristic cell search algorithm optimizes the network architecture through architecture stability, feature diversity, and gradient sensitivity analysis, which improves search efficiency and model robustness. Evaluated on the Gaofen-5 datasets from the Guangdong and Henan regions, HASSDE-NAS achieves overall accuracies of 92.61% and 96%, respectively. This approach outperforms existing methods in delineating narrow river systems and resolving water bodies with weak spectral contrast under complex backgrounds, such as vegetation or cloud shadows. By adaptively prioritizing task-relevant features, the framework provides an interpretable solution for hydrological monitoring and advances neural architecture search in intelligent remote sensing.Keywords
This publication has 57 references indexed in Scilit:
- WaterFormer: A coupled transformer and CNN network for waterbody detection in optical remotely-sensed imageryISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Unsupervised deep clustering via contractive feature representation and focal lossPattern Recognition, 2022
- Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationComputerized Medical Imaging and Graphics, 2022
- Robustness of convolutional neural network models in hyperspectral noisy datasets with loss functionsComputers and Electrical Engineering, 2021
- An overview on data representation learning: From traditional feature learning to recent deep learningThe Journal of Finance and Data Science, 2016
- A LiDAR-based decision-tree classification of open water surfaces in an Arctic deltaRemote Sensing of Environment, 2015
- Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imageryInformation Processing in Agriculture, 2015
- Automated Water Extraction Index: A new technique for surface water mapping using Landsat imageryRemote Sensing of Environment, 2014
- Comparative Analysis of Automatic Water Identification Method Based on Multispectral Remote SensingProcedia Environmental Sciences, 2011
- Wavelet analysis of hydrological and water quality signals in an agricultural watershedJournal of Hydrology, 2007