An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery
JongCheol Pyo
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Hongtao Duan
(Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China)
Mayzonee Ligaray
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Minjeong Kim
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Sangsoo Baek
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Yong Sung Kwon
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Hyuk Lee
(Water Quality Assessment Research Division, National Institute of Environmental Research, Environmental Research Complex, Incheon 22689, Korea)
Taegu Kang
(Water Quality Assessment Research Division, National Institute of Environmental Research, Environmental Research Complex, Incheon 22689, Korea)
Kyunghyun Kim
(Watershed and Total Load Management Research Division, National Institute of Environmental Research, Incheon 22689, Korea)
YoonKyung Cha
(School of Environmental Engineering, University of Seoul, Dongdaemun-gu, Seoul 130–743, Korea)
Kyung Hwa Cho
(School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, Korea)
Journal: Remote Sensing
•
• MDPI AG
• ISSN: 2072-4292
Abstract
Hyperspectral image sensing can be used to effectively detect the distribution of harmful cyanobacteria. To accomplish this, physical- and/or model-based simulations have been conducted to perform an atmospheric correction (AC) and an estimation of pigments, including phycocyanin (PC) and chlorophyll-a (Chl-a), in cyanobacteria. However, such simulations were undesirable in certain cases, due to the difficulty of representing dynamically changing aerosol and water vapor in the atmosphere and the optical complexity of inland water. Thus, this study was focused on the development of a deep neural network model for AC and cyanobacteria estimation, without considering the physical formulation. The stacked autoencoder (SAE) network was adopted for the feature extraction and dimensionality reduction of hyperspectral imagery. The artificial neural network (ANN) and support vector regression (SVR) were sequentially applied to achieve AC and estimate cyanobacteria concentrations (i.e., SAE-ANN and SAE-SVR). Further, the ANN and SVR models without SAE were compared with SAE-ANN and SAE-SVR models for the performance evaluations. In terms of AC performance, both SAE-ANN and SAE-SVR displayed reasonable accuracy with the Nash–Sutcliffe efficiency (NSE) > 0.7. For PC and Chl-a estimation, the SAE-ANN model showed the best performance, by yielding NSE values > 0.79 and > 0.77, respectively. SAE, with fine tuning operators, improved the accuracy of the original ANN and SVR estimations, in terms of both AC and cyanobacteria estimation. This is primarily attributed to the high-level feature extraction of SAE, which can represent the spatial features of cyanobacteria. Therefore, this study demonstrated that the deep neural network has a strong potential to realize an integrative remote sensing application.