An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery
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 chlorophyl...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/7/1073 |
id |
doaj-0068af8b942d4502b84556cd4f885c2e |
---|---|
record_format |
Article |
spelling |
doaj-0068af8b942d4502b84556cd4f885c2e2020-11-25T02:54:38ZengMDPI AGRemote Sensing2072-42922020-03-01121073107310.3390/rs12071073An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral ImageryJongCheol Pyo0Hongtao Duan1Mayzonee Ligaray2Minjeong Kim3Sangsoo Baek4Yong Sung Kwon5Hyuk Lee6Taegu Kang7Kyunghyun Kim8YoonKyung Cha9Kyung Hwa Cho10School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaKey Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, ChinaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaWater Quality Assessment Research Division, National Institute of Environmental Research, Environmental Research Complex, Incheon 22689, KoreaWater Quality Assessment Research Division, National Institute of Environmental Research, Environmental Research Complex, Incheon 22689, KoreaWatershed and Total Load Management Research Division, National Institute of Environmental Research, Incheon 22689, KoreaSchool of Environmental Engineering, University of Seoul, Dongdaemun-gu, Seoul 130–743, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 689–798, KoreaHyperspectral 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.https://www.mdpi.com/2072-4292/12/7/1073deep learningstacked autoencodercyanobacteriahyperspectral imagefeature extractiondimensionality reduction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
JongCheol Pyo Hongtao Duan Mayzonee Ligaray Minjeong Kim Sangsoo Baek Yong Sung Kwon Hyuk Lee Taegu Kang Kyunghyun Kim YoonKyung Cha Kyung Hwa Cho |
spellingShingle |
JongCheol Pyo Hongtao Duan Mayzonee Ligaray Minjeong Kim Sangsoo Baek Yong Sung Kwon Hyuk Lee Taegu Kang Kyunghyun Kim YoonKyung Cha Kyung Hwa Cho An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery Remote Sensing deep learning stacked autoencoder cyanobacteria hyperspectral image feature extraction dimensionality reduction |
author_facet |
JongCheol Pyo Hongtao Duan Mayzonee Ligaray Minjeong Kim Sangsoo Baek Yong Sung Kwon Hyuk Lee Taegu Kang Kyunghyun Kim YoonKyung Cha Kyung Hwa Cho |
author_sort |
JongCheol Pyo |
title |
An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery |
title_short |
An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery |
title_full |
An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery |
title_fullStr |
An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery |
title_full_unstemmed |
An Integrative Remote Sensing Application of Stacked Autoencoder for Atmospheric Correction and Cyanobacteria Estimation Using Hyperspectral Imagery |
title_sort |
integrative remote sensing application of stacked autoencoder for atmospheric correction and cyanobacteria estimation using hyperspectral imagery |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-03-01 |
description |
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. |
topic |
deep learning stacked autoencoder cyanobacteria hyperspectral image feature extraction dimensionality reduction |
url |
https://www.mdpi.com/2072-4292/12/7/1073 |
work_keys_str_mv |
AT jongcheolpyo anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT hongtaoduan anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT mayzoneeligaray anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT minjeongkim anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT sangsoobaek anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT yongsungkwon anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT hyuklee anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT taegukang anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT kyunghyunkim anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT yoonkyungcha anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT kyunghwacho anintegrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT jongcheolpyo integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT hongtaoduan integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT mayzoneeligaray integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT minjeongkim integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT sangsoobaek integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT yongsungkwon integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT hyuklee integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT taegukang integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT kyunghyunkim integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT yoonkyungcha integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery AT kyunghwacho integrativeremotesensingapplicationofstackedautoencoderforatmosphericcorrectionandcyanobacteriaestimationusinghyperspectralimagery |
_version_ |
1724719829320990720 |