Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery

Although remote sensing techniques have been used to monitor toxic cyanobacteria with hyperspectral data in inland water, it is difficult to optimize conventional bio-optical algorithms for individual water bodies because of the complex optical properties of various water components. Therefore, this...

Full description

Bibliographic Details
Main Authors: Seok Min Hong, Kyung Hwa Cho, Sanghyun Park, Taegu Kang, Moon Sung Kim, Gibeom Nam, JongCheol Pyo
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:GIScience & Remote Sensing
Subjects:
Online Access:http://dx.doi.org/10.1080/15481603.2022.2037887
_version_ 1797679012532715520
author Seok Min Hong
Kyung Hwa Cho
Sanghyun Park
Taegu Kang
Moon Sung Kim
Gibeom Nam
JongCheol Pyo
author_facet Seok Min Hong
Kyung Hwa Cho
Sanghyun Park
Taegu Kang
Moon Sung Kim
Gibeom Nam
JongCheol Pyo
author_sort Seok Min Hong
collection DOAJ
description Although remote sensing techniques have been used to monitor toxic cyanobacteria with hyperspectral data in inland water, it is difficult to optimize conventional bio-optical algorithms for individual water bodies because of the complex optical properties of various water components. Therefore, this study adopted a spatial attention convolutional neural network (spatial attention CNN) to estimate the chlorophyll-a (Chl-a) and phycocyanin (PC) concentrations in the Geum, Nakdong, and Yeongsan rivers in South Korea in order to evaluate cyanobacteria using remote sensing reflectance data. The CNN model utilized a spatial attention module to analyze the importance of the bands in the reflectance data. Then, the spatial attention CNN model was compared with different bio-optical algorithms for each study area. The spatial attention CNN model was generalized to estimate the pigment concentrations in the target rivers, and the model performance was evaluated by correlation coefficient (R) and root mean squared error (RMSE) between the observed and estimated concentrations of the algal pigments. The spatial attention CNN model, which was generalized to estimate the pigment concentrations in the target rivers, had R values above 0.87 and 0.88 for Chl-a and PC, respectively. However, the optimized band ratio algorithms for Chl-a and PC had R values above 0.83 and 0.70, respectively. Hence, it showed better performance than the conventional bio-optical algorithms. The spatial attention module provided attention weights for visualizing important features in the reflectance data. Specifically, the 600 nm, 650 nm, and near-infrared regions had high attention weights for estimating the concentrations of Chl-a and PC. Based on these findings, this study demonstrated that the spatial attention CNN model has a high potential for good application performance in various water bodies.
first_indexed 2024-03-11T23:08:13Z
format Article
id doaj.art-2e9fc947303843f182f55f7a6410b5ce
institution Directory Open Access Journal
issn 1548-1603
1943-7226
language English
last_indexed 2024-03-11T23:08:13Z
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series GIScience & Remote Sensing
spelling doaj.art-2e9fc947303843f182f55f7a6410b5ce2023-09-21T12:43:08ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262022-12-0159154756710.1080/15481603.2022.20378872037887Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagerySeok Min Hong0Kyung Hwa Cho1Sanghyun Park2Taegu Kang3Moon Sung Kim4Gibeom Nam5JongCheol Pyo6Ulsan National Institute of Science and TechnologyUlsan National Institute of Science and TechnologyNational Institute of Environmental ResearchNational Institute of Environmental ResearchUSDA Agricultural Research ServiceNational Institute of Environmental ResearchKorea Environment InstituteAlthough remote sensing techniques have been used to monitor toxic cyanobacteria with hyperspectral data in inland water, it is difficult to optimize conventional bio-optical algorithms for individual water bodies because of the complex optical properties of various water components. Therefore, this study adopted a spatial attention convolutional neural network (spatial attention CNN) to estimate the chlorophyll-a (Chl-a) and phycocyanin (PC) concentrations in the Geum, Nakdong, and Yeongsan rivers in South Korea in order to evaluate cyanobacteria using remote sensing reflectance data. The CNN model utilized a spatial attention module to analyze the importance of the bands in the reflectance data. Then, the spatial attention CNN model was compared with different bio-optical algorithms for each study area. The spatial attention CNN model was generalized to estimate the pigment concentrations in the target rivers, and the model performance was evaluated by correlation coefficient (R) and root mean squared error (RMSE) between the observed and estimated concentrations of the algal pigments. The spatial attention CNN model, which was generalized to estimate the pigment concentrations in the target rivers, had R values above 0.87 and 0.88 for Chl-a and PC, respectively. However, the optimized band ratio algorithms for Chl-a and PC had R values above 0.83 and 0.70, respectively. Hence, it showed better performance than the conventional bio-optical algorithms. The spatial attention module provided attention weights for visualizing important features in the reflectance data. Specifically, the 600 nm, 650 nm, and near-infrared regions had high attention weights for estimating the concentrations of Chl-a and PC. Based on these findings, this study demonstrated that the spatial attention CNN model has a high potential for good application performance in various water bodies.http://dx.doi.org/10.1080/15481603.2022.2037887algal pigmentdeep learning modelsensitivity analysisgeum rivernakdong riveryeongsan river
spellingShingle Seok Min Hong
Kyung Hwa Cho
Sanghyun Park
Taegu Kang
Moon Sung Kim
Gibeom Nam
JongCheol Pyo
Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
GIScience & Remote Sensing
algal pigment
deep learning model
sensitivity analysis
geum river
nakdong river
yeongsan river
title Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
title_full Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
title_fullStr Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
title_full_unstemmed Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
title_short Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery
title_sort estimation of cyanobacteria pigments in the main rivers of south korea using spatial attention convolutional neural network with hyperspectral imagery
topic algal pigment
deep learning model
sensitivity analysis
geum river
nakdong river
yeongsan river
url http://dx.doi.org/10.1080/15481603.2022.2037887
work_keys_str_mv AT seokminhong estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT kyunghwacho estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT sanghyunpark estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT taegukang estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT moonsungkim estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT gibeomnam estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery
AT jongcheolpyo estimationofcyanobacteriapigmentsinthemainriversofsouthkoreausingspatialattentionconvolutionalneuralnetworkwithhyperspectralimagery