Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China
Water quality assessment is essential for effective environmental management, yet traditional methods such as chemical sampling are often labor-intensive and inefficient for large-scale, continual monitoring. This study addresses these limitations by leveraging hyperspectral images (HSIs) analysis a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124003960 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846119462044958720 |
|---|---|
| author | Hongran Li Hui Zhao Chao Wei Min Cao Jian Zhang Heng Zhang Dongqing Yuan |
| author_facet | Hongran Li Hui Zhao Chao Wei Min Cao Jian Zhang Heng Zhang Dongqing Yuan |
| author_sort | Hongran Li |
| collection | DOAJ |
| description | Water quality assessment is essential for effective environmental management, yet traditional methods such as chemical sampling are often labor-intensive and inefficient for large-scale, continual monitoring. This study addresses these limitations by leveraging hyperspectral images (HSIs) analysis and introducing a capsule network (CapsNet) model enhanced with a multidimensional integration attention (MDIA) mechanism. The model is specifically designed to integrate both channel and spatial information, enabling precise water quality grade assessment by detecting subtle features within HSIs data. To validate the performance of the model, spectral data from 5 water quality regions are collected and processed via a UAV-carried spectrometer, with 4503 water quality data samples. Rigorous classification experiments demonstrated that the model achieves 98.73 % accuracy, with an average improvement of 4.89 % compared with the other models. This approach significantly improves decision support systems for water resource management, facilitating the sustainable use of water resources. |
| format | Article |
| id | doaj-art-2afc1fbe972b419c802df3207479f326 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-2afc1fbe972b419c802df3207479f3262024-12-17T04:59:07ZengElsevierEcological Informatics1574-95412024-12-0184102854Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, ChinaHongran Li0Hui Zhao1Chao Wei2Min Cao3Jian Zhang4Heng Zhang5Dongqing Yuan6Jiangsu Ocean University, Lianyungang 222005, Jiangsu, China; Corresponding author.Jiangsu Ocean University, Lianyungang 222005, Jiangsu, ChinaJiangsu Ocean University, Lianyungang 222005, Jiangsu, ChinaJiangsu Duke Industry CO., LTD, Lianyungang 222005, Jiangsu, ChinaJiangsu Ocean University, Lianyungang 222005, Jiangsu, ChinaJiangsu Ocean University, Lianyungang 222005, Jiangsu, ChinaJiangsu Ocean University, Lianyungang 222005, Jiangsu, ChinaWater quality assessment is essential for effective environmental management, yet traditional methods such as chemical sampling are often labor-intensive and inefficient for large-scale, continual monitoring. This study addresses these limitations by leveraging hyperspectral images (HSIs) analysis and introducing a capsule network (CapsNet) model enhanced with a multidimensional integration attention (MDIA) mechanism. The model is specifically designed to integrate both channel and spatial information, enabling precise water quality grade assessment by detecting subtle features within HSIs data. To validate the performance of the model, spectral data from 5 water quality regions are collected and processed via a UAV-carried spectrometer, with 4503 water quality data samples. Rigorous classification experiments demonstrated that the model achieves 98.73 % accuracy, with an average improvement of 4.89 % compared with the other models. This approach significantly improves decision support systems for water resource management, facilitating the sustainable use of water resources.http://www.sciencedirect.com/science/article/pii/S1574954124003960Water quality classificationMultidimensional integration attentionCapsule networkSpectral featureUAV-based sensingDeep learning |
| spellingShingle | Hongran Li Hui Zhao Chao Wei Min Cao Jian Zhang Heng Zhang Dongqing Yuan Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China Ecological Informatics Water quality classification Multidimensional integration attention Capsule network Spectral feature UAV-based sensing Deep learning |
| title | Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China |
| title_full | Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China |
| title_fullStr | Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China |
| title_full_unstemmed | Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China |
| title_short | Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China |
| title_sort | assessing water quality environmental grades using hyperspectral images and a deep learning model a case study in jiangsu china |
| topic | Water quality classification Multidimensional integration attention Capsule network Spectral feature UAV-based sensing Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124003960 |
| work_keys_str_mv | AT hongranli assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT huizhao assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT chaowei assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT mincao assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT jianzhang assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT hengzhang assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina AT dongqingyuan assessingwaterqualityenvironmentalgradesusinghyperspectralimagesandadeeplearningmodelacasestudyinjiangsuchina |