Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers
Study region: The study focuses on the 12 rivers across Hong Kong, that have been facing varying degrees of algal bloom risks. Study focus: Data-driven models are extensively employed to forecast and discern the catalysts of algal blooms, leveraging high temporal resolution data to unveil intricate...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Journal of Hydrology: Regional Studies |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214581824004579 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591854058602496 |
|---|---|
| author | Shujie Xu Zhongnan Ye Shu-Chien Hsu Xiaoyi Liu Chunmiao Zheng |
| author_facet | Shujie Xu Zhongnan Ye Shu-Chien Hsu Xiaoyi Liu Chunmiao Zheng |
| author_sort | Shujie Xu |
| collection | DOAJ |
| description | Study region: The study focuses on the 12 rivers across Hong Kong, that have been facing varying degrees of algal bloom risks. Study focus: Data-driven models are extensively employed to forecast and discern the catalysts of algal blooms, leveraging high temporal resolution data to unveil intricate numerical relationships among indicators. The efficacy of these models can be compromised due to the low temporal resolution of water quality monitoring. This study presents a data-driven algal bloom alert model employing machine learning and data discretization techniques to solve the data issue, utilizing monthly water quality data of 12 rivers and daily weather data in Hong Kong. The critical factors associated with algal blooms were then identified by feature importance analysis and false negative analysis of the optimal performance model, guiding potential algal control strategies for Hong Kong. New hydrological insights for the region: Models that integrate data discretization outperformed those using numerical normalization, showing higher recall scores and greater stability across selected algorithms (linear regression, support vector machine, random forest, and decision tree). Permutation importance analysis identified nitrogen compounds and rising temperatures as key triggers of algal blooms, while false negative analysis highlighted total phosphorus and flow as critical factors. This study offers a potential solution for prediction and forecasting without extensive datasets and emphasizes the importance of integrating domain knowledge in both prior and posterior analyses to enhance the interpretability of data-driven models in water science. |
| format | Article |
| id | doaj-art-8e90643867794cbea00cd788129398db |
| institution | Kabale University |
| issn | 2214-5818 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Hydrology: Regional Studies |
| spelling | doaj-art-8e90643867794cbea00cd788129398db2025-01-22T05:42:03ZengElsevierJournal of Hydrology: Regional Studies2214-58182025-02-0157102108Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong riversShujie Xu0Zhongnan Ye1Shu-Chien Hsu2Xiaoyi Liu3Chunmiao Zheng4Department of Civil and Environmental Engineering, the Hong Kong Polytechnic University, Hong Kong SAR; Guangdong-Hong Kong Joint Laboratory for Soil and Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China; Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, ChinaDepartment of Civil and Environmental Engineering, the Hong Kong Polytechnic University, Hong Kong SARDepartment of Civil and Environmental Engineering, the Hong Kong Polytechnic University, Hong Kong SAR; Corresponding author.Department of Civil and Environmental Engineering, the Hong Kong Polytechnic University, Hong Kong SARGuangdong-Hong Kong Joint Laboratory for Soil and Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China; Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China; Eastern Institute for Advanced Study, Eastern Institute of Technology, Ningbo, China; Corresponding author at: Guangdong-Hong Kong Joint Laboratory for Soil and Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China.Study region: The study focuses on the 12 rivers across Hong Kong, that have been facing varying degrees of algal bloom risks. Study focus: Data-driven models are extensively employed to forecast and discern the catalysts of algal blooms, leveraging high temporal resolution data to unveil intricate numerical relationships among indicators. The efficacy of these models can be compromised due to the low temporal resolution of water quality monitoring. This study presents a data-driven algal bloom alert model employing machine learning and data discretization techniques to solve the data issue, utilizing monthly water quality data of 12 rivers and daily weather data in Hong Kong. The critical factors associated with algal blooms were then identified by feature importance analysis and false negative analysis of the optimal performance model, guiding potential algal control strategies for Hong Kong. New hydrological insights for the region: Models that integrate data discretization outperformed those using numerical normalization, showing higher recall scores and greater stability across selected algorithms (linear regression, support vector machine, random forest, and decision tree). Permutation importance analysis identified nitrogen compounds and rising temperatures as key triggers of algal blooms, while false negative analysis highlighted total phosphorus and flow as critical factors. This study offers a potential solution for prediction and forecasting without extensive datasets and emphasizes the importance of integrating domain knowledge in both prior and posterior analyses to enhance the interpretability of data-driven models in water science.http://www.sciencedirect.com/science/article/pii/S2214581824004579Algal bloomsData-driven modelsData discretizationWater management |
| spellingShingle | Shujie Xu Zhongnan Ye Shu-Chien Hsu Xiaoyi Liu Chunmiao Zheng Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers Journal of Hydrology: Regional Studies Algal blooms Data-driven models Data discretization Water management |
| title | Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers |
| title_full | Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers |
| title_fullStr | Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers |
| title_full_unstemmed | Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers |
| title_short | Development of data-driven algal bloom alert models with low temporal resolution data and application to Hong Kong rivers |
| title_sort | development of data driven algal bloom alert models with low temporal resolution data and application to hong kong rivers |
| topic | Algal blooms Data-driven models Data discretization Water management |
| url | http://www.sciencedirect.com/science/article/pii/S2214581824004579 |
| work_keys_str_mv | AT shujiexu developmentofdatadrivenalgalbloomalertmodelswithlowtemporalresolutiondataandapplicationtohongkongrivers AT zhongnanye developmentofdatadrivenalgalbloomalertmodelswithlowtemporalresolutiondataandapplicationtohongkongrivers AT shuchienhsu developmentofdatadrivenalgalbloomalertmodelswithlowtemporalresolutiondataandapplicationtohongkongrivers AT xiaoyiliu developmentofdatadrivenalgalbloomalertmodelswithlowtemporalresolutiondataandapplicationtohongkongrivers AT chunmiaozheng developmentofdatadrivenalgalbloomalertmodelswithlowtemporalresolutiondataandapplicationtohongkongrivers |