Blue Waters, Green Solutions: The New Frontier in Water Quality
Forecasting and Harmful Algal Bloom Management for Smart Cities
Across the globe, our coastal waters face unprecedented challenges. Today, we embark on a journey through research that charts a new course for managing water quality and combating the rise of harmful algal blooms, or HABs. Now, researchers can use technologies like Artificial Intelligence (AI) to tackle such challenges in real time with higher precision.
Real-time Monitoring for Algal Bloom Identification
In Hong Kong’s coastal waters, a study utilizing the Imaging FlowCytobot (IFCB) and AI has achieved a remarkable accuracy of 94.2% in real-time monitoring of toxic algae, a first in Greater China and a pioneering step in marine conservation. This technique can process up to 30,000 images per hour in identifying 15 HAB species [1].
AI Enhances Algal Bloom Management
Using an AI-driven system, the Algal Morphology Deep Neural Network boasts a 99.87% accuracy in managing HABs [2]. This technology transitions from the labor-intensive manual analyses of the past to efficient, on-site AI monitoring.
Better Understanding of Dissolved Oxygen Levels
The combined IFCB and AI system provides more carbon to chlorophyll-a ratio information with invaluable insights for managing mariculture [3]. This finding improves the understanding of the impact of dissolved oxygen levels in coastal waters. Essentially, it is an approach that underscores the importance of precision in preserving the health of our marine environments.
AI Technology and Water Environment Research
AI technology is increasingly vital to water environment research, offering innovative solutions to some of the most pressing challenges in the field, such as predictive analytics. Take, for example, an AI-based model, EasyEnsemble, introduced to forecast beach water quality with an F-score of 0.84 [4]. Similarly, the WATERMAN system is powered by AI, utilizing 3D hydrodynamic models to predict water quality exceedances [5]. The continuous advancement in AI will further widen the scope of Water Environment Research by looking at Climate Change Adaptation, such as monitoring light extinction in coastal waters facilitated by a remotely controlled system [6].
Each of these studies marks a significant step forward in the science of water environment engineering. By harnessing the power of AI and real-time automated systems, we are now deepening our understanding of aquatic environments for a better world.
*Notes: This article provides research teasers for each reference to showcase the novelties
References
[1] J. Guo, Y. Ma, and J. H. W. Lee, “Real-time automated identification of algal bloom species for fisheries management in subtropical coastal waters,” Journal of Hydro-environment Research, vol. 36, pp. 1–32, May 2021, doi: 10.1016/j.jher.2021.03.002.
[2] A. Yuan, B. Wang, J. Li, and J. H. W. Lee, “A low-cost edge AI-chip-based system for real-time algae species classification and HAB prediction,” Water Research, vol. 233, p. 119727, Apr. 2023, doi: 10.1016/j.watres.2023.119727.
[3] Y. Ma, J. H. W. Lee, L. Chang, H. Tang, and H. Liu, “Field measurements of the carbon to chlorophyll-a ratio using Imaging FlowCytobot: Implications for dissolved oxygen modeling,” Estuarine, Coastal and Shelf Science, vol. 285, p. 108304, May 2023, doi: 10.1016/j.ecss.2023.108304.
[4] J. Guo and J. H. W. Lee, “Development of Predictive Models for ‘Very Poor’ Beach Water Quality Gradings Using Class-Imbalance Learning,” Environ. Sci. Technol., vol. 55, no. 21, pp. 14990–15000, Nov. 2021, doi: 10.1021/acs.est.1c03350.
[5] K. W. Choi, S. N. Chan, and J. H. W. Lee, “The WATERMAN system for daily beach water quality forecasting: a ten-year retrospective,” Environ Fluid Mech, vol. 23, no. 2, pp. 205–228, Feb. 2022, doi: 10.1007/s10652-022-09839-4.
[6] Y. Fan and J. H. W. Lee, “A remotely controlled automated field measurement system for light extinction in coastal waters,” Marine Pollution Bulletin, vol. 186, p. 114423, Jan. 2023, doi: 10.1016/j.marpolbul.2022.114423.
Curated based on the following publications
Blue Waters, Green Solutions: The New Frontier in Water Quality
Forecasting and Harmful Algal Bloom Management for Smart Cities
Across the globe, our coastal waters face unprecedented challenges. Today, we embark on a journey through research that charts a new course for managing water quality and combating the rise of harmful algal blooms, or HABs. Now, researchers can use technologies like Artificial Intelligence (AI) to tackle such challenges in real time with higher precision.
Real-time Monitoring for Algal Bloom Identification
In Hong Kong’s coastal waters, a study utilizing the Imaging FlowCytobot (IFCB) and AI has achieved a remarkable accuracy of 94.2% in real-time monitoring of toxic algae, a first in Greater China and a pioneering step in marine conservation. This technique can process up to 30,000 images per hour in identifying 15 HAB species [1].
AI Enhances Algal Bloom Management
Using an AI-driven system, the Algal Morphology Deep Neural Network boasts a 99.87% accuracy in managing HABs [2]. This technology transitions from the labor-intensive manual analyses of the past to efficient, on-site AI monitoring.
Better Understanding of Dissolved Oxygen Levels
The combined IFCB and AI system provides more carbon to chlorophyll-a ratio information with invaluable insights for managing mariculture [3]. This finding improves the understanding of the impact of dissolved oxygen levels in coastal waters. Essentially, it is an approach that underscores the importance of precision in preserving the health of our marine environments.
AI Technology and Water Environment Research
AI technology is increasingly vital to water environment research, offering innovative solutions to some of the most pressing challenges in the field, such as predictive analytics. Take, for example, an AI-based model, EasyEnsemble, introduced to forecast beach water quality with an F-score of 0.84 [4]. Similarly, the WATERMAN system is powered by AI, utilizing 3D hydrodynamic models to predict water quality exceedances [5]. The continuous advancement in AI will further widen the scope of Water Environment Research by looking at Climate Change Adaptation, such as monitoring light extinction in coastal waters facilitated by a remotely controlled system [6].
Each of these studies marks a significant step forward in the science of water environment engineering. By harnessing the power of AI and real-time automated systems, we are now deepening our understanding of aquatic environments for a better world.
*Notes: This article provides research teasers for each reference to showcase the novelties
References
[1] J. Guo, Y. Ma, and J. H. W. Lee, “Real-time automated identification of algal bloom species for fisheries management in subtropical coastal waters,” Journal of Hydro-environment Research, vol. 36, pp. 1–32, May 2021, doi: 10.1016/j.jher.2021.03.002.
[2] A. Yuan, B. Wang, J. Li, and J. H. W. Lee, “A low-cost edge AI-chip-based system for real-time algae species classification and HAB prediction,” Water Research, vol. 233, p. 119727, Apr. 2023, doi: 10.1016/j.watres.2023.119727.
[3] Y. Ma, J. H. W. Lee, L. Chang, H. Tang, and H. Liu, “Field measurements of the carbon to chlorophyll-a ratio using Imaging FlowCytobot: Implications for dissolved oxygen modeling,” Estuarine, Coastal and Shelf Science, vol. 285, p. 108304, May 2023, doi: 10.1016/j.ecss.2023.108304.
[4] J. Guo and J. H. W. Lee, “Development of Predictive Models for ‘Very Poor’ Beach Water Quality Gradings Using Class-Imbalance Learning,” Environ. Sci. Technol., vol. 55, no. 21, pp. 14990–15000, Nov. 2021, doi: 10.1021/acs.est.1c03350.
[5] K. W. Choi, S. N. Chan, and J. H. W. Lee, “The WATERMAN system for daily beach water quality forecasting: a ten-year retrospective,” Environ Fluid Mech, vol. 23, no. 2, pp. 205–228, Feb. 2022, doi: 10.1007/s10652-022-09839-4.
[6] Y. Fan and J. H. W. Lee, “A remotely controlled automated field measurement system for light extinction in coastal waters,” Marine Pollution Bulletin, vol. 186, p. 114423, Jan. 2023, doi: 10.1016/j.marpolbul.2022.114423.
