Machine-learning paradigms for selecting ecologically significant input variables |
| |
| Affiliation: | 1. Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, 73 East Beijing Road, Nanjing, 210008, China;2. Center for Eco-Environment Research, Nanjing Hydraulic Research Institute, Nanjing, 210098, China;3. China National Environmental Monitoring Centre, 8(B) Dayangfang Beiyuan Road, Chaoyang District, Beijing, 100012, China;4. Ecological Modelling Laboratory, Department of Physical & Environmental Sciences, University of Toronto, Toronto, ON, M1C 1A4, Canada;5. School of Geography and the Environment, University of Oxford, Oxford, OX1 3QY, United Kingdom;1. Jiangsu Key Laboratory of Big Data Security & Intelligent Processing, Nanjing University of Posts and Telecommunications, Nanjing, China;2. School of Environment, Guangzhou Key Laboratory of Environmental Exposure and Health, Guangdong Key Laboratory of Environmental Pollution and Health, Jinan University, Guangzhou, Guangdong, 510632, China;3. State Key Laboratory of Pollution Control and Resource Reuse, School of the Environment, Nanjing University, Nanjing, Jiangsu, 210023, China;4. College of Literature, Science, and the Arts, University of Michigan, Ann Arbor, MI, 48109, USA;5. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing, Beijing, 100048, China;6. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, 210023, China;1. Griffith School of Engineering and Built Environment, Griffith University, Parklands Drive, Southport, Queensland, 4222, Australia;2. Cities Research Institute, Griffith University, Parklands Drive, Southport, Queensland, 4222, Australia;3. Australian Rivers Institute, Griffith University, 170 Kessels Road, Nathan, Queensland, 4111, Australia;1. Key Laboratory of Yangtze River Water Environment, Ministry of Education, College of Environmental Science and Engineering, Tongji University, 200092 Shanghai, China;2. Institute of Urban Water Management, Technische Universität Dresden, 01062 Dresden, Germany;1. Yeongsan River Environment Research Laboratory, National Institute of Environmental Research, Gwangju 500-480, Republic of Korea;2. Department of Rural & Biosystems Engineering, Chonnam National University, Gwangju 500-757, Republic of Korea;3. Department of Environmental Science and Engineering, University of Ewha Womans, Seoul 120-75, Republic of Korea;4. Department of Civil and Environmental Engineering, University of Wisconsin – Madison, 1415 Engineering Drive, Madison, WI 53706, USA |
| |
| Abstract: | Harmful algal blooms, which are considered a serious environmental problem nowadays, occur in coastal waters in many parts of the world. They cause acute ecological damage and ensuing economic losses, due to fish kills and shellfish poisoning as well as public health threats posed by toxic blooms. Recently, data-driven models including machine-learning (ML) techniques have been employed to mimic dynamics of algal blooms. One of the most important steps in the application of a ML technique is the selection of significant model input variables. In the present paper, we use two extensively used ML techniques, artificial neural networks (ANN) and genetic programming (GP) for selecting the significant input variables. The efficacy of these techniques is first demonstrated on a test problem with known dependence and then they are applied to a real-world case study of water quality data from Tolo Harbour, Hong Kong. These ML techniques overcome some of the limitations of the currently used techniques for input variable selection, a review of which is also presented. The interpretation of the weights of the trained ANN and the GP evolved equations demonstrate their ability to identify the ecologically significant variables precisely. The significant variables suggested by the ML techniques also indicate chlorophyll-a (Chl-a) itself to be the most significant input in predicting the algal blooms, suggesting an auto-regressive nature or persistence in the algal bloom dynamics, which may be related to the long flushing time in the semi-enclosed coastal waters. The study also confirms the previous understanding that the algal blooms in coastal waters of Hong Kong often occur with a life cycle of the order of 1–2 weeks. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
