River/stream water temperature forecasting using artificial intelligence models: a systematic review
- PDF / 543,024 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 20 Downloads / 184 Views
REVIEW ARTICLE - HYDROLOGY
River/stream water temperature forecasting using artificial intelligence models: a systematic review Senlin Zhu1,2 · Adam P. Piotrowski3 Received: 7 May 2020 / Accepted: 3 September 2020 © Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences 2020
Abstract Water temperature is one of the most important indicators of aquatic system, and accurate forecasting of water temperature is crucial for rivers. It is a complex process to accurately predict stream water temperature as it is impacted by a lot of factors (e.g., meteorological, hydrological, and morphological parameters). In recent years, with the development of computational capacity and artificial intelligence (AI), AI models have been gradually applied for river water temperature (RWT) forecasting. The current survey aims to provide a systematic review of the AI applications for modeling RWT. The review is to show the progression of advances in AI models. The pros and cons of the established AI models are discussed in detail. Overall, this research will provide references for hydrologists and water resources engineers and planners to better forecast RWT, which will benefit river ecosystem management. Keywords River water temperature forecasting · Artificial intelligence models · Hybrid model · Review
Introduction Water temperature is one of the most important indicators for river systems, which controls many physical and biogeochemical processes within the waterbody, such as the reaeration process of oxygen (Gualtieri et al. 2002), decay process of organic matter (Matsumoto et al. 2007), nitrification kinetics (Zhang et al. 2014), etc. All the aquatic species have the specific water temperature ranges for development and production, and significant variations in water temperature may bring serious consequences to the ecosystem. For example, Quinn et al. (1994) indicated that water temperatures that occur in summer in many New Zealand rivers may limit the distribution and abundance of some invertebrate species. Lessard and Hayes (2003) found that increasing temperatures downstream of the dams impacted * Senlin Zhu [email protected] 1
College of Hydraulic Science and Engineering, Yangzhou University, Yangzhou 225127, China
2
State Key Laboratory of Hydrology‑Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing 210029, China
3
Institute of Geophysics, Polish Academy of Sciences, Ks. Janusza 64, 01‑452 Warsaw, Poland
the densities of several cold-water fish species and the community composition of macroinvertebrates. It is therefore of great significance to study the thermal regime of rivers. Mathematical models are important tools to evaluate the thermal dynamics in rivers. In the past decades, many models were developed and applied in different regions. Generally, these models can be classified into two categories: (1) statistical/stochastic models and (2) process-based deterministic models. For statistical/stochastic models, there are many types available, su
Data Loading...