Thermal stratification is a significant phenomenon driven by complex interconnected factors that reduce mixing between the top and the bottom layers, impacting oxygen and nutrient dispersion and potentially causing fish mortality. This study has assessed the non-mixing occurrence in river flow using a classification approach, developing a novel hybrid data-driven model from key datasets of the Darling River in Menindee, Australia. The influence of various input variables using the proposed model is investigated, including meteorological drivers, hydrological factors, key data generated by the one-dimensional process-based model named LAKEoneD, and Physics-Informed Neural Networks. The study also considers stratification indices based on the Schmidt stability and empirical river mixing criteria. Supervised machine learning methods were used to classify a given day as mixing or non-mixing conditions. The results showed that the proposed hybrid model integrating Support Vector Machines with key data generated by LAKEoneD outperformed benchmarking models. The study also employed explainable artificial intelligence analysis, suggesting that the minimum air temperature and relative humidity, as the model inputs, played a role in predicting non-mixing river flow conditions. Importantly, the maximum air temperature was another potential input that affected the river flow system, particularly near a fish death event. We conclude that the proposed model can be used as a scientific stratagem for future research in predicting fish and other aquatic organism health related to river flow dynamics, which has implications for environmental authorities guiding better water quality management in river systems.
扫码关注我们
求助内容:
应助结果提醒方式:
