RESUMO
Monitoring water quality and river ecosystems is vital for maintaining public health and environmental sustainability. Over the past decade, data-driven methods have been extensively used for river water quality modeling, including dissolved oxygen (DO) concentrations. Despite advancements, challenges persist regarding accuracy, scalability, and adaptability of data-driven models to diverse environmental conditions. Previous studies primarily employed singular models or basic combinations of machine learning techniques, lacking advanced integration of adaptive mechanisms to process complex and evolving datasets. The current study introduces innovative hybrid models that integrate temporal pattern attention (TPA) mechanisms with advanced neural networks, including feed-forward neural networks (FFNNs) and long short-term memory networks (LSTMs). This approach leverages the synergistic strengths of individual models, significantly enhancing the accuracy of DO predictions. The models were rigorously tested against water quality data obtained from two distinct riverine environments, the Illinois River (ILL) and Des Plaines River (DP). Daily measured water quality data, including DO, chlorophyll-a, nitrate plus nitrite, water temperature, specific conductance, and pH, from 2017 to 2024 provided a robust foundation for comprehensive analysis of DO dynamics in these rivers. We conducted 10 scenarios with different model inputs, wherein the hybrid TPACWRNN-LSTM-10 model particularly excelled, achieving coefficient of determination values of 0.993 and 0.965, and root mean squared errors of 0.241 mg/L and 0.450 mg/L for DO predictions at the ILL and DP stations, respectively. The model's reliability was further confirmed by Willmott's index values of 0.998 and 0.992 and Nash-Sutcliffe efficiency values of 0.990 and 0.961 at the ILL and DP stations, respectively. Additionally, Shapley additive explanations (SHAP) values were utilized to interpret each predictor's contribution, revealing key drivers of DO predictions. We believe the novel hybrid modeling approach presented in this study could benefit utilities and water resource management systems for predicting water quality in complex systems.
RESUMO
Degradation of freshwater ecosystems and the services they provide is a primary cause of increasing water insecurity, raising the need for integrated solutions to freshwater management. While methods for characterizing the multi-faceted challenges of managing freshwater ecosystems abound, they tend to emphasize either social or ecological dimensions and fall short of being truly integrative. This paper suggests that management for sustainability of freshwater systems needs to consider the linkages between human water uses, freshwater ecosystems and governance. We present a conceptualization of freshwater resources as part of an integrated social-ecological system and propose a set of corresponding indicators to monitor freshwater ecosystem health and to highlight priorities for management. We demonstrate an application of this new framework -the Freshwater Health Index (FHI) - in the Dongjiang River Basin in southern China, where stakeholders are addressing multiple and conflicting freshwater demands. By combining empirical and modeled datasets with surveys to gauge stakeholders' preferences and elicit expert information about governance mechanisms, the FHI helps stakeholders understand the status of freshwater ecosystems in their basin, how ecosystems are being manipulated to enhance or decrease water-related services, and how well the existing water resource management regime is equipped to govern these dynamics over time. This framework helps to operationalize a truly integrated approach to water resource management by recognizing the interplay between governance, stakeholders, freshwater ecosystems and the services they provide.