Trend analysis and forecasting of streamflow using random forest in the Punarbhaba River basin

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

“…Over the past 20 years, the use of AI approaches has expanded across various fields. In the context of simulating and predicting water quality, various machine learning algorithms, including adaptive boosting (Adaboost) [24], gradient boosting (GBM) [25], extreme gradient boosting (XGBoost) [26], decision tree (DT) [27], extra trees (ExT) [28], radial basis function (RBF) [29], artificial neural network (ANN) [29,30], random forest (RF) [31], deep feed-forward neural network (DFNN) [23], and convolutional neural network (CNN) [22] have been examined for their efficacy. However, researchers still face the challenge of determining the most suitable techniques for a given problem.…”

“…Existing models for predicting WQI have demonstrated certain limitations, and our chosen model overcomes these shortcomings while providing additional benefits. Firstly, when dealing with highly nonlinear data such as hydrologic and climatic data, some ML models can suffer from under-and overfitting, resulting in suboptimal performance [31]. In contrast, our approach incorporates ensemble stacking and CNN models, which were specifically chosen to address these limitations.…”

“…Firstly, we can overcome the under-and overfitting issues often encountered by traditional ML models, ensuring a more accurate representation of the underlying nonlinear relationships in the data. This leads to improved WQI prediction performance compared to existing models [31]. Secondly, by leveraging the power of DL models and the ensemble stacking approach, we can effectively capture the complex and intricate patterns present in water quality data, resulting in better prediction outcomes.…”

Analysis of Changes in Water Flow after Passing through the Planned Dam Reservoir Using a Mixture Distribution in the Face of Climate Change: A Case Study of the Nysa Kłodzka River, Poland

“…The construction of reservoirs can change the trend of the time series of river flows. To evaluate the impact of the dam, researchers often compare the results of the Mann-Kendall test [41], Sen slope trend test and Innovative Trend Analysis (ITA) for flow data before and after construction [42]. The Mann-Kendall trend test is commonly used to assess the presence of trends in time series data [33,43].…”

“…Specifically, when it comes to flow series data from the two periods, pre-dam construction and post-dam construction, this test is used to examine whether the reservoir has had a significant impact on flow patterns [41,44]. However, Sen's slope and ITA have also found application in this type of research [42]. A significant trend of flow series data in post-dam construction may indicate the presence of natural flow patterns (such as air temperature and precipitations) or other external factors influencing flow data (such as economic development, demands of growing population, and intensive urbanization and agriculture) [24,45].…”