Rivers are the world's most important resource for surface water supplies and influence many anthropogenic, environmental, ecological, and natural resource activities. The ever-increasing population has boosted industrial and agricultural activities, which has increased the imposed tension on rivers and led ...
Rivers are the world's most important resource for surface water supplies and influence many anthropogenic, environmental, ecological, and natural resource activities. The ever-increasing population has boosted industrial and agricultural activities, which has increased the imposed tension on rivers and led to quantitative and qualitative problems. River components have a wide range, including discharge, flood, baseflow, anthropogenic activities, environmental flow and demand, sediment load, interaction with groundwater, water quality, ecological characteristics, erosion and sedimentation, dam/reservoir impacts, and many others. Therefore, the importance of rivers has become more visible in the past few decades. Such a need for river components-related science has promoted extensive data collection in this field, which includes a wide range of quantitative, qualitative, descriptive, and visual information. In addition, river components-related data is highly diverse and may appear as time series, field observations, laboratory results, and spatial-temporal representations. Moreover, the development of sensors, remote sensing techniques, and the Internet of Things (IoT) in recent years has led to access to a large amount of river components-related data, which needs advanced data handling and modelling techniques to serve the studies in river components. Furthermore, with the development of artificial intelligence (AI) and more advanced (deep) machine learning techniques, it seems there are several new opportunities for better utilization of such extensive accessible data and more contribution to address complex problems in river components.
The nature of this Research Topic lies in interdisciplinary research and the interface of river components and AI. (Deep) Machine learning techniques have been widely used in various applications in recent years. Considering the wide range of topics in river components, machine learning models can be used for different purposes, such as supervised, unsupervised, reinforcement learning, and many other cases. In addition, AI methods can work as alternative or complementary tools for conventional methods. The goals of using machine learning and deep learning models could be diverse and includes reducing uncertainty, minimizing computational time, increasing accuracy, precision, and reliability, and enhancing generalization. Therefore, machine learning and deep learning techniques seem promising tools for handling the ever-growing data in river components.
The scope of this Research Topic includes, but is not limited to, the following:
- Physics-informed neural networks in river components interpretation
- Monitoring and supervising the issue-related big data in river components using deep learning techniques
- Reinforcement learning techniques instead of conventional methods to model river components data
- Evaluating the impact of data pre-processing and post-processing on river components simulations
- Development of novel and hybrid ML models for river component studies
- Modelling high dimensional data for river components
Keywords:
Learning, Supervised learning, Unsupervised learning, Prediction, Forecasting, Classification, Clustering, Regression, IoT
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.