Call for Papers: Artificial Intelligence in Hydrology
Hydrological research and hydrological engineering are facing a digital evolution including a more complete and accurate prediction of the complex systems. From a macroscopic perspective, the research object is evolving from local river sections, lakes, reservoirs, etc to the whole basin or even the global environment. For example, there may be dozens of reservoirs distributed on a major river, and the information exchange and linkage decision-making between them will face huge challenge for operation and control to limit flood damage. In these conditions, the amount of information and calculation is far beyond what traditional methods can handle. From a microscopic perspective, hydrological research is developing towards a more refined manner, with more and more factors covered in theoretical models. The application of various novel automatic sensors is bringing a huge amount of information to hydrology research and engineering. Thus, more and more real-time data needs to be processed. For example, in the past, the calculation of water flow in agricultural irrigation areas mainly calculated the average flow of its main rivers and precipitation over a period of time, but at present, we hope to obtain more accurate real-time data to support refined agricultural production. All these have resulted in large-scale real-time data processing and calculation. It is almost impossible to complete these tasks by traditional methods and human computation. Supercomputers can help people solve the problem of large amount of data calculation, yet the models they use might have significant limitation in assisting judgment and decision-making, being unable to provide estimates of complex processes under general conditions, especially for real-time simulation or forecasting.
The development of artificial intelligence (AI) provides the possibility for carrying out hydrological research and engineering in a more macro and accurate manner. Faced with a large number of complex mathematical models with target sets and constraint sets, AI, which has extremely high operation speed, ability to process massive data and judgment, is exactly what is needed in hydrological analysis, optimization calculation and prediction, complementary to physical based and conceptual modeling. The past few years have witnessed a rapid development of AI, and at the same time, many AI methods and models in hydrological fields have also been proposed. These include AI methods for simulating and predicting sedimentary time series in various rivers, AI classifiers for fecal pollution mapping, and Cascaded-based multi-scale AI approaches for modeling rainfall-runoff process, etc.
Thus, the development of AI is an inevitable trend in solving massive information and huge scale problems in the realm of hydrology. The purpose of this special issue is to promote outstanding studies concerning all aspects in the field of AI in hydrology, focusing on state-of-the-art progress, as well as the limitations of AI approaches being opportunities for the improvement of existing techniques, development of new ones and new trends.
Contributions are expected in all topics dealing with the application of Artificial Intelligence techniques in Hydrology, such as:
- AI Algorithms
- 5G and Satellite Communications
- Big Data Processing
- Deep Learning
- Application of Neural Networks
- Internet of Things
- Remote Sensing and Data Collection
- AI-assisted Sampling and Evaluation
- Land subsistence modeling
- Global Cooperation
- Data-supported hydrology policy formulation
- Nonstationarity detection and modeling
- Deadline for paper submission: 30 September 2021
- Expected Publication: Early 2022
Note: accepted manuscripts will be published online rapidly following acceptance.
How to submit:
Please make sure that your paper follows the Instructions to Authors, before submitting your paper directly to Hydrology Research’s peer review system, choosing the category - Special Issue: Artificial Intelligence in Hydrology.
Prof. Elena Volpi, Università Roma Tre, Italy
Prof. Jong Suk KIM, Wuhan University, China
Prof. Shaleen Jain, University of Maine, USA
Dr Sangam Shrestha, Asian Institute of Technology (AIT), Thailand