Abstract
Groundwater optimization models coupling Non-dominated Sorting Genetic Algorithm II (NSGAII) with surrogate models have shown great success in recent years. However, most previous models adopted global optimization over time steps while ignoring the time-varying properties of optimization objectives, which may lead to an unrealistic strategy for specific months. Moreover, employing global optimization for time-varying optimization may result in computation inefficient. To address these issues, We developed EGN combining Expert knowledge, Graph Attention Networks and the NSGAII algorithm. Specifically, EGN defines a deterministic policy based on the encoded Expert knowledge to efficiently select the optimal strategy from the Pareto Front given by NSGAII. The framework significantly reduced the asymptotic complexity from O(NT) (global optimization) to O(N2). We evaluate EGN on a real-world dataset and the results show that EGN outperforms baselines and global optimization.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
