paper-with-me

홈 › Papers

Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction

2025-11-10 · Pengfei Hu, Ming Fan, Xiaoxue Han, Chang Lu, Wei Zhang, Hyun Kang, Yue Ning, Dan Lu arxiv

Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

📄 PDF Abstract BibTeX arXiv:2511.07649

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

Optimal Reservoir Operations using Long Short-Term Memory Network

2021-09-07 · Asha Devi Singh, Anurag Singh

A reliable forecast of inflows to the reservoir is a key factor in the optimal operation of reservoirs. Real-time operation of the reservoir based on forecasts of inflows can lead to substantial economic gains. However, …

Anomaly Detection

Scenario-based model predictive control of water reservoir systems

2023-09-01 · Raffaele Giuseppe Cestari, Andrea Castelletti, Simone Formentin

The optimal operation of water reservoir systems is a challenging task involving multiple conflicting objectives. The main source of complexity is the presence of the water inflow, which acts as an exogenous, highly unce…

Model Predictive Control

HydroDCM: Hydrological Domain-Conditioned Modulation for Cross-Reservoir Inflow Prediction

2025-12-02 · Pengfei Hu, Fan Ming, Xiaoxue Han, Chang Lu 외 arxiv

Deep learning models have shown promise in reservoir inflow prediction, yet their performance often deteriorates when applied to different reservoirs due to distributional differences, referred to as the domain shift pro…

Domain Generalization

Investigating Changes of Water Quality in Reservoirs based on Flood and Inflow Fluctuations

2024-03-08 · Shabnam Salehi, Mojtaba Ardestani

Water temperature and dissolved oxygen are essential indicators of water quality and ecosystem sustainability. Lately, heavy rainfalls are happening frequently and forcefully affecting the thermal structure and mixing la…

Efficient Reservoir Management through Deep Reinforcement Learning

2020-12-07 · Xinrun Wang, Tarun Nair, Haoyang Li, Yuh Sheng Reuben Wong 외

Dams impact downstream river dynamics through flow regulation and disruption of upstream-downstream linkages. However, current dam operation is far from satisfactory due to the inability to respond the complicated and un…

Deep Reinforcement LearningManagementreinforcement-learningReinforcement Learning+1