Search for: All records

In coastal river systems, floods, often during major storms or king tides, severely threaten lives and property. However, hydraulic structures such as dams, gates, pumps, and reservoirs exist in these river systems, and these floods can be mitigated or even prevented by strategically releasing water before extreme weather events. A standard approach used by local water management agencies is the “rule-based” method, which specifies predetermined water prereleases based on historical human experience, but which tends to result in excessive or inadequate water release. Iterative optimization methods that rely on detailed physics-based models for prediction are an alternative approach. Whereas, such methods tend to be computationally intensive, requiring hours or even days to solve the problem optimally. In this paper, we propose a Forecast Informed Deep Learning Architecture, FIDLAR, to achieve rapid and near-optimal flood management with precise water prereleases. FIDLAR seamlessly integrates two neural network modules: one called the Flood Manager, which is responsible for generating water pre-release schedules, and another called the Flood Evaluator, which evaluates those generated schedules. The Evaluator module is pre-trained separately, and its gradient-based feedback is utilized to train the Manager model, ensuring near-optimal water pre-releases. We have conducted experiments with a flood-prone coastal area in South Florida. Results show that FIDLAR is several orders of magnitude faster than currently used physics-based approaches while outperforming baseline methods with improved water pre-release schedules. 

Abstract Flooding is one of the most frequent natural hazards and causes more economic loss than all the other natural hazards. Fast and accurate flood prediction has significance in preserving lives, minimizing economic damage, and reducing public health risks. However, current methods cannot achieve speed and accuracy simultaneously. Numerical methods can provide high-fidelity results, but they are time-consuming, particularly when pursuing high accuracy. Conversely, neural networks can provide results in a matter of seconds, but they have shown low accuracy in flood map generation by all existing methods. This work combines the strengths of numerical methods and neural networks and builds a framework that can quickly and accurately model the high-fidelity flood inundation map with detailed water depth information. In this paper, we employ the U-Net and generative adversarial network (GAN) models to recover the lost physics and information from ultra-fast, low-resolution numerical simulations, ultimately presenting high-resolution, high-fidelity flood maps as the end results. In this study, both the U-Net and GAN models have proven their ability to reduce the computation time for generating high-fidelity results, reducing it from 7–8 h down to 1 min. Furthermore, the accuracy of both models is notably high. 

A combined sewer system (CSS) collects rainwater runoff, domestic sewage, and industrial wastewater in the same pipe. The volume of wastewater can sometimes exceed the system capacity during heavy rainfall events. When this occurs, untreated stormwater and wastewater discharge directly to nearby streams, rivers, and other water bodies. This would threaten public health and the environment, contributing to drinking water contamination and other concerns. Minimizing sewer overflows requires an optimization method that can provide an optimal sequence of decision variables at control gates. Conventional strategies use classical optimization algorithms, such as genetic algorithms and pattern search, to find the optimal sequence of decision variables. However, these conventional frameworks are very time-consuming, and it is almost impossible to achieve near real-time optimal control. This paper presents a faster optimization framework by using a new optimal control tool: reinforcement learning. The environment (flow modeler) used in this paper is the numerical model: Environmental Protection Agency’s Storm Water Management Model (EPA SWMM) to ensure the accuracy of environment response. The reward function is constructed based on the calculated water depth and overflow rate from SWMM. The process keeps minimizing the reward function to obtain the optimal flow release sequence at each controlled orifice gate. The combined sewer system (CSS) of the Puritan-Fenkell 7-mile facility in Detroit, MI, is chosen as the case study.