Neural operator surrogates for ice-sheet models to accelerate probabilistic projections of sea-level rise
Explore the source record for details and available documents.
He, Qizhi↗
Engineering topics
He, Qizhi
Publications and source records attributed to He, Qizhi.
A coupled reinforcement learning and IDAES process modeling framework for automated conceptual design of energy and chemical systems
This study introduces an advanced automated system for designing diverse chemical or electrochemical systems, requiring minimal user expertise, and enabling designing and optimization from scratch.
42 ENGINEERING↗
Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
Advection-dispersion equations (ADEs) are commonly used to describe transport phenomena in porous media. Even though mature discretization-based numerical methods for ADEs exist, some challenges still remain, especially when it comes to solving advection-dominated forward ADEs and diffusion-dominated backward ADEs. The latter problem usually arises in the source identification context and leads to numerically unstable grid-based solutions that require a form of regularization or should be treated as an inverse problem that is computationally more expensive because it requires solving the forward problem multiple times. In this study, we propose a discretization-free approach based on the physics-informed neural network (PINN) method for solving coupled ADE and Darcy flow equations with space-dependent hydraulic conductivity. In this approach, the hydraulic conductivity, hydraulic head, and concentration fields are approximated with deep neural networks (DNNs). We assume that the conductivity field is given by its values on a grid, and we use these values to train the conductivity DNN. The head and concentration DNNs are trained by minimizing the residuals of the flow equation and ADE and using the initial and boundary conditions as additional constraints. The PINN method is applied to one- and two-dimensional forward ADE problems, where its performance for various P\'{e}clet numbers ($Pe$) is compared with the analytical and numerical solutions. We find that the PINN method is accurate with errors of less than 1\% and outperforms some conventional discretization-based methods for $Pe$ larger that 100. Next, we demonstrate that the PINN method remains accurate for the backward ADEs, with the relative errors in most cases staying under 5\% compared to the reference concentration field. Finally, we show that when available, the concentration measurements can be easily incorporated in the PINN method and significantly improve (by more than 50\% in the considered cases) the accuracy of the PINN solution of the backward ADE.
He, Qizhi↗
Represent precipitation-induced geological hazards in Earth system models using artificial intelligence
Precipitation-induced geological hazards, such as debris flow, landslides, mudflow and rockfalls (hereafter referred to as landslides), pose serious threats to public safety in many areas through the world. As residential properties and infrastructure in the US have increasingly expanded into landslide-prone areas and the drivers of landslides (e.g., wildfires and hurricanes) are predicted to intensify under climate warming, losses and fatalities from landslides are likely to increase in the future. Although our understanding of geoenvironmental factors and mechanisms contributing to landslides has greatly improved, only moderate progress has been made in predicting landslides out of well-studied watersheds. Furthermore, explicitly representing various landslide-related processes in Earth system models (ESMs), from the buckling of local bearing elements in granular materials, to frictional sliding between grains, formation of microcracks in the soil matrix, rupture of capillary bridges, or breakage of plant roots3 is still very unlikely within the next decade, even with the help of exascale computers.
54 ENVIRONMENTAL SCIENCES↗