More Like this

1. A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Finding

   Onken, Derek; Nurbekyan, Levon; Li, Xingjian; Wu Fung, Samy; Osher, Stan; Ruthotto, Lars (July 2022, IEEE transactions on control systems technology)

   We propose a neural network approach that yields approximate solutions for high-dimensional optimal control problems and demonstrate its effectiveness using examples from multi-agent path finding. Our approach yields controls in a feedback form, where the policy function is given by a neural network (NN). Specifically, we fuse the Hamilton-Jacobi-Bellman (HJB) and Pontryagin Maximum Principle (PMP) approaches by parameterizing the value function with an NN. Our approach enables us to obtain approximately optimal controls in real-time without having to solve an optimization problem. Once the policy function is trained, generating a control at a given space-time location takes milliseconds; in contrast, efficient nonlinear programming methods typically perform the same task in seconds. We train the NN offline using the objective function of the control problem and penalty terms that enforce the HJB equations. Therefore, our training algorithm does not involve data generated by another algorithm. By training on a distribution of initial states, we ensure the controls' optimality on a large portion of the state-space. Our grid-free approach scales efficiently to dimensions where grids become impractical or infeasible. We apply our approach to several multi-agent collision-avoidance problems in up to 150 dimensions. Furthermore, we empirically observe that the number of parameters in our approach scales linearly with the dimension of the control problem, thereby mitigating the curse of dimensionality. 

   more » « less
2. Accelerating Electric-magnetic machine simulation using the Fourier Neural Operator (FNO)

   Guo, Zhengke; Gu, Xianfeng David; Chen, Shikui (August 2025, American Society of Mechanical Engineers (ASME))

   Electrical machines traditionally rely on Finite Element Analysis (FEA) to evaluate or simulate their properties by solving the associated partial differential equations (PDEs). However, FEA is computationally costly, which limits its capability for rapid design iteration and real-time simulations. While recent surrogate models such as Physics-Informed Neural Networks (PINNs) have shown promise, they often suffer from slow convergence and scalability issues in complex geometries. In this paper, we propose the use of the Fourier Neural Operator (FNO) as a resolution-invariant surrogate model to significantly reduce the computation time required for FEA-based PDE solutions in electric machines. Previous research has demonstrated the FNO’s ability to learn mappings for time-sequence problems by approximating operators between function spaces. Building on this, we present a methodology to directly predict the later-state electromagnetic fields of a rotating interior permanent magnet (IPM) motor based on its earlier-stage data by approximating the underlying operator that governs these transitions. Our framework enables full-geometry modeling without relying on segmentation, preserving accuracy while dramatically improving computational efficiency. The model was trained and validated on an FEA dataset with multiple boundary conditions and motor configurations, demonstrating strong generalization across different designs and resolutions. Experimental results show that the proposed FNO method achieves a significant reduction in computational time compared to traditional FEA simulations while maintaining an acceptable level of accuracy. This study highlights the potential of neural operators for accelerating electromagnetic simulations, enabling faster design iterations and offering new possibilities for real-time and optimization-based applications in electric machine design. 

   more » « less
3. A Numerical Study on Hurricane Patricia (2015). Part I: Control Simulation and the Roles of Surface and Boundary Layer Processes

   https://doi.org/10.1175/MWR-D-24-0048.1  

   Zhu, Yiting; Wang, Yuqing (January 2025, Monthly Weather Review)

   Abstract Hurricane Patricia (2015) formed over the eastern North Pacific and is the most intense tropical cyclone (TC) on record with a maximum sustained wind speed of 95 m s⁻¹, which presented a great forecasting challenge due to its unprecedented rapid intensification, record-breaking lifetime maximum intensity, and subsequent rapid weakening. The intensity and structure changes in Patricia were successfully simulated in a control experiment using a two-way interactive, quadruply nested version of the Weather Research and Forecasting Model with both initial and lateral boundary conditions from the Global Forecast System Final Analysis data. The successful simulation resulted from the inclusion of dissipative heating, realistic horizontal mixing length, and sea-spray-mediated heat flux. The relative contributions of these processes were assessed based on a series of ensemble-based sensitivity experiments and energetic diagnostics. Results show that dissipative heating and reduced horizontal mixing length had the most significant impacts on the intensification rate of Patricia after it reached an intensity of category 3, contributing 25.8% and 28.9% to the intensification rate and 11.7% and 14.1% to the lifetime maximum intensity, respectively. The contribution by spray-mediated heat flux increased significantly with wind speed, contributing up to 20.1% to the intensification rate and 20% to the surface energy flux under the eyewall at the wind speed of 90 m s⁻¹. An alternative surface drag coefficient scheme and a constant surface roughness for moisture and heat were also tested and discussed via sensitivity experiments. The study provides insights into the physical processes key to successful simulations and forecasts of extremely strong TCs. 

   more » « less
4. An Energy-Efficient Inference Method in Convolutional Neural Networks Based on Dynamic Adjustment of the Pruning Level

   https://doi.org/10.1145/3460972  

   Maleki, Mohammad-Ali; Nabipour-Meybodi, Alireza; Kamal, Mehdi; Afzali-Kusha, Ali; Pedram, Massoud (August 2021, ACM Transactions on Design Automation of Electronic Systems)

   In this article, we present a low-energy inference method for convolutional neural networks in image classification applications. The lower energy consumption is achieved by using a highly pruned (lower-energy) network if the resulting network can provide a correct output. More specifically, the proposed inference method makes use of two pruned neural networks (NNs), namely mildly and aggressively pruned networks, which are both designed offline. In the system, a third NN makes use of the input data for the online selection of the appropriate pruned network. The third network, for its feature extraction, employs the same convolutional layers as those of the aggressively pruned NN, thereby reducing the overhead of the online management. There is some accuracy loss induced by the proposed method where, for a given level of accuracy, the energy gain of the proposed method is considerably larger than the case of employing any one pruning level. The proposed method is independent of both the pruning method and the network architecture. The efficacy of the proposed inference method is assessed on Eyeriss hardware accelerator platform for some of the state-of-the-art NN architectures. Our studies show that this method may provide, on average, 70% energy reduction compared to the original NN at the cost of about 3% accuracy loss on the CIFAR-10 dataset. 

   more » « less
5. Explainable Offline‐Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave‐QBO Testbed in the Small‐Data Regime

   https://doi.org/10.1029/2023GL106324  

   Pahlavan, Hamid A; Hassanzadeh, Pedram; Alexander, M Joan (January 2024, Geophysical Research Letters)

   Abstract There are different strategies for training neural networks (NNs) as subgrid‐scale parameterizations. Here, we use a 1D model of the quasi‐biennial oscillation (QBO) and gravity wave (GW) parameterizations as testbeds. A 12‐layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in abig‐dataregime (100‐year), produces realistic QBOs once coupled to the 1D model. In contrast, offline training of this NN in asmall‐dataregime (18‐month) yields unrealistic QBOs. However, online re‐training of just two layers of this NN using ensemble Kalman inversion and only time‐averaged QBO statistics leads to parameterizations that yield realistic QBOs. Fourier analysis of these three NNs' kernels suggests why/how re‐training works and reveals that these NNs primarily learn low‐pass, high‐pass, and a combination of band‐pass filters, potentially related to the local and non‐local dynamics in GW propagation and dissipation. These findings/strategies generally apply to data‐driven parameterizations of other climate processes. 

   more » « less