Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “two-stage training strategy”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

10 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

GW-PINN: A deep learning algorithm for solving groundwater flow equations

Machine learning methods provide new perspective for more convenient and efficient prediction of groundwater flow. In this study, a deep learning method “GW-PINN” without labeled data for solving groundwater flow equations with wells was proposed. GW-PINN takes the physics inform neural network (PINN) as the backbone and uses either the hard or soft constraint in the loss function for training. A locally refined sampling strategy (LRS) is adopted to generate the consistent spatial sampling points for problems with strong hydraulic head change, and then combined with an appropriate temporal sampling scheme to obtain the final spatial-temporal sampling points. A snowball-style two-stage training strategy by dividing the temporal domain into two subdomains is designed to decrease the sampling points. Five cases were designed to test the training performance of GW-PINN under different sampling strategies and two constraints. The predicted results of GW-PINN were compared with MODFLOW and the analytical solution. The results demonstrate that GW-PINN possesses strong ability in capturing the hydraulic head change for both confined and un-confined aquifers. The hard constraint owns more robust learning ability than the soft constraint. The LRS strategy can generate more accurate results with much fewer sampling points than traditional sampling strategies, and the snowball-style two-stage training strategy is significantly efficient for problems with the drastic change of hydraulic head. Additionally, the application of GW-PINN as a surrogate model for parameterized groundwater flow equations is illustrated. This study provides an option tool for efficient groundwater flow simulation, especially for those with local refinements are needed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Reinforcement Learning for Volt- Var Control: A Novel Two-stage Progressive Training Strategy

This paper develops a reinforcement learning (RL) approach to solve a cooperative, multi-agent Volt-Var Control (VVC) problem for high solar penetration distribution systems. The ingenuity of our RL method lies in a novel two-stage progressive training strategy that can effectively improve training speed and convergence of the machine learning algorithm. In Stage 1 (individual training), while holding all the other agents inactive, we separately train each agent to obtain its own optimal VVC actions in the action space: fconsume, generate, do-nothingg. In Stage 2 (cooperative training), all agents are trained again coordinatively to share VVC responsibility. Rewards and costs in our RL scheme include (i) a system-level reward (for taking an action), (ii) an agent-level reward (for doing-nothing), and (iii) an agent-level action cost function. This new framework allows rewards to be dynamically allocated to each agent based on their contribution while accounting for the trade-off between control effectiveness and action cost. The proposed methodology is tested and validated in a modified IEEE 123-bus system using realistic PV and load profiles. Simulation results confirm that the proposed approach is robust and computationally efficient; and it achieves desirable volt-var control performance under a wide range of operation conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network

X-ray fluorescence (XRF) microscopy is a powerful technique for quantifying the distribution of elements in complex materials, which makes it a crucial imaging technique across a wide range of disciplines in physical and biological sciences, including chemistry, materials science, microbiology, and geosciences. However, as a scanning microscopy technique, the spatial resolution of XRF imaging is inherently constrained by the x-ray probe profile and scanning step size. Here we propose a dual-branch machine learning (ML) model, which can extract scale-variant features and bypass abundant low-frequency information separately, to enhance the spatial resolution of the XRF images by mitigating the effects of blurring from the probe profile. The model is trained by simulated natural images, and a two-stage training strategy is used to overcome the domain gap between the natural images and experimental data. The tomography reconstruction from enhanced XRF projections shows an improvement in resolution by a scale factor of four and reveals distinct internal features invisible in low-resolution XRF within a battery sample. This study offers a promising approach for obtaining high-resolution XRF imaging from its low-resolution version, paving the way for future investigations in a broader range of disciplines and materials.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Deep Reinforcement Learning From Demonstrations to Assist Service Restoration in Islanded Microgrids

Microgrids can be operated in island mode during utility grid outages to support service restoration and improve system resilience. To schedule and dispatch distributed energy resources (DERs) in an islanded microgrid, conventional model-based methods rely on accurate distribution network models and lack generalization and adaptability. Data-driven methods are promising for DER coordination but face practical challenges such as potential hazards to microgrids during online training and insufficient online training opportunities due to low outage rates. This paper presents a novel two-stage learning framework that builds on the deep deterministic policy gradient from demonstrations to identify an optimal restoration strategy. At the pre-training stage, imitation learning is applied to equip the control agent with expert experiences to guarantee acceptable initial performance. At the online training stage, action clipping, reward shaping, and expert demonstrations are leveraged to ensure safe exploration while accelerating the training process. In conclusion, the proposed method is illustrated using the IEEE 123-node system and compared with a representative model-based method and the standard deep deterministic policy gradient method to prove solution accuracy and demonstrate increased computational efficiency.

Du, Yan↗
DOE OSTI2024

A Generation-Storage Coordination Dispatch Strategy for Power System Based on Causal Reinforcement Learning

In the backdrop of global energy transformation, power systems integrating high proportions of renewable energy sources are facing unprecedented challenges in operational stability and dispatch efficiency. To address these challenges, this study introduces a generation-storage coordination real-time dispatch strategy based on Causal Power System Dynamic Reinforcement Learning (CPSDRL). Diverging from traditional reinforcement learning approaches, CPSDRL innovatively incorporates causal inference within the state prediction model - the crux of model-based reinforcement learning - thereby establishing the Power Causal Dynamic Model (PCDM). Assisted by the prior knowledge of power systems, the model significantly enhances prediction accuracy and reliability through a two-stage training process. Utilizing PCDM, this study further applies a direct policy search algorithm to optimize the real-time dispatch strategy. Experimental results indicate that the proposed method improves the stability of generation-storage coordination real-time dispatch and exhibits competitive advantages in sample efficiency and computational speed, compared to traditional model-based and model-free reinforcement learning algorithms. This method is expected to enhance the practicality and adaptability of causal reinforcement learning techniques in power system scheduling and control.

causal reinforcement learning↗
DOE OSTI2025

Learning nuclear cross sections across the chart of nuclides with graph neural networks

We explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime. Our approach follows a two-stage learning framework. First, we apply representation learning to encode cross section data into a latent space using either variational autoencoders (VAEs) or implicit neural representations (INRs). Then, we train graph neural networks (GNNs) on the resulting embeddings to predict missing values across the nuclear chart by leveraging the topological structure of neighboring isotopes. We demonstrate accurate cross section predictions within a 9 × 9 block of missing nuclei. We also find that the optimal GNN training strategy depends on the type of latent representation used, with VAE embeddings performing best under end-to-end optimization in the original space, while INR embeddings achieve better results when the GNN is trained only in the latent space. Furthermore, using clustering algorithms, we map groups of latent vectors into regions of the nuclear chart and show that VAEs and INRs can discover some of the neutron magic numbers. These findings suggest that deep-learning models based on the representation encoding of cross sections combined with graph neural networks hold significant potential in augmenting nuclear theory models, e.g., by providing reliable estimates of covariances of cross sections, including cross-material covariances.

Machine learning↗
DOE OSTI2026

A two-stage optical fusion framework for wildfire severity mapping across the conterminous United States

Accurate wildfire severity mapping (WSM) is essential for post-fire recovery planning, erosion risk assessment, ecosystem monitoring, and disaster risk reduction. Although Landsat and Sentinel optical imagery have been widely used for burn severity assessment, the added value of fusing multiple optical sensors has not been sufficiently quantified across diverse fire events, particularly since the launch of Landsat-9. This study evaluates whether multisensor optical fusion improves wildfire severity mapping relative to single-sensor baselines using Sentinel-2, Landsat-8, and Landsat-9 imagery across 40 wildfire events in the conterminous United States. We tested a two-stage fusion framework that combines feature-level fusion with pixel-level dimensionality reduction. First, feature-level fused datasets were created through early fusion by combining standardized post-fire bands from each sensor into a single predictor stack. Both raw reflectance bands and pairwise spectral transforms were retained to capture within- and cross-sensor spectral interactions. Second, Linear Discriminant Analysis was applied to both single-sensor and fused datasets to produce comparable low-dimensional feature spaces. Six machine-learning classifiers were then used to benchmark model performance with repeated spatially buffered train–test splits. Results show that Landsat-9 was the strongest single-sensor baseline. Among the fusion strategies, Sentinel-2 + Landsat-9 produced the most consistent improvement and reduced performance variability. Landscape-condition analysis further showed that this fusion was most beneficial in shrubland-dominated and high-terrain fires, where it achieved the highest overall mean accuracy and the fewest failures. In contrast, its benefits were less reliable in evergreen forests, mixed vegetation, and low- to moderate-elevation terrain. In operational settings, the Sentinel-2 + Landsat-9 configuration offers a practical solution for post-fire recovery planning, erosion-risk assessment, watershed management, and ecological monitoring when field observations are available and timely satellite-based information is needed.

Landsat↗
DOE OSTI2023

A Simulation Framework for Analyzing the Impact of Stochastic Occupant Behaviors on Demand Flexibility in Typical Commercial Buildings

As one of the primary users of the electric grid, buildings and building equipment, including heating, ventilation, and air conditioning (HVAC) systems, can be leveraged to provide the flexible demand needed to balance the grid. Typical strategies to achieve demand flexibility are to reduce electricity use during peak or critical periods by shutting down equipment or relaxing system setpoints, which will inevitably impact the occupants’ comfort. When occupants feel uncomfortable, they may take actions to regain their comfort, and some of those actions (such as turning on a personal fan) may have a negative impact on meeting the demand response goal. Therefore, it is important to incorporate occupant behaviors into the assessment ofthe building demand flexibility potential. In this study, a simulation framework that includes simulation of zone thermal loads, an HVAC system, and occupant behaviors, was developed to investigate the impact of occupant behaviors on demand flexibility. A case study was conducted using a small office model from the U.S. Department of Energy (DOE) Commercial Prototype Building Models to simulate the building envelope and zone loads. An agent-based occupant thermal behavior model was adapted to forecast occupants’ thermal comfort and their resulting thermal behaviors. An artificial neural network (ANN) based airflow model trained from a computational fluid dynamics (CFD) model of the zone was adopted to better predict the ambient environment of each occupant. An air-source heat pump simulation model that was calibrated from a real two-stage air-source heat pump system was used as the HVAC system. A typical load shedding event during peak hours was studied. Repeated simulations were conducted to capture the stochastic effects of occupant behaviors. The interplay between the demand flexibility, occupant comfort and behavior were analyzed by evaluating key performance indicators, including the energy use, occupant discomfort duration, and occupant behavior duration during the peak period. The results suggest that this framework can be used to analyze typical commercial buildings and their HVAC systems in terms ofdemand flexibility potential under the impact of occupant behaviors.

Chen, Zhelun↗
DOE OSTI2025

An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture

This work presents a two-stage adaptive framework for progressively developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We impose desirable structures on the DNN by employing manifold regularization, sparsity regularization, and physics-informed terms. We introduce a ε – δ – stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a ε – δ stability-promoting algorithm. Further, we also derive the necessary conditions for the trainability of a newly added layer and investigate the training saturation problem. In the second stage of the algorithm (post-processing), a sequence of shallow networks is employed to extract information from the residual produced in the first stage, thereby improving the prediction accuracy. Numerical investigations on prototype regression and classification problems demonstrate that the proposed approach can outperform fully connected DNNs of the same size. Moreover, by equipping the physics-informed neural network (PINN) with the proposed adaptive architecture strategy to solve partial differential equations, we numerically show that adaptive PINNs not only are superior to standard PINNs but also produce interpretable hidden layers with provable stability. As a result, we also apply our architecture design strategy to solve inverse problems governed by elliptic partial differential equations.

42 ENGINEERING↗
DOE OSTI2023

Learning Provably Stable Local Volt/Var Controllers for Efficient Network Operation

Here this paper develops a data-driven framework to synthesize local Volt/Var control strategies for distributed energy resources (DERs) in power distribution grids (DGs). Aiming to improve DG operational efficiency, as quantified by a generic optimal reactive power flow (ORPF) problem, we propose a two-stage approach. The first stage involves learning the manifold of optimal operating points determined by an ORPF instance. To synthesize local Volt/Var controllers, the learning task is partitioned into learning local surrogates (one per DER) of the optimal manifold with voltage input and reactive power output. Since these surrogates characterize efficient DG operating points, in the second stage, we develop local control schemes that steer the DG to these operating points. We identify the conditions on the surrogates and control parameters to ensure that the locally acting controllers collectively converge, in a global asymptotic sense, to a DG operating point agreeing with the local surrogates. We use neural networks to model the surrogates and enforce the identified conditions in the training phase. AC power flow simulations on the IEEE 37-bus network empirically bolster the theoretical stability guarantees obtained under linearized power flow assumptions. The tests further highlight the optimality improvement compared to prevalent benchmark methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗