Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scalable performance”

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.

At least 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Mapping Rare Earths and Toxics in E-Waste via Hyperspectral Imaging and Machine Learning

Electronic waste (e-waste) presents a mounting challenge to environmental sustainability due to its complex composition, which includes high-value rare earth elements, hazardous organic compounds, and non-recyclable plastics. Accurate and scalable material classification is essential for enabling efficient resource recovery and safe recycling practices. This study introduces a confidence-aware classification pipeline that combines mid-infrared hyperspectral imaging (HSI), spectral angle mapping (SAM), and iterative machine learning to perform pixel-level material identification across e-waste devices. A curated spectral library encompassing artificial materials (e.g., plastic iron oxide, galvanized metals), minerals (e.g., allanite, hematite), and organic compounds (e.g., benzanthracene, toluene) was used to generate pseudo-labels, each assigned a confidence score based on SAM-derived spectral similarity. High-confidence samples from seven consumer electronics—digital cameras, keyboards, laptop fans, modems, motherboards, TV remotes, and speakers—were iteratively expanded and classified using models such as Support Vector Machine (SVM), Random Forest, Gradient Boosting Classifier, Partial Least Squares Discriminant Analysis (PLSDA) and Logistic Regression. The best-performing classifiers achieved macro F1 scores approaching 1.0. Results revealed widespread plastic content (dominated by plastic iron oxide), the presence of rare earth-bearing minerals like cerium-containing allanite, and pervasive detection of hazardous organics such as benzanthracene. Principal Component Analysis (PCA) visualizations and confusion matrices confirmed high separability and robust classification performance. This methodology enables precise, non-destructive, and scalable classification of heterogeneous e-waste streams. It supports automated, hazard-aware sorting in recycling workflows, facilitating selective recovery of critical materials and compliance with circular economy goals. The confidence-aware framework provides a foundation for real-time deployment in industrial settings, offering significant implications for smart e-recycling infrastructure and policy-driven material stewardship.

Circular economy↗
DOE OSTI2025

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges, requiring efficient hardware acceleration. Benchmarking the performance of LLMs across diverse hardware platforms is crucial to understanding their scalability and throughput characteristics. We introduce LLM-Inference-Bench, a comprehensive benchmarking suite to evaluate the hardware inference performance of LLMs. We thoroughly analyze diverse hardware platforms, including GPUs from Nvidia and AMD and specialized AI accelerators, Intel Habana and SambaNova. Our evaluation includes several LLM inference frameworks and models from LLaMA, Mistral, and Qwen families with 7B and 70B parameters. Our benchmarking results reveal the strengths and limitations of various models, hardware platforms, and inference frameworks. We provide an interactive dashboard to help identify configurations for optimal performance for a given hardware platform.

Chitty-Venkata, Krishna Teja↗
DOE OSTI2020

Distributed Ledger Technology Preliminary Performance Assessment for Applications in Utilities Operational Technology

This paper provides descriptions of the key components of different distributed ledger technology platforms. Distributed ledger technology (DLT) allows for distribution of databases among different organizations and devices. The platforms use cryptographically linked “blocks” to store and verify transactional information between these organizations. DLT increases data security, data integrity, trust among its participants. Different organizations are looking to deploy this distributed and decentralized approach to avoid the single-point-of-failure vulnerabilities associated with centralized data repositories. In this study we examine twelve different DLT platforms. There is agreement within the community that of all the platforms considered here, Hyperledger and Ethereum are the most mature when it comes to privacy and permissions. These DLT platforms are being used for applications such as transactive energy, health care, and the food and goods supply chain. However, further development is required to realize the full promise of DLT. Our assessment includes a general description of each DLT and its key characteristics. Such characteristics include consensus protocol and cryptography used, public vs. private, and permissioned or permissionless. The selection and implementation of a DLT architecture depends heavily on the use case and performance requirements. During this research we found key parameters to measure performance and existing tools for assessment. Four different parameters were identified 1) consensus, 2) throughput, 3) latency, and 4) scalability. The architectures of Hyperledger Caliper and Blockbench are described as different performance assessment frameworks. From this preliminary study it is evident that there are dissimilarities on the performance assessments methods developers and users are characterizing DLT architectures. The purpose of this paper is to identify key parameters to test performance, tools that are being used and provide information on results from previous studies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Performance and Accuracy Implications of Parallel Split Physics-Dynamics Coupling in the Energy Exascale Earth System Atmosphere Model

Simultaneous calculation of atmospheric processes is faster than calculating processes one at a time. This type of parallelism is beneficial or perhaps even necessary to provide good performance on modern supercomputers, which achieve faster performance through increased processor count rather than improved clock speed. The scalability of the Energy Exascale Earth System Model (E3SM) Atmosphere Model (EAM) is limited by the fluid dynamics which scales up to the number of mesh cells in the global mesh. In contrast, the suite of physics parameterizations in EAM is scalable up to the total number of physics columns, which is an order of magnitude greater than the number of mesh cells. A proposed solution to unlocking the greater potential performance from the physics suite is to solve the physics and dynamics in parallel. This work represents a first attempt at parallel splitting of the grid-scale fluid dynamics model and the subgrid-scale physics parameterizations in a global atmosphere model. We will demonstrate that switching to parallel physics-dynamics coupling extends the scalability of the EAM to up to 3 times the previous peak scalability limit and is up to 20% faster than the sequentially split coupling at the highest core counts and the same time step. Decadal simulations of both coupling approaches show very little impact to the model climate. This improved performance does not come without drawbacks, however. Parallel splitting requires a shorter time step and other modifications which largely offset performance gains. A mass fixer is required for conservation. Techniques for mitigating these issues are also discussed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Comparative performance and technoeconomic analyses of two microalgae harvesting systems evaluated at a commercially relevant scale

Using a commercially scalable system designed for processing thousands of liters a day, here we evaluated the factors that affected the performance, energy consumption and capital/operating costs of both flocculation-based and filtration-based algal harvesting systems over a 16 month period. Coagulation efficiency was the primary driver of harvest efficiency in the flocculation-based method, while cell lysis was important for the filtration-based method. Culture (algae) age differentially influenced harvest efficiency through changes in cell fragility and stickiness. The average energy consumption of the flocculation-based method was 0.389 kWh/m 3 , while that for the filtration-based method was 4.343 kWh/m 3 . The average harvesting cost of the filtration-based method was 5.35 $\$$/m 3 , while for flocculation-based method it was 4.52 $\$$/m 3 . The concentration factor of filtration-based and flocculation-based method were 770–1086 and 407–448, respectively. For both harvesting methods, labor costs dominated and ranged from 55.84%–67.94% of total cost. Further system automation is a potential method to lower the harvesting cost. The filtration-based harvesting method could produce a better quality of algal biomass with higher concentration factors and less ash content, but needed more energy input, as compared with a flocculation-based method. This study highlights the importance of algal culture status to successful harvesting, and it also provides insight into developing more efficient harvesting technology with lower energy and capital cost.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Performance Evaluation of Python Based Data Analytics Frameworks in Summit: Early Experiences

The explosion in the volumes of data generated from ever-larger simulation campaigns and experiments or observations necessitates competent tools for data wrangling and analysis). While the Oak Ridge Leadership Computing Facility (OLCF) provides a variety of tools to perform data wrangling and data analysis tasks, Python based tools often lack scalability, or the ability to fully exploit the computational capability of OLCF’s Summit supercomputer. NVIDIA RAPIDS and Dask offer a promising solution to accelerate and distribute data analytics workloads from personal computers to heterogeneous supercomputing systems. We discuss early performance evaluation results of RAPIDS and Dask on Summit to understand their capabilities, scalability, and limitations. Our evaluation includes a subset of RAPIDS libraries, i.e., cuDF, cuML, and cuGraph, and Chainer’s CuPy, and their multi-GPU variants when available.We also draw on the observed trends from the performance evaluation results to discuss best practices for maximizing performance.

Hernandez Arreguin, Benjamin↗
DOE OSTI2024

Microstructure Optimization and Novel Processing Development of ODS Steels for Fusion Environments (Final ARPA-E Report)

This project aimed to develop scalable, cost-effective fabrication of high-performance, oxide- dispersion-strengthened (ODS) steel using advanced manufacturing methods (AMMs) for fusion blanket-breeding applications. Gas atomization reaction synthesis (GARS) enables the synthesis of precursor ODS steel powders without prolonged mechanical alloying. This process creates a chromium (Cr)-enriched surface oxide with yttrium/titanium (Y/Ti)-enriched intermetallics in powder interiors. GARS powders were consolidated to >99% of the theoretical density using a first-of-a-kind shear assisted processing and extrusion (ShAPE) and laser-based powder bed fusion (L-PBF) AM processes. These processes led to ODS steels containing a high-density of nano-oxide dispersoids that enhance high-temperature mechanical properties. Such scalable, cost-effective fabrication of ODS steels can enable efficient power conversion cycles (=40%) at operating temperatures beyond 900 K in future fusion power plants.

36 MATERIALS SCIENCE↗
DOE OSTI2025

SAGIPS: a physics-inspired scalable asynchronous generative inverse-problem solver

Abstract Solving large-scale inverse problems using deep-learning algorithms have become an essential part of modern research and industrial applications. The complexity of the underlying inverse problem may require the utilization of high performance computing systems which poses a challenge on the algorithmic design of the inverse problem solver. Most deep learning algorithms require, due to their design, custom parallelization techniques in order to be resource efficient while showing a reasonable convergence. In this paper we introduce a S calable A synchronous G enerative I nverse P roblem S olver (SAGIPS) on high-performance computing systems. We present a workflow that utilizes an asynchronous ring-allreduce algorithm to transfer the gradients of the generator network across multiple GPUs. Experiments with a scientific proxy application demonstrate that SAGIPS shows near linear weak scaling, together with a convergence quality that is comparable to traditional methods. The approach presented here allows leveraging Generative Adverserial Network across multiple GPUs, promising advancements in solving complex inverse problems at scale.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Efficient bidirectional quantum frequency conversion between telecom and visible bands using adaptively phase-matched III-V nanophotonic waveguides

Quantum frequency conversion (QFC) is essential for interfacing quantum systems operating at different wavelengths and for realizing scalable quantum networks. Despite extensive progress, achieving QFC with simultaneous high efficiency, low pump power, minimal noise, broad bandwidth, and pump-wavelength flexibility remains challenging. Here, we demonstrate efficient, low-noise, and bidirectional QFC between the telecom (1550-nm) and visible (780-nm) bands using unpoled indium gallium phosphide (InGaP) χ (2) nanophotonic waveguides, eliminating the need for a long-wavelength pump. Leveraging the large nonlinear susceptibility of InGaP together with adaptive phase-matching control, we obtain 27% (55%) internal efficiency in a 6-mm (2.5-mm)-long waveguide with a low pump power of 20 mW (50 mW) and a noise flux spectral density of 10 −4 counts per second per hertz at signal–pump detuning of 20 nm. These results mark a significant advance in integrated nonlinear photonics for high-performance QFC, facilitating the development of versatile and scalable quantum networks.

Hu, Jierui [Univ. of Illinois at Urbana-Champaign,↗
DOE OSTI2022

Data Storage for HEP Experiments in the Era of High-Performance Computing

As particle physics experiments push their limits on both the energy and the intensity frontiers, the amount and complexity of the produced data are also expected to increase accordingly. With such large data volumes, next-generation efforts like the HL-LHC and DUNE will rely even more on both high-throughput (HTC) and high-performance (HPC) computing clusters. Full utilization of HPC resources requires scalable and efficient data-handling and I/O. For the last few decades, ROOT has been used by most HEP experiments to store data. However, other storage technologies like HDF5 may perform better in HPC environments. Initial explorations with HDF5 have begun using ATLAS, CMS and DUNE data; the DUNE experiment has also adopted HDF5 for its data-acquisition system. This paper presents the future outlook of the HEP computing and the role of HPC, and a summary of ongoing and future works to use HDF5 as a possible data storage technology for the HEP experiments to use in HPC environments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Local time stepping for the shallow water equations in MPAS

In this work we assess the performance of a set of local time-stepping (LTS) schemes for the shallow water equations implemented in the Model for Prediction Across Scales (MPAS). The goal of LTS is to speed up the simulation by allowing different time-steps on different regions of the computational grid. The LTS schemes considered here were originally introduced by Hoang et al. (2019) [26], who laid out the mathematical foundation of the methods. Here, the authors take on the task of presenting a fast, efficient and scalable parallel implementation of these LTS methods on high performance computing machines, with the aim to provide a recipe for other climate modeling groups that may be interested in employing LTS algorithms in their codes. As a matter of fact, even if MPAS is our framework of choice, our approach is general enough and could be of interest to other groups beyond the MPAS community. Due to their nature, LTS methods possess an inherent load imbalance that needs to be carefully addressed in order to obtain efficient scalability. Even more important is the far from trivial task of computing the right-hand side terms only on specific LTS regions during the time-stepping procedure. An inefficient handling of this task causes a drastic decay of the CPU time performance, making the LTS algorithms practically of no use. The emphasis of the present work is therefore on the computational and parallel aspects of the LTS methods, whose proper treatment is crucial to make the methods run faster against existing strategies, such as for instance high-order explicit global time-stepping schemes. This is in fact the ultimate goal of using an LTS procedure and it is the one to which we direct all our optimization efforts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Direction-optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis

Label Propagation is not only a well-known machine learning algorithm for classification but also an effective method for discovering communities and connected components in networks. We propose a new Direction-optimizing Label Propagation Algorithm (DOLPA) framework that enhances the performance of the standard Label Propagation Algorithm (LPA), increases its scalability, and extends its versatility and application scope. As a central feature, the DOLPA framework relies on the use of frontiers and alternates between label push and label pull operations to attain high performance. It is formulated in such a way that the same basic algorithm can be used for finding communities or connected components in graphs by only changing the objective function used. Additionally, DOLPA has parameters for tuning the processing order of vertices in a graph to reduce the number of edges visited and improve the quality of solution obtained. We present the design and implementation of the enhanced algorithm as well as our shared-memory parallelization of it using OpenMP. We also present an extensive experimental evaluation of our implementations using the LFR benchmark and real-world networks drawn from various domains. Compared with an implementation of LPA for community detection available in a widely used network analysis software, we achieve at most five times the F-Score while maintaining similar runtime for graphs with overlapping communities. We also compare DOLPA against an implementation of the Louvain method for community detection using the same LFR-graphs and show that DOLPA achieves about three times the F-Score at just 10% of the runtime. For connected component decomposition, our algorithm achieves orders of magnitude speedups over the basic LP-based algorithm on large-diameter graphs, up to 13.2× speedup over the Shiloach-Vishkin algorithm, and up to 1.6× speedup over Afforest on an Intel Xeon processor using 40 threads.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

High-Performance Nanoparticle-Mediated Surfaces for Bio-medical Applications

CONCLUSIONS Scalability: could reduce produce cost of nanomaterials for widespread application • Nanomaterials can be produced on macro-scale supports, i.e. metal filters, textile, via solution chemistries • Applications: • Antimicrobial and antiviral applications • Capturing contaminants from aqueous environments • Biocompatibility and Toxicity: safety & long-term effects • Airborne Release Fraction and Respirable Fraction must be considered when moieties released in the atmosphere • Evidence for Bioavailability of Au Nanoparticles from Soil and Biodistribution within Earthworms

Murph, Simona E. [Savannah River National Laborato↗
DOE OSTI2024

High-Efficiency and Low-Carbon Energy Storage and Power Generation System for Electric Aviation

This report summarizes the work performed by University of California San Diego (UCSD) – Honeywell Aerospace (Honeywell) team for the U.S. Department of Energy/Advanced Research Projects Agency-Energy (DOE/ARPA-E) under Phase 1 (April 2021 – October 2023) project, Cooperative Agreement DE-AR0001347 entitled “High-Efficiency and Low-Carbon Energy Storage and Power Generation System for Electric Aviation”. The main objective of this project is to develop and demonstrate an energy storage and power generation (ESPG) system operating on bio liquid natural gas (LNG) for electric aviation applications. The ESPG system concept in this project is a fuel cell, battery, and gas turbine hybrid system that incorporates an innovative solid oxide fuel cell (SOFC) technology. This SOFC technology has two main novel elements: (i) a lightweight and compact stack architecture that consists of cells and cell modules in electrical parallel and series connections (the module design) and (ii) exceptionally high performance, direct methane thin-film cells on porous substrate made by sputtering deposition process. This fuel cell has the specific power and volumetric power density suitable for electric aviation applications. Based on the current status of the SOFC technology, the Phase 1 work focused on the following activities: (i) ESPG System Modeling – to design and optimize an aircraft SOFC-based ESPG system concept that met the performance, weight and cost targets; (ii) Cell Material Development and Scaleup – to demonstrate scalability of the sputtering process for manufacture of thin-film SOFC cells of practical sizes, confirm the exceptional performance of sputtered cells, improve cell stability and durability for operation with hydrogen and methane fuel, and develop a suitable electrically conducting porous substrate to replace the current non-conducting ceramic substrate; (iii) Stack Development – to design and manufacture stack components for the stack architecture, evaluate and select a suitable sealant, and build and operate multi-cell stacks to demonstrate stack operation, and (iv) Technology to Market – to develop business models and commercialization plans, conduct various market and technology analysis and estimate SOFC and ESPG system costs.

25 ENERGY STORAGE↗
DOE OSTI2020

Estimating posterior quantity of interest expectations in a multilevel scalable framework

Scalable approaches for uncertainty quantification are necessary for characterizing prediction confidence in large-scale subsurface flow simulations with uncertain permeability. To this end we explore a multilevel Monte Carlo approach for estimating posterior moments of a particular quantity of interest, where we employ an element-agglomerated algebraic multigrid (AMG) technique to generate the hierarchy of coarse spaces with guaranteed approximation properties for both the generation of spatially correlated random fields and the forward simulation of Darcy's law to model subsurface flow. In both these components (sampling and forward solves), we exploit solvers that rely on state-of-the-art scalable AMG. To illustrate the applicability of this approach, numerical tests are performed on two 3D examples-a unit cube and an egg-shaped domain with an irregular boundary-where the scalability of each simulation as well as the scalability of the overall algorithm are demonstrated.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Grid-Connected Modular Soft-Switching Solid State Transformers (M-S4T)

The objective of this project is to develop and verify the concept of a flexible and modular soft-switching solid-state transformer (M-S4T) for direct grid-connected applications. The ability to directly connect power electronics converters to the medium voltage grid (4 kV – 13 kV), and to potentially replace the passive and bulky, but ubiquitous 60 hertz service transformer in the 25 kVA to 100 kVA range, with a more flexible and controllable device, has been regarded as the ‘holy grail’ in grid control. However, this has proven to be extremely difficult. This project has developed the solutions to several key challenges of the direct grid-connected power electronics and realized a 7.2 kV M-S4T prototype. First, a protection method to protect the M-S4T from the high voltages (110 kV for the 13 kV system) that occur on the grid due to transients and lightning strikes have been developed and experimentally verified. Second, the realization and the operation of the M-S4T based on high-voltage SiC devices (>3.3 kV) and a medium-frequency medium-voltage low-leakage transformer in a single-stage solid-state transformer with zero-voltage switching, low dv/dt, and low electromagnetic interference has been successfully demonstrated up to 7.5 kV peak. Third, an oil-cooling system and stable communication and distributed control system for converter module voltage sharing have been developed and experimentally verified. The developed M-S4T has realized a modular universal high-performance power conversion system. This conversion system is scalable to different voltage and power levels and adaptable to four-quadrant bidirectional operation. Moreover, the use of passive cooling techniques meets the equipment life requirements, and the lightning protection scheme fulfills the basic insulation level specifications for direct grid connection. Such power conversion system opens up near-term opportunities, including energy storage, solar PV, or electric vehicle charging with significant cost and footprint savings. In the longer term, the possibility of replacing the utility distribution transformer with an M-S4T will be transformative for future distribution grids with a compact footprint and full controllability to enable high renewable energy and storage penetration. In addition to the main project, this report expands on the Plus-Up projected including as part of the main award. This project developed and demonstrated the technology for autonomous collaborative inverters that can be connected in an ad hoc manner to the grid. The aim of the project was to: (1) evaluate the existing techniques for grid-connected inverters and find their limitations; (2) develop detailed requirements for grid-connected inverters in the modern grid with millions of active nodes; (3) design a unified control strategy that brings more autonomy and intelligence to grid-connected inverters, and addresses parts of the issues with the existing techniques. The proposed technique, called UniCon, enables inverters to 1) connect/disconnect to/from the grid in an ad hoc manner; (2) work based on local sensing. Slow communication could be used for a more optimized behavior; (3) work automatically in both grid-forming/grid-following mode; (4) handle large disturbances, e.g., big load step and fault, in an oscillation-free manner; (5) work collaboratively with other inverters in steady-state and during transients. UniCon can be implemented in the middle-level control; hence it is agnostic to the vendor and to the implementation of the inner voltage/current and protection loops. Furthermore, a new synchronization scheme, based on deep learning, was developed that can extract the grid voltage phase and amplitude in a stable manner. The method is cheap to implement can improve the dynamic performance of the grid-connected inverters during fast transients, e.g., fault. The proposed control scheme was validated by (1) MATLAB/Simulink; (2) hardware-in-the-loop results, and; (3) experimental results using three inverters that form a microgrid in a down-scaled feeder. Lastly, both the M-S4T and UniCon have achieved promising tangible paths to markets. In the case of the M-S4T, the underlying technology — the Soft Switching Solid State Transformer (S4T) developed at the Georgia Tech Center for Distributed Energy (GT-CDE) has been licensed by GridBlock from the Georgia Tech Research Corporation, and GridBlock has been working with manufacturing partner Jabil (one of the largest US-based contract manufacturers) and system integrator Power Secure (largest deployer of microgrids in the US with 4.7 GW under management), to meet the strong initial demand. Similarly, GridBlock has an exclusive license to the UniCon technology, developed under this award by GT-CDE. The UniCon provides an intermediate control layer that enables the implementation of the higher-level ‘transactive’ control commands for the system. The architecture of the system - slow communications with the cloud for system optimization and setpoints, and the use of locally measured quantities for real-time control, provide a very robust and secure way of implementing a real-time must-run grid that is also secure and stable. This is a brand-new functionality that is critical for the future grid and key to GridBlock’s business model.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Toward performance-portable PETSc for GPU-based exascale systems

The Portable Extensible Toolkit for Scientific computation (PETSc) library delivers scalable solvers for nonlinear time-dependent differential and algebraic equations and for numerical optimization. The PETSc design for performance portability addresses fundamental GPU accelerator challenges and stresses flexibility and extensibility by separating the programming model used by the application from that used by the library, and it enables application developers to use their preferred programming model, such as Kokkos, RAJA, SYCL, HIP, CUDA, or OpenCL, on upcoming exascale systems. Furthermore, a blueprint for using GPUs from PETSc-based codes is provided, and case studies emphasize the flexibility and high performance achieved on current GPU-based systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Physics Informed Reinforcement Learning for Power Grid Control using Augmented Random Search

Wide adoption of deep reinforcement learning need to overcome several challenges in energy system domain, including scalability, learning from limited samples, and high-dimensional continuous state and action spaces. In this paper, we integrated physics-based information from the normal generator operation state formula in the reinforcement learning agent's neural network loss function, and applied an augmented random search agent to optimize the generator control under dynamic contingency. Simulation results demonstrated the reliability performance improvements in training speed, reward convergence, sampling efficiency, scalability, and transferability.

physics informed ML, Physics Informed Neural Netwo↗