Search NASA⌕ Search

SEARCH · Search NASA

Results for “Evolutionary Algorithms”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II

Deep neural network (DNN) potentials are an emerging tool for simulation of dynamical atomistic systems, with the promise of quantum mechanical accuracy at speedups of 10000$\times$. As with other DNN methods, hyperparameters used during training can make a substantial difference in model accuracy, and optimal settings vary with dataset. To enable rapid tuning of hyperparameters for DNN potential training, we developed a scalable multiobjective optimization evolutionary algorithm for supercomputers and tested it on the Summit system at the Oak Ridge Leadership Computing Facility (OLCF). The multiobjective approach is required due to the coupling of two learned values defining the potential: the energy and force. Using a large-scale implementation of the NSGA-II algorithm adapted for training DNN potentials, we discovered several optimal multiobjective combinations, including best choices of activation functions, learning rate scaling scheme, and pairing of the two radial cutoffs used in the three dimensional descriptor function.

Coletti, Mark↗
DOE OSTI2024

Behavior, Energy, Autonomy, Mobility Modeling Framework (BEAM) v1.0

The Behavior, Energy, Autonomy, and Mobility (BEAM) model is an integrated, agent-based travel demand simulation framework. Individual agents express preferences through a utility- maximizing evolutionary algorithm that minimizes each individual’s cost and time spent traveling via diverse modal options, including the competition for scarce supply resources such as parking spaces and charging infrastructure. BEAM simulates the essential elements that compose a dynamic transportation system. From the road network, parking and charging infrastructure, to the transit system and a synthetic population with plans and preferences, the virtual system is an amalgamation of multiple spatially resolved layers that together represent an integrated transportation system. BEAM is an extension to the MATSim (Multi-Agent Transportation Simulation) model, where agents employ reinforcement learning across successive simulated days to maximize their personal utility through plan mutation (exploration) and selecting between previously executed plans (exploitation). The BEAM model shifts some of the behavioral emphasis in MATSim from across-day planning to within- day planning, where agents dynamically respond to the state of the system during the mobility simulation. In BEAM, agents can plan across all major modes of travel including driving, walking, biking, transit, and demand-responsive ride hailing. It is designed to integrate with other open source transportation models, such as ActivitySim.

Lazarus, Jessica↗
DOE OSTI2022

LINAC OPTICS OPTIMIZATION WITH MULTI-OBJECTIVE OPTIMIZATION

The beamline design of recirculating linacs requires special attention to avoid beam instabilities due to RF wakefields. A proposed high-energy, multi-pass energy recovery demonstration at CEBAF uses a low beam current. Stronger focusing at lower energies is necessary to avoid beam breakup(BBU) instabilities, even with this small beam current. The CEBAF linac optics optimization balances over-focusing at higher energies and beta excursions at lower energies. Using proper mathematical expressions, linac optics optimization can be achieved with evolutionary algorithms. Here, we present the optimization process of North Linac optics using multi-objective optimization.

Neththikumara, I.↗
DOE OSTI2021

Technoeconomic Analysis of Novel PV Plant Designs for Extreme Cost Reductions

This project sought to gain a deeper understanding of the cost and performance of future solar photovoltaic (PV) plant components, including bifacial PV modules, tandem PV modules, increased plant voltage architectures, and module-level power electronics, and how they may be integrated into new PV plant designs to significantly reduce the levelized cost of electricity (LCOE) of PV. This was done through extensive modeling of current PV plants and future technologies in three different locations, informed by a comprehensive literature review and informational interviews to develop performance and cost assumptions for these technologies. Sensitivities were conducted to understand tradeoffs between different design options, such as the added energy from increasing row spacing versus additional land costs. An optimization tool was then created utilizing an evolutionary algorithm to determine an optimal PV plant configuration for a given set of technologies that resulted in minimized plant LCOE based upon typical performance and cost inputs.

14 SOLAR ENERGY↗
DOE OSTI2021

Initial use of Nek5000/Cardinal to improve closure models in Pronghorn

Heat transfer coefficient closure models for pebble bed reactors are built using a data-driven approach by leveraging the capabilities of an Evolutionary Algorithm entitled Particle Swarm Optimization (PSO). In the present work, the Computational Fluid Dynamics code nekRS was used in order to collect the high-fidelity flow data for a core with 1,568 pebbles. To characterize the heat transfer, multiple concentric regions were considered to extract the physical quantities of interest, e.g./ the Reynolds number. The PSO algorithm is employed as part of an inverse problem targeting determine what are the coefficients for a Nusselt number correlation to match the collected data. Such correlation should follow any given format that is defined a priori. Finally, two correlations are proposed, one with an implicit dependence on the pebbles’ wall temperatures and another expressed as a fully explicit correlation depending on the flow conditions and the position within the core. Anyway, given the generic nature of the proposed approach, correlations following different formats could be tested. Preliminary results for the high-fidelity simulation of a fast MSR core are presented. The target Reynolds number is currently 20K, with the expectation that this will increase, pending the availability of further computational resources. These simulations will be used to inform lower fidelity models, including a coarse CFD turbulence model in Pronghorn. Additionally, they will serve as a reference for the RANS models in Nek5000/NekRS.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

ARENA: Adversary-Resistant Evolving Neural Architectures

Neural networks are becoming the cornerstone for national security prediction tasks. However, designing them requires significant research and trial/error, as they have many hyperparameters, including their computation graph (“architecture”). Neural architecture search (NAS) employs secondary optimizers to search for architectures maximizing objectives like accuracy. Evolutionary algorithms (EAs) are the most used class of optimizer for NAS. However, existing Python libraries for writing EAs limit the complexity of experiments a user can design. In this project, we built ARENA, a Python framework that encodes complex, hyper-realistic EAs. ARENA collects detailed information as it runs and is flexible enough to encode non-EA search algorithms. We tested ARENA on 4 toy optimization problems by encoding 3 search algorithms for each—random search, an EA, and simulated annealing. We also designed an EA that performs NAS on the MNIST dataset. Our experiments suggest the potential for immediate mission impact through solving lab-wide optimization problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2021

Unsupervised Resource Allocation with Graph Neural Networks

We present an approach for maximizing a global utility function by learning how to allocate resources in an unsupervised way. We expect interactions between allocation targets to be important and therefore propose to learn the reward structure for near-optimal allocation policies with a GNN. By relaxing the resource constraint, we can employ gradient-based optimization in contrast to more standard evolutionary algorithms. Our algorithm is motivated by a problem in modern astronomy, where one needs to select-based on limited initial information-among $10^9$ galaxies those whose detailed measurement will lead to optimal inference of the composition of the universe. Our technique presents a way of flexibly learning an allocation strategy by only requiring forward simulators for the physics of interest and the measurement process. We anticipate that our technique will also find applications in a range of resource allocation problems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Gremlin

Gremlin is an evolutionary algorithm that discovers weaknesses in machine learning models.

Coletti, Mark↗
DOE OSTI2021

A parallel evolutionary multiple-try metropolis Markov chain Monte Carlo algorithm for sampling spatial partitions

We develop an Evolutionary Markov Chain Monte Carlo (EMCMC) algorithm for sampling spatial partitions that lie within a large, complex, and constrained spatial state space. Our algorithm combines the advantages of evolutionary algorithms (EAs) as optimization heuristics for state space traversal and the theoretical convergence properties of Markov Chain Monte Carlo algorithms for sampling from unknown distributions. Local optimality information that is identified via a directed search by our optimization heuristic is used to adaptively update a Markov chain in a promising direction within the framework of a Multiple-Try Metropolis Markov Chain model that incorporates a generalized Metropolis-Hastings ratio. We further expand the reach of our EMCMC algorithm by harnessing the computational power afforded by massively parallel computing architecture through the integration of a parallel EA framework that guides Markov chains running in parallel.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Inference of neutrino flavor evolution through data assimilation and neural differential equations

The evolution of neutrino flavor in dense environments such as core-collapse supernovae and binary compact object mergers constitutes an important and unsolved problem. Its solution has potential implications for the dynamics and heavy-element nucleosynthesis in these environments. In this paper, we build upon recent work to explore inference-based techniques for the estimation of model parameters and neutrino flavor evolution histories. Here, we combine data assimilation, ordinary differential equation solvers, and neural networks to craft an inference approach tailored for nonlinear dynamical systems. Using this architecture, and a simple two-neutrino-beam, two-flavor model, we compare the performances of nine different optimization algorithms and expand upon previous assessments of the efficacy of inference for tackling problems in flavor evolution. We find that employing this new architecture, together with evolutionary optimization algorithms, accurately captures flavor histories in the small-scale model and allows us to quickly explore both model parameters and initial flavor content. In future work we plan to extend these inference techniques to large numbers of neutrinos.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

Here using a model heat engine, we show that neural-network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

AI-assisted optimization of the ECCE tracking system at the Electron Ion Collider

The Electron-Ion Collider (EIC) is a cutting-edge accelerator facility that will study the nature of the “glue” that binds the building blocks of the visible matter in the universe. The proposed experiment will be realized at Brookhaven National Laboratory in approximately 10 years from now, with detector design and R&D currently ongoing. Notably, EIC is one of the first large-scale facilities to leverage Artificial Intelligence (AI) already starting from the design and R&D phases. The EIC Comprehensive Chromodynamics Experiment (ECCE) is a consortium that proposed a detector design based on a 1.5 T solenoid. The EIC detector proposal review concluded that the ECCE design will serve as the reference design for an EIC detector. Herein we describe a comprehensive optimization of the ECCE tracker using AI. The work required a complex parametrization of the simulated detector system. Herein our approach dealt with an optimization problem in a multidimensional design space driven by multiple objectives that encode the detector performance, while satisfying several mechanical constraints. We describe our strategy and show results obtained for the ECCE tracking system. The AI-assisted design is agnostic to the simulation framework and can be extended to other sub-detectors or to a system of sub-detectors to further optimize the performance of the EIC detector.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Bayesian Optimized Deep Ensemble for Uncertainty Quantification of Deep Neural Networks: a System Safety Case Study on Sodium Fast Reactor Thermal Stratification Modeling

Deep neural networks (DNNs) are increasingly important to scientific computing and engineering system simulations. Accurate uncertainty quantification (UQ) for DNNs is critical in safety-sensitive engineering domains. Traditional Deep Ensemble (DE) methods, while easy to implement, frequently suffer from poorly calibrated uncertainty estimates and limited predictive accuracy due to reliance on fixed architectures with varied weight initializations. To address these issues, we introduce a workflow that combines Bayesian Optimization (BO) and DE. The workflow is modular, scalable, and integrates parallel BO initialized with Sobol sequences to individually optimize the hyperparameters of each ensemble member. This method enhances ensemble diversity, improves predictive accuracy, and provides reliable uncertainty estimates. We evaluate the proposed BODE approach in a sodium fast reactor thermal stratification modeling case study, where we used a densely connected convolutional neural network to predict turbulent viscosity during the reactor transient with consideration of data noise. We benchmark its performance against several optimization approaches, including baseline deep ensemble, evolutionary algorithm-optimized ensemble, ensemble formed via random search combined with greedy selection, and a BO ensemble using random initialization. Here, our results demonstrate superior performance of the developed BODE approach. In noise-free scenarios, BODE notably reduces incorrect aleatoric uncertainty and significantly enhances predictive accuracy. Under conditions of 5% and 10% Gaussian noise, BODE adaptively quantifies uncertainty proportional to data noise, achieving up to an 80% reduction in root mean square error compared to baseline methods and producing well-calibrated prediction intervals.

Bayesian optimization↗
DOE OSTI2020

Fourier Analysis-Based Evolutionary Multi-Objective Multiphysics Optimization of Liquid-Cooled Heat Sinks

Optimal heat dissipation in power modules can significantly increase their power density. Removing the generated heat is critical for capturing the benefits of advanced semiconductor materials and improving the reliability of the device operation. This article proposes a design optimization method for liquid-cooled heat sinks that use a Fourier analysis-based tool and an evolutionary optimization algorithm to optimize the heat sink geometry for specified objectives. The optimized heat sink geometry is then compared with state-of-the-art solutions in literature based on finite element analysis of different designs. The proposed methodology can develop complex geometries that outperform the conventional heat sink geometries.

Sahu, Raj↗
DOE OSTI2025

Plant Reload Optimization (prlo)

The PRLO framework is built on a modular and extensible architecture that tightly couples advanced evolutionary optimization algorithms with nuclear fuel depletion solvers (i.e., nuclear physics neutronics code). It supports exploring complex, high-dimensional design spaces constrained by user-specified operational, safety, and economic constraints. Objectives such as minimizing fresh fuel enrichment, flattening radial and axial power distributions, and maximizing discharge burnup are evaluated. PRLO’s equilibrium cycle optimization capability enables the identification of core configurations that maintain fuel cycle sustainability over extended planning horizons. Its integration with the RAVEN platform facilitates optimization of loading patterns or fuel shuffling schemes across multiple cycles. The interface with SIMULATE, a licensed industry-standard nodal code developed by Studsvik, ensures accurate neutronic and thermal-hydraulic feedback for reactor core design. PRLO’s automated workflow engine supports iterative design refinement, enabling utilities to streamline core design processes and meet evolving performance and regulatory targets.

Kim, Junyung [Idaho National Laboratory] (00090005↗