Search NASA⌕ Search

SEARCH · Search NASA

Results for “evolutionary optimization”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Variational quantum reinforcement learning via evolutionary optimization

Abstract Recent advances in classical reinforcement learning (RL) and quantum computation point to a promising direction for performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here, we present two frameworks for deep quantum RL tasks using gradient-free evolutionary optimization. First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using amplitude encoding. Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL in the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Eco-evolutionary optimality as a means to improve vegetation and land-surface models

Global vegetation and land-surface models embody interdisciplinary scientific understanding of the behaviour of plants and ecosystems, and are indispensable to project the impacts of environmental change on vegetation and the interactions between vegetation and climate. Furthermore, systematic errors and persistently large differences among carbon and water cycle projections by different models highlight the limitations of current process formulations. In this review, focusing on core plant functions in the terrestrial carbon and water cycles, we show how unifying hypotheses derived from eco-evolutionary optimality (EEO) principles can provide novel, parameter-sparse representations of plant and vegetation processes. We present case studies that demonstrate how EEO generates parsimonious representations of core, leaf-level processes that are individually testable and supported by evidence. EEO approaches to photosynthesis and primary production, dark respiration and stomatal behaviour are ripe for implementation in global models. EEO approaches to other important traits, including the leaf economics spectrum and applications of EEO at the community level are active research areas. Independently tested modules emerging from EEO studies could profitably be integrated into modelling frameworks that account for the multiple time scales on which plants and plant communities adjust to environmental change.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks

While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization techniques is difficult. Even though evolutionary algorithms (EAs) have been shown to promise to optimize SNNs, understanding the relationship between evolving the characteristics of SNNs and their performance to improve the optimization algorithm is challenging because of the complex characteristics and huge population size. We propose visual analytics with novel graph embedding for evolutionary SNNs to address the challenges. While existing graph embedding techniques have limitations in preserving the specific features of the nodes and edges, our approach maintains them. Also, we develop visual analytics for understanding the relationship between the network performance and the features of nodes and edges and exploring and analyzing the evolving SNNs to build insights into improving the EA.

Chae, Junghoon [ORNL] (ORCID:0000000206016746)↗
DOE OSTI2025

MOOSE ProbML: Parallelized probabilistic machine learning and uncertainty quantification for computational energy applications

Here, this paper presents the development and demonstration of massively parallel probabilistic machine learning (ML) and uncertainty quantification (UQ) capabilities within the Multiphysics Object-Oriented Simulation Environment (MOOSE), an open-source computational platform for parallel finite element and finite volume analyses. In addressing the computational expense and uncertainties inherent in complex multiphysics simulations, this paper integrates Gaussian process (GP) variants, active learning, Bayesian inverse UQ, adaptive forward UQ, Bayesian optimization, evolutionary optimization, and Markov chain Monte Carlo (MCMC) within MOOSE. It also elaborates on the interaction among key MOOSE systems — Sampler, MultiApp, Reporter, and Surrogate — in enabling these capabilities. The modularity offered by these systems enables development of a multitude of probabilistic ML and UQ algorithms in MOOSE. Example code demonstrations include parallel active learning and parallel Bayesian inference via active learning. The impact of these developments is illustrated through five applications relevant to computational energy applications: UQ of nuclear fuel fission product release, using parallel active learning Bayesian inference; very rare events analysis in nuclear microreactors using active learning; advanced manufacturing process modeling using multi-output GPs (MOGPs) and dimensionality reduction; fluid flow using deep GPs (DGPs); and tritium transport model parameter optimization for fusion energy, using batch Bayesian optimization. These capabilities are part of the MOOSE framework.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Evolving Ensembles of Spiking Neural Networks for Neuromorphic Systems

Evolutionary algorithms have been proposed as a solution to overcome many of the challenges associated with training spiking neural networks. While evolutionary optimization for spiking neural networks is very flexible, its performance has difficulty scaling to complex tasks and correspondingly complex network structures. Here we propose a method for evolving ensembles of spiking neural networks. By using ensemble learning, the flexibility of evolutionary optimization is fully preserved while scaling to more challenging tasks. We test the performance of the proposed method using handwritten digit classification. We investigate multiple strategies for constructing ensembles of spiking neural networks, and demonstrate that evolving ensembles of SNNs offers significant performance advantages over evolutionary optimization.

Elbrecht, Daniel↗
DOE OSTI2022

Multi-objective optimization of root phenotypes for nutrient capture using evolutionary algorithms

Root phenotypes are avenues to the development of crop cultivars with improved nutrient capture, which is an important goal for global agriculture. The fitness landscape of root phenotypes is highly complex and multidimensional. It is difficult to predict which combinations of traits (phene states) will create the best performing integrated phenotypes in various environments. Brute force methods to map the fitness landscape by simulating millions of phenotypes in multiple environments are computationally challenging. Evolutionary optimization algorithms may provide more efficient avenues to explore high dimensional domains such as the root phenotypic space. We coupled the three-dimensional functional–structural plant model, SimRoot, to the Borg Multi-Objective Evolutionary Algorithm (MOEA) and the evolutionary search over several generations facilitated the identification of optimal root phenotypes balancing trade-offs across nutrient uptake, biomass accumulation, and root carbon costs in environments varying in nutrient availability. Our results show that several combinations of root phenes generate optimal integrated phenotypes where performance in one objective comes at the cost of reduced performance in one or more of the remaining objectives, and such combinations differed for mobile and non-mobile nutrients and for maize (a monocot) and bean (a dicot). Functional–structural plant models can be used with multi-objective optimization to identify optimal root phenotypes under various environments, including future climate scenarios, which will be useful in developing the more resilient, efficient crops urgently needed in global agriculture.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Is the exquisite specificity of lymphocytes generated by thymic selection or due to evolution?

We have previously argued that the antigen receptors of T and B lymphocytes evolved to be sufficiently specific to avoid massive deletion of clonotypes by negative selection. Their optimal ‘specificity’ level, i.e., probability of binding any particular epitope, was shown to be inversely related to the number of self-antigens that the cells have to be tolerant to. Experiments have demonstrated that T lymphocytes also become more specific during negative selection in the thymus, because cells expressing the most crossreactive receptors have the highest likelihood of binding a self-antigen, and hence to be tolerized (i.e., deleted, anergized, or diverted into a regulatory T cell phenotype). Thus, there are two —not mutually exclusive— explanations for the exquisite specificity of T cells, one involving evolution and the other thymic selection. To better understand the impact of both, we extend a previously developed mathematical model by allowing for T cells with very different binding probabilities in the pre-selection repertoire. We confirm that negative selection tends to tolerize the most crossreactive clonotypes. As a result, the average level of specificity in the functional post-selection repertoire depends on the number of self-antigens, even if there is no evolutionary optimization of binding probabilities. However, the evolutionary optimal range of binding probabilities in the pre-selection repertoire also depends on the number of self-antigens. Species with more self antigens need more specific pre-selection repertoires to avoid excessive loss of T cells during thymic selection, and hence mount protective immune responses. We conclude that both evolution and negative selection are responsible for the high level of specificity of lymphocytes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Training Spiking Neural Networks Using Combined Learning Approaches

Spiking neural networks (SNNs), the class of neural networks used in neuromorphic computing, are difficult to train using traditional back-propagation techniques. Spike timingdependent plasticity (STDP) is a biologically inspired learning mechanism that can be used to train SNNs. Evolutionary algorithms have also been demonstrated as a method for training SNNs. In this work, we explore the relationship between these two training methodologies. We evaluate STDP and evolutionary optimization as standalone methods for training networks, and also evaluate a combined approach where STDP weight updates are applied within an evolutionary algorithm. We also apply Bayesian hyperparameter optimization as a meta learner for each of the algorithms. We find that STDP by itself is not an ideal learning rule for randomly connected networks, while the inclusion of STDP within an evolutionary algorithm leads to similar performance, with a few interesting differences. This study suggests future work in understanding the relationship between network topology and learning rules.

Elbrecht, Daniel↗
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↗
DOE OSTI2021

Reinforcement learning in discrete action space applied to inverse defect design

Abstract Reinforcement learning (RL) algorithms that include Monte Carlo Tree Search (MCTS) have found tremendous success in computer games such as Go, Shiga and Chess. Such learning algorithms have demonstrated super-human capabilities in navigating through an exhaustive discrete action search space. Motivated by their success in computer games, we demonstrate that RL can be applied to inverse materials design problems. We deploy RL for a representative case of the optimal atomic scale inverse design of extended defects via rearrangement of chalcogen (e.g. S) vacancies in 2D transition metal dichalcogenides (e.g. MoS 2 ). These defect rearrangements and their dynamics are important from the perspective of tunable phase transition in 2D materials i.e. 2H (semi-conducting) to 1T (metallic) in MoS 2 . We demonstrate the ability of MCTS interfaced with a reactive molecular dynamics simulator to efficiently sample the defect phase space and perform inverse design—starting from randomly distributed S vacancies, the optimal defect rearrangement of defects corresponds a line defect of S vacancies. We compare MCTS performance with evolutionary optimization i.e. genetic algorithms and show that MCTS converges to a better optimal solution (lower objective) and in fewer evaluations compared to GA. We also comprehensively evaluate and discuss the effect of MCTS hyperparameters on the convergence to solution. Overall, our study demonstrates the effectives of using RL approaches that operate in discrete action space for inverse defect design problems.

42 ENGINEERING↗
DOE OSTI2022

Evolutionary vs imitation learning for neuromorphic control at the edge*

Abstract Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.

Schuman, Catherine↗
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 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 OSTI2021

Liquid-Cooled Heat Sink Optimization for Thermal Imbalance Mitigation in Wide-Bandgap Power Modules

Power semiconductor die placement on substrates used in high-power modules is generally optimized to minimize electrical parasitic (e.g., stray inductance, common-mode capacitance), taking into account the minimum spacing between semiconductor dies for thermal decoupling. The layout assumes sufficient heat spreading and transfer from dies to the cooling structure. Insulated metal substrate-based power module designs may lead to asymmetrical thermal resistance across the dies, which may cause significant temperature differences among the devices. Such unintentional thermal asymmetries can lead to oversizing the cooling system design or underusing the semiconductor power processing capability. This article proposes a thermal imbalance mitigation method that uses evolutionary optimized liquid-cooled heat sinks to improve the thermal loading among devices.

42 ENGINEERING↗
DOE OSTI2020

Liquid-Cooled Heat Sink Optimization for Thermal Imbalance Mitigation in Wide-Bandgap Power Modules

Power semiconductor die layout in substrates used in power modules is generally optimized for minimum electrical parasitics (e.g., stray inductance) by considering the minimum spacing between dies for thermal decoupling. The layout assumes sufficient heat spreading and transfer from dies to the cooling structure. For module designs using a direct substrate cooling method, the base plate is removed, leading to a steady-state thermal asymmetry in the power module due to insufficient heat spreading/transfer. This causes significant temperature differences among the devices. Such unintentional thermal asymmetries can lead to undesirable asymmetries in power conversion among semiconductor devices, which impact reliability. This article proposes a thermal imbalance mitigation method that uses evolutionary optimized liquid-cooled heat sinks to improve the thermal loading among devices.

Sahu, Raj↗