Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning 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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Reliable and Efficient Machine Learning (Final Technical Report)

Modern scientific experiments generate massive amounts of data at a pace much faster than humans can manually analyze. While machine learning has revolutionized commercial data analysis (such as recommending movies or recognizing faces), applying these tools to complex scientific discovery is challenging because scientific answers must be precise, interpretable, and adhere to physical laws. The research under this project aims to develop new mathematical tools and computer algorithms specifically designed for scientific applications. Major progress has been made in automatically cleaning and deconstructing messy experimental data, analyzing the visual information of physical phenomena, determining the underlying physical variables, and providing rig orous mathematical analysis of interesting algorithms and concepts widely used in machine learning. This project addressed the critical gap between our ability to generate massive scientific data and our ability to extract interpretable information from it. We established mathematical foundations for Scientific Machine Learning (SciML) aimed at effective data analytics and automated discovery. Our work focused on three core objectives: (1) developing reliable feature extraction methods for dynamic high-dimensional data, (2) establishing mathematical foundations for discovering dynamics via neural networks, and (3) creating rigorous optimization techniques for these models. Key outcomes come from two fronts. On the practical side, they include the development of algorithms that significantly enhance the extraction of signals from field data, as well as the capability to handle situations that exhibit smooth variations or physical stretching due to temperature changes. They also include the creation of an automated framework for discovering fundamental state variables from raw experimental data, demonstrating the ability to identify intrinsic physical dimensions without prior knowledge of the governing laws. On the theoretical front, the research results in theoretical advances in Optimal Transport, a widely used notion in SciML, specifically regarding functions with fixed-size nodal sets, provide sharp bounds relevant to uncertainty quantification. Meanwhile, the outcomes also include the establishment of convergence theories for nonlocal gradient descent methods, enabling robust optimization with noisy data in high-dimensional settings commonly encountered in scientific modeling. The project also helps creating opportunities to train the next generation of researchers, equipping them with the necessary technical skills for today’s workplace and preparing them for future advances.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Accelerated version of NUBEAM capabilities in DIII-D using neural networks

A neural network model of the effects of neutral beam injection on DIII-D has been developed. The training and testing data used by the model have been generated by the NUBEAM module of TRANSP for experimental discharges from the 2018 DIII-D campaign. Using a principle component analysis to reduce the dimensionality of profile data, the model has been shown to reproduce the results of the Monte Carlo code NUBEAM with a high level of accuracy and an execution time orders of magnitude faster than the execution time of NUBEAM. Furthermore, this makes the neural network model uniquely suited to applications in model-based scenario planning (off-line) and active control (on-line), where a large number of simulation runs are required by the associated optimization tasks that need to be performed before and during the discharge.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Prediction of Distributed River Sediment Respiration Rates Using Community-Generated Data and Machine Learning

River sediment microbial respiration is a key indicator of ecosystem functioning and the biogeochemical fluxes across this critical zone link surface and subsurface waters. As such, there is tremendous interest in measuring and mapping these respiration rates. Respiration observations are expensive and labor intensive; there is limited data available to the community. An open science, collaborative initiative is collecting samples for respiration rate analysis and multi-scale metadata; this evolving data set is being used for making machine learning (ML) predictions at unsampled sites to help inform continued community engagement. However, it is a challenge to find an optimum configuration for ML models to work with this feature-rich (i.e., 100+ possible input variables) data set. Here, we present results from a two-tiered approach to managing the analysis of this complex data set: (a) a stacked ensemble of models that automatically optimizes hyperparameters and manages the training of many models and (b) feature permutation importance to detect the most important features in the models. The major elements of this workflow are modular, portable, open, and cloud-based thus making this implementation a potential template for other applications. The models developed here predict that sediment organic matter chemistry is one of the most important features for predicting sediment respiration rate. Other larger-scale, important features fall into the categories of climatic, ecological, geological, and fluvial settings. Leveraging these larger-scale features to generate data-driven estimates of river sediment respiration rates reveals spatially consistent but heterogeneous patterns across the river network of the Columbia River Basin.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

EFIT-Prime: Probabilistic and physics-constrained reduced-order neural network model for equilibrium reconstruction in DIII-D

We introduce EFIT-Prime, a novel machine learning surrogate model for EFIT (Equilibrium FIT) that integrates probabilistic and physics-informed methodologies to overcome typical limitations associated with deterministic and ad hoc neural network architectures. EFIT-Prime utilizes a neural architecture search-based deep ensemble for robust uncertainty quantification, providing scalable and efficient neural architectures that comprehensively quantify both data and model uncertainties. Physically informed by the Grad–Shafranov equation, EFIT-Prime applies a constraint on the current density J tor and a smoothness constraint on the first derivative of the poloidal flux, ensuring physically plausible solutions. Furthermore, the spatial location of the diagnostics is explicitly incorporated in the inputs to account for their spatial correlation. Extensive evaluations demonstrate EFIT-Prime's accuracy and robustness across diverse scenarios, most notably showing good generalization on negative-triangularity discharges that were excluded from training. Timing studies indicate an ensemble inference time of 15 ms for predicting a new equilibrium, offering the possibility of plasma control in real-time, if the model is optimized for speed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Understanding Adsorption and Reactions at Aqueous Oxide Interfaces with Neural Network Potential Molecular Dynamics

Chemical processes at metal oxide−water interfaces are of central importance in geochemistry, biology, and energy technologies. A better understanding of these processes would allow us to make a significant step toward optimizing and controlling them, which could in turn lead to broader impacts. Computational modeling is indispensable to accomplishing this task because complexity and disorder often make it difficult to extract atomistic information from experiments. Balancing computational cost and accuracy, simulation schemes based on efficient machine learning representations of the potential energy surface (PES) predicted by ab initio calculations have become increasingly popular over the past decade. In particular, several studies have demonstrated the ability of machine learning models to accurately reproduce the complex ab initio PESs of aqueous oxide interfaces, allowing simulations of systems and processes that are not accessible with ab initio methods. In this Account, we review our recent efforts to understand adsorption processes and reactions at aqueous oxide interfaces using deep potential molecular dynamics (DPMD), a simulation scheme employing deep neural networks (DNNs), which has proven to be quite successful in accurately describing many different systems in the condensed phase. After summarizing the DPMD methodology, we first review our work on the acid−base chemistry of oxide surfaces in contact with water, a fundamental characteristic that controls proton transfer and surface charge at the interface. We focus on the aqueous interface of rutile IrO 2 , an oxide material thus far considered the best catalyst for the oxygen evolution reaction (OER). We show that this interface is characterized by a large fraction of dissociated water and a strong Brønsted acidity of the surface sites, in good agreement with the experimentally measured value of the point of zero proton charge. In our second example, we investigate how the adsorption of organic species from ambient air or water affects the structure and wettability of the aqueous interfaces of TiO 2 , a prototypical photocatalytic material. This is a question that is relevant to understanding the UV-induced hydrophilicity of TiO 2 surfaces, a property at the basis of self-cleaning windows and related applications. Specifically focusing on formic and acetic acids, the two most common atmospheric organic acids, our simulations reveal that these acids control the wettability of TiO 2 largely through acid−base chemistry at the interface rather than chemisorption on the oxide surface, a finding that could help improve the design of self-cleaning surfaces and photocatalytic devices. Finally, we review our recent study of methanol at TiO 2 −water interfaces, a system whose interest is largely motivated by the role of methanol in enhancing photocatalytic hydrogen evolution on TiO 2 . Our simulations provide mechanistic insights into the coupled roles of the organic adsorbate and water at the TiO 2 interface, with implications for how methanol enhances the activity of H 2 evolution.

adsorption↗
DOE OSTI2023

Probing Accuracy-Speedup Tradeoff in Machine Learning Surrogates for Molecular Dynamics Simulations

The performance promise of machine learning surrogates of molecular dynamics simulations of soft materials is significant but generally comes at the cost of acquiring large training datasets to learn the complex relationships between input soft material attributes and output properties. Under the constraint of limited high-performance computing resources, optimizing the size of the training datasets becomes paramount. Using an artificial neural network based surrogate for molecular dynamics simulations of confined electrolytes, we explore the tradeoff between surrogate accuracy and computational gains. Accuracy is assessed by computing the root-mean-square errors between the surrogate predictions and the ground truth results obtained via molecular dynamics simulations. The computational performance is judged by evaluating the speedup which incorporates the training dataset creation time. Improvement in accuracy occurs with a loss of speedup, which scales as the inverse of the training dataset size. Furthermore, the link between surrogate generalizability and the accuracy-speedup tradeoff is assessed by examining the errors incurred in surrogate predictions on unseen, interpolated input variables and developing a net speedup metric to capture the associated gains.

Anions↗
DOE OSTI2024

Efficient learning of accurate surrogates for simulations of complex systems

Machine learning methods are increasingly deployed to construct surrogate models for complex physical systems at a reduced computational cost. However, the predictive capability of these surrogates degrades in the presence of noisy, sparse or dynamic data. Here, we introduce an online learning method empowered by optimizer-driven sampling that has two advantages over current approaches: it ensures that all local extrema (including endpoints) of the model response surface are included in the training data, and it employs a continuous validation and update process in which surrogates undergo retraining when their performance falls below a validity threshold. We find, using benchmark functions, that optimizer-directed sampling generally outperforms traditional sampling methods in terms of accuracy around local extrema even when the scoring metric is biased towards assessing overall accuracy. Finally, the application to dense nuclear matter demonstrates that highly accurate surrogates for a nuclear equation-of-state model can be reliably autogenerated from expensive calculations using few model evaluations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Parametric and Sensitivity Analysis of a Steam Generator Model Using Python and Machine-Learning Tools

For this study, we used Python and machine-learning tools to perform a comprehensive parametric and sensitivity analysis on a steam generator (SG) model. (The Python model was based on a previously completed MATLAB framework for the Holtec SMR-160 SG.) We investigated the influence of various input parameters (e.g., heat transfer coefficient [HTC], Nusselt number, and heat exchanger effectiveness) on the system’s output. With machine-learning tools such as the Risk Analysis Virtual Environment (RAVEN), which was developed at Idaho National Laboratory, we were then able to perform an automated analysis of the SG inputs’ effect on the HTC. The analysis results give valuable insights into the performance and optimization of SG systems. We found the inlet mass flow rate (MFR) to have the greatest impact on the HTC, followed closely by the inlet temperature, and then pressure. Shifting of the input parameters causes the location of the maximum HTC along the SG length to change incrementally. The cold leg (CL) MFR was also found to impact the HTC magnitude as well as the location of the maximum HTC. At between 0.4–0.9 of the total SG length, the input parameters experience maximum impact on the HTC, leading us to suggest that sensors be efficiently placed on the SG so as to closely and effectively monitor thermal-hydraulic properties during reactor operation. We also found that the sensitivity data calculated manually agrees with the RAVEN – based data, confirming the same range of maximum sensitivity. However, the RAVEN-based analysis showed that cold leg pressure and hot leg temperature have a greater impact on the heat transfer coefficient than the mass flow rate, implying that a manual sensitivity study taking only two samples is not accurate.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2025

Addressing the Split Incentive Challenge for Enhanced Solar Adoption in Multifamily Rental Properties [Abstract]

The split incentive problem is particularly pronounced in rental markets, where landlords prioritize investments that directly increase property value or rental income. Since energy savings from solar photovoltaic (PV) systems primarily benefit tenants, landlords may perceive little return on investment unless mechanisms exist to recapture some of the financial gains. The primary objective of this project is to develop a publicly available, web-based tool to analyze the U.S. Department of Energy’s ResStock database, which models the U.S. residential building stock. The tool allows users to filter buildings by location, type, HVAC system, square footage, and other characteristics, and outputs typical electric load profiles. By leveraging location-specific electric load data, Fram Energy aims to advance business strategies that address the split incentive barrier and promote the adoption of solar PV installations in rental properties. In addition, a machine learning model will be developed to weigh the marginal contribution of building features across the dataset in predicting electricity demand, supporting guided decision making in forecasting electric load profiles. Lastly, based on each building’s location, load profile, and utility’s electricity rate, an optimized solar photovoltaic array and battery energy storage system will be sized to provide energy arbitrage opportunities.

14 SOLAR ENERGY↗
DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

LENS: Learning Enabled Network Synthesis

RTRC and UMD have developed novel machine learning based methods under the ARPA-E DIFFERENTIATE program for rapid acceleration of hypothesis generation in complex architecture design spaces involving both discrete choices of component inclusion and interconnection and continuous parametric decisions. The project named Learning Enabled Network Synthesis (LENS) further demonstrated the developed methods on challenging electrical power converter design problems by identifying the most suitable circuit topologies and simultaneously selecting the most appropriate components to achieve optimized design of power converter with improved performances. We demonstrated that LENS could enable exploration of very large design space of circuit topologies and components by addressing the limitations of conventional design process in non-linear, high switching speed, multi-dimensional power converter design and optimization. The key innovation developed in LENS is the seamless integration of statistical learning and logical reasoning techniques and building on the individual strengths of these techniques for rapid hypothesis discovery. The main component of LENS comprises of: 1) Graph Reasoning Engine (GRE) to enforce composition rules that rapidly reject all discrete architectures that are composed incorrectly and generates an adaptive database of feasible designs which can be used by ML modules, 2) Graph Generative Learning module which is a deep neural network based generative model for graph architectures which can enable design space exploration beyond the dataset generated by the GRE, 3) Graph Reduced Order Model (ROM) for graph domains for accelerating computation of output metrics, and 4) Active learning and Rule Discovery module for sample efficient learning and extracting logical rules from the learned ML models which will be integrated in the GRE to enhance the filtering effectiveness. LENS approach can be applied to any design domains where designs can be represented as multi-attribute graphs. The LENS team integrated the various technical innovations listed above into an optimization pipeline and exercised the optimization pipeline on the converter design problem. The LENS project demonstrated that the developed AI/ML technologies can be used to generate novel converter circuits >45x faster than experts on chosen use-cases. This can enable faster design space exploration and identification of new designs which are not considered by experts due to the increasing design space complexity. This has significant potential impact on the public and energy needs of the country. It is currently estimated that 30% of all electrical powers generated passes through power converters. The future estimate is that 80% of all power generated would be passing through converters. LENS fills a critical gap in this space since by accelerating the design process the designers would be able to generate more efficient converters which can lead to significant energy savings for the country.

42 ENGINEERING↗
DOE OSTI2024

Modeling injection-induced fault slip using long short-term memory networks

Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault. This can be due to subsurface (geo)engineering activities such as fluid injections and geologic disposal of nuclear waste. Such activities are expected to rise in the future making it necessary to assess their short- and long-term safety. Here, a new machine learning (ML) approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed. The focus is on fault behavior near the injection borehole. To capture the temporal dependencies in the data, long short-term memory (LSTM) networks are utilized. To prevent error accumulation within the forecast window, four critical measures to train a robust LSTM model for predicting fault response are highlighted: (i) setting an appropriate value of LSTM lag, (ii) calibrating the LSTM cell dimension, (iii) learning rate reduction during weight optimization, and (iv) not adopting an independent injection cycle as a validation set. Several numerical experiments were conducted, which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection. The model also captured the decay in pressure and displacement during the injection shut-in period. Further, the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated, which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.

58 GEOSCIENCES↗
DOE OSTI2023

Robust deep learning framework for constitutive relations modeling

Modeling the full-range deformation behaviors of materials under complex loading and materials conditions is a significant challenge for constitutive relations (CRs) modeling. Here, we propose a general encoder-decoder deep learning framework that can model high-dimensional stress-strain data and complex loading histories with robustness and universal capability. The framework employs an encoder to project high-dimensional input information (e.g., loading history, loading conditions, and materials information) to a lower-dimensional hidden space and a decoder to map the hidden representation to the stress of interest. We evaluated various encoder architectures, including gated recurrent unit (GRU), GRU with attention, temporal convolutional network (TCN), and the Transformer encoder, on two complex stress-strain datasets that were designed to include a wide range of complex loading histories and loading conditions. All architectures achieved excellent test results with an root-mean-square error (RMSE) below 1 MPa. Additionally, we analyzed the capability of the different architectures to make predictions on out-of-domain applications, with an uncertainty estimation based on deep ensembles. The proposed approach provides a robust alternative to empirical/semi-empirical models for CRs modeling, offering the potential for more accurate and efficient materials design and optimization.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Performance Prediction of High‐Entropy Perovskites La 0.8 Sr 0.2 Mn x Co y Fe z O 3 with Automated High‐Throughput Characterization of Combinatorial Libraries and Machine Learning

Perovskite oxides form a large family of materials with applications across various fields, owing to their structural and chemical flexibility. Efficient exploration of this extensive compositional space is now achievable through automated high-throughput experimentation combined with machine learning. In this study, we investigate the composition–structure–performance relationships of high-entropy La 0.8 Sr 0.2 Mn x Co y Fe z O 3±𝞭 perovskite oxides (0 < x, y, z <1; x+y+z≈1) for application as oxygen electrodes in Solid Oxide Cells. Following the deposition of a continuous compositional map using thin-film combinatorial pulsed laser deposition, compositional, structural, and performance properties are characterized using six different techniques with mapping capabilities. Random forests effectively model electrochemical performance, consistently identifying Fe-rich oxides as optimal compounds with the lowest area-specific resistance values for oxygen electrodes at 700 °C. Additionally, the models identify a statistical correlation between oxygen sublattice distortion—derived from spectral analysis of Raman-active modes—and enhanced performance.

high entropy oxides↗
DOE OSTI2021

MADLens, a python package for fast and differentiable non-Gaussian lensing simulations

Here, we present MADLens a python package for producing non-Gaussian lensing convergence maps at arbitrary source redshifts with unprecedented precision. MADLens is designed to achieve high accuracy while keeping computational costs as low as possible. A MADLens simulation with only particles produces convergence maps whose power agrees with theoretical lensing power spectra up to within the accuracy limits of HaloFit. This is made possible by a combination of a highly parallelizable particle-mesh algorithm, a sub-evolution scheme in the lensing projection, and a machine-learning inspired sharpening step. Further, MADLens is fully differentiable with respect to the initial conditions of the underlying particle-mesh simulations and a number of cosmological parameters. These properties allow MADLens to be used as a forward model in Bayesian inference algorithms that require optimization or derivative-aided sampling. Another use case for MADLens is the production of large, high resolution simulation sets as they are required for training novel deep-learning-based lensing analysis tools. We make the MADLens package publicly available under a Creative Commons License

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Expediting field-effect transistor chemical sensor design with neuromorphic spiking graph neural networks

Improving the sensitive and selective detection of analytes in a variety of applications requires accelerating the rational design of field-effect transistor (FET) chemical sensors. Achieving high-performance detection relies on identifying optimal probe materials that can effectively interact with target analytes, a process traditionally driven by chemical intuition and time-consuming trial-and-error methods. To address the difficulties in probe screening for FET sensor development, this work presents a methodology that combines neuromorphic machine learning (ML) architectures, specifically a hybrid spiking graph neural network (SGNN), with an enriched dataset of physicochemical properties through semi-automated data extraction using large language models. Achieving a classification accuracy of 0.89 in predicting sensor sensitivity categories, the SGNN model outperformed traditional ML techniques by leveraging its ability to capture both global physicochemical properties and sparse topological features through a hybrid modeling framework. Next-generation sensor design was informed by the actionable insights into the connections between material properties and sensing performance offered by the SGNN framework. Through virtual screening for the detection of per- and polyfluoroalkyl substances (PFAS) as a use case, the effectiveness of the SGNN model was further validated. Density functional theory simulations confirmed graphene as a promising active material for PFAS detection as suggested by the SGNN framework. By bridging gaps in predictive modeling and data availability, this integrated approach provides a strong foundation for accelerating advancements in FET sensor design and innovation.

Ferreira, Rodrigo Pires [Univ. of Chicago, IL (Uni↗
DOE OSTI2023

Reinforcement Learning Approach to Cybersecurity in Space (RELACSS)

Securing satellite groundstations against cyber-attacks is vital to national security missions. However, these cyber threats are constantly evolving. As vulnerabilities are discovered and patched, new vulnerabilities are discovered and exploited. In order to automate the process of discovering existing vulnerabilities and the means to exploit them, a reinforcement learning framework is presented in this report. We demonstrate that this framework can learn to successfully navigate an unknown network and detect nodes of interest despite the presence of a moving target defense. The agent then exfiltrates a file of interest from the node as quickly as possible. This framework also incorporates a defensive software agent that learns to impede the attacking agents progress. This setup allows for the agents to work against each other and improve their abilities. We anticipate that this capability will help uncover unforeseen vulnerabilities and the means to mitigate them. The modular nature of the framework enables users to swap out learning algorithms and modify the reward functions in order to adapt the learning tasks to various use cases and environments. Several algorithms, viz., tabular Q learning, deep Q networks, proximal policy optimization, advantage actor-critic, generative adversarial imitation learning, are explored for the agents and the results highlighted. The agent learns to solve the tasks in a light-weight abstract environment. Once the agent learns to perform sufficiently well, it can be deployed in a minimega virtual machine environment (or a real network) with wrappers that map abstract actions to software commands. The agent also uses a local representation of the actions called a ‘slot-mechanism’. This allows the agent to learn in a certain network and generalize it to different networks. The defensive agent learns to predict the actions taken by an offensive agent and uses that information to anticipate the threat. This information can then either be used to raise an alarm or to take actions to thwart the attack. We believe that with the appropriate reward design, a representative environment, and action set, this framework can be generalized to tackle other cybersecurity tasks. By sufficiently training these agents, we can anticipate vulnerabilities leading to robust future designs. We can also deploy automated defensive agents that can help secure satellite groundstation and their vital national security missions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗