SEARCH · Search NASA

Results for “interpretable AI”

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.

SourceResearch connectionFrom yearThrough year

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

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Explainable Neural Architecture Search (XNAS)

Code for the paper Learning Interpretable Models Through Multi-Objective Neural Architecture Search by Zachariah Carmichael, Tim Moon, and Sam Ade Jacobs. Monumental advances in deep learning have led to unprecedented achievements across a multitude of domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial. Research has been introduced to automate the design of neural network architectures through neural architecture search (NAS). Recent progress has made these methods more pragmatic by exploiting distributed computation and novel optimization algorithms. However, there is little work in optimizing architectures for interpretability. To this end, we propose a multiobjective distributed NAS framework that optimizes for both task performance and introspection. We leverage the non-dominated sorting genetic algorithm (NSGA-II) and explainable AI (XAI) techniques to reward architectures that can be better comprehended by humans. The framework is evaluated on several image classification datasets. We demonstrate that jointly optimizing for introspection ability and task error leads to more disentangled architectures that perform within tolerable error.

Carmichael, ZachariahJ↗

DOE OSTI2021

Semi-automated Design of Artificial Intelligence Earth Systems Models

Prediction and observation of water cycles at various scales involve not only patterns isolated in space and time, but also modeling of complex spatio-temporal relationships across multiple domains. For instance, evapotranspiration (ET) and leaf area indexes (LAI) are two parameters that are needed to accurately model and understand land-atmosphere processes. Accurate assessments of ET and LAI are critical for understanding hydrological processes, deforestation, crop yield, and irrigation impacts. However, ET estimates for global simulations are available at very coarse spatial resolution. They are usually derived from satellite data based on broad plant functional types (PFTs), which fail to capture fine-scale variations because of changes in vegetation type across the globe. Similarly LAI estimates have typically been derived from vegetation indices at global scales or estimated locally using physical models, both of which suffer from a range of uncertainties that impact model sensitivity. The new era of AI model development for Earth systems (ES) calls for data-driven methods that provide domain scientists with uncertainty-aware estimations of biophysical parameters such as ET and LAI in a generalizable, interpretable, and discoverable manner.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Fracture Characterization Via AI‐Assisted Analysis of Temperature Logs

Abstract Fractures control fluid flow, mass transport, and heat transfer in a geothermal reservoir. This makes accurate characterization of fracture networks a prerequisite for optimal design and control of a reservoir's exploitation. We develop a deep‐learning procedure to identify fracture locations via interpretation of temporally and spatially continuous downhole temperature measurements. A long short‐term memory fully convolutional network (LSTM‐FCN) is used both to capture long‐term dependencies in sequential temperature data and to distill local features around fractures. A wellbore and fractured‐reservoir thermal model is established to generate temperature data for network training. The trained LSTM‐FCN exhibits a unique ability to detect multiple fractures intersecting a borehole. We use the LSTM‐FCN algorithm to evaluate the effectiveness of different‐stage wellbore temperature measurements on fracture detection in a complex fractured system. Our experiments reveal that the use of various‐stage temperature information as an input feature set improves the robustness of fracture detection to noise interference. This study indicates the practical feasibility of obtaining accurate fracture‐network reconstructions from temperature signals, at reasonable computational cost.

Yang, Xiaoyu↗

DOE OSTI2025

2025 Workshop on Envisioning Frontiers in AI and Computing for Biological Research: Position Papers

This workshop aims to identify key research directions for transforming biology using artificial intelligence (AI), machine learning (ML) and computational methods to facilitate the discovery of new behaviors, mechanisms, and designs of biological processes relevant to DOE missions, underpinning a broader U.S. bioeconomy. By developing novel AI/ML technologies to analyze and interpret complex biological data, researchers can organize and simulate biological processes at various scales as well as advance predictive understanding and manipulation of biological systems. This integration of computation, experimentation, and next-generation experimental technologies can lead to discoveries in new biological behaviors and mechanisms relevant to DOE missions. The focus is on how advanced computational and mathematical methods can impact this mission by exploring digital twins, foundation models, automated laboratory experiments, modeling of complex living systems, and data-driven approaches for the biodesign of plants and microbial systems. While data management is important, it is not the primary focus of this workshop, which will assess the current state, trends, and AI/ML challenges at the interface between biology and computational science to identify opportunities for high-impact research at their intersection. The goal is to define research needs and opportunities that align with biological sciences, computational sciences, and applied mathematics research.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

MCP-eGridGPT (MCP-Enabled Chatbot with Electrical Power System Analysis and Interactive Visualization Tool) [SWR-25-126]

This software is an advanced chatbot system that integrates the Model Context Protocol (MCP) to provide intelligent electrical power system analysis and automated visualization generation. The system enables users to interact with complex electrical engineering tools through natural language, automatically analyzes power system data for voltage violations and grid health assessment, and generates professional interactive HTML dashboards and reports. Key features include dynamic tool discovery from MCP servers, multi-LLM provider support, intelligent data interpretation using large language models, automated chart generation, and a web-based interface for real-time analysis. The software bridges sophisticated electrical engineering analysis with user-friendly interfaces, making power system diagnostics accessible through conversational AI.

Choi, Seong [National Laboratory of the Rockies (N↗

DOE OSTI2023

Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images

Ultrasound imaging is a critical tool for triaging and diagnosing subjects but only if images can be properly interpreted. Unfortunately, in remote or military medicine situations, the expertise to interpret images can be lacking. Machine-learning image interpretation models that are explainable to the end user and deployable in real time with ultrasound equipment have the potential to solve this problem. We have previously shown how a YOLOv3 (You Only Look Once) object detection algorithm can be used for tracking shrapnel, artery, vein, and nerve fiber bundle features in a tissue phantom. However, real-time implementation of an object detection model requires optimizing model inference time. Here, we compare the performance of five different object detection deep-learning models with varying architectures and trainable parameters to determine which model is most suitable for this shrapnel-tracking ultrasound image application. We used a dataset of more than 16,000 ultrasound images from gelatin tissue phantoms containing artery, vein, nerve fiber, and shrapnel features for training and evaluating each model. Every object detection model surpassed 0.85 mean average precision except for the detection transformer model. Overall, the YOLOv7tiny model had the higher mean average precision and quickest inference time, making it the obvious model choice for this ultrasound imaging application. Other object detection models were overfitting the data as was determined by lower testing performance compared with higher training performance. In summary, the YOLOv7tiny object detection model had the best mean average precision and inference time and was selected as optimal for this application. Next steps will implement this object detection algorithm for real-time applications, an important next step in translating AI models for emergency and military medicine.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Observation of Significant Flavor-SU(3) Breaking in the Kaon Wave Function at 12 < Q 2 < 25 GeV 2 and Discovery of the Charmless Decay ψ ( 3770 ) → K S 0 K L 0

We present cross sections for the reaction e + e − → K S 0 K L 0 at center-of-mass energies ranging from 3.51 to 4.95 GeV using data samples collected in the BESIII experiment, corresponding to a total integrated luminosity of 26.5 fb − 1 . The ratio of neutral-to-charged kaon form factors at large momentum transfers ( 12 < Q 2 < 25 GeV 2 ) is determined to be 0.21 ± 0.01 , which indicates a small but significant effect of flavor-SU(3) breaking in the kaon wave function, and, consequently, excludes the possibility that flavor-SU(3) breaking is the primary reason for the strong experimental violation of the pQCD prediction | F ( π ± ) | / | F ( K ± ) | = f π 2 / f K 2 , where F ( π ± ) and F ( K ± ) are the form factors, and f π and f K are the decay constants of charged pions and kaons, respectively. We also observe a significant signal for the charmless decay ψ ( 3770 ) → K S 0 K L 0 for the first time. Within a 1 σ contour of the likelihood value, the branching fraction for ψ ( 3770 ) → K S 0 K L 0 is determined to be B = ( 2.6 3 − 1.59 + 1.40 ) × 10 − 5 , and the relative phase between the continuum and ψ ( 3770 ) amplitudes is ϕ = ( − 0.3 9 − 0.10 + 0.05 ) π . The branching fraction is in good agreement with the S - and D -wave charmonia mixing scheme proposed in the interpretation of the “ ρ π puzzle” between J / ψ and ψ ( 3686 ) decays. Published by the American Physical Society 2024

Physics↗

DOE OSTI2023

Quantum biological insights into CRISPR-Cas9 sgRNA efficiency from explainable-AI driven feature engineering

Abstract CRISPR-Cas9 tools have transformed genetic manipulation capabilities in the laboratory. Empirical rules-of-thumb have been developed for only a narrow range of model organisms, and mechanistic underpinnings for sgRNA efficiency remain poorly understood. This work establishes a novel feature set and new public resource, produced with quantum chemical tensors, for interpreting and predicting sgRNA efficiency. Feature engineering for sgRNA efficiency is performed using an explainable-artificial intelligence model: iterative Random Forest (iRF). By encoding quantitative attributes of position-specific sequences for Escherichia coli sgRNAs, we identify important traits for sgRNA design in bacterial species. Additionally, we show that expanding positional encoding to quantum descriptors of base-pair, dimer, trimer, and tetramer sequences captures intricate interactions in local and neighboring nucleotides of the target DNA. These features highlight variation in CRISPR-Cas9 sgRNA dynamics between E. coli and H. sapiens genomes. These novel encodings of sgRNAs enhance our understanding of the elaborate quantum biological processes involved in CRISPR-Cas9 machinery.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Scientific machine learning for closure models in multiscale problems: A review

Here, closure problems are omnipresent when simulating multiscale systems, where some quantities and processes cannot be fully prescribed despite their effects on the simulation's accuracy. Recently, scientific machine learning approaches have been proposed as a way to tackle the closure problem, combining traditional (physics-based) modeling with data-driven (machine-learned) techniques, typically through enriching differential equations with neural networks. This paper reviews the different reduced model forms, distinguished by the degree to which they include known physics, and the different objectives of a priori and a posteriori learning. The importance of adhering to physical laws (such as symmetries and conservation laws) in choosing the reduced model form and choosing the learning method is discussed. The effect of spatial and temporal discretization and recent trends toward discretization-invariant models are reviewed. In addition, we make the connections between closure problems and several other research disciplines: inverse problems, Mori-Zwanzig theory, and multi-fidelity methods. In conclusion, much progress has been made with scientific machine learning approaches for solving closure problems, but many challenges remain. In particular, the generalizability and interpretability of learned models is a major issue that needs to be addressed further.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗

DOE OSTI2021

Deep Analysis Net with Causal Embedding for Coal-fired Power Plant Fault Detection and Diagnosis (DANCE4CFDD)

Fault detection and diagnosis is critical to power plant operation to ensure attaining high reliability while reducing operation cost. As more renewable power is introduced to the power grid, traditional fossil power plants take on the extra burden of excessive load cycling to compensate the generation variability from renewable power. Such load cycling will pose more reliability challenges to power plant operation. There are a number of challenges faced by today’s asset health management system in coal- fired (or gas) power plants: 1) high-dimensional nonlinear interaction among multiple time series measurements; 2) high measurement variance induced by operational conditions/modes; 3) variation among asset types and plant configurations; and 4) a small number of faulty events to learn from. To cope with these challenges, today’s fielded asset health management systems rely heavily on manual efforts from domain experts and hand-crafted features or rules based on domain knowledge. Despite its role in plant reliability, such a practice is costly and hinders its scalability and sustainability, particularly when a plant undergoes modifications. The objective of this project is to develop a novel end-to-end AI learning system that is trainable (i.e., the AI representation of a complex system behavior can be directly learned from properly labeled data) for accurate fault detection and root cause analysis. The ability to create a fault detection model directly from time series could alleviate the efforts associated with today’s asset management solution development. In the course of this project, we have achieved the following: Created an AI model development environment incorporating state-of-the-art neural network architectures for rapid model development and evaluation; Developed novel learning strategies for training of fault detection model; Developed special-purpose neural network architecture embedded with variable association graph aiming for better interpretability; Developed a learning strategy to leverage a small number of faulty events for enhanced fault detection capability; Conducted detailed experimental study based on public benchmark datasets and demonstrated the effectiveness of the proposed solution; and Validated the developed system with data from both a coal-fired plant boiler dynamic simulation model and real-world coal-fired power plant covering multiple asset and fault types. Overall, the project attained a technology readiness level of TRL 5 from TRL 2 at the beginning of the project.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2024

R ( 3780 ) Resonance Interpreted as the 1 D 1 3 -Wave Dominant State of Charmonium from Precise Measurements of the Cross Section of e + e − → Hadrons

We report the precise measurements of the cross section of e + e − → hadrons at center-of-mass energies from 3.645 to 3.871 GeV. We thereby perform the most precise study of the cross sections and find a complex system composed of three resonances of R ( 3760 ) , R ( 3780 ) , and R ( 3810 ) . For the first time, we measure the R ( 3810 ) electronic width to be ( 19.4 ± 7.4 ± 12.1 ) eV . For the R ( 3760 ) resonance, we measure the mass to be ( 3751.9 ± 3.8 ± 2.8 ) MeV / c 2 , the total width to be ( 32.8 ± 5.8 ± 8.7 ) MeV , and the electronic width to be ( 184 ± 75 ± 86 ) eV . For the R ( 3780 ) resonance, we measure its mass to be ( 3778.7 ± 0.5 ± 0.3 ) MeV / c 2 , total width to be ( 20.3 ± 0.8 ± 1.7 ) MeV , and electronic width to be ( 265 ± 67 ± 83 ) eV . Forty-seven years ago, the ψ ( 3770 ) resonance was discovered, and was subsequently interpreted as the 1 D 1 3 -wave dominant state of charmonium. However, our analysis of the total-hadron cross sections indicates that the ψ ( 3770 ) is not a single state, but a complex system composed of the R ( 3760 ) , R ( 3780 ) , and R ( 3810 ) resonances. Among these, we interpret the R ( 3780 ) is a resonance dominated by the 1 D 1 3 charmonium state. Published by the American Physical Society 2024

Ablikim, M.↗

DOE OSTI2026

Using Explainable Artificial Intelligence to Predict Perovskite Solar Cell Electrical Metastability from Operando Photoluminescence Images in Accelerated Stress Testing

Metal halide perovskite (MHP) solar cells exhibit a metastable response to bias governed by coupled ionic–electronic processes, complicating the conventional reciprocity relation between luminescence intensity and device open-circuit voltage (V oc ). This limits the use of luminescence as a diagnostic for device screening or accelerated stress testing, motivating new approaches that can interpret photoluminescence (PL) signals under nonequilibrium conditions. From the artificial intelligence perspective, we develop an explainable deep learning framework that integrates convolutional neural networks (CNN), long short-term memory (LSTM) layers, and an attention mechanism to learn spatiotemporal features from operando photoluminescence PL image sequences. The model achieves a mean absolute error of ±0.027 V in predicting open-circuit voltage transients and reduces extreme-tail errors by up to 78% compared to physics-based reciprocity calculations. Gradient-weighted Class Activation Mapping (Grad-CAM) provides interpretability by highlighting physically meaningful regions such as electrode edges and emergent defect features. From the engineering application perspective, this framework enables accurate, contactless prediction of device V oc and identification of degradation-relevant features during accelerated aging of perovskite solar cells. This approach demonstrates how explainable AI can enhance operando diagnostics and reliability analysis in photovoltaic devices under nonequilibrium conditions.

14 SOLAR ENERGY↗

DOE OSTI2025

Data Integration and Visualization for Enhanced Resilience and Sustainability in Hydropower (DIVERS-H)

U.S. hydropower plants face potential threats from shrinking water supply, rising demands, and warmer stream temperatures from various causes. Power plant owners, operators, and regulators require new tools to take advantage of and interpret the diverse range of scientific data being produced by both observational methods (for example, satellite, radar, stream gauges) and computer modeling methods that evaluate and predict how earth's dynamic systems (atmosphere, oceans, land surface, and sea ice) are changing and interacting. Combining datasets such as these with AI-based analyses introduces a novel decision support system to help users anticipate and address potential impacts on power generation stations. This new technology has been named DIVERS-H for "Data Integration and Visualization for Enhanced Resilience and Sustainability in Hydropower." In Phase I, technical feasibility was established with the development and demonstration of all the new technologies that are required. Most notably, DIVERS-H will use new artificial intelligence (AI) methods to capture the complex dynamics of water availability, demand, and environmental changes. In addition, new data management software was developed, and a prototype user interface was implemented as the precursor to a full scale decision support system. With technical research complete, the project focus now shifts to development of a commercial software product to provide users with actionable insight into water availability and the risk/resilience of critical systems at their locations of interest. Although DIVER-H was originally conceived as a tool for hydroelectric power applications, the same underlying technology can be readily applied to other water-consuming systems including coal, natural gas, oil, and nuclear power plants.

Chaudhary, Aashish [Kitware, Inc., Clifton Park, N↗

DOE OSTI2025

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

60 years of science in ICF: from conception to scientific breakeven on the National Ignition Facility

The recent achievements of a burning plasma, fusion ignition, and scientific energy gain with deuterium-tritium (DT) fuel at Lawrence Livermore National Laboratory’s National Ignition Facility (NIF) represents a major milestone in the development of inertial confinement fusion (ICF) and all of fusion research. In these experiments, fuel pressures well in excess of hundreds of GBars were achieved in the compressed fuel, and robust alpha heating of the fuel, far in excess of the energy provided by the implosion, were demonstrated for the first time. These achievements occurred 60 years after the inception of ICF and the first laser demonstration, and were made possible by more than five decades of research at laser facilities around the world. Advances in laser technology both in wavelength and precision, motivated by improved understanding of laser-plasma interaction physics and the demands of targets; improvements in target fabrication inspired by the need to control and minimize hydrodynamic instabilities in the implosion; and multi-dimensional simulations and diagnostics have been critical to this achievement. This paper will summarize the scientific and technical advances, the surprises, and the challenges that had to be overcome to achieve these goals.

fusion↗

DOE OSTI2024

Towards interpretable Cryo-EM: disentangling latent spaces of molecular conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

A computational pipeline to generate a synthetic dataset of metal ion sorption to oxides for AI/ML exploration

The charged mineral/electrolyte interfaces are ubiquitous in the surface and subsurface–including the surroundings of the geological disposal sites for radioactive waste. Therefore, understanding how ions interact with charged surfaces is critically important for predicting radionuclide mobility in the case of waste leakage. At present, the Surface Complexation Models (SCMs) are the most successful thermodynamic frameworks to describe ion retention by mineral surfaces. SCMs are interfacial speciation models that account for the effect of the electric field generated by charged surfaces on sorption equilibria. These models have been successfully used to analyze and interpret a broad range of experimental observations including potentiometric and electrokinetic titrations or spectroscopy. Unfortunately, many of the current procedures to solve and fit SCM to experimental data are not optimal, which leads to a non-transferable or non-unique description of interfacial electrostatics and consequently of the strength and extent of ion retention by mineral surfaces. Recent developments in Artificial Intelligence (AI) offer a new avenue to replace SCM solvers and fitting algorithms with trained AI surrogates. Unfortunately, there is a lack of a standardized dataset covering a wide range of SCM parameter values available for AI exploration and training–a gap filled by this study. Here, we described the computational pipeline to generate synthetic SCM data and discussed approaches to transform this dataset into AI-learnable input. First, we used this pipeline to generate a synthetic dataset of electrostatic properties for a broad range of the prototypical oxide/electrolyte interfaces. The next step is to extend this dataset to include complex radionuclide sorption and complexation, and finally, to provide trained AI architectures able to infer SCMs parameter values rapidly from experimental data. Here, we illustrated the AI-surrogate development using the ensemble learning algorithms, such as Random Forest and Gradient Boosting. These surrogate models allow a rapid prediction of the SCM model parameters, do not rely on an initial guess, and guarantee convergence in all cases.

Li, Chunhui↗