SEARCH · Engineering Papers

Results for “Robust artificial intelligence”

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 163 records · Page 9

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Quantum-Inspired Bayesian Sampling for Uncertainty Quantification and Machine Learning (Final Technical Report)

With increasing simulation and measurement data, machine learning and artificial intelligence have been widely used in computational decision-making of complex engineering systems. The resulting tools, such as uncertainty quantification solvers, reinforcement learning, and physics-informed machine learning, have achieved great success in critical DOE tasks such as material discovery and design, energy system modeling and control, and numerical weather and climate prediction. A core topic in scientific machine learning and artificial intelligence is Bayesian inference: given an observed data set, people want to estimate the posterior distribution of a (possibly large) number of hidden parameters. Due to the flexibility and weak assumptions, Bayesian sampling has been the mainstream Bayesian inference solvers despite the rapid progress of approximate Bayesian inference. Classical Bayesian sampling methods such as Markov-chain Monte Carlo suffer from a low-acceptance rate due to the random walk nature, therefore state-of-the-art techniques use Hamiltonian Monte Carlo and its variants to efficiently draw posterior samples in a high dimension. The key idea of Hamiltonian Monte Carlo and its variants is to simulate the Hamiltonian dynamics of a classical particle with a fixed mass, and their performance significantly degrades when the posterior distribution is highly spiky or has multiple modes. Leveraging the idea of quantum physics, this project has investigated new theory, algorithms and applications of Bayesian inference (especially Bayesian sampling). The main results include: (1) novel quantum-inspired Bayesian sampling methods that can lead to better accuracy for challenging multi-modal or spiky distributions, (2) more scalable machine learning framework leveraging tensor-compressed Bayesian inference, and (3) Bayesian and sampling approaches for verifying the robustness of continuous and binary neural networks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Accelerating computational fluid dynamics simulation of post-combustion carbon capture modeling with MeshGraphNets

Packed columns are commonly used in post-combustion processes to capture CO 2 emissions by providing enhanced contact area between a CO 2 -laden gas and CO 2 -absorbing solvent. To study and optimize solvent-based post-combustion carbon capture systems (CCSs), computational fluid dynamics (CFD) can be used to model the liquid–gas countercurrent flow hydrodynamics in these columns and derive key determinants of CO 2 -capture efficiency. However, the large design space of these systems hinders the application of CFD for design optimization due to its high computational cost. In contrast, data-driven modeling approaches can produce fast surrogates to study large-scale physics problems. We build our surrogates using MeshGraphNets (MGN), a graph neural network framework that efficiently learns and produces mesh-based simulations. We apply MGN to a random packed column modeled with over 160K graph nodes and a design space consisting of three key input parameters: solvent surface tension, inlet velocity, and contact angle. Our models can adapt to a wide range of these parameters and accurately predict the complex interactions within the system at rates over 1700 times faster than CFD, affirming its practicality in downstream design optimization tasks. This underscores the robustness and versatility of MGN in modeling complex fluid dynamics for large-scale CCS analyses.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

The Art of Automation: Translating Electron Microscopy Workflows Into Automated Processes

Acquiring data using a scanning transmission electron microscope (STEM) is a complex, multi-step process. The intricacy of the process depends on the type of sample, composition of the material, desired results of the experiment, resolution requirement and other experimental factors. Each experiment presents unique complications, such as sample drift and contamination, that the microscopist must consider when acquiring data. All these challenges are handled fluidly and expertly by experienced microscopists, but to reach new levels of innovation in material development, including greater reproducibility, throughput, and precision, the automation of these workflows is essential. The initial phase of this work involved translating intuition-based workflows into discrete, programmable steps. Some common key stages in STEM workflows are the initial tuning, scanning the sample for areas of interest, and then acquiring the data. Each stage can be broken further into specific parameter adjustments, such as aberration correction and dwell time optimization, depending on the experiment. When deconstructing various experiments each step was assessed for automation feasibility based on the amount of real time operator decisions. There are steps that lend themselves to automation more readily than others, such as course focusing and sample screening, but there is potential for full automation of all stages with time. As an initial step, an automated montage routine was developed, allowing for the efficient acquisition of large portions of the sample without requiring continuous intervention from the operator. The automation of this small process of the procedure demonstrates the value of this capability. A major challenge in automation arises from discrepancies between commanded, reported and actual stage movements. Using systematic tests, stage movement was quantified. This error can be corrected algorithmically for more accurate workflows in the future. Expanding automation capabilities would result in larger, more efficient data acquisition which allows for more robust statistical analysis. Additionally, this work lays the groundwork for a closed loop system where machine learning algorithms would intake automatically acquired data and make real time decisions. By progressively automating this instrument, this work establishes the foundation for fully automated experimentation in transmission electron microscopy.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Efficient high-dimensional variational data assimilation with machine-learned reduced-order models

Abstract. Data assimilation (DA) in geophysical sciences remains the cornerstone of robust forecasts from numerical models. Indeed, DA plays a crucial role in the quality of numerical weather prediction and is a crucial building block that has allowed dramatic improvements in weather forecasting over the past few decades. DA is commonly framed in a variational setting, where one solves an optimization problem within a Bayesian formulation using raw model forecasts as a prior and observations as likelihood. This leads to a DA objective function that needs to be minimized, where the decision variables are the initial conditions specified to the model. In traditional DA, the forward model is numerically and computationally expensive. Here we replace the forward model with a low-dimensional, data-driven, and differentiable emulator. Consequently, gradients of our DA objective function with respect to the decision variables are obtained rapidly via automatic differentiation. We demonstrate our approach by performing an emulator-assisted DA forecast of geopotential height. Our results indicate that emulator-assisted DA is faster than traditional equation-based DA forecasts by 4 orders of magnitude, allowing computations to be performed on a workstation rather than a dedicated high-performance computer. In addition, we describe accuracy benefits of emulator-assisted DA when compared to simply using the emulator for forecasting (i.e., without DA). Our overall formulation is denoted AIEADA (Artificial Intelligence Emulator-Assisted Data Assimilation).

58 GEOSCIENCES↗

DOE OSTI2026

Machine learning reveals strong grid-scale dependence in the satellite N d –LWP relationship

The relationship between cloud droplet number concentration ( N d ) and liquid water path (LWP) is highly uncertain yet crucial for determining the impact of aerosol-cloud interactions (ACI) on Earth's radiation budget. The N d -LWP relationship is examined using a machine learning (ML) random forest model applied to five years of satellite data at grid resolutions ranging from 10° to 0.05° in 12 distinct regions. In the subtropics, the shape of the N d -LWP relationship switches from an inverted-V at 1° grid-resolution to an “M” shape at 0.1° resolution with decreased $\frac{\textrm{dln⁡LWP}}{\textrm{dln⁡}N_d}$ sensitivity. Tropical and midlatitude regions generally show a more positive sensitivity. Cloud sampling and filtering also influence this slope, wherein the exclusion of thin clouds, as commonly performed to reduce retrieval uncertainty, leads to strongly negative sensitivity across all regions. Precipitation is primarily responsible for driving the strength of the sensitivity, with strong positive slopes in raining clouds and negative and/or neutral responses found in non-raining clouds. A new method to compute radiative forcing from the ML model shows a robust Twomey radiative forcing across all regions and grid resolutions. However, LWP and cloud fraction adjustments to the radiative forcing, which are ∼50 % or smaller than the Twomey effect, decrease to negligible values with higher spatial resolution data. As Earth system models move toward higher spatial resolutions in the future, evaluating the LWP and CF adjustment contributions to the radiative forcing budget at these finer resolutions will be essential for evaluation and model development.

Aerosol-Cloud Interactions↗

DOE OSTI2021

Revisiting the ODE Method for Recursive Algorithms: Fast Convergence Using Quasi Stochastic Approximation

Several decades ago, Profs. Sean Meyn and Lei Guo were postdoctoral fellows at ANU, where they shared interest in recursive algorithms. It seems fitting to celebrate Lei Guo's 60th birthday with a review of the ODE Method and its recent evolution. The method has been regarded as a technique for algorithm analysis. It is argued that this viewpoint is backwards: The original stochastic approximation method was surely motivated by an ODE, and tools for analysis came much later (based on establishing robustness of Euler approximations). The paper presents a brief survey of recent research in machine learning that shows the power of algorithm design in continuous time, following by careful approximation to obtain a practical recursive algorithm. While these methods are usually presented in a stochastic setting, this is not a prerequisite. In fact, recent theory shows that rates of convergence can be dramatically accelerated by applying techniques inspired by quasi Monte-Carlo. Subject to conditions, the optimal rate of convergence can be obtained by applying the averaging technique of Polyak and Ruppert. The conditions are not universal, but theory suggests alternatives to achieve acceleration. The theory is illustrated with applications to gradient-free optimization, and policy gradient algorithms for reinforcement learning.

learning and adaptive systems in artificial intell↗

DOE OSTI2022

Principles of the Battery Data Genome

Batteries are central to modern society. They are no longer just a convenience but a critical enabler of the transition to a resilient, low-carbon economy. Battery development capabilities are provided by communities spanning materials discovery, battery chemistry and electrochemistry, cell and pack design, scale-up, manufacturing, and deployments. Despite their relative maturity, data-science practices among these diverse groups are far behind the state of the art in other fields, which have demonstrated an ability to significantly improve innovation and economic impact. The negative consequences of the present paradigm include incremental improvements but few breakthroughs, significant manufacturing uncertainties, and cascading investment risks that collectively slow deployments. The primary roadblock to a battery-data-science renaissance is the requirement for large amounts of high-quality data, which are not available in the current fragmented ecosystem. Here, in this study, we identify gaps and propose principles that enable the solution by building a robust community of data hubs with standardized practices and flexible sharing options that will seed advanced tools spanning innovation to deployment. Precedents are offered that demonstrate that both public good and immense economic gains will arise from sharing valuable battery data. The proposed Battery Data Genome looks to broadly transform innovations and revolutionize their translation from research to societal impact.

25 ENERGY STORAGE↗

DOE OSTI2020

Accelerating Hanford Site Cleanup through Operations Research Modeling - 20238

The Hanford Site cleanup effort will require the integration of dozens of unique facilities and processes, many of which will be first-of-a-kind in implementation and design. Each facility will be governed by its own set of operating logic, configured with a unique array of unit operations, and subject to a set of constraints that will affect its behavior. The collection of facilities have multiple points of interface, making the operations of any one facility potentially significant to the operations of other up- or downstream processes. It is therefore highly desirable to accurately predict these operations, as it allows for Site officials to identify and preempt bottlenecks and vulnerabilities before they unexpectedly inhibit the cleanup mission. With the quantity and complexity of the processes that will be on Site, building a pen-and-paper or even a spreadsheet-assisted model of the cleanup mission quickly becomes overwhelming in scope and inaccurate in execution. The Engineering organization for the Site's Tank Operations Contract (TOC) has therefore implemented the use of operations research (OR) modeling to simulate and predict future operations of Site facilities. These models are created using a discrete event simulation tool that allows for the development of detailed, versatile, and robust models. Not only can these models account for complex logical behaviors, but they can also simulate process details down to the level of vessel sizing, labor utilization, equipment reliability, and resource availability. To date, the TOC has developed OR models for several facilities on Site, including for single-shell tank (SST) farms, double-shell tank (DST) farms, the Effluent Treatment Facility (ETF), and the waste transfer system. These models have focused on identifying bottlenecks and operational constraints, and have been used to quantify the effects of implementing process changes. This latter point is particularly valuable, as it allows for several alternatives to be studied in a virtual setting before committing resources to making a change in the field. The decision to develop OR models has gained tremendous support from the Site's stakeholders and the U.S. Department of Energy (DOE) management, and has prompted the use of the tool to support additional internal and external initiatives. Recently, an initiative was proposed to use the models to help identify and provide quantitative backing for risks and opportunities for the TOC. This application of OR could not only help inform how the TOC manages its risks (e.g. quantities and types of spare parts), but could also help drive process improvements whose benefits might otherwise be hard to quantify. The models have also been used to drive the TOC's cloud computing, artificial intelligence (AI), and machine learning (ML) initiatives. These initiatives will not only improve the ability of the TOC to more rapidly respond to the needs of its customers, but it will also aid in the ability of the TOC to analyze and improve the processes it studies. Partnership with two external software development and consulting companies (Lanner and Ynformed) has furthered not only the application of AI and ML within the TOC, but has also spurred the development of new/improved software tools and platforms used by the companies. These partnerships have proven to be mutually beneficial and productive, and have set a precedent for the types of gains that can be made by exploring such options. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2026

Application of artificial intelligence methods in the international roughness index prediction of rigid and composite pavements: a systematic review

The International Roughness Index (IRI) is a widely adopted metric for quantifying pavement roughness, directly influencing vehicle safety, ride comfort, and overall roadway performance. In recent years, the use of Machine Learning (ML) models for IRI prediction has gained momentum, with the goal of improving the allocation of maintenance and rehabilitation resources by enabling accurate assessments of pavement conditions. Most prior reviews, however, have concentrated on flexible pavements, leaving a notable gap regarding rigid and composite pavements. To address this gap, the present study conducts a systematic review of Artificial Intelligence (AI) methods applied to IRI prediction for rigid and composite pavements. Literature published between 2004 and 2025 is synthesized to highlight prevailing trends, methodological contributions, and directions for future research. Particular attention is given to the types of models employed, the datasets used for training and validation, and the role of input variables and data-processing strategies. Across the included studies, ensemble learning methods (especially gradient boosting variants such as XGBoost), artificial neural networks, and hybrid architectures frequently achieved high predictive skill, with several models reporting test-set coefficients of determination approaching 0.9–0.96, indicating strong potential for capturing the influence of traffic, pavement structure, and climatic factors. Since these results are obtained from heterogeneous datasets and evaluation protocols, they are interpreted qualitatively rather than as strict cross-study rankings. Analysis of input variables revealed that pavement age and initial IRI were included in 91% (21 of 23) and 78% (18 of 23) of studies, respectively. Climatic variables such as the freezing index appeared in 57% (13 of 23), while traffic-related factors were considered in 65% (15 of 23). The findings underscore the importance of standardized, high-quality datasets, such as those from the Long-Term Pavement Performance (LTPP) program, along with data consistency, model interpretability, computational efficiency, and replicability in enhancing IRI prediction. Future research should focus on incorporating input variable selection techniques to identify the most influential predictors, thereby improving accuracy and robustness. Integrating these approaches with advanced non-linear data-driven models, coupled with robust hyperparameter optimization, holds considerable promise for strengthening the reliability of IRI prediction and supporting resilient pavement management strategies.

42 ENGINEERING↗

DOE OSTI2023

CoolPINNs: A physics-informed neural network modeling of active cooling in vascular systems

Emerging technologies like hypersonic aircraft, space exploration vehicles, and batteries avail fluid circulation in embedded microvasculatures for efficient thermal regulation. Modeling is vital during the design and operational phases of these engineered systems. However, many challenges exist in developing a modeling framework. What is lacking is an accurate framework that (i) captures sharp jumps in the thermal flux across complex vasculature layouts, (ii) deals with oblique derivatives (involving tangential and normal components), (iii) handles nonlinearity because of radiative heat transfer, (iv) provides a high-speed forecast for real-time monitoring, and (v) facilitates robust inverse modeling. Here, this paper addresses these challenges by availing the power of physics-informed neural networks (PINNs). We develop a fast, reliable, and accurate Scientific Machine Learning (SciML) framework for vascular-based thermal regulation—called CoolPINNs: a PINNs-based modeling framework for active cooling. The proposed mesh-less framework elegantly overcomes all the mentioned challenges. The significance of the reported research is multi-fold. First, the framework is valuable for real-time monitoring of thermal regulatory systems because of rapid forecasting. Second, researchers can address complex thermoregulation designs since the approach is meshless. Finally, the framework facilitates systematic parameter identification and inverse modeling studies, perhaps the most significant utility of the current framework.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Anatomy of Continuous Mars SEIS and Pressure Data from Unsupervised Learning

The seismic noise recorded by the Interior Exploration using Seismic Investigations, Geodesy, and Heat Transport (InSight) seismometer (Seismic Experiment for Interior Structure [SEIS]) has a strong daily quasi-periodicity and numerous transient microevents, associated mostly with an active Martian environment with wind bursts, pressure drops, in addition to thermally induced lander and instrument cracks. That noise is far from the Earth’s microseismic noise. Quantifying the importance of nonstochasticity and identifying these microevents is mandatory for improving continuous data quality and noise analysis techniques, including autocorrelation. Cataloging these events has so far been made with specific algorithms and operator’s visual inspection. We investigate here the continuous data with an unsupervised deep-learning approach built on a deep scattering network. This leads to the successful detection and clustering of these microevents as well as better determination of daily cycles associated with changes in the intensity and color of the background noise. We first provide a description of our approach, and then present the learned clusters followed by a study of their origin and associated physical phenomena. We show that the clustering is robust over several Martian days, showing distinct types of glitches that repeat at a rate of several tens per sol with stable time differences. We show that the clustering and detection efficiency for pressure drops and glitches is comparable to or better than manual or targeted detection techniques proposed to date, noticeably with an unsupervised approach. Finally, here we discuss the origin of other clusters found, especially glitch sequences with stable time offsets that might generate artifacts in autocorrelation analyses. We conclude with presenting the potential of unsupervised learning for long-term space mission operations, in particular, for geophysical and environmental observatories.

58 GEOSCIENCES↗

DOE OSTI2024

Performance Comparison of Machine Learning Models for Ultrasonic Nondestructive Evaluation of Alkali-Silica Reaction in Concrete

Alkali-silica reaction (ASR) causes concrete degradation, leading to cracking, rebar corrosion, and reduced structural integrity, which raises safety concerns. Ultrasonic nondestructive evaluation (NDE) effectively assesses concrete properties and monitors ASR progression. However, its deployment and analysis require specialized expertise and subjective interpretation. As computational power increases, artificial intelligence (AI) and machine learning (ML) algorithms are increasingly being used to automate NDE data analysis across various industries for AI-assisted automation. Regulatory agencies are adapting to this technological shift, prompting a need to evaluate current ML technologies’ capabilities and limitations in assessing concrete material properties and damage. This report presents a comparative analysis of four ML regression models for predicting concrete material damage induced by ASR expansion using long-term ultrasonic data monitoring. The models investigated include linear regression (LR), support vector regression (SVR), shallow neural networks (NN), and deep neural networks (DNN). LR, SVR, and shallow NN models use features extracted from ultrasonic signals, whereas the DNN model processes time-domain ultrasonic signals and frequency spectra directly. The study systematically compared the models’ performance from various perspectives, including model input, prediction performance, and generalization ability. The findings indicate significant variability in model performance, with some ML algorithms achieving very high or very low prediction accuracy depending on the preprocessing and feature engineering (extraction and selection) applied. Key insights include the observation that shallow ML models (LR, SVR, and shallow NNs) require meticulous preprocessing and feature extraction to achieve high accuracy. In contrast, the DNN model, although it bypasses the need for feature engineering, necessitates extensive preprocessing to mitigate noise and computational demands. The SVR model emerged as the top performer among the shallow models, and the DNN model exhibited superior performance on specific datasets but struggled with generalization across specimens from different batches. Additionally, the SVR model is sensitive to temperature variations, whereas the DNN model is robust in this regard. Using recurrent neural networks is recommended for future ASR expansion prediction studies. Recurrent neural networks’ inherent ability to capture temporal dependencies and long-term patterns makes them well suited for analyzing sequential ultrasonic monitoring data. Overall, the results and conclusions of this study could provide insights into the capabilities and effectiveness of ML when applied to ultrasonic NDE data and help identify best practices for using ML for ultrasonic NDE of concrete material properties.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Machine learning assisted phase and size-controlled synthesis of iron oxide particles

Synthesis of iron oxides with specific phases and particle sizes is a crucial challenge in various fields, including materials science, energy storage, biomedical applications, environmental science, and earth science. However, despite significant advances in this area, much of the current palette of particle outcomes has been based on time-consuming trial-and-error exploration of synthesis conditions. The present study was designed to explore a very different approach to 1) predict the outcome of synthesis from specified reaction parameters based on using machine learning (ML) techniques, and 2) correlate sets of parameters to obtain products with desired outcomes by a newly designed recommendation algorithm. To achieve this, four ML algorithms were tested, namely random forest, logistic regression, support vector machine, and k-nearest neighbor. Among the models, random forest outperformed the others, attaining 96% and 81% accuracy when predicting the phase and size of iron oxide particles in the test dataset. Surprisingly, the permutation feature importance analysis revealed that volume, which may strongly relate to pressure, was one of the important features, along with precursor concentration, pH, temperature, and time, influencing the phase and size of iron oxide particles during synthesis. To verify the robustness of the random forest models, prediction and experimental results were compared based on 24 randomly generated methods in additive and non-additive systems not included in the datasets. The predictions of product phase and particle size from the models agreed well with the experimental results. Furthermore, a searching and ranking algorithm was developed to recommend potential synthesis parameters for obtaining iron oxide products with the desired phase and particle size from previous studies in the dataset. Furthermore, this study lays the foundation for a closed-loop approach in materials synthesis and preparation, beginning with suggesting potential reaction parameters from the dataset and predicting potential outcomes, followed by conducting experiments and analyses, and ultimately enriching the dataset.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

A data-driven framework for predicting machining stability: employing simulated data, operational modal analysis, and enhanced transfer learning

Chatter, a self-excited vibration phenomenon, presents a significant challenge in machining operations, particularly in high-speed milling, where it can degrade tool life, reduce material removal efficiency, and compromise workpiece quality. Addressing this challenge requires a reliable predictive model that can accommodate the complex dynamics of various machining scenarios. This study introduces a novel, data-driven approach to predicting machining stability, leveraging over 140,000 simulated datasets and employing advanced techniques such as operational modal analysis (OMA), enhanced transfer learning (TL), and receptance coupling substructure analysis (RCSA). By integrating these methodologies, the framework effectively classifies and predicts chatter across diverse operational modes, achieving robust and accurate outcomes. Our model utilizes a Random Forest (RF) classifier trained with the comprehensive dataset, which demonstrates substantial improvements in both predictive accuracy and robustness. Specifically, the RF model achieved an accuracy rate of 85%, an area under the curve (AUC) of 0.90, and an F1 score of 0.88, underscoring its capability to adapt to varying machining configurations. These results highlight the framework’s potential to enhance operational efficiency and machining quality by providing reliable chatter predictions across a broad range of machining parameters. In conclusion, this research thus offers a significant advancement in predictive maintenance for machining processes, enabling more stable and efficient manufacturing operations.

42 ENGINEERING↗

DOE OSTI2020

Deep Learning for Automated Identification of Eels in Sonar Data

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploited new data collected in the laboratory and the existing data from the prior EPRI field study to develop and test deep learning and other data analytic tools, including wavelet filtering, differencing for static object removal, and convolutional neural network analysis. The analysis of the laboratory data demonstrated feasibility of the approach, revealed object characteristics observed with the sonar that distinguish eels from similarly sized and shaped acoustic targets, and provided additional data for algorithm selection and training. Deep learning algorithms trained and tested on the laboratory data alone achieved accuracy rates of greater than 98% when classifying acoustic images of eels and similar-sized neutrally buoyant sticks. The algorithm trained and tested on the pre-existing field data alone, and yielded classification accuracy of 9.3% false positives and 13.3% false negatives when distinguishing between eels and sticks/PVC pipes based on video clips (i.e., multiple, consecutive images). This performance is comparable to the classification accuracy achieved by human analysts in the prior study. The deep learning algorithm trained on a combination of video clips obtained in the laboratory and the field and tested on video clips from the field, was able to distinguish eels from sticks and PVC pipes (a river debris analog) of similar size with 100% accuracy. Outreach to the hardware, software, and end-user communities early in the project helped to identify needs and specify the application space. Outreach to those communities at the end of the project communicated project results and opportunities for further development. The project achieved proof of concept for automated identification of eel in multibeam sonar data. Future work should focus on acquisition of additional data for more robust algorithm training and testing; modification of the software tools to accommodate multiple acoustic targets in the acoustic field at a given time; identification of additional object classes; incorporation of motion in the object identification and classification algorithms; operationalizing the software tools, including integration with other existing sonar data analysis tools; and partnering with hardware and software providers for distribution of the software tools with their commercial products.

13 HYDRO ENERGY↗

DOE OSTI2022

MetaText: Compositional Generalization in Deep Language Models

Compositional generalization, the ability to infer and reason using novel combinations of previously encountered entities and structures, is a trait of great utility across a variety of deep learning tasks; it implies a certain ability to reason using consistent and therefore interpretable rules, to understand the constituent parts of its input at multiple levels of granularity, to be robust to spurious differences between semantically equivalent inputs, and more. We seek to understand the degree to which existing natural language models achieve or fall short of compositional generalization across a variety of tasks, whether there are distinct types of compositional generalization in practice, and to identify avenues of intervention through which we can improve models’ compositional generalization ability. After exploring these questions using an array of models, tasks, and potential interventions we see that large, pretrained language models have encountered sufficient training data to account for a variety of fine-grained compositional behavior but still struggle to reason at the level of phrases or larger language structures. Non-intrusive, data-based interventions in the form of augmenting individual sequences with compressed versions of themselves or deriving new examples from induced grammars prove insufficient to encourage greater levels of compositional reasoning, indicating that future work might benefit most from focusing on changes to a model’s inductive bias at the architectural or loss level, or by integrating compositionality-boosting data interventions into the large-scale pretraining process itself.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Automatic building energy model development and debugging using large language models agentic workflow

Building energy modeling (BEM) is a complex process that demands significant time and expertise, limiting its broader application in building design and operations. While Large Language Models (LLMs) agentic workflow have facilitated complex engineering processes, their application in BEM has not been specifically explored. This paper investigates the feasibility of automating BEM using LLM agentic workflow. Here, we developed a generic LLM-planning-based workflow that takes a building description as input and generates an error-free EnergyPlus building energy model. Our robust workflow includes four core agents: 1) Building Description Pre-Processing, 2) IDF Object Information Extraction, 3) Single IDF Object Generator Suite, and 4) IDF Debugging Agent. These agents divide the complex tasks into manageable sub-steps, enabling LLMs to generate accurate and reliable results at each stage. The case study demonstrates the successful translation of a building description into an error-free EnergyPlus model for the iUnit modular building at the National Renewable Energy Laboratory. The effectiveness of our workflow surpasses: 1) naive prompt engineering, 2) other LLM-based workflows, and 3) manual modeling, in terms of accuracy, reliability, and time efficiency. The paper concludes with a discussion on the interplay between foundational models and LLM agent planning design, advocating for the use of fine-tuned, specialized models to advance this field.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models With 3D Diffusion Models

Earth system models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low-cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low-cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio-temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.

54 ENVIRONMENTAL SCIENCES↗