Search NASA⌕ Search

SEARCH · Search NASA

Results for “Continual Learning”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

PDF Entity Annotation Tool (PEAT)

While different text mining approaches – including the use of Artificial Intelligence (AI) and other machine based methods - continue to expand at a rapid pace, the tools used by researchers to create the labeled datasets required for training, modeling, and evaluation remain rudimentary. Labeled datasets contain the target attributes the machine is going to learn; for example, training an algorithm to delineate between images of a car or truck would generally require a set of images with a quantitative description of the underlying features of each vehicle type. Development of labeled textual data that can be used to build natural language machine learning models for scientific literature is not currently integrated into existing manual workflows used by domain experts. Published literature is rich with important information, such as different types of embedded text, plots, and tables that can all be used as inputs to train ML/natural language processing (NLP) models, when extracted and prepared in machine readable formats. Currently, both normalized data extraction of use to domain experts and extraction to support development of ML/NLP models are labor intensive and cumbersome manual processes. Automatic extraction of data and information from formats such as PDFs that are optimized for layout and human readability, not machine readability. The PDF (Portable Document Format) Entity Annotation Tool (PEAT) was developed with the goal of allowing users to annotate publications within their current print format, while also allowing those annotations to be captured in a machine-readable format. One of the main issues with traditional annotation tools is that they require transforming the PDF into plain text to facilitate the annotation process. While doing so lessens the technical challenges of annotating data, the user loses all structure and provenance that was inherent in the underlying PDF. Also, textual data extraction from PDFs can be an error prone process. Challenges include identifying sequential blocks of text and a multitude of document formats (multiple columns, font encodings, etc.). As a result of these challenges, using existing tools for development of NLP/ML models directly from PDFs is difficult because the generated outputs are not interoperable. We created a system that allows annotations to be completed on the original PDF document structure, with no plain text extraction. The result is an application that allows for easier and more accurate annotations. In addition, by including a feature that grants the user the ability to easily create a schema, we have developed a system that can be used to annotate text for different domain-centric schemas of relevance to subject matter experts. Different knowledge domains require distinct schemas and annotation tags to support machine learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Leverage modern artificial intelligence (AI) enabled systems for waste reduction

Manufacturing industries continue to face challenges in reducing waste, as upstream strategies such as source reduction and product redesign require a deeper understanding of processes compared to conventional recycling methods. Recent advancements in artificial intelligence (AI) and machine learning (ML) have opened new opportunities to integrate modern computational techniques with traditional waste minimization strategies. This paper explores AI-enabled approaches for product redesign, source reduction, and recycling that can significantly reduce waste generation while improving efficiency and sustainability. AI-driven material substitution and lightweighting in product design enable discovery of novel materials with optimized properties, reducing waste without compromising performance. Reinforcement learning models optimize process parameters, raw material specifications, and machine sequencing to minimize production losses, while Industrial Internet of Things (IIoT) systems paired with AI analytics enhance real-time waste tracking, predictive maintenance, and quality inspection. Furthermore, AI-based demand forecasting and production planning reduce overproduction and excess inventory, as demonstrated in industrial applications. In recycling, ML-powered pattern recognition and robotic sorting technologies achieve higher accuracy in waste segregation, directly improving recycling efficiency. Complementary solutions such as smart bins and AI-enabled waste pickup scheduling optimize collection logistics, reducing both costs and emissions. Although implementation requires upfront investment in infrastructure and training, the long-term benefits include higher material efficiency, reduced waste, improved product quality, and stronger sustainability outcomes across the supply chain. By leveraging AI-enabled systems, manufacturers can align waste minimization efforts with circular economy principles, creating scalable solutions for both industry and society.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

U-Surf: a global 1 km spatially continuous urban surface property dataset for kilometer-scale urban-resolving Earth system modeling

High-resolution urban climate modeling has faced substantial challenges due to the absence of a globally consistent, spatially continuous, and accurate dataset to represent the spatial heterogeneity of urban surfaces and their biophysical properties. This deficiency has long obstructed the development of urban-resolving Earth system models (ESMs) and ultra-high-resolution urban climate modeling, over large domains. Here, we present U-Surf, a first-of-its-kind 1 km resolution present-day (circa 2020) global continuous urban surface parameter dataset. Using the urban canopy model (UCM) in the Community Earth System Model as a base model for satisfying dataset requirements, U-Surf leverages the latest advances in remote sensing, machine learning, and cloud computing to provide the most relevant urban surface biophysical parameters, including radiative, morphological, and thermal properties, for UCMs at the facet and canopy level. Generated using a systematically unified workflow, U-Surf ensures internal consistency among key parameters, making it the first globally coherent urban canopy surface dataset. U-Surf significantly improves the representation of the urban land heterogeneity both within and across cities globally; provides essential, high-fidelity surface biophysical constraints to urban-resolving ESMs; enables detailed city-to-city comparisons across the globe; and supports next-generation kilometer-resolution Earth system modeling across scales. U-Surf parameters can be easily converted or adapted to various types of UCMs, such as those embedded in weather and regional climate models, as well as air quality models. The fundamental urban surface constraints provided by U-Surf can also be used as features for machine learning models and can have other broad-scale applications for socioeconomic, public health, and urban planning contexts. We expect U-Surf to advance the research frontier of urban system science, climate-sensitive urban design, and coupled human–Earth systems in the future. The dataset is publicly available at https://doi.org/10.5281/zenodo.11247598 (Cheng et al., 2024).

Cheng, Yifan [Univ. of Illinois at Urbana-Champaig↗
DOE OSTI2025

Digital Safety Analysis for Small Modular Nuclear Reactors (SMRs)

A Documented Safety Analysis (DSA) is a Department of Energy (DOE) construct that defines the extent to which a nuclear facility can be operated safely. It includes a description of hazards, safe boundaries, and hazard controls. The authors assert that a Digital Safety Analysis (DgSA) is far superior to a legacy DSA for several reasons: • The underling database is structured such that it is possible to perform a comprehensive design review and safety analysis by iterating systematically across a hierarchy of linked objects versus a redundant and spotty review by entities of various abilities under unknown resource and schedule constraints. • The analysis of a new design can discover elements that are similar to elements in previous designs. The discovery of similarities is made possible by using the same structure for the underlying database for each new DgSA. The “prior learning” from previous designs is then applied automatically to new designs. • Outputs from the DgSA are from a single source to ensure consistency among various views of the same information. After the DgSA is released, the continued use of a single source implements a configuration management program to ensure consistency between the design basis, the design, the built system, and system procedures. • The development of the DgSA is agile in that any change in a linked object triggers an analysis of impacts on other linked objects and updates of linked objects are made accordingly. After the DgSA is released, the continued maintenance of these links and objects automates the “unreviewed safety question” process.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Conditional distribution estimation of building characteristics with diffusion models for urban energy modeling

Understanding current energy consumption behavior in communities is critical for informing future energy use decisions and enabling efficient energy management. Urban energy models, which are used to simulate these energy use patterns, require large datasets with detailed building characteristics for accurate outcomes. However, such detailed characteristics at the individual building level are often unknown and costly to acquire, or unavailable. Through this work, we propose using a generative modeling approach to generate realistic building attributes to fill in the data gaps and finally provide complete characteristics as inputs to energy models. Our model learns complex, building-level patterns from training on a large-scale residential building stock model containing 2.2 million buildings. We employ a tabular diffusion-based framework that is designed to handle heterogeneous (discrete and continuous) features in tabular building data, such as occupancy, floor area, heating, cooling, and other equipment details. We develop a capability for conditional diffusion, enabling the imputation of missing building characteristics conditioned on known attributes. We conduct a comprehensive validation of our conditional diffusion model, firstly by comparing the generated conditional distributions against the underlying data distribution, and secondly, by performing a case study for a Baltimore residential region, showing the practical utility of our approach. Our work is one of the first to demonstrate the potential of generative modeling to accelerate building energy modeling workflows.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Vision Foundation Models in Remote Sensing: A survey

Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.

data models↗
DOE OSTI2024

Towards in-situ certification of additively manufactured parts: the vital roles of physics-based and data-driven models

Certifying additively manufactured (AM) parts in-situ at the completion of a build is an enticing prospect, as it can help reduce the high costs associated with post-build testing and evaluation. However, achieving this goal presents significant challenges that may keep it aspirational for the foreseeable future. Nonetheless, incremental progress can pave the way forward. A critical aspect of in-situ certification involves continuous quality checking due to the random nature of the AM process and the difficulties in detecting defects or anomalies once layers are built over. While real-time in-situ monitoring strategies assisted by machine learning (ML) play a pivotal role in auditing part quality, they must ideally be supported by real-time (or near real-time) adaptive process control enabled by ML-assisted decision-making. By analyzing in-situ monitoring data in real-time (or near real- time) to dynamically adjust manufacturing parameters, such intervention can ensure AM parts are built to meet stringent certification standards. This can be achieved virtually by using high-fidelity performance models for the physical testing and evaluation tasks. In this short editorial, we discuss the key contributions made by data-driven and physics-based models in providing intelligence to the monitoring and process control tasks underpinning in-situ certification and in the simulation of the build’s performance under test and service conditions. While our focus lies in metal AM, the concepts discussed here are also relevant to other AM processes.

: In-situ monitoring↗
DOE OSTI2025

Evaluating Cloud Properties at Scott Base: Comparing Ceilometer Observations With ERA5, JRA55, and MERRA2 Reanalyses Using an Instrument Simulator

This study compares CL51 ceilometer observations made at Scott Base, Antarctica, with statistics from the ERA5, JRA55, and MERRA2 reanalyses. To enhance the comparison we use a lidar instrument simulator to derive cloud statistics from the reanalyses which account for instrumental factors. The cloud occurrence in the three reanalyses is slightly overestimated above 3 km, but displays a larger underestimation below 3 km relative to observations. Unlike previous studies, we see no relationship between relative humidity and cloud occurrence biases, suggesting that the cloud biases do not result from the representation of moisture. We also show that the seasonal variation of cloud occurrence and cloud fraction, defined as the vertically integrated cloud occurrence, are small in both the observations and the reanalyses. We also examine the quality of the cloud representation for a set of weather states derived from ERA5 surface winds. The variability associated with grouping cloud occurrence based on weather state is much larger than the seasonal variation, highlighting weather state is a strong control of cloud occurrence. All the reanalyses continue to display underestimates below 3 km and overestimates above 3 km for each weather state. But the variability in ERA5 statistics matches the changes in the observations better than the other reanalyses. We also use a machine learning scheme to estimate the quantity of supercooled liquid water cloud from the ceilometer observations. Ceilometer low-level supercooled liquid water cloud occurrences are considerably larger than values derived from the reanalyses, further highlighting the poor representation of low-level clouds in the reanalyses.

54 ENVIRONMENTAL SCIENCES↗
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 OSTI2024

Optimal Coordination of Electric Vehicles for Grid Services using Deep Reinforcement Learning

Recent research has shown the effectiveness of reinforcement learning (RL) in coordinating electric vehicles (EVs) with vehicle-to-grid capabilities for grid services. However, many of these studies rely on lookup table and deep Q-network techniques, which can be impractical when dealing with continuous states and actions. In addition, existing RL designs inadequately account for battery aging effects, EV user satisfaction, uncertain departure and arrival time, and trip distance, which may compromise effective coordination. This paper aims to bridge these gaps by developing an innovative deep deterministic policy gradient-based RL framework for optimal coordination of EVs. Case studies were carried out using a test system with 100 EVs, and numerical analysis results showed that the proposed RL framework can effectively coordinate EVs to maximize economic benefits and user satisfaction while ensuring the expected battery lifespan.

Das, Avijit↗
DOE OSTI2025

Deep potential molecular dynamics simulations of ion-enhanced etching of silicon by atomic chlorine

The continued development of plasma-assisted processing techniques requires a fundamental understanding of plasma-surface interactions. Molecular dynamics (MD) simulations have been employed to complement experimental studies and better understand the properties of such systems. Recently, machine learning (ML) methods have enabled the development of ab initio-based interatomic potentials, which can be generalized to complex combinations of multiple atom types. In this work, we use ML potentials developed using the Deep Potential Molecular Dynamics (DeepMD) framework to provide a model of ion-enhanced etching of Si by Cl atoms. We demonstrate the importance of proper selection of the training data set to the accuracy of the DeepMD model and compare our results to MD results using empirical potentials, as well as to experimental measurements. Exposure of undoped Si at 300 K to thermal Cl atoms yields a steady-state Cl coverage of 1.25 monolayers, which is slightly lower than the value obtained in previous experimental studies. Predictions of Si etch yields by simultaneous Cl atom and Ar + ion impacts as a function of ion energy, neutral to ion flux ratio, and angle of incidence of the ions are in reasonably good agreement with classical MD results and experimental measurements. Finally, etch yields and SiCl x mixed layer thicknesses during simultaneous bombardment of the Si(100) surface by Cl atoms and Cl + ions are in good agreement with experimental data. In conclusion, the present work is a necessary condition for the extension of the DeepMD procedure to more complex systems of interest in plasma-surface interactions.

Artificial neural networks↗
DOE OSTI2026

FIB-ToF-SIMS characterization of irradiated U-10Zr

Post-irradiation examination (PIE) is critical for the performance assessment and qualification of nuclear fuels. Secondary ion mass spectrometry (SIMS) is a powerful materials characterization technique that allows for elemental and isotopic mapping with a depth resolution greater than EDS and EPMA. However, it has not yet been applied to PIE of metallic nuclear fuel. Here, in this work, we characterize an fast neutron spectrum irradiated U-10Zr fuel sample using a time-of-flight SIMS (ToF-SIMS) system connected to a FIB/SEM system, which allows for flexible sample analysis compared to a dedicated ToF-SIMS instrument. Analysis of the resulting hyperspectral micrograph data was aided by the development of an unsupervised machine learning (ML) algorithm that iterates on existing methods to segment the 3D micrographic datasets based on the similarity of mass spectra. The results showed that the FIB-ToF-SIMS instrument was potentially capable of spatially resolving closed fission gas bubbles in 3D by continued ion sputtering of the analyzed volume. Additionally, the ML algorithm proved useful in revealing the chemical segregation of light fission products (those with an atomic mass between approximately 85–105 amu, such as ruthenium and rhodium) plus matrix zirconium, heavy fission products (those with an atomic mass between approximately 135–150 amu, such as the lanthanides) and uranium. Future studies are planned to conduct FIB-ToF-SIMS analysis on more irradiated U-Zr samples to study the constituent redistribution.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Pre-training Vision Models for the Classification of Alerts from Wide-field Time-domain Surveys

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

MINERvA s Open Data Product: A First for Neutrino Data Preservation

Access to information on neutrino nucleus interactions is critical to the success of all neutrino oscillation experiments. MINERvA's rich dataset covers a range of energies and nuclei unique amongst experiments, and as such is critical to the community in building the important shared knowledge needed to unravel the mysteries of the neutrino. In particular, its dataset provides the greatest statistical coverage in in the range of neutrino energies pertinent for DUNE until DUNE's near detector begins operation. Historically, such significant datasets in neutrino physics have been preserved primarily through their published results. While meaningful and useful, this limits the ability to explore the data to its fullest extent as new perspectives continue to form. MINERvA has undertaken a major effort to break this trend and preserve its data in a format to be as analyzable as possible from outside the collaboration. This has culminated in the officially-released MINERvA Open Data Product for the community to take advantage of and utilize. Maintaining direct access to the dataset in an analyzable form will allow new insights to continue to be extracted indefinitely. This talk will cover the contents of this product, the information included (and excluded), the tools provided to utilize the product effectively, the support MINERvA intends to provide in its use, and some lessons learned through the process.

Last, David [Rochester U.] (ORCID:0000000245147183↗
DOE OSTI2025

Super-Resolution for Renewable Energy Resource Data with Wind from Reanalysis Data and Application to Ukraine

With a potentially increasing share of the electricity grid relying on wind to provide generating capacity and energy, there is an expanding global need for historically accurate, spatiotemporally continuous, high-resolution wind data. Conventional downscaling methods for generating these data based on numerical weather prediction have a high computational burden and require extensive tuning for historical accuracy. In this work, we present a novel deep learning-based spatiotemporal downscaling method using generative adversarial networks (GANs) for generating historically accurate high-resolution wind resource data from the European Centre for Medium-Range Weather Forecasting Reanalysis version 5 data (ERA5). In contrast to previous approaches, which used coarsened high-resolution data as low-resolution training data, we use true low-resolution simulation outputs. We show that by training a GAN model with ERA5 as the low-resolution input and Wind Integration National Dataset Toolkit (WTK) data as the high-resolution target, we achieved results comparable in historical accuracy and spatiotemporal variability to conventional dynamical downscaling. This GAN-based downscaling method additionally reduces computational costs over dynamical downscaling by two orders of magnitude. We applied this approach to downscale 30 km, hourly ERA5 data to 2 km, 5 min wind data for January 2000 through December 2023 at multiple hub heights over Ukraine, Moldova, and part of Romania. With WTK coverage limited to North America from 2007–2013, this is a significant spatiotemporal generalization. The geographic extent centered on Ukraine was motivated by stakeholders and energy-planning needs to rebuild the Ukrainian power grid in a decentralized manner. This 24-year data record is the first member of the super-resolution for renewable energy resource data with wind from the reanalysis data dataset (Sup3rWind).

17 WIND ENERGY↗
DOE OSTI2026

WM26 Paper Multi-Robot Collaboration for Hazardous Environments

Hazardous nuclear and industrial facilities are rarely designed for robots. Work in these domains demand precise manipulation and robust mobility in cluttered, constrained spaces where off-the-shelf platforms struggle and “one-size-fits-all” machines become costly and complex. Idaho National Laboratory (INL) is developing an autonomous, multi-robot inspection system that coordinates task-specific platforms rather than relying on a single omni-tool robot. An electric truck serves as a power and compute hub for a custom manipulator co-developed with Florida International University (FIU), a commercial mini crawler, a pan–tilt–zoom camera, and a Nexxis Argus LiDAR mapping system. Working in concert, these robots generate spatial, radiation, and temperature maps of the pit environments at the Hanford Waste Tank Farms. These systems will capture visual records and environmental telemetry to allow for analysis post inspection. The system architecture uses Robot Operating System 2 (ROS 2) for publish/subscribe integration, NVIDIA Isaac Sim and Unity for simulation and visualization, and algorithms such as NVBlox to fuse data into unified 3D overlays. This robot-agnostic approach reduces operator burden by enabling autonomy across heterogeneous platforms and lets each robot be used where it is strongest. Having autonomous functions means operators don’t have to fully control multiple different components. The ease of use could allow for more widespread adoption of advanced robotics at waste management sites that see continued use. By coordinating simpler, purpose-built mechanisms, the approach lowers design and manufacturing complexity, reduces capital risk in contaminated settings, and improves controllability for complex inspection and manipulation tasks. We present the architecture, early results, and lessons learned from building and deploying this coordinated multi-robot system, with the goal of accelerating safe, cost-effective adoption of advanced robotics at waste-management sites.

42 - ENGINEERING↗
DOE OSTI2025

Accelerating Discovery of Solid‐State Thin‐Film Metal Dealloying for 3D Nanoarchitecture Materials Design through Laser Thermal Gradient Treatment

Thin‐film solid‐state metal dealloying (thin‐film SSMD) is a promising method for fabricating nanostructures with controlled morphology and efficiency, offering advantages over conventional bulk materials processing methods for integration into practical applications. Although machine learning (ML) has facilitated the design of dealloying systems, the selection of key thermal treatment parameters for nanostructure formation remains largely unknown and dependent on experimental trial and error. To overcome this challenge, a workflow enabling high‐throughput characterization of thermal treatment parameters is demonstrated using a laser‐based thermal treatment to create temperature gradients on single thin‐film samples of Nb‐Al/Sc and Nb‐Al/Cu. This continuous thermal space enables observation of dealloying transitions and the resulting nanostructures of interest. Through synchrotron X‐ray multimodal and high‐throughput characterization, critical transitions and nanostructures can be rapidly captured and subsequently verified using electron microscopy. The key temperatures driving chemical reactions and morphological evolutions are clearly identified. While the oxidation may influence nanostructure formation during thin‐film treatment, the dealloying process at the dealloying front involves interactions solely between the dealloying elements, highlighting the availability and viability of the selected systems. Further, this approach enables efficient exploration of the dealloying process and validation of ML predictions, thereby accelerating the discovery of thin‐film SSMD systems with targeted nanostructures.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Machine learning-driven predictive resource management in complex science workflows

Here, the collaborative efforts of large communities in science experiments, often comprising thousands of global members, reflect a monumental commitment to exploration and discovery. Recently, advanced and complex data processing has gained increasing importance in science experiments. Data processing workflows typically consist of multiple intricate steps, and the precise specification of resource requirements is crucial for each step to allocate optimal resources for effective processing. Estimating resource requirements in advance is challenging due to a wide range of analysis scenarios, varying skill levels among community members, and the continuously increasing spectrum of computing options. One practical approach to mitigate these challenges involves initially processing a subset of each step to measure precise resource utilization from actual processing profiles before completing the entire step. While this two-staged approach enables processing on optimal resources for most of the workflow, it has drawbacks such as initial inaccuracies leading to potential failures and suboptimal resource usage, along with overhead from waiting for initial processing completion, which is critical for fast-turnaround analyses. In this context, our study introduces a novel pipeline of machine learning models within a comprehensive workflow management system, the Production and Distributed Analysis (PanDA) system. These models employ advanced machine learning techniques to predict key resource requirements, overcoming challenges posed by limited upfront knowledge of characteristics at each step. Accurate forecasts of resource requirements enable informed and proactive decision-making in workflow management, enhancing the efficiency of handling diverse, complex workflows across heterogeneous resources.

97 MATHEMATICS AND COMPUTING↗