Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Optimization”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

VA EDH Advanced Software Pipeline Framework Report: Enhancing Automation and Scalability

The VA Environmental Determinants of Health (EDH) Advanced Software Pipeline Framework is designed to enhance the efficiency, scalability, and security of geospatial data processing workflows. This framework integrates modern data orchestration and containerization technologies, including Prefect for workflow automation, Docker for containerization, and PostgreSQL/PostGIS for geospatial data storage and analysis. It ensures standardized, reproducible, and automated data processing, supporting VA objectives related to substance use risk assessment and recovery research. The pipeline addresses key scalability and performance challenges through horizontal and vertical scaling, high-performance computing (HPC) integration, parallel processing, task caching, and dynamic resource allocation. These optimizations improve throughput and reduce latency, allowing the system to efficiently manage large and complex datasets. Additionally, security and compliance measures—such as data encryption (SSL), Role-Based Access Control (RBAC), and adherence to GDPR and HIPAA standards—safeguard sensitive information throughout data transmission and storage. A key implementation of this framework includes the automation of shelter list geolocation workflows, ensuring that up-to-date data is readily available for VA decision-making. Lessons learned from this project include the transition from in-memory processing to incremental storage writes, improving resource management and reliability. Future enhancements aim to expand automation, integrate AI-driven anomaly detection, and incorporate high-performance computing resources. This framework provides a scalable, secure, and adaptable solution for managing geospatial datasets, reinforcing the VA’s ability to support clinical and strategic initiatives through data-driven decision-making.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Holistic energy analysis method for thermal management architectures of data centers

Modern high-performance computing (HPC) data centers (DCs), particularly those supporting energy-intensive artificial intelligence (AI) workloads, face escalating thermal management challenges that degrade performance through thermal throttling and drive up cooling power consumption and operational costs. To address this challenge, many have developed a wide variety of thermal management solutions (single-phase, two-phase, direct, indirect, hybrid, and more) which attempt to cool HPC DCs effectively while attempting to minimize overall system power consumption. However, the analysis of these solutions and methods to effectively compare one with another is lacking. Overall power usage effectiveness (PUE) and total-power usage effectiveness (TUE) provide a metric to quantify power consumption but fail to identify components in the system which require further optimization. To address this, we propose a holistic analytical framework – the waterfall diagram (WFD) – which leverages a waterfall chart methodology, offering a comprehensive visualization of both the thermal management system loop and heat flow pathways from individual server components to the outdoor ambient. Use of the WFD enables graphical estimations of power efficiency and cooling performance across each component of a DC cooling system and complements Sankey-style energy flow visualizations by additionally resolving stage-wise temperature changes and incremental TUE contributions. The framework is used in conjunction with simulation-based approaches, to conduct a detailed pressure drop and flow distribution analysis aimed at identifying the optimal coolant distribution architecture for a single-phase direct-to-chip water-cooled DC, which serves as the baseline for subsequent WFD analysis. Among the evaluated architectures, the 3 U modular coolant distribution architecture is found to demonstrate the best performance, considering minimal pressure drop and uniform flow distribution. In addition, TUE is calculated for each cooling loop component based on its associated pressure drop and corresponding pumping power, which are integrated into the WFD. This correlation between TUE and local temperature offers immediate insight into the power efficiency and thermal performance contributions of individual components, facilitating further development and optimization. Examples of WFD applications are presented under varying thermal loads and ambient conditions, demonstrating reasonable cooling strategies. Notably, the 3 U modular architecture maintains a consistent chip case temperature of 85°C, achieving a TUE of 1.016 at ambient temperature of 47°C, and a TUE of 1.026 at ambient temperature of 52°C. The WFD methodology provides an efficient, holistic, and streamlined framework for DC thermal management architecture assessment and enables design optimization which is important for addressing the thermal-fluidic energy challenges of current and next-generation DCs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against emerging, stealthy, or previously unseen threats. These conventional methods suffer from high false alarm rates and fail to adapt to the ever-evolving nature of network traffic, particularly in large-scale, decentralized environments where data volume, velocity, and variety are constantly increasing. This dissertation presents artificial intelligence (AI)-driven approaches to anomaly detection that leverage graphics processing unit (GPU)-enabled high-performance computing (HPC) platforms for processing massive network traffic data and monitoring the components of cyber-physical systems (CPS) for potentially hazardous conditions. The research advances several key contributions: (1) Designing efficient machine learning techniques for CPS condition monitoring and anomaly detection; (2) enabling federated learning (FL) frameworks that enable distributed detection while preserving data privacy and system resilience; (3) exploring graph-based methodologies combining graph neural networks (GNN) and graph machine learning (ML) approaches for the Internet of Things (IoT) and automotive network security, and (4) performing distributed edge computing optimizations that integrate FL with scalable technologies for reduced communication overhead. Through extensive experiments, these methodologies demonstrate that complex anomaly detection and condition monitoring tasks can be achieved while balancing computational efficiency and detection accuracy through fine-grained network information processing. The frameworks developed in this research establish a robust foundation for network anomaly detection, providing scalable, adaptive, and privacy-preserving solutions for safeguarding CPS and IoT networks in an increasingly interconnected digital landscape. The practical implications of these research findings are significant, as they can inform the development of next-generation network security systems and contribute to the protection of critical infrastructure against sophisticated cyber attacks.

Marfo, William↗
DOE OSTI2026

Intelligent Experiments through Real-Time AI: Fast Data Processing and Autonomous Detector Control for High-Energy Nuclear Experiments

The aim of this project is to develop software and hardware for fast real-time data processing and autonomous detector control and calibration for the sPHENIX and the future EIC experiments. Below summarizes Georgia Tech team efforts in the past year: 1. We developed a real-time clustering algorithm and FPGA-based pipeline architecture for processing fired pixel data from ALPIDE sensors in sPHENIX experiments. Our Columnar Clustering Co-Design introduces a hardware-aware, stream-friendly approach that segments pixel data by column pairs using a Column Pair Clustering (CPC) strategy, followed by Cluster Stitching to merge adjacent subclusters. Implemented in Vitis HLS, the pipeline comprises five stages—read-in, subclustering, stitching, analysis, and write-out—connected by tagged HLS streams with custom end-of-event signaling for robust synchronization. We designed a pipelined dataflow model optimized for throughput, low latency, and minimal buffering, enabling scalable clustering across events of arbitrary size. Our system maintains spatial precision via center-of-mass and shape key extraction and efficiently handles edge cases such as fragmented or nested clusters. Compared against DBSCAN in both software and hardware, our approach demonstrates competitive performance under FPGA constraints. 2. We also conducted a comprehensive algorithm-to-hardware co-design of connected component analysis tailored for sPHENIX experiments, focusing on real-time, low-latency processing using FPGAs and High-Level Synthesis (HLS). Starting from a Python-based particle tracking pipeline, the team translated the core logic—graph traversal via DFS and Union-Find—into an HLS-compatible C++ model, replacing dynamic memory and recursion with static arrays and pipelined control flow. The final design includes a fully streamed and dataflow-compatible Union-Find kernel optimized across five iterations, incorporating loop pipelining, array partitioning, AXI/FIFO interface tuning, and function flattening. Experimental results show up to 14.8× speedup over the CPU baseline, reducing per-graph latency to 1.58 μs and demonstrating strong resource efficiency with only ~7k LUTs and zero BRAM usage. The design maintains functional correctness against the Python reference using a Python-based C-simulation framework and Mean Squared Error metrics. This work validates the potential of HLS-driven FPGA designs for edge-level HEP data acquisition, laying a scalable foundation for future integration with real-time detector pipelines and multi-graph processing systems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Quantum Routing and Entanglement Dynamics Through Bottlenecks

To implement arbitrary quantum circuits in architectures with restricted interactions, one may effectively simulate all-to-all connectivity by routing quantum information. We consider the entanglement dynamics and routing between two regions only connected through an intermediate “bottleneck” region with few qubits. In such systems, where the entanglement rate is restricted by a vertex boundary rather than an edge boundary of the underlying interaction graph, existing results such as the small incremental entangling theorem give only a trivial constant lower bound on the routing time (the minimum time to perform an arbitrary permutation). We significantly improve the lower bound on the routing time in systems with a vertex bottleneck. Specifically, for any system with two regions 𝐿,𝑅 with 𝑁 𝐿 ,𝑁 𝑅 qubits, respectively, coupled only through an intermediate region 𝐶 with 𝑁 𝐶 qubits, for any 𝛿 > 0 we show a lower bound of Ω⁢(𝑁$^{1−𝛿}_{𝑅}$/√𝑁 𝐿⁢ 𝑁 𝐶 ) on the Hamiltonian quantum routing time when using piecewise time-independent Hamiltonians, or time-dependent Hamiltonians subject to a smoothness condition. We also prove an upper bound on the average amount of bipartite entanglement between 𝐿 and 𝐶,𝑅 that can be generated in time 𝑡 by such architecture-respecting Hamiltonians in systems constrained by vertex bottlenecks, improving the scaling in the system size from 𝑂⁡(𝑁 𝐿⁢ 𝑡) to 𝑂⁡(√𝑁 𝐿⁢ 𝑡). As a special case, when applied to the star graph (i.e., one vertex connected to 𝑁 leaves), we obtain an Ω⁡(√𝑁 1−𝛿 ) lower bound on the routing time and on the time to prepare 𝑁/2 Bell pairs between the vertices. We also show that, in systems of free particles, we can route optimally on the star graph in time Θ⁡(√𝑁) using Hamiltonian quantum routing, obtaining a speedup over gate-based routing, which takes time Θ⁡(𝑁).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Prime Time for Model-Predictive Control? Assessing the Technical and Market Readiness of Advanced Controls in Buildings

Despite three decades of extensive research and field testing that have consistently validated the benefits of Model Predictive Control (MPC) in building applications, the technology has seen limited market adoption. This paper evaluates the readiness of MPC for widespread deployment, showcases recent demonstrations and field tests across diverse building types, including residential, small commercial, large commercial, and campus settings. Our results demonstrate that MPC can optimize system operations to achieve load shifting, minimize curtailment of on-site generation, and reduce energy costs by up to 80 %, while maintaining or improving occupant comfort. We also show that MPC can effectively control large assets, such as MW-sized thermal storage systems, and respond to dynamic pricing signals. However, achieving scale remains difficult due to labor-intensive workflows, reliance on a “PhD-in-the-loop” for MPC design and maintenance, susceptibility to fragile data infrastructure, and persistent workforce education and acceptance barriers. To bridge this gap, we outline a transition from bespoke, labor intensive prototypes toward streamlined, segment-targeted deployment strategies that leverage model templates, semantic tools, and generative AI. By automating control configuration and reducing engineering effort, these recommendations provide a pathway for transforming successful research demonstrations into scalable, market ready solutions for MPC-based controls.

Pritoni, Marco↗
DOE OSTI2025

From Electronic Structure to Ion Transport: Photoelectron Spectroscopy and Molecular Dynamics Simulations Reveal the Role of Anions in Lithium Battery Electrolytes

Electrolyte anions are pivotal for lithium battery performance, yet their fundamental electronic structural properties are not well understood. In this work, we employ a combination of negative-ion photoelectron spectroscopy (NIPES), ab initio calculations, and molecular dynamics (MD) simulations to investigate the electronic structures of three representative electrolyte anions. This multiscale approach enables us to elucidate how their intrinsic electronic properties govern anion–solvent interactions in gas-phase clusters, as well as lithium-ion (Li + ) solvation structures and ion transport behavior in the condensed phase. NIPES reveals that difluoro(oxalato)borate (DFOB – ), bis(fluorosulfonyl)imide (FSI – ), and bis(oxalato)borate (BOB – ) all exhibit high electron binding energies, with vertical/adiabatic detachment energies increasing from DFOB – (6.09/5.70 eV) to FSI – (6.80/6.10 eV) to BOB – (6.82/6.40 eV), correlating with enhanced oxidation stability. Ab initio calculations reveal that DFOB – /FSI – –solvent complexes bind Li + ∼ 10 kcal/mol stronger than BOB – series, aligning with the strength of a Li + –anion model. DFOB – exhibits pronounced charge localization on both oxygen and fluorine atoms, enabling their involvement in Li + coordination. In contrast, fluorine atoms in FSI – are largely electron-depleted and remain excluded from direct Li + binding. MD simulations further demonstrate that LiDFOB and LiFSI systems exhibit Li + diffusion coefficients three and five times higher than those of LiBOB across four common solvents. Notably, LiFSI salt in acetonitrile (AN) exhibits the fastest Li + diffusion among 12 electrolyte systems, highlighting the synergistic effect of FSI – and AN in promoting ion mobility. In conclusion, these findings provide a molecular-level understanding of the critical roles of anion and its microsolvation in optimizing Li + diffusion dynamics, once again emphasizing the positioning of FSI – and DFOB – as prime candidates for next-generation electrolytes.

25 ENERGY STORAGE↗
DOE OSTI2025

I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey

Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Neural operator transformers capture bifurcating drift-wave turbulence in fusion plasma simulations

Self-consistent modeling of turbulence-driven transport is critical for optimizing confinement in magnetically confined fusion plasmas, such as tokamaks and stellarators. In particular, capturing the long-term co-evolution of turbulence, flow, and background plasma profiles remains computationally challenging. Direct numerical simulation of these multiscale, highly nonlinear processes is often demanding and impractical for real-time control or design optimization. To address this bottleneck, we investigate transformer-based neural operator partial differential equation surrogates for emulating the dynamics of drift-wave turbulence bifurcation mediated by zonal flows, using the modified Hasegawa–Wakatani (MHW) model as a prototypical system. We find that the finetuned neural operator model has excellent performance in capturing the multi-spatiotemporal-scales of MHW turbulence bifurcation and is robust to testing on rare and out-of-distribution dynamics. Specifically, we demonstrate that a single unified model accurately predicts both quasi-steady-state turbulence and a wide range of dynamical transition processes, such as nonlinear saturation, spontaneous suppression of turbulence, and the emergence of macroscopic zonal flows, over time horizons vastly exceeding the local turbulence correlation time. This computationally efficient approach establishes a strong foundation for fast, AI-based modeling of complex, multiscale phenomena in magnetized fusion plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Advancing the Performance of Anion Exchange Membrane Electrolysis by Employing a Powder-Based Ionomer during Anode Catalyst Layer Fabrication

The performance of anion exchange membrane water electrolysis (AEMWE) can be significantly improved by utilizing powdered ionomers during the fabrication of the anode catalyst layer (CL) to modify the CL properties. When comparing powdered ionomers to dispersed ionomers across various catalysts including cobalt oxide (Co 3 O 4 ), nickel−iron oxide (NiFe 2 O 4 ), and iridium oxide (IrO 2 ) the anode fabricated with powdered ionomers demonstrates improved performance in polarization curves, enhanced charge transfer kinetics, and reduced ohmic and transport losses, as evidenced by voltage breakdown and electrochemical impedance spectroscopy analyses. Optimal performance is achieved using a Co 3 O 4 catalyst with a 10 wt % powdered ionomer via the catalystcoated substrate method. Microscopy analyses reveal that electrodes formed with powdered ionomers during fabrication exhibit a more uniform catalyst and ionomer distribution, increased porosity with smaller pore areas, improved electronic conduction with less catalyst agglomeration isolated by a nonconductive ionomer, and enhanced interfacial contact with the membrane and transport layer. These findings highlight that ionomers in a powdered form can promote beneficial properties and are a promising approach to improving AEMWE efficiency.

08 HYDROGEN↗
DOE OSTI2026

Techno-Economic Assessment of Data Center Load Demand Powered by Small Modular Reactors and Distributed Energy Resources

The rapid increase in data center energy demand, driven by AI and large-scale data processing, poses significant challenges to global energy infrastructure. Data centers require substantial and reliable energy for continuous operations and high-performance computing. Current electrical grids face issues such as transmission bottlenecks and aging infrastructure, making it difficult to meet these demands. Integrating inverter-based-resources (IBRs) like solar and wind presents both opportunities and challenges due to their intermittent nature. Small Modular Reactors (SMRs) offer a promising solution with their enhanced safety, modularity, reliability, and scalability, providing consistent base load power ideal for data center operations. This study presents a comprehensive techno-economic assessment of powering data center load demand using a combination of SMRs and IBRs with grid-connected and islanded mode. This study utilized Idaho National Laboratory’s (INL) HPC data center hourly load profiles and Xendee microgrid optimization platform to conduct the analysis. In this configuration, SMRs serves as the primary base load power source, consistently providing a steady supply of electricity necessary to meet the minimum load demand of the data center with support from the IBRs. Key performance indicators such as Levelized Cost of Electricity (LCOE), Net Present Value (NPV) has been calculated to assess the economic feasibility. The findings from this research will underscore the strategic benefits of integrating SMR plant with DERs – particularly for critical infrastructure load such as data centers.

14 - SOLAR ENERGY↗
DOE OSTI2025

Fully‐Printed Ion Sensor Arrays for Measuring Agricultural Nitrogen and Potassium Concentrations Using Nernstian and AI Models

Abstract The chemical composition of growing media is a key factor for plant growth, impacting agricultural yield and sustainability. However, there is a lack of affordable chemical sensors for ubiquitous nutrient ion monitoring in agricultural applications. This work investigates using fully printed ion‐sensor arrays to measure the concentrations of nitrate, ammonium, and potassium in mixed‐electrolyte media. Ion sensor arrays composed of nitrate, ammonium, and potassium ion‐selective electrodes and a printed silver‐silver chloride (Ag/AgCl) reference electrode are fabricated and characterized in aqueous solutions in a range of concentrations that encompass what is typical for agricultural growing media (0.01 m m –1 m ). The sensors are also tested in mixed‐electrolyte solutions of NaNO 3 , NH 4 Cl, and KCl of varying concentrations, and the recorded potentials are input into Nernstian and artificial neural network models to compare the prediction accuracy of the models against ground truth. The artificial neural network models demonstrated higher accuracy over the Nernstian model, and the model using only ion‐sensor inputs is 7.5% more accurate than the Nernstian model under the same conditions. By enabling more precise and efficient fertilizer application, these sensor arrays coupled to computational models can help increase crop yields, optimize resource use, and reduce environmental impact.

Goodrich, Payton [University of California Berkele↗
DOE OSTI2025

Certifying almost all quantum states with few single-qubit measurements

Certifying that an n -qubit state synthesized in the laboratory is close to a given target state is a fundamental task in quantum information science. However, existing rigorous protocols applicable to general target states have potentially prohibitive resource requirements in the form of either deep quantum circuits or exponentially many single-qubit measurements. Here we prove that almost all n -qubit target states, including those with exponential circuit complexity, can be certified from only O ( n 2 ) single-qubit measurements. Given access to the target state’s amplitudes, our protocol requires only O ( n 3 ) classical computation. This result is established by a technique that relates certification to the mixing time of a random walk. Our protocol has applications for benchmarking quantum systems, for optimizing quantum circuits to generate a desired target state and for learning and verifying neural networks, tensor networks and various other representations of quantum states using only single-qubit measurements. We show that such verified representations can be used to efficiently predict highly non-local properties of a synthesized state that would otherwise require an exponential number of measurements on the state. We demonstrate these applications in numerical experiments with up to 120 qubits and observe an advantage over existing methods such as cross-entropy benchmarking.

information theory and computation↗
DOE OSTI2025

Designing Antifouling and Antimicrobial Interfaces: Structural Characterization using CryoEM, Automated Microscopy, and AI Image Segmentation

The design of functionalized surfaces for interactions with biological systems is critical across sectors such as healthcare, energy, and agriculture. Tailoring materials for specific applications, such as antifouling and antimicrobial surfaces, demands a comprehensive understanding of topology and chemistry across multiple length and time scales on both biological and materials systems. This work presents the development and characterization of nanostructured surfaces with controlled topographies and chemistries that enhance bacterial membrane disruption, reduce biofilm formation, and improve antimicrobial and antifouling capabilities. Two specific use cases will be presented - the use of cellulose nanocrystals (CNCs) for bacterial growth inhibition and the development of antifouling surfaces to prevent protein and bacterial adsorption [1-4]. By leveraging large language models (LLMs) for image segmentation and training [5], we enable automated analysis of terabyte-scale cryogenic electron microscopy (cryoEM) datasets. This analysis provides statistical insights into the biotic/abiotic interface and facilitates automated electron microscopy experiments to mitigate time and dose. The integration of cryogenic electron tomography (cryoET) and cryogenic focused ion beam (cryoFIB) milling enables high-resolution, near-native-state imaging and 3D reconstructions of bio/material interfaces [6]. Orthogonal characterization techniques and computational modeling further enhances our understanding, offering a robust platform for the design and optimization of next-generation functional surfaces [7].

Williams, Alexis [ORNL] (ORCID:0000000252835822)↗
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 OSTI2025

A Preferences Corpus and Annotation Scheme for Human-Guided Alignment of Time-Series GPTs

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings.

DPO↗
DOE OSTI2025

EcoBOT: an AI/ML enabled automated phenotyping capability for model plants

Introduction: Advances in automation and AI/ML offer new opportunities for plant science, including design, modeling, and analysis. This study aimed to develop an automated platform for researching small model plants under axenic conditions and integrate it with AI/ML tools. Methods: The EcoBOT platform was developed, which consists of sterile containers (EcoFABs) for growing plants and imaging for monitoring plant growth and health. Brachypodium distachyon was grown on the EcoBOT, and its response to nutrient limitation and copper stress was evaluated. Results: The results showed that Brachypodium distachyon grown in the EcoBOT maintained sterility and responded to nutrient limitation and copper stress. Analysis of over 6,500 root and shoot images revealed varying sensitivity and response rates to copper. Bayesian Optimization was used to improve model accuracies relating copper concentrations to plant biomass via sequential experiments, resulting in a >30% improvement. Discussion: The findings of this study demonstrate the potential of the EcoBOT platform for researching plant responses to environmental factors. Future experiments could focus on relating other chemical stresses and microbial interactions to create generalized models of plant responses.

AI image analysis↗
DOE OSTI2024

Efficient Mixed-Precision Matrix Factorization of the Inverse Overlap Matrix in Electronic Structure Calculations with AI-Hardware and GPUs

In recent years, a new kind of accelerated hardware has gained popularity in the artificial intelligence (AI) community which enables extremely high-performance tensor contractions in reduced precision for deep neural network calculations. In this article, we exploit Nvidia Tensor cores, a prototypical example of such AI-hardware, to develop a mixed precision approach for computing a dense matrix factorization of the inverse overlap matrix in electronic structure theory, S –1 . This factorization of S –1 , written as ZZT = S –1 , is used to transform the general matrix eigenvalue problem into a standard matrix eigenvalue problem. Here we present a mixed precision iterative refinement algorithm where Z is given recursively using matrix–matrix multiplications and can be computed with high performance on Tensor cores. To understand the performance and accuracy of Tensor cores, comparisons are made to GPU-only implementations in single and double precision. Additionally, we propose a nonparametric stopping criteria which is robust in the face of lower precision floating point operations. The algorithm is particularly useful when we have a good initial guess to Z, for example, from previous time steps in quantum-mechanical molecular dynamics simulations or from a previous iteration in a geometry optimization.

36 MATERIALS SCIENCE↗