AI-Driven Breakthroughs in Energy Systems from Vision to Design
Presentation conducted at the DOE booth at the AI Expo in Washington, DC, May 2024.
Weber, Justin↗
SEARCH · Engineering Papers
Results for “AI”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Rapid AI-based Dissection of Ashes using Raman and XRF Spectroscopy (RADAR-X)
Waste-to-energy (WTE) facilities incinerate ~35 million tons of municipal solid waste annually in the United States. The incineration process reduces the mass and the volume of the waste fraction by over 75 and 95%, respectively. The fraction left after incineration remains as ash residues and is referred to as WTE ash, compromising of bottom and fly ash. In the United States, ~10 million tons of WTE ashes are generated annually and predominantly landfilled because of the lack of secondary end-use pathways. This incurs a significant financial burden (landfilling costs) on U.S. WTE facilities and also results in the loss of materials to the landfill. The primary objective of this research is to understand better the elemental and mineralogical composition of WTE ashes from diverse origins and find composition dependent upcycling pathways for diverting these ashes from landfills. This primary objective was addressed through three research tasks –(Task I) An AI-led Multi-Modal Approach for Compositional Analysis, (Task II) Developing a Dissolution-Based Test for Real Time Analysis, and (Task III) Establishing composition-dependent end uses. The chemical composition of WTE ash is dependent on two factors, i.e., the input waste composition and the operational parameters of a WTE facility (combustion conditions). Amongst these two factors, the input waste composition will likely show spatial and temporal variation. As a result, the chemical composition of WTE ash will also fluctuate. To understand the spatial and temporal variation in WTE ash composition, in Task I, we collected 128 ash samples (62 bottom ash and 66 fly ash samples) from 11 WTE facilities located in 11 U.S. states and characterized them via X-ray Fluorescence, powder X-ray Diffraction, and Raman Spectroscopy. The findings from this extensive characterization work indicated that the key elements in WTE fly ashes are Ca, Cl (greater than 10 wt. %), Si, S, K, Zn ( between 1 and 10 wt. %), Mg, Al, P, Ti, Fe, Cu, Br, and Pb (between 0.1 and 1 wt. %). Similarly, the key elements in WTE bottom ash fraction finer than 45μm are Ca (greater than 10 wt. %), Mg, Al, Si, S, Cl, K, Ti, Fe, Zn (between 1 and 10 wt. %), P, V, Cr, Mn, Cu, Br, and Pb (between 0.1 and 1 wt. %). Here, we note that the dominant fraction of WTE bottom ash is the coarse fraction. The coarse WTE bottom ash fraction (rich in silicon) was not characterized in this study because of excessive grinding requirements and their unsuitability as a supplementary cementitious material due to their coarse nature. The elements in WTE bottom ashes are present as calcite, anhydrite, vaterite, hydroxyapatite, quartz, bassanite, gehlenite, akermanite, hydrocalumite, and portlandite. Similarly, the mineralogical species present in WTE fly ashes are calcium chloride hydroxide, halite, calcite, anhydrite, sylvite, hydrocalumite, vaterite, hannebachite, quartz, and bassanite. Temporal variation in ash composition may also result in significant fluctuations in chemical compositions. Therefore, a WTE facility may need to monitor the ash composition (elemental and mineralogical composition) in real time. In Task I, we evaluated the possibility of using a portable X-ray fluorescence (XRF) spectrometer to monitor the elemental composition in real-time. Specifically, we collected XRF data on identical specimens via a portable XRF spectrometer (low-end) and a lab-based benchtop XRF spectrometer (high-end). The collected data was used to train an A.I. algorithm (portable XRF data as an input and benchtop XRF data as an output) to predict accurate elemental composition using portable XRF data. Finally, we developed a 2-minute photobleaching protocol to monitor the mineralogical characteristics of WTE ashes via Raman spectroscopy. Overall, the activities in Task I improved our understanding of ash composition and developed techniques to monitor elemental and mineralogical composition in near real-time. Based on the findings of Task I, we find that WTE ashes exhibit wide variability in mineralogy. For ICP-based elemental analysis, all the mineralogical species in WTE ashes must be brought into solution. This is traditionally accomplished with acid digestion using a combination of multiple acids. However, acid digestion with multiple acids is time-consuming and often fails to ensure complete digestion of the ash matrix. To address this limitation, in Task II, we developed an alkali-fusion-based digestion protocol using a combination of lithium tetraborate, lithium metaborate, and their combinations as possible alkali fluxes for digesting WTE ashes entirely and rapidly. The validity of the developed method was evaluated on two standard ash specimens, i.e., SRM 1633c coal fly ash and BCR-176R incineration fly ash specimen. The findings suggest that the developed protocol can ensure complete digestion of elements such as Al, Ba, Ca, Cr, Cu, Mg, Mn, P, Sr, V, Zn, Be, K, and rare earth elements. The recent changes in the energy market towards renewables and increased metal recycling have resulted in reduced supplies of supplementary cementitious materials (coal fly ash and slag). Therefore, in Task III, we evaluated the possibility of employing WTE ashes as SCMs. As the chemical composition of WTE ashes varies temporally (on an hourly basis), there was also a need to develop tests that can evaluate the suitability of material to act as supplementary cementitious material rapidly, i.e., in a few minutes. Therefore, in Task II, we also developed a rapid test to assess the suitability of a material to act as an SCM in 5 minutes. This represents a significant advance over the state-of-the-art R 3 test, which takes ~144 hours. This test was initially validated on amorphous aluminosilicates, such as calcined clays, and could be extended to evaluate other industrial by-products, such as WTE ashes. In Task III, we evaluated the possibility of employing WTE ashes for two applications, i.e., as an SCM and a lime substitute for clay stabilization. The findings from Task I indicated that WTE ashes are enriched in chlorine and, therefore, cannot be used directly as an SCM due to corrosion-related risks and altered hydration kinetics. Accordingly, we developed an ash treatment protocol to reduce the solubility of chlorine-containing species in WTE ashes. The developed treatment protocol also immobilized lead in certain mineral forms. As a result of the treatment, WTE ashes can be used as SCMs without any corrosion or heavy metal leaching concerns. The second application examined in this study was clay stabilization. WTE ashes are calcium-rich and can be an adequate lime replacement for clay stabilization. Our findings reveal that the sum of the concentrations of Ca(OH) 2 and CaClOH controls the clay stabilization capability of WTE ashes. In summary, in this work, we evaluated the elemental and mineralogical characteristics of U.S. WTE ashes from diverse origins and developed tests to evaluate the chemical characteristics of these ashes in real time through a portable XRF and a benchtop Raman spectrometer. Based on the chemical characteristics of these ashes, we developed an ash treatment process to enable the use of WTE ashes as an SCM and also evaluated the possibility of employing these ashes for clay stabilization. Overall, the findings from this work enables the diversion of WTE ashes from landfills for multiple end-uses, i.e., as an SCM or a lime substitute for clay stabilization.
36 MATERIALS SCIENCE↗
A demonstrator for a real-time AI-FPGA-based triggering system for sPHENIX at RHIC
The RHIC interaction rate at sPHENIX will reach around 3 MHz in pp collisions and requires the detector readout to reject events by a factor of over 200 to fit the DAQ bandwidth of 15 kHz. Some critical measurements, such as heavy flavor production in pp collisions, often require the analysis of particles produced at low momentum. This prohibits adopting the traditional approach, where data rates are reduced through triggering on rare high momentum probes. We explore a new approach based on real-time AI technology, adopt an FPGA-based implementation using a custom designed FELIX-712 board with the Xilinx Kintex Ultrascale FPGA, and deploy the system in the detector readout electronics loop for real-time trigger decision.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Creating Unit Tests for GlideinWMS using AI tools
GlideinWMS is a workload management system that uses distributed computing to complete tasks, also known as jobs. It is particularly useful for high-throughput computing that’s used in research projects. It relies on Glideins, which are pilot jobs that pull jobs from a queue and provide resources for their completion, based on the jobs requirements. These decisions are made based on resource availability and job requirements. We used new AI tools to add unit tests to GlideinWMS.
Baburashvili, Ilya↗
AI-Enhanced Co-Design for Next-Generation Microelectronics: Innovating Innovation (Workshop Report)
The Artificial Intelligence Enhanced Co-Design for Next Generation Microelectronics virtual workshop was held April 4-5, 2023, and attended by subject matter experts from universities, industry, and national laboratories. This was the third in a series of workshops to motivate the research community to identify and address major challenges facing microelectronics research and production. The 2023 workshop focused on a set of topics from materials to computing algorithms, and included discussions on relevant federal legislation and such as the Creating Helpful Incentives to Produce Semiconductors and Science Act (CHIPS Act) which was signed into law in the summer of 2022. Talks at the workshop included edge computing in radiation environments, new materials for neuromorphic computing, advanced packaging for microelectronics, and new AI techniques. We also received project updates from several of the Department of Energy (DOE) microelectronics co-design projects funded in the fall of 2021, and from three of the Energy Frontier Research Centers (EFRCs) that had been funded in the fall of 2022. The workshop also conducted a set of breakout discussions around the five principal research directions (PRDs) from the 2018 Department of Energy workshop report: 1) define innovative material, device, and architecture requirements driven by applications, algorithms, and software; 2) revolutionize memory and data storage; 3) re-imagine information flow unconstrained by interconnects; 4) redefine computing by leveraging unexploited physical phenomena; 5) reinvent the electricity grid through new materials, devices, and architectures. We tasked each breakout group to consider one primary PRD (and other PRDs as relevant topics arose during discussions) and to address questions such as whether the research community has embraced co-design as a methodology and whether new developments at any level of innovation from materials to programming models requires the research community to reevaluate the PRDs developed back in 2018.
97 MATHEMATICS AND COMPUTING↗
Smart Pixels: In-pixel AI for on-sensor data filtering
We present a smart pixel prototype readout integrated circuit (ROIC) designed in CMOS 28 nm bulk process, with in-pixel implementation of an artificial intelligence (AI) / machine learning (ML) based data filtering algorithm designed as proof-of-principle for a Phase III upgrade at the Large Hadron Collider (LHC) pixel detector. The first version of the ROIC consists of two matrices of 256 smart pixels, each 25$\times$25 µm\textsuperscript{2} in size. Each pixel consists of a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. The frontend is capable of synchronously digitizing the sensor charge within 25 ns. Measurement results show an equivalent noise charge (ENC) of $\sim$30e\textsuperscript{-} and a total dispersion of $\sim$100e\textsuperscript{-} The second version of the ROIC uses a fully connected two-layer neural network (NN) to process information from a cluster of 256 pixels to determine if the pattern corresponds to highly desirable high-momentum particle tracks for selection and readout. The digital NN is embedded in-between analog signal processing regions of the 256 pixels without increasing the pixel size and is implemented as fully combinatorial digital logic to minimize power consumption and eliminate clock distribution, and is active only in the presence of an input signal. The total power consumption of the neural network is $\sim$ 300 $\mu$W. The NN performs momentum classification based on the generated cluster patterns and even with a modest momentum threshold, it is capable of 54.4\% – 75.4\% total data rejection, opening the possibility of using the pixel information at 40MHz for the trigger. The total power consumption of analog and digital functions per pixel is $\sim$ 6 $\mu$W per pixel, which corresponds to $\sim$ 1 W/cm\textsuperscript{2} staying within the experimental constraints.
Parpillon, Benjamin↗
Radiation-Hard Smart-Pixel Detector ASIC ReadOut with Digital AI in 28nm
Detectors at future high energy colliders will face enormous technical challenges. Disentangling the unprecedented numbers of particles expected in each event will require highly granular silicon pixel detectors with billions of readout channels. With event rates as high as 40 MHz, these detectors will generate petabytes of data per second. To enable discovery within strict bandwidth and latency constraints, future trackers must be capable of fast, power efficient, and radiation hard data-reduction at the source. This effort is pursuing the co-design development of high-performance readout smart pixel ASICs for a future Phase III High Luminosity upgrade of the Large Hadron Collider. A 1.6mm2 ASIC prototype was designed by Fermilab in CMOS 28 nm bulk process and submitted for manufacturing in February 2024. It leverages the analog front-end pixel design of a previous prototype fabricated and tested in 2023, which achieved a simulated detection level of ~400e- with 30fF input capacitance. The ROIC consists of two matrices of 16×16 smart pixels, each 25×25 μm2 in size. Each smart pixel contains a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. There is digital space for the integration of our fully combinatorial AI that performs momentum classification at the bunch crossing rate. The total power consumption is ∼6μW per pixel, which corresponds to ~1mW/cm2. The ASIC incorporates programmable front-end charge injection circuitry to generate pixel cluster charges during characterization. The cluster profile will be generated to duplicate hit characteristics of various momentum (pT). We will present early results from chip testing.
Parpillon, Benjamin↗
EFIT‐AI: Machine Learning and Artificial Intelligence Assisted Equilibrium Reconstruction for Tokamak Experiments and Burning Plasmas (Final Report)
The EFIT-AI project is creating a modern advanced equilibrium reconstruction code suitable for tokamak experiments of burning plasmas. EFIT [1,2] was the first and is the most extensively used equilibrium reconstruction code in the world. This project builds on the production-level experience and adds key elements as follows. 1. A Model Order Reduction (MOR) version of the two-dimensional (2D) Grad-Shafranov equation solver (EFIT-MORNN) using physics-informed neural networks. 2. Improved optimization and data analysis capabilities using a Bayesian framework enhanced with machine learning. 3. A MOR version of the three-dimensional (3D) perturbed equilibrium reconstruction tool.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
2025 Workshop on Envisioning Frontiers in AI and Computing for Biological Research: Position Papers
This workshop aims to identify key research directions for transforming biology using artificial intelligence (AI), machine learning (ML) and computational methods to facilitate the discovery of new behaviors, mechanisms, and designs of biological processes relevant to DOE missions, underpinning a broader U.S. bioeconomy. By developing novel AI/ML technologies to analyze and interpret complex biological data, researchers can organize and simulate biological processes at various scales as well as advance predictive understanding and manipulation of biological systems. This integration of computation, experimentation, and next-generation experimental technologies can lead to discoveries in new biological behaviors and mechanisms relevant to DOE missions. The focus is on how advanced computational and mathematical methods can impact this mission by exploring digital twins, foundation models, automated laboratory experiments, modeling of complex living systems, and data-driven approaches for the biodesign of plants and microbial systems. While data management is important, it is not the primary focus of this workshop, which will assess the current state, trends, and AI/ML challenges at the interface between biology and computational science to identify opportunities for high-impact research at their intersection. The goal is to define research needs and opportunities that align with biological sciences, computational sciences, and applied mathematics research.
59 BASIC BIOLOGICAL SCIENCES↗
PMDT: AI-Enabled Predictive Maintenance Digital Twins for Advanced Nuclear Reactors
Our team made substantial technical progress on various fronts during the course of the program. Multiple milestones were geared towards demonstrating the feasibility of machine learning based predictive maintenance digital twins towards reducing O&M costs, whereas some other milestones actually focused on identifying technical gaps and developing technologies such as humble AI to provide necessary robustness to the ML-based models. We were able to demonstrate in many cases that Machine learning-based methods can be successfully adapted for Nuclear plant environments especially for remote monitoring applications. Detailed analyses were carried out with plant and full scope simulation data along with capabilities of enhanced analytics to assess and set realistic expectations on cost reductions in O&M. These assessments are paving the way for investments towards reactor design improvements as well project planning for SMR projects as they develop and mature in the next few years. Technology developed under this program got direct visibility to GE Hitachi and their utility customers and resulted in positive intents to deploy some of the elements from design phase. The project additionally resulted in several reports, publications, software and data generation that will be useful in deployment and O&M services for BWRX300 fleets.
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
AI Driven Optimization of Public Transit
This project explores the application of AI-driven methods to optimize public transit operations for the Chattanooga Area Regional Transportation Authority (CARTA). By leveraging data analytics, machine learning, and predictive modeling, the initiative seeks to enhance system efficiency, improve rider experience, and support sustainability goals. This research, supported by the National Science Foundation and the U.S. Department of Energy, integrates real-time transit data with advanced computational tools to inform decision-making, optimize routes, and balance operational demands. The work exemplifies a forward-looking model for mid-sized cities aiming to modernize mobility systems through intelligent technology integration.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Modernizing to an AI-Ready Control System
The Accelerator Controls Operations Research Network (ACORN) project will modernize the accelerator control system and upgrade power supplies to enable future operations of the Fermilab Accelerator Complex with megawatt proton beams. By focusing on MLOps, ACORN enables full integration of AI into the control system to allow safe and reliable improvements to accelerator beam operations.
43 PARTICLE ACCELERATORS↗
Report for the DOE Office of Science Workshop on Envisioning Frontiers in AI and Computing for Biological Research
Artificial intelligence (AI), machine learning (ML), and high-performance computing (HPC) are poised to transform biological research, spurring innovation in biotechnology and biosystems design. "is transformation will bring an explosion of new capabilities to control the expression of genomic information in living organisms and harness that information to invent new biobased technologies (Jinek et al. 2012; NASEM 2025).
59 BASIC BIOLOGICAL SCIENCES↗
Wafer Scale Engine Enabled AI Modeling of Geologic Carbon Utilization and Storage
Conference presentation on hardware acceleration of AI model training, validation, and testing using wafer scale engines, to improve efficiency and effectiveness of carbon management.
wafer scale engine↗
Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML
With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.
Di Guglielmo, Giuseppe [Fermilab]↗
Data-Driven and Physics informed AI approaches for manipulation
Workshop presentation on the future of work in the age of robotics & AI
Slightam, Jonathon↗
AI‐Accelerated Optimization of Self‐Assembled Organic Mixed Ionic‐Electronic Conductors (OMIEC) (Final Report)
This document describes research activities, products and outcomes of a DOE-funded program to help accelerate development of Organic Mixed Ionic Electronic Conductors (OMIECs) using neutron scattering and high-throughput experimentation. OMIECs are organic materials that conduct both ionic and electronic charge carriers. For these new OMIEC materials, self-assembling ion-conducting block copolymers (BCPs) are used as a structural template for electronic conducting polymers. This forms OMIECs with long-range structural order that can help facilitate long-range electronic transport. The conductive properties of OMIECs are closely associated with their structure, which is affected by solution conditions and polymer macromolecular designs. Thus high-throughput experimentation has been implemented to explore this large design space effectively. The BCP-CP OMIEC systems explored are composed of ion-conducting diblock or triblock copolymers containing polyethylene oxide (PEO), di(ethylene glycol) ethyl ether acrylate (DEGEEA) or poly(ethylene glycol) methyl ether acrylate) (PEGMEA) hydrophilic blocks. These blocks will be coupled with either polypropylene oxide (PPO) or polyheptafluorobutyl acrylate (PHFBA) hydrophobic blocks to drive assembly. The electronic conducting component consists of several different types of conjugated polymers. Small angle scattering of neutrons and X-rays (SANS/SAXS) as well as electrochemical analysis have been coupled with modern algorithms for autonomous research using artificial intelligence (AI).
36 MATERIALS SCIENCE↗
Leveraging AI and Spatial Data to Unlock Pipeline Integrity Insights: NETL’s Advanced Infrastructure Integrity Model (AIIM)
Maintaining the integrity of natural gas infrastructure plays a critical role in ensuring energy security. Robust, data-driven foundational AI models for pipeline integrity can help address risk management and mitigation issues. Trusted foundational models can help with industry adoption and accelerate innovation by enhancing integrity predictions, reduce costs, and informing infrastructure build-out. The AIIM dashboard was released in 2022 and utilizes multi-ML models for ensemble-type insights. It was expanded to include analytics on reported incidents. It was developed as an ESRI Dashboard to support data visualization & interrogation and contains pipeline data and model results.
Advanced Infrastructure Integrity Model (AIIM)↗