Search NASA⌕ Search

SEARCH · Search NASA

Results for “trade space exploration”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

DEVELOPMENT AND APPLICATION OF RISK ANALYSIS TOOLKIT FOR PLANT RESOURCE OPTIMIZATION

This paper presents the development of methods and tools that are being designed to optimize plant operations (e.g., maintenance/replacement schedules and optimal maintenance postures for plant components) in a manner that is more cost effective than current approaches and makes better use of available component health and cost data. These methods include both data- and model-based optimization methods. Model-based optimization methods directly include reliability and cost models to determine an optimal plant operational strategy. We consider gradient-based and evolutionary (based on genetic algorithms) optimization methods. The second class of methods target more specific use cases (e.g., project schedule optimization) and are not based on reliability models directly, but they require specific component reliability and cost data. This class of methods is based on variants of the knapsack problem with an aim to determine an optimal project schedule that maximizes the overall NPV. This paper also presents multi-objective methods designed to identify an optimal maintenance posture based on a Pareto frontier analysis. Rather than dictating the “right” tradeoff (i.e., identify the absolute best posture), we show how it is possible to perform a trade space exploration approach (i.e., identify value and costs of several postures and let the analysis account for desired value and cost metrics). This is performed by identifying maintenance postures that maximize value (e.g., system availability) and minimize operational costs, i.e., the Pareto frontier in a value-cost trade space. For all these methods we present detailed applicative examples that show their validity from a decision-making perspective.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Physics basis for the reference flat-top plasma scenario in the ST–E1 fusion power plant

As part of the U.S. Department of Energy’s Milestone-Based Fusion Energy Development Program, Tokamak Energy has completed the pre-concept design of the ST–E1 fusion power plant. ST–E1 is envisaged to operate in two phases: a pilot plant phase, targeting sustained net power production of 300 - 500 MWe for a duration >1 hr, followed by a commercial power plant phase targeting steady-state operations and a normalised overnight capital cost of ⩽12 000 $\$$/kWe. The design process adopted was highly iterative, integrating all major plant systems and progressing in a phased fidelity approach. At the pre-conceptual stage, the emphasis has been on exploring the design space, identifying the main system-level trade-offs, and making the key decisions that define the overall plant concept, rather than optimising a single operating point. This paper, part of a focused collection detailing the ST–E1 pre-concept design, addresses the development of a series of reference flat-top plasma operating points for the pilot plant phase. A modelling workflow was established to develop and assess candidate plasma design points and explore key dependencies. The workflow includes integrated core plasma modelling, magnetohydrodynamic (MHD) stability assessment, equilibrium generation, scrape-off-layer and exhaust modelling, heating & current drive design and optimisation, and turbulent transport modelling. Using this framework, the impact of several key parameters on the flat-top operating space was investigated, including the density limit, core radiation fraction and divertor power loading, level of external heating and curent drive power and assumed pedestal characteristics. The MHD stability, controllability and micro-stability characteristics of these plasmas were also analysed. These investigations informed the definition of a set of fully non-inductive, flat-top reference operating points that satisfy the high-level ST–E1 mission, including a low and high density case, a case that is stable to resistive wall modes and a case with reduced divertor power loading.

ST–E1↗
DOE OSTI2025

Web-Based Tools for Data-Informed Remedy Optimization: Software Theory and User Guide

This report documents the development and application of two web-based decision-support tools for pump-and-treat (P&T) groundwater remediation systems: PTOLEMY (Pump-and-Treat Optimized Location Evaluation to Maximize Yields) and OPTIMA (Optimization for Pump-and-Treat Implementation, Management, & Assessment). These tools enhance remedy design and management by leveraging advanced computational methods – specifically deep learning and multi-objective optimization – within a user-friendly platform. By integrating data-driven models with established hydrogeological knowledge, PTOLEMY and OPTIMA enable more efficient evaluation of well placement and operational strategies, helping site managers balance multiple remediation objectives under complex conditions. Both tools are implemented as modules within the SOCRATES (Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites) web platform, which provides data access, visualization, and analytics to support remedy optimization across sites in the U.S. Department of Energy Office of Environmental Management complex. PTOLEMY is a rapid screening module designed to identify promising locations for new extraction wells. It employs a multi-channel three-dimensional convolutional neural network (MC3D-CNN) trained on high-fidelity simulation data to predict the relative performance (in terms of contaminant mass recovery) of potential well sites. Through an interactive web interface, PTOLEMY visualizes the probability of high performance across a site, highlighting areas where an extraction well is likely to yield above-threshold contaminant removal over a multi-year period. PTOLEMY’s map-based displays and exportable results support transparent communication of screening analyses. By focusing attention on the most favorable candidate locations, the tool augments traditional engineering judgment and physics-based modeling, providing a data informed basis for subsequent detailed evaluations. OPTIMA is a multi objective optimization module designed to find wellfield layouts and operating schedules that meet various cleanup goals. It quickly evaluates thousands of candidate setups – combinations of well locations, timing, and rates – and returns a small set of best trade-off options for comparison. At its core, OPTIMA uses a U-Net-based surrogate model – a deep-learning emulator of a groundwater flow and transport simulator – to dramatically accelerate scenario evaluations. Coupling this fast surrogate with the NSGA-II (Non-dominated Sorting Genetic Algorithm II) evolutionary algorithm, OPTIMA explores a wide decision space of well locations and schedules to identify Pareto-optimal solutions that trade off key objectives (e.g., minimizing cleanup time, maximizing contaminant mass removal, and minimizing plume extent). The tool outputs a family of optimal configurations and visualizes their trade-offs (Pareto frontiers of cleanup metrics and maps of optimized well placements). Site managers can use these results to understand the range of viable strategies and to select candidate designs for more detailed verification. OPTIMA is currently under active development and not yet fully released; this guide provides early documentation to support planning and gather user feedback.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Performance Impact and Trade-Offs for Tuning Key Architectural Parameters on CPU+GPU Systems

In this work, we performed an initial design space exploration of an accelerated processing unit (APU)—a hybrid CPU+GPU architecture that integrates both compute units (CUs) and memory into a unified system. This integration aims to reduce data movement, enhance memory locality, and improve energy efficiency by enabling the CPU and GPU to share memory directly. This effort focused on the interplay of key design components—cache line size, the number of CUs, and main memory technology—and the trade-offs of each configuration were analyzed. This paper highlights the various configurations’ impact on memory accesses, data reuse, and power utilization. The results provide valuable insights that can be leveraged to optimize APU architectures for high-performance and energy-efficient computing and thus create a balanced architecture. This optimization can be achieved by adopting dynamic cache management, runtime CU scaling, and advanced memory integration, highlighting the potential of APUs to address critical challenges in compute, data movement, and memory power consumption.

Asifuzzaman, Kazi [ORNL] (ORCID:0000000240044791)↗
DOE OSTI2025

Super-Resolution Ptychography with Small Segmented Detectors

To overcome the spatial resolution limit set by aperture-limited diffraction in traditional scanning transmission electron microscopy, microscopists have developed ptychography enabled by iterative phase retrieval algorithms and high-dynamic-range pixel array detectors. Current detector designs are limited by the data rate off chip, so a high-pixel-count detector has a proportionally lower frame rate than the few-segment detectors used for differential phase contrast (DPC) imaging. This slower acquisition speed leads to heightened vulnerability to scan noise, drift, and potential sample damage. This creates opportunities for repurposing fast segmented detectors for ptychography by trading a reduction in reciprocal space pixels for an increase in real space pixels. Here, we explore a strategy of oversampling in real space and instead apply detector pixel upsampling during the reconstruction process. Further, we demonstrate the viability of achieving super-resolution ptychography on thin objects using only 2 × 2 detector pixels, surpassing the resolution of integrated DPC (iDPC) imaging. With optimization using simulated datasets and experiments on MoTe 2 /WSe 2 bilayer moiré superlattices, we achieved super-resolution ptychography reconstructions under rapid acquisition conditions (37.5 pA, 1 μs dwell time), yielding over 50% improvements in contrast and information limit compared to annular dark field and iDPC imaging on the same detectors.

2D materials↗
DOE OSTI2024

Automatic Extraction of Network Configurations for Realistic Simulation and Validation

Popular HPC network interconnection simulators such as SST Macro provide a variety of configurable parameters to explore the design space of hardware components such as network links and switches. While such knobs provide flexibility to explore design trade-offs for novel hardware, manually configuring simulations for existing hardware to focus on topology exploration can be cumbersome and error-prone, leading to widely inaccurate simulations. This challenge is compounded when specifications of various (proprietary) technologies are not readily available or are intentionally omitted. In this work, we provide a methodology to automatically tune the simulation configuration of the multiple network models running within SST Macro using Bayesian optimization. We perform this optimization in the context of multiple messaging regimes (i.e., small to large and latency to bandwidth-bound messages) and provide a detailed analysis of the simulation error for four systems. With our automated framework, we achieve a 5x improvement in accuracy over best-effort configurations based on available hardware specifications.

Suetterlein, Joshua D.↗
DOE OSTI2025

Extending High-Level Synthesis with AI/ML Methods

Artificial Intelligence (AI) and Machine Learning (ML) methods provide significant opportunities of improving quality of results when performing high-level synthesis (HLS). For example, they can be used to model and predict metrics of the final design (e.g., area, considering aspects such as interconnect overhead for different device technologies), facilitating exploration when searching for the best design trade-offs. They can also enable identifying hidden correlations across the various phases of the synthesis and the various optimizations performed, identifying the most effective pipelines. Finally, in more general terms, bio-inspired heuristic algorithms can improve the design space exploration for the synthesis process in terms of time and quality of the result. This paper discusses opportunities and challenges to augment HLS with AI/ML using as example flow the SODA Synthesizer, an open-source hardware generation toolchain which includes SODA-OPT, a hardware/software partitioning and pre-optimization tool developed with the MLIR framework, and PandA-Bambu, a state-of-the art HLS tool. SODA interfaces with OpenROAD to provide a complete end-to-end toolchain.

artificial intelligence↗
DOE OSTI2026

Primary Heat Transport System Design Considerations for Xcimer Energy’s Athena Fusion Pilot Plant

Fusion energy promises a reliable, carbon-free source of power; however, significant challenges remain before it can be deployed as an economical energy source. In addition to achieving fusion conditions, power plants must operate under extreme temperatures, radiation, and mechanical loads while maintaining high efficiency and availability. These requirements place strong demands on engineering design and plant operation. This work focuses on the engineering challenges associated with balance of plant analysis for inertial fusion energy systems. In particular, this paper examines the design considerations for primary heat transfer systems in fusion pilot plants employing molten fluoride salt coolants, with particular emphasis on system layout optimization and the balance between competing design objectives using the Xcimer Energy Athena inertial pilot plant design as a case study. Through systematic analysis of candidate system configurations and parametric sensitivity studies, we identify key engineering trade-offs governing salt inventory, pumping power requirements, and operational flexibility. The analysis employs system-level modeling tools to explore the design space and establish relationships between geometric parameters and system performance metrics.

Greenwood, Scott [ORNL] (ORCID:0000000333480736)↗
DOE OSTI2024

HPC Network Simulation Tuning via Automatic Extraction of Hardware Parameters

Popular HPC network interconnection simulators such as SST/macro provide a variety of configurable parameters to explore the design space of hardware components such as network interface cards (NIC), switches, and links among them. While such knobs provide flexibility to explore design trade-offs for novel hardware, manually configuring simulations for matching configurations of the existing hardware to focus on topology exploration can be cumbersome and error-prone, leading to widely inaccurate simulations. This challenge is compounded when specifications of various (proprietary) technologies are not readily available or intentionally omitted. In this work, we propose a framework to autotune the multiple network models’ simulation configurations within SST/macro using Tree-structured Parzen Estimator-based Bayesian optimization to observe the effect on simulation accuracy across different message regimes. These regimes consist of small to large message sizes and latency to bandwidth-bound messages. We provide a detailed analysis of the simulation error for four representative HPC systems. Our Bayesian optimization based autotuning framework for network models achieves a maximum of 5x improvement in accuracy over best-effort manual configurations based on available hardware specifications.

Simulation, autotuning↗
DOE OSTI2025

Bridging the Gap: User-Centric Energy Monitoring for Policy-Driven Application Optimization in HPC Data Centers

Application energy optimization in HPC data centers face two critical gaps. Systematic methodologies that connect data center policies to application decisions and accessible monitoring tools that enable data-driven optimization. We address both gaps through two complementary pillars. First, we present a methodology based on extended weighted Energy Delay Product (EDP) to translate data center operational priorities and integrate energy considerations into the energy optimization workflow which starts from continuous monitoring through targeted optimization. Second, we present a user-space monitoring tool, Omnistat, that enables this methodology by providing developers with direct access to actionable energy telemetry. Through deployment on the Frontier supercomputer and case studies exploring performance-energy trade-offs, we show how these pillars help energy as an integral optimization target for developers as active participants in data center efficiency.

Shin, Woong [ORNL] (ORCID:0000000172077814)↗
DOE OSTI2026

Exploring the fusion power plant design space: comparative analysis of positive and negative triangularity tokamaks through optimization

The optimal configuration choice between positive triangularity (PT) and negative triangularity (NT) tokamaks for fusion power plants hinges on navigating different operational constraints rather than achieving specific plasma performance metrics. This study presents a systematic comparison using constrained multi-objective optimization with the integrated FUsion Synthesis Engine (FUSE) framework. Over 200 000 integrated design evaluations were performed exploring the trade-offs between capital cost minimization and operational reliability (maximizing q 95 ) while satisfying engineering constraints including 250 ± 50 MW net electric power, tritium breeding ratio > 1.1, power exhaust limits and an hour flattop time. Both configurations achieve similar cost-performance Pareto fronts through contrasting design philosophies. PT, while demonstrating resilience to pedestal degradation (compensating for up to 40% reduction), are constrained to larger machines (R 0 > 6.5 m) by the narrow operational window between L–H threshold requirements and the research-established power exhaust limit (P sol /R < 15 MW m –1 ). This forces optimization through comparatively reduced magnetic field (∼8 T). NT configurations exploit their freedom from these constraints to access compact, high-field designs (R 0 ~ 5.5 m, B 0 >12 T), creating natural synergy with advancing HTS technology. Sensitivity analyses reveal that PT’s economic viability depends critically on uncertainties in L–H threshold scaling and power handling limits. Notably, a 50% variation in either could eliminate viable designs or enable access to the compact design space. These results suggest configuration selection should be risk-informed: PT offers the lowest-cost path when operational constraints can be confidently predicted, while NT is robust to large variations in constraints and physics uncertainties.

FUSE framework↗
DOE OSTI2024

Bacterial community dynamics as a result of growth-yield trade-off and multispecies metabolic interactions toward understanding the gut biofilm niche

Abstract Bacterial communities are ubiquitous, found in natural ecosystems, such as soil, and within living organisms, like the human microbiome. The dynamics of these communities in diverse environments depend on factors such as spatial features of the microbial niche, biochemical kinetics, and interactions among bacteria. Moreover, in many systems, bacterial communities are influenced by multiple physical mechanisms, such as mass transport and detachment forces. One example is gut mucosal communities, where dense, closely packed communities develop under the concurrent influence of nutrient transport from the lumen and fluid-mediated detachment of bacteria. In this study, we model a mucosal niche through a coupled agent-based and finite-volume modeling approach. This methodology enables us to model bacterial interactions affected by nutrient release from various sources while adjusting individual bacterial kinetics. We explored how the dispersion and abundance of bacteria are influenced by biochemical kinetics in different types of metabolic interactions, with a particular focus on the trade-off between growth rate and yield. Our findings demonstrate that in competitive scenarios, higher growth rates result in a larger share of the niche space. In contrast, growth yield plays a critical role in neutralism, commensalism, and mutualism interactions. When bacteria are introduced sequentially, they cause distinct spatiotemporal effects, such as deeper niche colonization in commensalism and mutualism scenarios driven by species intermixing effects, which are enhanced by high growth yields. Moreover, sub-ecosystem interactions dictate the dynamics of three-species communities, sometimes yielding unexpected outcomes. Competitive, fast-growing bacteria demonstrate robust colonization abilities, yet they face challenges in displacing established mutualistic systems. Bacteria that develop a cooperative relationship with existing species typically obtain niche residence, regardless of their growth rates, although higher growth yields significantly enhance their abundance. Our results underscore the importance of bacterial niche dynamics in shaping community properties and succession, highlighting a new approach to manipulating microbial systems.

Microbiology↗
DOE OSTI2026

Optimizing fluvial flood mitigation strategies: A multi-objective approach for cost-effective and socially-aware infrastructure feasibility analysis

Effective levee planning must balance capital cost, risk reduction, and community priorities. These objectives are rarely optimized together. This study presents a feasibility phase, simulationin-the-loop framework that couples terrain-based flood modeling with a socially aware multiobjective optimizer. Flood risk is measured as Expected Annual Exposed Population (EAEP), obtained by integrating exposure over Annual Exceedance Probability (AEP) nodes, mirroring the Hydrologic Engineering Center's Flood Damage Reduction Analysis (HEC-FDA) expected-annual formulation but with people rather than dollars. Exposure per scenario is computed by overlaying binary inundation masks with a population surface at the tract level. Distributional fairness is encoded through a Group Benefit Share (GBS) constraint that requires high-SVI tracts to receive at least a baseline share of annualized benefits. Capital cost is represented by a height-dependent unit-cost model suitable for screening. This study addresses the two-objective problem, minimize cost and expected annual exposure subject to the GBS constraint, using Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and leveraging Pareto front for feasibility phase decision making. Implemented with terrain-based flood modeling, GeoFlood, for rapid scenario evaluation, the framework is demonstrated in Southeast Texas. The results reveal clear trade-offs among cost, risk, and social benefits and identify non-dominated levee height configurations that satisfy the benefit-share floor. The contributions are a scalable decision support method that operationalizes expected annual population-based risk, embeds enforceable benefit-sharing guarantees, and uses lightweight simulation to explore large design spaces before higher fidelity design stages.

Flood mitigation↗
DOE OSTI2024

Multi-objective Bayesian active learning for MeV-ultrafast electron diffraction

Ultrafast electron diffraction using MeV energy beams(MeV-UED) has enabled unprecedented scientific opportunities in the study of ultrafast structural dynamics in a variety of gas, liquid and solid state systems. Broad scientific applications usually pose different requirements for electron probe properties. Due to the complex, nonlinear and correlated nature of accelerator systems, electron beam property optimization is a time-taking process and often relies on extensive hand-tuning by experienced human operators. Algorithm based efficient online tuning strategies are highly desired. Here, we demonstrate multi-objective Bayesian active learning for speeding up online beam tuning at the SLAC MeV-UED facility. The multi-objective Bayesian optimization algorithm was used for efficiently searching the parameter space and mapping out the Pareto Fronts which give the trade-offs between key beam properties. Such scheme enables an unprecedented overview of the global behavior of the experimental system and takes a significantly smaller number of measurements compared with traditional methods such as a grid scan. This methodology can be applied in other experimental scenarios that require simultaneously optimizing multiple objectives by explorations in high dimensional, nonlinear and correlated systems.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

AI‐Driven Defect Engineering for Advanced Thermoelectric Materials

Thermoelectric materials offer a promising pathway to directly convert waste heat to electricity. However, achieving high performance remains challenging due to intrinsic trade-offs between electrical conductivity, the Seebeck coefficient, and thermal conductivity, which are further complicated by the presence of defects. This review explores how artificial intelligence (AI) and machine learning (ML) are transforming thermoelectric materials design. Advanced ML approaches including deep neural networks, graph-based models, and transformer architectures, integrated with high-throughput simulations and growing databases, effectively capture structure-property relationships in a complex multiscale defect space and overcome the “curse of dimensionality”. This review discusses AI-enhanced defect engineering strategies such as composition optimization, entropy and dislocation engineering, and grain boundary design, along with emerging inverse design techniques for generating materials with targeted properties. Finally, it outlines future opportunities in novel physics mechanisms and sustainability, highlighting the critical role of AI in accelerating the discovery of thermoelectric materials.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Sustainable Triacetic Acid Lactone Production from Sugarcane by Fermentation and Crystallization

Triacetic acid lactone (TAL) has the potential to serve as a bioderived platform chemical for commercial products including sorbic acid and recyclable polydiketoenamine plastics. In this study, we leveraged BioSTEAM to design, simulate, and evaluate (via techno-economic analysis, TEA, and life cycle assessment, LCA) TAL production from sugarcane. We experimentally characterized TAL solubility, calibrated solubility models, and designed a process to separate TAL from fermentation broths by crystallization. The biorefinery could produce TAL at a minimum product selling price (MPSP) of $\$3.73$–5.86·kg –1 (5th–95th percentiles; baseline at $\$4.60$·kg –1 ) and a carbon intensity (CI) of 5.31 [2.60–8.71] kg CO 2 -eq·kg –1 , which could enable financially viable, low-CI production of sorbic acid and polydiketoenamines. To drive down costs and CI, we explored the theoretical fermentation space (titer, yield, productivity combinations), operation scheduling and capacity expansion strategies (e.g., integrated sorghum processing), and potential separation improvements (mitigating TAL loss through pH control). Advancements in key design and technological parameters could further reduce MPSP by 51% to $\$2.26$·kg –1 [$\$1.97$–2.80·kg –1 ] and CI by 43% to 3.05 [1.91–4.15] kg CO 2 -eq·kg –1 . This research highlights the ability of agile TEA-LCA to screen promising designs, navigate sustainability trade-offs, prioritize research needs, and chart quantitative roadmaps to advance bioproducts and biofuels.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Potential Adoption and Benefits of Co-Optimized Multimode Engines and Fuels for U.S. Light-Duty Vehicles

Exploring a diverse portfolio of technologies for decarbonization is crucial to understanding the potential impacts of different technological solutions and their associated environmental implications. Using high-octane, high-sensitivity biofuel blends in co-optimized multimode engines can increase engine efficiency and reduce vehicle emissions. Here, the multimode engine research focuses on the benefits of light-duty vehicle engines, which can operate in multiple modes depending on the vehicle's load. Low-temperature combustion can improve efficiency and reduce emissions (such as those from oxides of nitrogen and particulate matter) during low-load operation, while spark ignition performance is maintained in high-load operation. These advanced engines can be optimized to run on blends of biobased fuels. This analysis models scenarios for potential market adoption of co-optimized multimode vehicles fueled by three different bioblendstocks: ethanol, isopropanol, and isobutanol. An integrated modeling approach is used to forecast the energy and environmental impacts of the deployment of co-optimized multimode vehicles and fuels in the light-duty sector over the 2020-to-2050 time horizon. The multidisciplinary approach combines vehicle sales modeling, system dynamics modeling of the biorefining industry, and life cycle assessment to estimate the emissions and energy benefits. The models consider market forces such as consumer preferences for vehicle attributes, biofuel supply and demand dynamics subject to biorefinery capacity build-out and bioresource constraints, and forecasted changes to the U.S. bulk energy system over time. Market adoption of co-optimized vehicles is evaluated across a wide parameter space for incremental vehicle cost and engine efficiency improvement. This analysis reveals that the deployment of co-optimized multimode fuels and vehicles results in up to a 5% reduction in annual sector-wide life cycle greenhouse gas (GHG) emissions by 2050, relative to a business-as-usual scenario, but is also indicates environmental trade-offs, such as higher life cycle water-use. Emission benefits could potentially increase beyond 2050, as the new technologies penetrate the market and gain a foothold. Results also show that, under certain circumstances, vehicles with engines co-optimized for use with high-octane, high-sensitivity biofuel blends can be cost-competitive with conventional gasoline, while reducing GHG emissions. Our modeling results indicate that co-optimized multimode fuels and engines can be strategically leveraged in tandem with electrification to decarbonize the light-duty sector. Co-optimized vehicles could play a role in the early years of the time horizon, while electric vehicles (EVs) could become more competitive in the later years, highlighting the complementary benefits of these technologies for GHG reductions.

Oke, Doris↗
DOE OSTI2024

Investigating resource-efficient neutron/gamma classification ML models targeting eFPGAs

There has been considerable interest and resulting progress in implementing machine learning (ML) models in hardware over the last several years from the particle and nuclear physics communities. A big driver has been the release of the Python package, hls4ml, which has enabled porting models specified and trained using Python ML libraries to register transfer level (RTL) code. So far, the primary end targets have been commercial field-programmable gate arrays (FPGAs) or synthesized custom blocks on application specific integrated circuits (ASICs). However, recent developments in open-source embedded FPGA (eFPGA) frameworks now provide an alternate, more flexible pathway for implementing ML models in hardware. These customized eFPGA fabrics can be integrated as part of an overall chip design. In general, the decision between a fully custom, eFPGA, or commercial FPGA ML implementation will depend on the details of the end-use application. In this work, we explored the parameter space for eFPGA implementations of fully-connected neural network (fcNN) and boosted decision tree (BDT) models using the task of neutron/gamma classification with a specific focus on resource efficiency. We used data collected using an AmBe sealed source incident on Stilbene, which was optically coupled to an OnSemi J-series silicon photomultiplier (SiPM) to generate training and test data for this study. We investigated relevant input features and the effects of bit-resolution and sampling rate as well as trade-offs in hyperparameters for both ML architectures while tracking total resource usage. The performance metric used to track model performance was the calculated neutron efficiency at a gamma leakage of 10 -3 . The results of the study will be used to aid the specification of an eFPGA fabric, which will be integrated as part of a test chip.

47 OTHER INSTRUMENTATION↗