Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Explainable machine learning”

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

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

At least 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

PM 2.5 Is Insufficient to Explain Personal PAH Exposure

To understand how chemical exposure can impact health, researchers need tools that capture the complexities of personal chemical exposure. In practice, fine particulate matter (PM 2.5 ) air quality index (AQI) data from outdoor stationary monitors and Hazard Mapping System (HMS) smoke density data from satellites are often used as proxies for personal chemical exposure, but do not capture total chemical exposure. Silicone wristbands can quantify more individualized exposure data than stationary air monitors or smoke satellites. However, it is not understood how these proxy measurements compare to chemical data measured from wristbands. In this study, participants wore daily wristbands, carried a phone that recorded locations, and answered daily questionnaires for a 7-day period in multiple seasons. We gathered publicly available daily PM 2.5 AQI data and HMS data. We analyzed wristbands for 94 organic chemicals, including 53 polycyclic aromatic hydrocarbons. Wristband chemical detections and concentrations, behavioral variables (e.g., time spent indoors), and environmental conditions (e.g., PM 2.5 AQI) significantly differed between seasons. Machine learning models were fit to predict personal chemical exposure using PM 2.5 AQI only, HMS only, and a multivariate feature set including PM 2.5 AQI, HMS, and other environmental and behavioral information. On average, the multivariate models increased predictive accuracy by approximately 70% compared to either the AQI model or the HMS model for all chemicals modeled. This study provides evidence that PM 2.5 AQI data alone or HMS data alone is insufficient to explain personal chemical exposures. Our results identify additional key predictors of personal chemical exposure.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
NASA NTRSDate not supplied

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗
DOE OSTI2025

Machine Learning-Accelerated First-Principles Molecular Dynamics Reveals C–C Coupling Mechanisms toward Ethylene on Cu(100)

Here, the Cu(100) termination has been identified as the most effective facet for converting CO and CO 2 into ethylene. To enhance both the activity and selectivity of ethylene production, we perform machine-learning-accelerated, first-principles molecular dynamics simulations at 298 K in an explicit solvent at pH 7 to elucidate the C–C coupling mechanism─the critical reaction step in forming C 2+ products. Among the six potential C–C coupling pathways, the most feasible are CO* dimerization and CO – CHO* and CHO* – CHO* couplings. Using the computational hydrogen electrode method, we demonstrate that all three pathways are equally accessible at −0.6 V vs RHE. At a potential below −1.0 V vs RHE, the thermodynamic barriers for the CO – CHO* and CHO* – CHO* pathways become negligible. Our computational findings explain the experimental observations, particularly the absence of C 2+ products above −0.4 V vs RHE and the peaks in ethylene production near −0.6 and −1.0 V vs RHE. Since CHO* acts as a key intermediate common to both C–C coupling and CH 4 formation, we propose that suppressing CHO* hydrogenation would inhibit CH 4 pathways, thereby maximizing ethylene selectivity.

CO2 reduction↗
NASA NTRSDate not supplied

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗
DOE OSTI2024

Continuous integration data-driven platform of industrial-scale subsurface storage for real-time analytics

This project helped address the growing need for efficient and scalable models to support geological carbon and energy storage, which are crucial for achieving net-zero emissions. Traditionally accurate high-fidelity numerical models have been used to simulate relevant storage processes under a handful of processes, however such models are computationally demanding, making uncertainty quantification impractical. Consequently, we first developed a machine learning framework, based on Graph Neural Operators (GNOs), to improving the accuracy of model predictions for a fixed computational budget. We then developed an Ensemble of Improved Neural Operators (ENO), which uses bagging and Monte Carlo dropout techniques, to further improve prediction accuracy. Lastly, we developed the way to explain progressive transfer learning methods to reduce the amount of training data and computational cost of training (i.e., reduce trainable parameters) when using our models for multiple storage sites. Our numerical investigation, which used real-world case studies, demonstrated that our framework can significantly improve the safety and efficiency of geological storage operations, with potential applications in other domains such as geothermal reservoirs and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2019

Deep Learning Method for Detecting Precursors to Adverse Events

With the recent advancements in Deep Learning methods, the ability to model large complex heterogeneous data sets are fundamentally changing industry and research. Coupled with hardware improvements, and ease of implementation, a wide variety of deep neural network architectures can quickly be developed to solve a sweeping range of problems such as: object detection in images, automatic healthcare diagnosis using heterogenous data sources, real time language translating and sentence prediction, upscaling low resolution images, and forecasting of multivariate timeseries. Generally, many of these architectures outperform classical machine learning approaches in their respective tasks, however, this typically comes at a cost of interpretability. These black box algorithms generally suffer from lack of transparency in both model complexity as well as the rationale behind the prediction. This lack of comprehension, is driving an emerging area of interest in “Explainable AI”. An algorithm called: “Deep Temporal Multiple Instance Learning”1 was a recently developed to identify precursors to adverse events and has been applied in the aviation domain. The deep learning architecture is designed to capture the evolution of the probability of the outcome over the time preceding the adverse event using a multiple instance learning approach as illustrated in Figure 1. Precursors are defined when the probability of the event has exceeded a threshold at some point in the timeseries, at which point, a sensitivity analysis is performed to determine contributing factors. The contributing factors are used to explain and define the precursor during the periods where the probability score is high. The identified contributing factors are then presented to subject matter experts to provide objective insights into the leading factors associated with the particular adverse event. The algorithm has been tested on flight data from a commercial airline and has the ability to discover precursors to known adverse events that take the form of safety critical operations, such as unstable approach events on final approach. Apart from detecting precursors to adverse events, the converse can also be leveraged to discover corrective actions. These positive actions manifest themselves as periods in the timeseries when the precursor score has been lowered from an elevated state; meaning that if the system had been left uncorrected, it would have eventually reached the adverse event state. Characterizing these state changes can help identify successful interventions that may not have been known before. Policy makers and procedure designers can use this additional knowledge to craft more safety and efficient resilient procedures for future operations and therefore improve the overall performance of the National Airspace.

Matthews, Bryan L.↗
DOE OSTI2022

Synthesis and Analysis of Performance-Advantaged Bioproducts

Performance-advantaged bioproducts (PABPs) are "novel products where the bio-based product does not resemble an existing petroleum-derived molecule but offers a performance advantage over existing products" (Fitzgerald, Bailey 2018). PABPs are an exciting area with near-term potential to accelerate the bioeconomy. We focus on synthesis, characterization, and economic and sustainability analyses for PABPs, aiming to leverage the inherent chemical functionality of molecules from carbohydrates and lignin via chemical and biological transformations. We collaborate with other BETO projects to source new molecules. Our work is integrated with the Inverse Design project, which provides computational predictions for PABPs and first principles-based results to explain observed properties. Primary outcomes include 1) a Nature Reviews Materials paper that establishes PABP design principles, 2) PA nylons from beta-ketoadipic acid, 3) new recyclable thermosets from bio-aromatic amines, 4) new PA plasticizers that are less toxic, and 5) the experimental validation of a machine learning tool, PolyML, from the Inverse Design project. Going forward, we are working towards an integrated framework to dramatically narrow PABP design space and a materials flow analysis of commodity chemicals as a benchmark for PABPs. Our main challenges are in the sourcing of new molecules that are not commercially available and the need for comprehensive characterizations and scale-up for technology transfer.

BIOMASS FUELS↗
DOE OSTI2026

Spatiotemporal Dynamics of the Relative Abundance of Soil Nutrient‐Degrading Enzyme‐Encoding Genes Across Continental US Ecoregions

Understanding the spatiotemporal patterns in the relative abundance of soil extracellular enzyme‐encoding genes is critical for predicting microbial responses to environmental change and their potential role in nutrient cycling. Yet, integrating novel metagenomic observations with spatiotemporal environmental gradients to infer regional patterns and future trajectories has remained unclear. To address this gap, we applied a machine learning (ML) approach, integrating soil metagenomic data with environmental variables—soil properties, topography, vegetation, and climate—to predict the relative abundance of enzyme‐encoding genes for soil carbon (C), nitrogen (N), and phosphorus (P) across surface soils of the continental United States. We assessed potential responses under future emission scenarios (SSP2‐4.5 and SSP5‐8.5) by comparing a baseline (1985–2014) to a future period (2071–2100). The ML model explained 57%–63% of baseline variation. Precipitation was identified as the most influential factor for the relative abundance of C‐ and N‐degrading enzyme‐encoding genes, while slope length, representing horizontal distance that water can travel downslope, was the primary driver for P‐degrading enzyme‐encoding genes abundance. Projections revealed spatially heterogeneous shifts across continental US ecoregions: the relative abundance of C‐ and N‐degrading enzyme‐encoding genes decreased in wetter ecoregions and increased in drier ecoregions under future climate, while P‐degrading enzyme‐encoding genes abundance decreased significantly in semiarid and Mediterranean ecoregions. This study demonstrates the utility of metagenomic data for mapping soil genetic potential and predicting its regional response to environmental change, to inform ecosystem management strategies.

extracellular enzyme-encoding genes↗
DOE OSTI2023

Intermediate Molecular Phenotypes to Identify Genetic Markers of Anthracycline-Induced Cardiotoxicity Risk

Cardiotoxicity due to anthracyclines (CDA) affects cancer patients, but we cannot predict who may suffer from this complication. CDA is a complex trait with a polygenic component that is mainly unidentified. We propose that levels of intermediate molecular phenotypes (IMPs) in the myocardium associated with histopathological damage could explain CDA susceptibility, so variants of genes encoding these IMPs could identify patients susceptible to this complication. Thus, a genetically heterogeneous cohort of mice (n = 165) generated by backcrossing were treated with doxorubicin and docetaxel. We quantified heart fibrosis using an Ariol slide scanner and intramyocardial levels of IMPs using multiplex bead arrays and QPCR. We identified quantitative trait loci linked to IMPs (ipQTLs) and cdaQTLs via linkage analysis. In three cancer patient cohorts, CDA was quantified using echocardiography or Cardiac Magnetic Resonance. CDA behaves as a complex trait in the mouse cohort. IMP levels in the myocardium were associated with CDA. ipQTLs integrated into genetic models with cdaQTLs account for more CDA phenotypic variation than that explained by cda-QTLs alone. Allelic forms of genes encoding IMPs associated with CDA in mice, including AKT1, MAPK14, MAPK8, STAT3, CAS3, and TP53, are genetic determinants of CDA in patients. Two genetic risk scores for pediatric patients (n = 71) and women with breast cancer (n = 420) were generated using machine-learning Least Absolute Shrinkage and Selection Operator (LASSO) regression. Thus, IMPs associated with heart damage identify genetic markers of CDA risk, thereby allowing more personalized patient management.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2004

Development of a State Machine Sequencer for the Keck Interferometer: Evolution, Development and Lessons Learned using a CASE Tool Approach

This paper presents a discussion of the evolution of a sequencer from a simple EPICS (Experimental Physics and Industrial Control System) based sequencer into a complex implementation designed utilizing UML (Unified Modeling Language) methodologies and a CASE (Computer Aided Software Engineering) tool approach. The main purpose of the sequencer (called the IF Sequencer) is to provide overall control of the Keck Interferometer to enable science operations be carried out by a single operator (and/or observer). The interferometer links the two 10m telescopes of the W. M. Keck Observatory at Mauna Kea, Hawaii. The IF Sequencer is a high-level, multi-threaded, Hare1 finite state machine, software program designed to orchestrate several lower-level hardware and software hard real time subsystems that must perform their work in a specific and sequential order. The sequencing need not be done in hard real-time. Each state machine thread commands either a high-speed real-time multiple mode embedded controller via CORB A, or slower controllers via EPICS Channel Access interfaces. The overall operation of the system is simplified by the automation. The UML is discussed and our use of it to implement the sequencer is presented. The decision to use the Rhapsody product as our CASE tool is explained and reflected upon. Most importantly, a section on lessons learned is presented and the difficulty of integrating CASE tool automatically generated C++ code into a large control system consisting of multiple infrastructures is presented.

interferometer↗
DOE OSTI2024

Human-Centered and Explainable Artificial Intelligence in Nuclear Operations

Nuclear power plants in the United States are critical to the nation’s energy security, accounting for 20% of all electricity produced for the power grid. As energy needs grow, 100 gigawatts of additional nuclear power will be necessary by 2050, more than double the current capacity. Realizing this target requires cutting-edge technology like artificial intelligence (AI) and machine learning (ML) that can bring about significant increases in the level of automation. Human-centered AI (HCAI) is a combination of human-centered design (human factors, human-in-the-loop, etc.) with AI/ML to help produce an efficient and reliable system with full consideration for human engagement. This paper provides a comprehensive and novel discussion of HCAI considerations in nuclear power, introducing unique applications for the existing fleet as well as new advanced reactor designs. We include real-life use cases of AI applications to work management processes at nuclear power sites and highlight lessons learned for HCAI.

Hall, Anna↗
DOE OSTI2022

Mesoscale structural gradients in human tooth enamel

The outstanding mechanical and chemical properties of dental enamel emerge from its complex hierarchical architecture. An accurate, detailed multiscale model of the structure and composition of enamel is important for understanding lesion formation in tooth decay (dental caries), enamel development (amelogenesis) and associated pathologies (e.g., amelogenesis imperfecta or molar hypomineralization), and minimally invasive dentistry. Although features at length scales smaller than 100 nm (individual crystallites) and greater than 50 µm (multiple rods) are well understood, competing field of view and sampling considerations have hindered exploration of mesoscale features, i.e., at the level of single enamel rods and the interrod enamel (1 to 10 µm). Here, we combine synchrotron X-ray diffraction at submicrometer resolution, analysis of crystallite orientation distribution, and unsupervised machine learning to show that crystallographic parameters differ between rod head and rod tail/interrod enamel. This variation strongly suggests that crystallites in different microarchitectural domains also differ in their composition. Thus, we use a dilute linear model to predict the concentrations of minority ions in hydroxylapatite (Mg 2+ and CO 3 2- /Na + ) that plausibly explain the observed lattice parameter variations. While differences within samples are highly significant and of similar magnitude, absolute values and the sign of the effect for some crystallographic parameters show interindividual variation that warrants further investigation. In conclusion, by revealing additional complexity at the rod/interrod level of human enamel and leaving open the possibility of modulation across larger length scales, these results inform future investigations into mechanisms governing amelogenesis and introduce another feature to consider when modeling the mechanical and chemical performance of enamel.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

AI to Automate ModEx for Optimal Predictive Improvement and Scientific Discovery

Focal Areas: Data acquisition and assimilation enabled by machine learning, AI, advanced experimental optimization, unsupervised learning, and hardware-related AI efforts; Predictive modeling through AI techniques and AI-derived model components; Using AI to design a hierarchical model prediction system consisting and model selection; and, Interrogating complex data (observed and simulated) using AI, big data analytics, and other advanced methods such as explainable AI and physics- or knowledge-guided AI.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Unified epigenomic, transcriptomic, proteomic, and metabolomic taxonomy of Alzheimer’s disease progression and heterogeneity

Alzheimer’s disease (AD) is a heterogeneous disorder with abnormalities in multiple biological domains. In an advanced machine learning analysis of postmortem brain and in vivo blood multi-omics molecular data ( N = 1863), we integrated epigenomic, transcriptomic, proteomic, and metabolomic profiles into a multilevel biological AD taxonomy. We obtained a personalized multilevel molecular index of AD dementia progression that predicts severity of neuropathologies, and identified three robust molecular-based subtypes that explain much of the pathologic and clinical heterogeneity of AD. These subtypes present distinct patterns of alteration in DNA methylation, RNA, proteins, and metabolites, identifiable in the brain and subsequently in blood. In addition, the genetic variations that predispose to the various AD subtypes in brain predict distinct spatial patterns of alteration in cell types, suggesting a unique influence of each putative AD variant on neuropathological mechanisms. These observations support that an individually tailored multi-omics molecular taxonomy of AD may represent distinct targets for preventive or treatment interventions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Appendices for Geothermal Exploration Artificial Intelligence Report

The Geothermal Exploration Artificial Intelligence looks to use machine learning to spot geothermal identifiers from land maps. This is done to remotely detect geothermal sites for the purpose of energy uses. Such uses include enhanced geothermal system (EGS) applications, especially regarding finding locations for viable EGS sites. This submission includes the appendices and reports formerly attached to the Geothermal Exploration Artificial Intelligence Quarterly and Final Reports. The appendices below include methodologies, results, and some data regarding what was used to train the Geothermal Exploration AI. The methodology reports explain how specific anomaly detection modes were selected for use with the Geo Exploration AI. This also includes how the detection mode is useful for finding geothermal sites. Some methodology reports also include small amounts of code. Results from these reports explain the accuracy of methods used for the selected sites (Brady Desert Peak and Salton Sea). Data from these detection modes can be found in some of the reports, such as the Mineral Markers Maps, but most of the raw data is included the DOE Database which includes Brady, Desert Peak, and Salton Sea Geothermal Sites.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Machine Learning Prediction of Tritium‐Helium Groundwater Ages in the Central Valley, California, USA

Abstract Groundwater ages provides insight into recharge rates, flow velocities, and vulnerability to contaminants. The ability to predict groundwater ages based on more accessible parameters via Machine Learning (ML) would advance our ability to guide sustainable management of groundwater resources. In this study, ML models were trained and tested on a large data set of tritium concentrations and tritium‐helium groundwater ages from the California Central Valley, a large groundwater basin with complex land use, irrigation, and water management practices. The ML models were trained on 63 features, including location, well construction information, landscape characteristics, and climate variables, water chemistry, and stable isotopes. The Bagging regressor method can accurately classify (F1‐score = 0.91) groundwater samples as either modern or pre‐modern whereas the accuracy of the ML prediction of continuous tritium‐helium groundwater ages is limited and explains only of the variability in this data set. In general, ML groundwater age prediction relies mostly on features related to (a) the source of groundwater recharge, (b) contaminant history, (c) aquifer materials, (d) well construction, and (e) geochemical reactions along flow paths.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Improving the accuracy of freight mode choice models: A case study using the 2017 CFS PUF data set and ensemble learning techniques

Here, the US Census Bureau has collected two rounds of experimental data from the Commodity Flow Survey, providing shipment-level characteristics of nationwide commodity movements, published in 2012 (i.e., Public Use Microdata) and in 2017 (i.e., Public Use File). With this information, data-driven methods have become increasingly valuable for understanding detailed patterns in freight logistics. In this study, we used the 2017 Commodity Flow Survey Public Use File data set to explore building a high-performance freight mode choice model, considering three main improvements: (1) constructing local models for each separate commodity/industry category; (2) extracting useful geographical features, particularly the derived distance of each freight mode between origin/destination zones; and (3) applying additional ensemble learning methods such as stacking or voting to combine results from local and unified models for improved performance. The proposed method achieved over 92% accuracy without incorporating external information, an over 19% increase compared to directly fitting Random Forests models over 10,000 samples. Furthermore, SHAP (Shapely Additive Explanations) values were computed to explain the outputs and major patterns obtained from the proposed model. The model framework could enhance the performance and interpretability of existing freight mode choice models.

42 ENGINEERING↗
DOE OSTI2020

Artificial Intelligence for Digital Security and Protections

Proper functioning of nuclear power plants relies on a mix of well-regulated human and machine-driven workflows. This regulation supports nuclear safety through a series of processes and many of the tasks that support these processes have a repetitive nature that make artificial intelligence (AI) informed by machine learning (ML) a potential aid in a variety of tasks. AI is being evaluated for activities that include inspections, fuel processing, monitoring, and other activities. The introduction of any new technology presents a potential new attack vector. In the case of AI/ML, there are many attacks that have already been discovered and over time the attacks can be expected to follow the growth pattern observed in cyber security. While future planning is necessary, current efforts need to be established now to predict the threat emergence over the next year 10 years and mitigate potential threats. Based on these observations, AI/ML will need to become trustworthy, which corresponds to techniques and procedures that emphasize AI explainability along with resilience techniques to data, algorithms, models, and systems. This kind of system robustness is the foundation for defenses against AI/ML-specific attacks. Attempting to look forward and take a broad view of capabilities provides input to research roadmaps and the ability to distill vulnerabilities into specific use cases may provide greater assistance in understanding the technology benefits while introducing new risks. The impact of current and future AI in three areas—capabilities, challenges, and recovery strategies—represents an initial attempt at balancing both.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗