Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep learning methods”

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 1,603 records · Page 89
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

Molecular and Histopathological Changes in Mouse Intestinal Tissue After Proton Exposure

Radiation in space, including types from solar particle events (SPE's), poses serious health risks to astronauts and is especially dangerous for long duration missions. Protons are the most abundant particles in deep space and to date there is little known about the details of the negative consequences crew members will face upon exposure to them. This ongoing project involves a mouse model subjected to several minutes of proton radiation at an energy of 250 MeV and doses of 0 Gy, 0.1 Gy, 1 Gy, and 2 Gy. The gastrointestinal tract of each animal was dissected four hours post-irradiation and the small intestine was isolated and flash-frozen. Three specimens per dose were studied. Tissue was homogenized and RNA was isolated in order for cDNA synthesis and real-time PCR to be performed. Gene expression changes are currently being analyzed specific to mouse apoptosis. Immunohistochemistry will be used to confirm any significant changes found in the analyses. Immunohistochemistry is also being used to observe gamma H2AX staining to learn of any DNA damage that occurred as a result of proton exposure. We expect to see increased DNA damage due to proton exposure. Finally, histopathologic observation of the tissue will be completed using standard H&E staining methods to screen for morphologic changes. Increased apoptosis is expected to be seen in the tissues which is typical of radiation damage. Observations will be confirmed by a pathologist.

Purgason, A.↗
DOE OSTI2024

Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources

The primary goals of this project are identifying hidden geothermal resources in the USA and designing profitable enhanced geothermal systems (EGS). Many non-obvious processes and parameters could characterize geothermal resources and could control the ultimate energy potential of geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize geothermal resources, but this data is sparse and multi-scale. This has hindered attempts to leverage the datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) give promise to overcome these issues. Modern ML methods and tools can (1) analyze large datasets, (2) assimilate model ensembles that include a multitude of inputs and outputs, (3) process sparse datasets, (4) perform transfer learning between sites with different data quality, (5) extract hidden geothermal signatures from field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. In this work, we implement ML-based geothermal exploration and an enhanced geothermal systems (EGS) design tool to achieve the above goals. Our exploration tool is GeoThermalCloud (GTC) EGS design tool is GeoDT-ML. GTC (github.com/SmartTensors/GeoThermalCloud.jl) utilizes a LANL unsupervised ML platform called SmartTensors (https://tensors.lanl.gov/) to automate data analyses and interpretations by extracting hidden signatures to identify geothermal prospects. It enables the identification of critical measurements needed to identify geothermal resource signatures. GeoDT-ML (github.com/SmartTensors/GeoThermalCloud.jl/tree/master/) adds coupling to GeoDT (https://github.com/GeoDesignTool/GeoDT.git) for stochastic EGS design optimization and performance prediction. GeoDT-ML leverages recent advances in deep learning and high-performance computing. Contributors to this effort include LANL, PNNL, Google, Stanford, and Julia Computing.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Data-driven Community-centered Resilient Assessment and Planning Toolkit for Nexus of Energy and Water (DCRAPT-NEW)

Urban areas, including Detroit and Pittsburgh, have suffered significant dual outages of the electrical and water infrastructure in the past decade due, in part, to the increasing number of extreme weather events. With increasing temperatures and rainfall intensity, these regions need to prepare for increasing extreme events through community-based energy and water resilience analysis, planning, and enhancement. This project developed a suite of open-source, open-access, community-centered, data-driven assessment and distributed energy resource (DER) and planning tools for energy and water resilience enhancement in urban areas. Through establishing a multi-level community awareness and engagement mechanism and a comprehensive collection of power outage and flooding data, an innovative group of community energy and water resilience assessment and planning tools have been developed for a wide range of users with differing and variable sets of data available to them. The developed tools include (1) DOE EAGLE-I data-driven, deep-learning assisted resilience assessment and DER planning tools at the county level with socioeconomic factors incorporated; (2) Utility annual power outage data-driven tools for long term resilience assessment and DER planning and 15-min power outage data-driven tools for short term resilience assessment and planning; (3) Detailed engineering tools for energy and water systems resilience assessment and planning when the system topology and component fragility curves are available; (4) Alternative Resiliency Metric Calculation that extracts and separates outage and restoration processes; and (5) Co-optimization tools that evaluate the resilience of the power and sewage system and allow users to conduct joint planning with energy and wastewater systems. The developed tools provide planners, decision-makers, and stakeholders with powerful capabilities to systematically evaluate system/community resilience and optimal and actionable guidance for enhancing resilience while prioritizing DER investments. The tools have been used and validated in Detroit and Pittsburgh and can be used in other areas of the nation. In addition, this project will (1) advance the knowledge and applications of machine-learning methods in analyzing and fusing different layers of information and generating meaningful data points such as generating rare weather events; (2) significantly improve the energy and water resilience of the identified communities in Detroit and Pittsburgh and prepare for more frequent and severe weather conditions; (3) help communities assess extreme weather event impacts and address short-term and long-term resilience-related issues The developed tools have been made public via GitHub and demonstrated to community stakeholders and utility companies via the two annual workshops and numerous community engagement meetings. The project outcomes are also disseminated through publications in various journals and conference proceedings, and presentations at top conferences.

13 HYDRO ENERGY↗
DOE OSTI2026

Multidimensional Distributional Neural Network Output Demonstrated in Super‐Resolution of Surface Wind Speed

Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While existing methods capture either aleatoric or epistemic uncertainty, few offer closed-form, multidimensional distributions that preserve spatial correlation while remaining computationally tractable. In this work, we present a framework for training neural networks with a multidimensional Gaussian loss, generating a closed-form predictive distribution over outputs informed by non-identically distributed training data. Our approach captures aleatoric uncertainty by iteratively estimating the means and covariance matrices, and is demonstrated on a super-resolution example out-of-training-sample. We leverage a Fourier representation of the covariance matrix to stabilize network training and preserve spatial correlation. We introduce a novel regularization strategy—referred to as information sharing—that interpolates between image-specific and global covariance estimates, enabling convergence of the super-resolution downscaling network trained on image-specific distributional loss functions. This framework allows for efficient sampling, explicit correlation modeling, and extensions to more complex distribution families all without disrupting prediction performance. We demonstrate the method on a surface wind speed downscaling task and discuss its broader applicability to uncertainty-aware prediction in scientific models.

17 WIND ENERGY↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
DOE OSTI2021

The radioactive nuclei 26 Al and 60 Fe in the Cosmos and in the solar system

The cosmic evolution of the chemical elements from the Big Bang to the present time is driven by nuclear fusion reactions inside stars and stellar explosions. A cycle of matter recurrently re-processes metal-enriched stellar ejecta into the next generation of stars. The study of cosmic nucleosynthesis and this matter cycle requires the understanding of the physics of nuclear reactions, of the conditions at which the nuclear reactions are activated inside the stars and stellar explosions, of the stellar ejection mechanisms through winds and explosions, and of the transport of the ejecta towards the next cycle, from hot plasma to cold, star-forming gas. Due to the long timescales of stellar evolution, and because of the infrequent occurrence of stellar explosions, observational studies are challenging, as they have biases in time and space as well as different sensitivities related to the various astronomical methods. Here, we describe in detail the astrophysical and nuclear-physical processes involved in creating two radioactive isotopes useful in such studies, 26 Al and 60 Fe. Due to their radioactive lifetime of the order of a million years, these isotopes are suitable to characterise simultaneously the processes of nuclear fusion reactions and of interstellar transport. We describe and discuss the nuclear reactions involved in the production and destruction of 26 Al and 60 Fe, the key characteristics of the stellar sites of their nucleosynthesis and their interstellar journey after ejection from the nucleosynthesis sites. This allows us to connect the theoretical astrophysical aspects to the variety of astronomical messengers presented here, from stardust and cosmic-ray composition measurements, through observation of γ rays produced by radioactivity, to material deposited in deep-sea ocean crusts and to the inferred composition of the first solids that have formed in the Solar System. We show that considering measurements of the isotopic ratio of 26 Al to 60 Fe eliminate some of the unknowns when interpreting astronomical results, and discuss the lessons learned from these two isotopes on cosmic chemical evolution. This review paper has emerged from an ISSI-BJ Team project in 2017–2019, bringing together nuclear physicists, astronomers, and astrophysicists in this inter-disciplinary discussion.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRSDate not supplied

The Porous Microstructure Analysis (PuMA) software

The open-source Porous Microstructure Analysis (PuMA) software was implemented to offer an efficient framework for determining material characteristics from 3D microstructures. Its development was inspired by progress in X-ray microtomography, an imaging technology that captures the internal structure of materials in 3D, and even in a 4D temporal context. Over recent years, this method has transformed the domain of materials science due to its capability to non-destructively examine material microstructures while presenting digital data about their geometrical details. It has provided insights into materials relevant to several NASA missions, including heatshields, parachute fabrics, meteorites, and other advanced composites. PuMA, in its current version 3, delivers an array of features, spanning from basic geometric insights of a microstructure to intricate anisotropic thermo-elastic and chemical behavior. Specifically, the software evaluates morphological attributes (specific surface area, volume fractions, mean intercept lengths, orientation) and physical characteristics (conductivity, elasticity, permeability, and tortuosity). Additionally, it can model material degradation processes, such as oxidation and surface chemistry interactions. The software can generate synthetic microstructures, from straightforward geometrical designs to intricate woven and non-woven geometries. Coupling material generation and characterization enable parametric studies and sensitivity analysis to optimize the microstructural performance and inform design decisions and reliability assessment based on uncertainty quantification. A recent addition to PuMA includes the TomoSAM plugin, devised to incorporate the cutting-edge Segment Anything Model (SAM). SAM is a promptable deep learning model that can identify objects and create image masks in a zero-shot manner, based only on a few user clicks. The synergy between these tools aids in the segmentation of complex 3D datasets from tomography or other imaging techniques, which would otherwise require a laborious manual segmentation process.

Tomography↗
NASA NTRS1998

Exploration of the Moon with Remote Sensing, Ground-Penetrating Radar, and the Regolith-Evolved Gas Analyzer (REGA)

There are two important reasons to explore the Moon. First, we would like to know more about the Moon itself: its history, its geology, its chemistry, and its diversity. Second, we would like to apply this knowledge to a useful purpose. namely finding and using lunar resources. As a result of the recent Clementine and Lunar Prospector missions, we now have global data on the regional surface mineralogy of the Moon, and we have good reason to believe that water exists in the lunar polar regions. However, there is still very little information about the subsurface. If we wish to go to the lunar polar regions to extract water, or if we wish to go anywhere else on the Moon and extract (or learn) anything at all, we need information in three dimensions an understanding of what lies below the surface, both shallow and deep. The terrestrial mining industry provides an example of the logical steps that lead to an understanding of where resources are located and their economic significance. Surface maps are examined to determine likely locations for detailed study. Geochemical soil sample surveys, using broad or narrow grid patterns, are then used to gather additional data. Next, a detailed surface map is developed for a selected area, along with an interpretation of the subsurface structure that would give rise to the observed features. After that, further sampling and geophysical exploration are used to validate and refine the original interpretation, as well as to make further exploration/ mining decisions. Integrating remotely sensed, geophysical, and sample datasets gives the maximum likelihood of a correct interpretation of the subsurface geology and surface morphology. Apollo-era geophysical and automated sampling experiments sought to look beyond the upper few microns of the lunar surface. These experiments, including ground-penetrating radar and spectrometry, proved the usefulness of these methods for determining the best sites for lunar bases and lunar mining operations.

Cooper, B. L.↗
DOE OSTI2021

Arrested Phase Separation in Double-Exchange Models: Large-Scale Simulation Enabled by Machine Learning

In this work, we present large-scale dynamical simulations of electronic phase separation in the single-band double-exchange model based on deep-learning neural-network potentials trained from small-size exact diagonalization solutions. We uncover an intriguing correlation-induced freezing behavior as doped holes are segregated from half filled insulating background during equilibration. While the aggregation of holes is stabilized by the formation of ferromagnetic clusters through Hund’s coupling between charge carriers and local magnetic moments, this stabilization also creates confining potentials for holes when antiferromagnetic spin-spin correlation is well developed in the background. The dramatically reduced mobility of the self-trapped holes prematurely disrupts further growth of the ferromagnetic clusters, leading to an arrested phase separation. Implications of our findings for phase separation dynamics in materials that exhibit colossal magnetoresistance effect are discussed.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Deciphering the Scattering of Mechanically Driven Polymers Using Deep Learning

Here, we present a deep learning approach for analyzing two-dimensional scattering data of semiflexible polymers under external forces. In our framework, scattering functions are compressed into a three-dimensional latent space using a Variational Autoencoder (VAE), and two converter networks establish a bidirectional mapping between the polymer parameters (bending modulus, stretching force, and steady shear) and the scattering functions. The training data are generated using off-lattice Monte Carlo simulations to avoid the orientational bias inherent in lattice models, ensuring robust sampling of polymer conformations. The feasibility of this bidirectional mapping is demonstrated by the organized distribution of polymer parameters in the latent space. By integrating the converter networks with the VAE, we obtain a generator that produces scattering functions from given polymer parameters and an inferrer that directly extracts polymer parameters from scattering data. While the generator can be utilized in a traditional least-squares fitting procedure, the inferrer produces comparable results in a single pass and operates 3 orders of magnitude faster. This approach offers a scalable automated tool for polymer scattering analysis and provides a promising foundation for extending the method to other scattering models, experimental validation, and the study of time-dependent scattering data.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗
DOE OSTI2022

Materials structure–property factorization for identification of synergistic phase interactions in complex solar fuels photoanodes

Abstract Properties can be tailored by tuning composition in high-order composition spaces. For spaces with complex phase behavior, modeling the properties as a function of composition and phase distribution remains a formidable challenge. We present materials structure–property factorization (MSPF) as an approach to automate modeling of such data and identify synergistic phase interactions. MSPF is an interpretable machine learning algorithm that couples phase mapping via Deep Reasoning Networks (DRNets) to matrix factorization-based modeling of the representative properties of each phase in a dataset. MSPF is demonstrated for Bi–Cu–V oxide photoanodes for solar fuel generation, which contains 25 different phase combinations and correspondingly exhibits complex composition-structure-photoactivity relationships. Comparing the measured photoactivity to a learned model for non-interacting phases, synergistic phase interactions are identified to guide further photoactivity optimization and understanding. MSPF identifies synergistic interactions of a BiVO 4 -like phase with both Cu 2 V 2 O 7 -like and CuV 2 O 6 -like phases, creating avenues for understanding complex photoelectrocatalysts.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Development of a Deep Learning Model for Predicting the Drag Coefficients of Spherical and Non-Spherical Particles,

There is yet to be a well-established drag model for non-spherical particles required in a particle-laden flow that could cover a wide range of sphericities. This talk will explore the development of a general drag model for non-spherical particles by applying deep learning using available experimental data available in the literature. The integration of several raw experimental measurements from different sources and research directions allows the training of robust Artificial Intelligence and Machine Learning (ML) models. Neural networks are an ML approach inspired by the inner biological workings of the brain. This work aims to develop a Deep Neural Network (DNN) that predicts drag coefficient values with the ability to adapt appropriately to unseen data. Given the limited number of data points available and the variance found within the data collected from various sources, challenges may arise when looking to train the model. Our study tests and implements various model regularization techniques and assesses different loss and activation functions for the proposed DNN. The proposed model considers a broader range of features other than sphericity and Reynold number. These features include density ratio, solid volume fraction, lengthwise and crosswise sphericity, and more. Furthermore, we present the features that play a significant role in predicting different drag coefficients through feature importance. Within the investigated parameter ranges in this study, the following conclusions can be achieved and summarized below: • An improved drag coefficient model can be developed by considering more features such as, aspect ratio, lengthwise sphericity, crosswise sphericity, and density ratio. • DNN model can predict better results compared to traditional methods using MAE metric. • The proposed model addresses data challenges such as limited data and extreme data points through expanded feature-set and regularization. • Three major features that mostly affect the drag coefficient were identified from a feature importance analysis.

Presa-Reyes, Maria↗
DOE OSTI2021

Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks

Abstract Streamflow forecasting over gauged and ungauged basins play a vital role in water resources planning, especially under the changing climate. Increased availability of large sample hydrology data sets, together with recent advances in deep learning techniques, has presented new opportunities to explore temporal and spatial patterns in hydrological signatures for improving streamflow forecasting. The purpose of this study is to adapt and benchmark several state‐of‐the‐art graph neural network (GNN) architectures, including ChebNet, Graph Convolutional Network (GCN), and GraphWaveNet, for end‐to‐end graph learning. We explicitly represent river basins as nodes in a graph, learn the spatiotemporal nodal dependencies, and then use the learned relations to predict streamflow simultaneously across all nodes in the graph. The efficacy of the developed GNN models is investigated using the Catchment Attributes and MEteorology for Large‐sample Studies (CAMELS) data set under two settings, fixed graph topology (transductive learning), and variable graph topology (inductive learning), with the latter applicable to prediction in ungauged basins (PUB). Results indicate that GNNs are generally robust and computationally efficient, achieving similar or better performance than a baseline model trained using the long short‐term memory (LSTM) network. Further analyses are conducted to interpret the graph learning process at the edge and node levels and to investigate the effect of different model configurations. We conclude that graph learning constitutes a viable machine learning‐based method for aggregating spatiotemporal information from a multitude of sources for streamflow forecasting

Sun, Alexander Y.↗
NASA NTRSDate not supplied

The Porous Microstructure Analysis (PuMA) software

The open-source Porous Microstructure Analysis (PuMA) software was created to offer an efficient framework for determining material properties from 3D microstructures. Its development was inspired by progress in X-ray microtomography, an imaging technology that captures the internal structure of materials in 3D, and even in a 4D temporal context. Over recent years, this method has transformed the domain of materials science due to its capability to non-destructively examine material microstructures while presenting digital data about their geometrical details. It has provided insights into materials relevant to several NASA missions, including heatshields, parachute fabrics, meteorites, and other advanced composites. PuMA, in its current version 3, delivers an array of features, spanning from basic geometric insights of a microstructure to intricate anisotropic thermo-elastic and chemical behavior. Specifically, the software evaluates morphological attributes (specific surface area, volume fractions, mean intercept lengths, orientation) and physical characteristics (conductivity, elasticity, permeability, and tortuosity). Additionally, it can model material degradation processes, such as oxidation and surface chemistry interactions. The software can generate synthetic microstructures, from straightforward geometrical designs to intricate woven and non-woven geometries. Coupling material generation and characterization enables parametric studies and sensitivity analysis to optimize the microstructural performance and inform design decisions and reliability assessment based on uncertainty quantification. A recent addition to PuMA includes the TomoSAM plugin, devised to incorporate the cutting-edge Segment Anything Model (SAM) into our image segmentation workflow. SAM is a promptable deep learning model that can identify objects and create image masks in a zero-shot manner, based only on a few user clicks. The synergy between these tools aids in the segmentation of complex 3D datasets from tomography and other imaging techniques, which would otherwise require a laborious manual segmentation process.

Tomography↗
DOE OSTI2025

Emulation of the calculations of final r -process abundance patterns with a neural network

This work explores the construction of a fast emulator for the calculation of the final pattern of nucleosynthesis in the rapid neutron capture process (the r-process). An emulator is built using a feed-forward artificial neural network (ANN). We train the ANN with nuclear data and relative abundance patterns. We take as input the β-decay half-lives and the one-neutron separation energy of the nuclei in the rare-earth region. The output is the final isotopic abundance pattern. In this work, we focus on the nuclear data and abundance patterns in the rare-earth region to reduce the dimension of the input and output space. We show that the ANN can capture the effect of the changes in the nuclear physics inputs on the final r-process abundance pattern in the adopted astrophysical conditions. We employ the deep ensemble method to quantify the prediction uncertainty of the neural network emulator. The emulator achieves a speed-up by a factor of about 20 000 in obtaining a final abundance pattern in the rare-earth region. The emulator may be utilized in statistical analyses such as uncertainty quantification, inverse problems, and sensitivity analysis.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

Neutral pion reconstruction using machine learning in the experiment at 〈E ν〉 6 GeV

This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013–2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈E ν〉 between 1–10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current νe events arising from νμ → νe appearance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Photon classification with Gradient Boosted Trees at CLAS12

Dihadron semi-inclusive deep inelastic scattering (SIDIS) of 10.6 GeV longitudinally polarized electrons off the proton has been measured using the CLAS12 detector at Jefferson Lab. Two separate channels, π + π 0 and π - π 0 , were analyzed, requiring the reconstruction of diphoton pairs. Here, in this analysis, we addressed the problem of false neutral particles being reconstructed by CLAS12's event builder, polluting the otherwise physical combinatorial background underneath the π 0 peak. A photon classifier using a Gradient Boosted Trees (GBTs) architecture was trained with Monte Carlo simulations to reduce the amount of background π 0 's. We show that the nearest-neighbor features learned by the model lead to a substantial increase in signal vs. background discrimination compared to previous CLAS12 π^0 analyses. The machine learning approach recovers several times more dihadron statistics for the dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

GeoThermalCloud: Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources

The primary goals of this project are exploring hidden geothermal resources in the U.S.A. and designing profitable enhanced geothermal systems (EGS). Many processes and parameters control geothermal exploration and energy production from geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize subsurface geothermal conditions. Sparse and multi-scale characteristics of these datasets prohibit properly leveraging these datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) promise to resolve these issues. The tremendous challenges and risks of geothermal exploration and production bring the demand for novel ML methods and tools that can (1) analyze large field datasets, (2) assimilate model simulations (large inputs and outputs), (3) process sparse datasets, (4) perform transfer learning (between sites with different exploratory levels), (5) extract hidden geothermal signatures in the field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. To address these necessities, ML-based geothermal resources exploration and enhanced geothermal systems (EGS) design tools have been developed. The exploration tool is called GeoThermalCloud and EGS design tool is called GeoDT-ML. GeoThermalCloud (https://github.com/SmartTensors/GeoThermalCloud.jl) utilizes a LANL unsupervised ML platform called SmartTensors (https://tensors.lanl.gov/) to automate data analyses and interpretations by extracting hidden signatures to identify geothermal prospects. Also, it enables the identification of critical measurements needed to identify geothermal resource signatures. Alternatively, GeoDT-ML (https://github.com/SmartTensors/GeoThermalCloud.jl/tree/master/EGS) is an ML-based alternative to GeoDT (https://github.com/GeoDesignTool/GeoDT.git), a fast, simplified multi-physics solver to evaluate EGS project designs in uncertain geologic systems. GeoDT-ML leverages recent advances in deep learning and high-performance computing. It is a faster and simpler version of GeoDT. To make this project a success, we used capabilities of LANL, PNNL, Google, Stanford, and Julia Computing. We analyzed eight datasets of the U.S.A. using GeothermalCloud and demonstrated potential highly prospective geothermal resources and identified key factors defining highly prospective sites. The first data set includes 44 locations in southwest New Mexico and 18 geological, hydrogeological, geophysical, geothermal, geochemical attributes. We defined low- and medium-temperature hydrothermal systems and discovered a new highly prospective site. The second data set analyzed 18 shallow water chemistry attributes at 14,342 locations in the Great Basin. It demarcated modestly, moderately, and highly prospective sites including key attributes for each type of prospectivity. The third data set analyzed Utah FORGE data including satellite (InSAR), geophysical (gravity, seismic), geochemical, and geothermal attributes. Here, we performed prospectivity analysis to identify future drilling locations using geological, geochemical, and geophysical attributes. Maps of temperature at depth and heat flow are constructed based on the available data. Prospectivity maps were generated, and drilling locations were proposed for future geothermal field exploration. The fourth data set analyzed 21 attributes at 120 locations in Tularosa Basin, New Mexico; data comes from past play fairway analyses in this region. ML analyses identified geothermal signatures associated with modestly, moderately, and highly hydrothermal systems. We also defined dominant attributes and spatial distribution of the geothermal signatures. The fifth, sixth, seventh, and eighth datasets include Tohatchi Springs, New Mexico, Hawaii, Brady site, Nevada, and EGS Collab, respectively. Moreover, we coupled GeothermalCloud and magnetotellurics data to pinpoint drilling locations for developing geothermal projects in the Tularosa Basin, New Mexico. GeothermalCloud found potential prospective locations for geothermal resources near White Sands Missile Range and McGregor Range at Fort Bliss. Magnetotellurics data determined the potential depth (~1800m) of geothermal prospects at McGregor Range based on apparent resistivity structures/layers in the subsurface. The McGregor Range consists of three resistivity layers and two resistivity structures. Magnetotellurics data also helps identify that the western portion of the McGregor Range has thick and low-resistivity earth materials. The low resistivity to the west is most likely for a fault system. Assuming temperature is consistent with a geothermal reservoir, the west-central part of the McGregor Range has the highest geothermal potential because of the increase in porosity and associated permeability attributed to the interpreted fault system. Also, we devised a coupling strategy between a process model and GeothermalCloud to characterize hydrogeological conditions and geothermal conditions, respectively. The process model characterizes hydrogeological and geothermal conditions on highly prospective geothermal sites provided by GeothermalCloud. We developed a physics-informed neural network (PINN) version of the Burns equation that can be easily coupled with GeothermalCloud. Furthermore, we performed an optimal design decision maximizing the economic value of an EGS power plant. This study optimized the range of well spacing between injection and production wells maximizing net present value in dollars (NPV). For this task, we used the GeoDT to simulate the Utah FORGE EGS development cycle from the initial well design to the end of production. Next, we accomplished another crucial task, which is predicting permeability of geothermal reservoirs. Predicting permeability of geothermal reservoirs is a non-trivial task because of huge computational runtime of simulation and lack of measurements. To avoid these limitations, we used easy-to-measure chemical concentrations in the subsurface as measurement data and convolutional neural network based ML model of a high-fidelity model. Next, we predicted permeability using Markov chain Monte Carlo simulation. We found that Markov chain Monte Carlo simulation predicts permeability with a high certainty if the prediction zone in the simulation area has chemical concentration data. Finally, we analyzed the DOE funded INGENIOUS and GeoDAWN projects data. For discovering hidden geothermal systems in the Great Basin, the INGENIOUS project accumulated old data, collected new data, and released them in 2022. The dataset includes a total of 24 geological, geophysical, and geochemical attributes. Data resolution and scale significantly vary prohibiting an appropriate usage. To avoid such limitations, we brought all data in the same resolution and scale by applying the inverse distance weighting interpolation technique for predicting data in unsampled locations. Subsequently, we analyzed LiDAR data of the GeoDAWN project. We received data in tiles format. The DOE’s overarching goal is to use ML on LiDAR data for finding favorable geological structures (e.g., step up faults in Brady, Nevada). To serve the purpose, we need to label favorable geologic structures that correspond to LiDAR data. We wrote an algorithm to label the LiDAR data with the favorable geologic structures.

15 GEOTHERMAL ENERGY↗