Search NASA⌕ Search

SEARCH · Search NASA

Results for “LABELLING”

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 973 records · Page 54

PDF Entity Annotation Tool (PEAT)

While different text mining approaches – including the use of Artificial Intelligence (AI) and other machine based methods - continue to expand at a rapid pace, the tools used by researchers to create the labeled datasets required for training, modeling, and evaluation remain rudimentary. Labeled datasets contain the target attributes the machine is going to learn; for example, training an algorithm to delineate between images of a car or truck would generally require a set of images with a quantitative description of the underlying features of each vehicle type. Development of labeled textual data that can be used to build natural language machine learning models for scientific literature is not currently integrated into existing manual workflows used by domain experts. Published literature is rich with important information, such as different types of embedded text, plots, and tables that can all be used as inputs to train ML/natural language processing (NLP) models, when extracted and prepared in machine readable formats. Currently, both normalized data extraction of use to domain experts and extraction to support development of ML/NLP models are labor intensive and cumbersome manual processes. Automatic extraction of data and information from formats such as PDFs that are optimized for layout and human readability, not machine readability. The PDF (Portable Document Format) Entity Annotation Tool (PEAT) was developed with the goal of allowing users to annotate publications within their current print format, while also allowing those annotations to be captured in a machine-readable format. One of the main issues with traditional annotation tools is that they require transforming the PDF into plain text to facilitate the annotation process. While doing so lessens the technical challenges of annotating data, the user loses all structure and provenance that was inherent in the underlying PDF. Also, textual data extraction from PDFs can be an error prone process. Challenges include identifying sequential blocks of text and a multitude of document formats (multiple columns, font encodings, etc.). As a result of these challenges, using existing tools for development of NLP/ML models directly from PDFs is difficult because the generated outputs are not interoperable. We created a system that allows annotations to be completed on the original PDF document structure, with no plain text extraction. The result is an application that allows for easier and more accurate annotations. In addition, by including a feature that grants the user the ability to easily create a schema, we have developed a system that can be used to annotate text for different domain-centric schemas of relevance to subject matter experts. Different knowledge domains require distinct schemas and annotation tags to support machine learning.

97 MATHEMATICS AND COMPUTING↗

Carbon Sink Strength of Subsurface Horizons in Brazilian Oxisols

Interactions with pedogenic oxides are a known mechanism of soil organic matter (SOM) protection, but little is known about how the protective power of pedogenic oxides varies with soil depth in highly weathered tropical soils. To address this issue, we followed the decomposition of a double-labeled plant litter ( 13 C/ 15 N) in microcosm experiments using samples collected at four depths (0–10, 10–20, 20–40, and 60–100 cm) from six Brazilian Oxisols. These soils were selected to include a range of taxonomic subtypes, spanning wide variations in mineralogy and texture. After a 12-mo incubation, we quantified the proportion of isotopically-labeled SOM ( 13 C/ 15 N) within the mineral fraction <53 µm (i.e., clay+silt). We found that litter-C retention increased with depth, while the opposite occurred for litter-N. Correlations between isotopically-labeled SOM and short-range order (SRO) Al-/Fe-(hydr)oxides were insignificant in topsoil (0–10 cm), but increased with depth, reaching peak significance in the 20- to 40-cm interval (r = 0.64 and 0.58, for litter-C and -N, respectively). A similar trend was observed for crystalline Al-/Fe-(hydr)oxides, which were more strongly correlated with the retention of 13 C than 15 N. We posit that in subsoil, both SRO and crystalline Al-/Fe-(hydr)oxides are more readily involved in the neoformation of mineral-organic associations. Overall, litter-C is less efficiently transferred into the clay+silt fraction of C-rich topsoil relative to C-depleted subsoil horizons, which may represent a significant C sink for Oxisols.

54 ENVIRONMENTAL SCIENCES↗

Analysis of Potential Energy Saving and CO2 Emission Reduction of Home Appliances and Commercial Equipments in China

China has implemented a series of minimum energy performance standards (MEPS) for over 30 appliances, voluntary energy efficiency label for 40 products and a mandatory energy information label that covers 19 products to date. However, the impact of these programs and their savings potential has not been evaluated on a consistent basis. This paper uses modeling to estimate the energy saving and CO{sub 2} emission reduction potential of the appliances standard and labeling program for products for which standards are currently in place, under development or those proposed for development in 2010 under three scenarios that differ in the pace and stringency of MEPS development. In addition to a baseline 'Frozen Efficiency' scenario at 2009 MEPS level, the 'Continued Improvement Scenario' (CIS) reflects the likely pace of post-2009 MEPS revisions, and the likely improvement at each revision step. The 'Best Practice Scenario' (BPS) examined the potential of an achievement of international best practice efficiency in broad commercial use today in 2014. This paper concludes that under 'CIS', cumulative electricity consumption could be reduced by 9503 TWh, and annual CO{sub 2} emissions of energy used for all 37 products would be 16% lower than in the frozen efficiency scenario. Under a 'BPS' scenario for a subset of products, cumulative electricity savings would be 5450 TWh and annual CO{sub 2} emissions reduction of energy used for 11 appliances would be 35% lower.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

International comparison of product certification and verification methods for appliances

Enforcement of appliance standards and consumer trust in appliance labeling are important foundations of growing a more energy efficient economy. Product certification and verification increase compliance rates which in turn increase both energy savings and consumer trust. This paper will serve two purposes: 1) to review international practices for product certification and verification as they relate to the enforcement of standards and labeling programs in the U.S., E.U., Australia, Japan, Canada, and China; and 2) to make recommendations for China to implement improved certification processes related to their mandatory standards and labeling program such as to increase compliance rates and energy savings potential.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

International Comparison of Product Certification and Verification Methods for Appliances

Enforcement of appliance standards and consumer trust in appliance labeling are important foundations of growing a more energy efficient economy. Product certification and verification increase compliance rates which in turn increase both energy savings and consumer trust. This paper will serve two purposes: 1) to review international practices for product certification and verification as they relate to the enforcement of standards and labeling programs in the U.S., E.U., Australia, Japan, Canada, and China; and 2) to make recommendations for China to implement improved certification processes related to their mandatory standards and labeling program such as to increase compliance rates and energy savings potential.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Hazardous Material Packaging and Transportation

This is a student training course. Some course objectives are to: recognize and use standard international and US customary units to describe activities and exposure rates associated with radioactive material; determine whether a quantity of a single radionuclide meets the definition of a class 7 (radioactive) material; determine, for a given single radionuclide, the shipping quantity activity limits per 49 Code of Federal Regulations (CFR) 173.435; determine the appropriate radioactive material hazard class proper shipping name for a given material; determine when a single radionuclide meets the DOT definition of a hazardous substance; determine the appropriate packaging required for a given radioactive material; identify the markings to be placed on a package of radioactive material; determine the label(s) to apply to a given radioactive material package; identify the entry requirements for radioactive material labels; determine the proper placement for radioactive material label(s); identify the shipping paper entry requirements for radioactive material; select the appropriate placards for a given radioactive material shipment or vehicle load; and identify allowable transport limits and unacceptable transport conditions for radioactive material.

07 ISOTOPE AND RADIATION SOURCES↗

Assessment of commercially available energy-efficient room air conditioners including models with low global warming potential (GWP) refrigerants

Improving the energy efficiency of room air conditioners (RACs) while transitioning to low global-warming-potential (GWP) refrigerants will be a critical step toward reducing the energy, peak load, and emissions impacts of RACs while keeping costs low. Previous research quantified the benefits of leapfrogging to high efficiency in tandem with the transition to low-GWP refrigerants for RACs (Shah et al., 2015) and identified opportunities for initial action to coordinate energy efficiency with refrigerant transition in economies constituting about 65% of the global RAC market (Shah et al., 2017). This report describes further research performed to identify the best-performing (i.e., most efficient and low-GWP-refrigerant using) RACs on the market, to support an understanding of the best available technology (BAT). Understanding BAT can help support market-transformation programs for high-efficiency and low-GWP equipment such as minimum energy performance standards (MEPS), labeling, procurement, and incentive programs. We studied RACs available in six economies—China, Europe, India, Japan, South Korea, and the United States—that together account for about 70% of global RAC demand, as well as other emerging economies. The following are our key findings: • Highly efficient RACs using low-GWP refrigerants, e.g., HFC-32 (R-32) and HC-290 (R-290), are commercially available today at prices comparable to similar RACs using high-GWP HCFC-22 (R-22) or HFC-410A (R-410A). • High efficiency is typically a feature of high-end products. However, highly efficient, cost-competitive (less than 1,000 or 1,500 U.S. dollars in retail price, depending on size) RACs are available. • Where R-22 is being phased out, high GWP R-410A still dominates RAC sales in most mature markets except Japan, where R-32 dominates. • In all of the economies studied except Japan, only a few models are energy efficient and use low-GWP refrigerants. For example, in Europe, India, and Indonesia, the highest-efficiency RAC models employ the low-GWP refrigerants R-32 or R-290. • RACs are available in most regions and worldwide that surpass the highest efficiency levels recognized by labeling programs. • Fixed-speed RACs using high-GWP and ozone-depleting R-22 refrigerant still dominate the market in many emerging economies. There is significant scope to improve RAC efficiency and transition to low-GWP refrigerants using commercially available technology and to design market-transformation programs for high-efficiency, low-GWP equipment including standards, labeling, procurement, and incentive programs.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Learning Memento archive routing with Character-based Artificial Neural Networks

This white paper describes a series of tests that were performed to determine if a neural network could learn patterns from a service that maintains a cache of routing decisions for the discovery of version information for discrete web-at-large URLs. Labeled training data was derived from a log file that records the by-archive availability of Memento availability for a given URL. Training data sets were generated from this log file on a by-archive basis (thus making it a binary classification problem). Each training data set consisted of equal numbers of hit and miss URLs, selected at random. The URLs were converted to a normalized numeric representation where each integer in a URL training vector represents a character in that URL. The corresponding label indicates whether or not Mementos were available for that URL in the selected archive. The training data matrix and the label vector became input to a neural network. A number of neural network architectures and network hyperparameters were explored, however the log entries themselves were used as-is, without any feature engineering, beyond the aforementioned normalization.

97 MATHEMATICS AND COMPUTING↗

CENC PSN VOID FY20 Report

Maritime trade accounts for approximately 80 percent of international commerce. The high volume of vessels traversing domestic and international ports makes port areas prime targets for terrorism as well as illegal trafficking of drugs and arms (conventional or nuclear). Port security is therefore a worldwide concern affecting global economies, freedom of movement, and national security. However, extensive port monitoring is inherently complex and time consuming — making it truly viable only via an automated framework that can detect potential illicit activity and alert authorities in a timely manner. The development of image processing algorithms for this purpose requires access to large, labeled datasets that cover the breadth of targets of interest as well as the environments that they are observed within. Curated and labeled datasets of this nature are of enormous value to Sandia's Defense Nuclear Nonproliferation and National Security Program portfolios, as well as to Sandia's machine learning/automatic target recognition (ML/ATR) algorithm development and R&D communities. The goal of this project is to create a commercial satellite imagery dataset of labeled maritime vessels in port areas to support the development of ML/ATR algorithms for port security nonproliferation purposes. This dataset — Port Security Nonproliferation Vessel Overhead Imagery Dataset (PSN VOID) — has the potential to support a variety of other ancillary missions, such as maritime domain awareness, domestic and international security, drug interdiction, and weapons trafficking.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Opportunities for Simultaneous Efficiency Improvement and Refrigerant Transition in Air Conditioning

In October of 2016, nearly 200 Parties agreed to amend the Montreal Protocol in Kigali, Rwanda, to phase-down consumption and production of hydrofluorocarbons (HFCs) by 2050. Growth in the use of HFCs, including those currently used as refrigerants in air-conditioning systems, is being driven by demand from emerging economies, hot climates, and rising incomes that are also undergoing rapid urbanization and electrification. Air conditioners (ACs), as an energy-intensive end-use technology, are also covered by a growing number of energy efficiency standards, labeling, procurement, incentive, and other supporting efficiency programs. Therefore, improving room AC energy efficiency and transitioning to low-global warming potential (GWP) refrigerants simultaneously presents significant opportunities to deploy energy efficient technology and reduce the energy and emissions impacts of room ACs, while keeping costs low for consumers. This report aims to provide an initial sense of the opportunities to improve efficiency and transition to low-GWP refrigerants by reviewing the HCFC and HFC regulatory framework and energy efficiency standards and labeling programs in 19 economies that account for roughly 65 percent of global room AC demand. Based on this analysis, we identified key opportunities for coordinated action on efficiency improvement and refrigerant transition for the domestic room AC sector (i.e., ductless mini-split ACs), such as: - implementing or revising standards and labeling programs to improve efficiency levels with the possibility of adding a low-GWP criterion. - combining fixed speed and inverter AC product categories to account for seasonal variations in climate and part-load operating conditions, and using seasonal energy efficiency ratio (SEER) instead of energy efficiency ratio (EER) to better reflect performance of inverter ACs. - implementing market transformation programs, such as bulk procurement programs, to drive down the costs of efficient technology through economies of scale. - aligning timelines for implementing efficiency standards with timelines for refrigerant management plans to coordinate policy actions. - maximizing the energy efficiency improvements of Montreal Protocol investments by coordinating efforts to help keep costs low for consumers and manufacturers during equipment redesign and manufacturing line retooling for refrigerant transition. In order to realize the significant peak load, energy saving and climate benefits of these opportunities associated with improving energy efficiency in tandem with the refrigerant transition, some risks may need to be mitigated, principally safety concerns over risks of accidental ignition with refrigerants rated flammable. This can be mitigated by continuing and accelerating the development of safety standards currently being updated, for example, by the International Electrotechnical Commission (IEC) and improving training for production, installation and maintenance during the use of flammable refrigerants. While some low-GWP refrigerants may cost more than the current baseline refrigerants, the cost of refrigerants is only ~1% of lifecycle costs for an AC. Costs can also be reduced through manufacturing advances and efficiency improvements, particularly if they are supported by policies that encourage technological development through deployment of superefficient ACs at scale. Finally, during the transition, there is a risk of obsolete technology being deployed in markets that either have not updated their standards or have later compliance dates. This risk can be mitigated by updating standards and reviewing them periodically to ensure their effectiveness.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Safeguards-Informed Hybrid Imagery Dataset [Poster]

Deep Learning computer vision models require many thousands of properly labelled images for training, which is especially challenging for safeguards and nonproliferation, given that safeguards-relevant images are typically rare due to the sensitivity and limited availability of the technologies. Creating relevant images through real-world staging is costly and limiting in scope. Expert-labeling is expensive, time consuming, and error prone. We aim to develop a data set of both realworld and synthetic images that are relevant to the nuclear safeguards domain that can be used to support multiple data science research questions. In the process of developing this data, we aim to develop a novel workflow to validate synthetic images using machine learning explainability methods, testing among multiple computer vision algorithms, and iterative synthetic data rendering. We will deliver one million images – both real-world and synthetically rendered – of two types uranium storage and transportation containers with labelled ground truth and associated adversarial examples.

97 MATHEMATICS AND COMPUTING↗

Active Learning for Language Modeling

Foreign disinformation campaigns undermine national security. Various supervised language modeling techniques in NLP can help to understand and dismantle these campaigns, but they rely heavily on large, labeled (often by humans) datasets. This work provides a solution to this problem in the form of an active learning (AL) framework, which is used to generate labeled datasets and leverage human input for detecting disinformation. The developed AL framework utilizes task adaptive pretraining to fully leverage the unlabeled data and boost the performance of the classifier used for labeling. A disinformation rhetoric metric was developed to measure the presence of common rhetorical techniques used in text that are meant to deceive, for both the classifier and human to use in the task of identifying disinformation. This metric was combined with an uncertainty criterion to create a hybrid acquisition method for AL, and this hybrid method was tested alongside other acquisition functions. A sophisticated and robust stopping strategy was developed to signal the AL process should terminate, saving human time from being wasted on iterations that would not significantly benefit classifier performance.

99 GENERAL AND MISCELLANEOUS↗

Cooling Egypt: Cost and benefits of room air conditioner efficiency improvement in Egypt

Egypt is one of the largest countries in the Middle East and North Africa region with a population of a total of 106 million (as of July 2022). Increasing urbanization, population growth, and increasing temperatures will likely continue to drive demand for electricity from air conditioning, with corresponding negative impacts on the peak load, air quality, and greenhouse gas emissions from refrigerant use and energy consumption. Since 2003, Egypt has adopted a standards and labeling program for various appliances, and has improved its room air conditioner (RAC) energy efficiency requirements in 2016 and 2017. However, its market is still dominated by inefficient fixed-speed drive (FSD) RACs due to a price-sensitive market. Seasonal metrics such as Cooling Season Performance Factor (CSPF) measure the energy efficiency of FSD and variable-speed drive (VSD) RACs on the same scale. Leading markets, most notably China, have already adopted a new MEPS in 2020 and 2022, which align largely with the United for Efficiency (U4E) Model Regulations Guidelines. India has also adopted a CSPF metric. Both India and China are now experiencing (1) increased demand and consumption of higher efficiency VSD RACs, as well as (2) a corresponding drop in prices from the economies of scale of production of these higher efficiency RACs. Because China is a leading manufacturer in the global air conditioner (AC) market, its adoption of the model U4E regulations have effectively raised the energy efficiency of the ACs in the global market. To achieve the benefits of taking a similar approach to Egypt’s market, we offer the following recommendations: 1. Adopt a common metric to measure the efficiency of both FSD and VSD RACs 2. Raise the stringency of MEPS to the level of the U4E Model Regulation Guidelines 3. Restructure the labeling program from the “A++” labeling scheme to a simpler A through E or a star-rating program 4. Strengthen the compliance regime governing the Egyptian AC MEPS 5. Assist small and medium AC manufacturers in Egypt to transition manufacturing lines to produce low-cost, high-efficiency VSD RACs. Adopting these recommendations would reduce Egypt’s electricity consumption to 11 TWh in 2030 and 89 TWh in 2050—with corresponding carbon dioxide (CO2) emissions reductions and avoided generation capacity requirements compared to the baseline.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Grid Event Signature Library Analytics Report: Signature Matching Tool Development Efforts

This report describes the purpose and features of the Signature Matching Tool (SMT), employed in the Department of Energy (DOE) Grid Event Signature Library (GESL). The SMT supports a user of GESL to identify snippets of electric signatures, usually from sensor devices measuring electric characteristics such as phase voltages and currents, frequency, etc., suspected to represent certain events in the power grid but are not known to the user. The SMT uses a classification method to identify an event of the unknown signature, using the repository of known and labeled signatures in the GESL. The classifier applies a local binary classifier per node (LCN) approach to the unique event tag taxonomy used in the GESL, where training phases are separated based on the Primary labels in the taxonomy, sensor type, and voltage level. Results show that this method helps with computing time during training, in comparison to a flat, multinomial classifier, and produces acceptable average accuracy of 83% across all Primary labels. The report concludes with planned future work including integration to the web interface and API.

97 MATHEMATICS AND COMPUTING↗

Commentary: Duckweeds as model organisms for metabolic studies

Duckweeds have many practical applications, for example in human nutrition, as animal feed, in the production of bioplastics or vaccines, and phytoremediation (Acosta et al., 2021). Under most conditions, they reproduce asexually which provides genetically uniform material with predictable patterns of growth that make them ideal as sentinel organisms for phytotoxicity testing (Park et al., 2021). Asexual growth also results in high biomass production which makes duckweeds promising candidates as biofuel feedstocks (Acosta et al., 2021; Liang et al., 2023). In addition, duckweed species like Lemna minor and Spirodela polyrhiza are also reemerging as model organisms in plant biology as high-quality full genome assemblies and other genomic resources become available (Chang et al., 2016; Acosta et al., 2021). We argue that duckweed species are particularly of interest for the study of primary plant metabolism. Primary metabolism concerns the part of metabolism that is directly involved in the growth and development of plants, and which tends to be highly conserved among plant species. What makes duckweeds particularly attractive is that when grown on liquid media more precise control of physiological conditions can be attained relative to growth of plants in soil. Also, due to their relatively simple anatomical structure and asexual reproduction of fronds by budding, precise characterization of the physiological state under study is possible through one simple metric, i.e., the specific growth rate (rate of dry weight increase per existing dry weight), which can be incorporated relatively easily into metabolic models. This is not possible for land plants, such as Arabidopsis, because over the course of their life cycle, they go through multiple growth stages and phases of anatomical differentiation, which are much more complex to quantify. Furthermore, duckweeds can grow on organic substrates under heterotrophic or photomixotrophic conditions that facilitate isotope tracer studies. For example, in a previous study on duckweed by one of the authors, Lemna gibba (L). was grown on glucose with a position-specific 13 C-label that can be detected and resolved by Mass Spectrometry or Nuclear Magnetic Resonance spectrometry. Using this approach, the 13 C-label was traced into biomass compounds formed from glucose, particularly isoprenoid compounds. Some of the resulting labeling patterns were in apparent disagreement with predictions based on known metabolic pathways for the biosynthesis of isopentenyl pyrophosphate, the universal building block for isoprenoids, (Lichtenthaler et al., 1997). From this data it was deduced that isoprenoid compounds such as carotenoids and isoprenoid chains of phytol and plastoquinone, synthesized in the chloroplast, are produced via a previously unreported plant metabolic pathway, now known as the methylerythitol/deoxyxylulose-5-phosphate pathway (Lichtenthaler et al., 1997).

59 BASIC BIOLOGICAL SCIENCES↗

Massive all-atom analysis of 2D materials with quantum properties (Final report)

Improvements in microscopy have enabled the acquisition of data at a scale that is difficult to process manually, making automated machine learning approaches to analyzing experimental images essential. In this project, we developed and applied machine learning (ML) workflows for atomic resolution scanning transmission electron microscopy (STEM) images. This development included improving both methodology as well as generating user-friendly codes. We developed machine learning architectures which, after training, automatically identify the location and types of defects throughout a material. We used these data to produce class-averaged images of 2D atomic coordinates with up to 0.3 pm precision, uncovering the structure and oscillations of long-range strain fields around point defects in WSe 2-2x Te 2x . We also resolved a long-standing problem in this field in the training of ML models, a lack of labeled experimental data, by developing a cycle-GAN that transformed simulated-generated labeled data into labeled data indistinguishable from experiment and therefore suitable for training. This removed the remaining parts of the ML data processing workflow where human intervention was still critical and therefore a bottleneck to working at scale. Codes have been developed and released for this full machine learning workflow. ML approaches to partially automate STEM acquisition were also developed. Finally we applied ML and other advanced data processing methods to several materials science problems in two-dimensional materials, including studying the evolution of hyperuniformity with defect concentration in WSe2, understanding phase transformations in transition metal dichalcogenides during in-situ heating in the STEM, and exploring how 2D interfaces transform from twisted into aligned structures.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

A Semi-supervised Hybrid Machine Learning Framework for the Qualification of Resistance Spot Welds

• Industries requiring high structural integrity, including automotive, aerospace, and construction, place considerable significance on weld quality classification. • The inspection normally involves human expertise through predefined quality metrics that are subjective, error-prone, and time-intensive • The challenge to classification model development is the scarcity of labeled data and imbalanced distributions in the data that are labeled. • This work develops a new hybrid methodology that achieves clustering using KMeans++ together with supervised classification to overcome these challenges. • The ensemble-based classifiers were identified as optimal, with accuracy enhancements of up to 8% using the pseudo-labeled dataset. • The work provides practical insight into feature engineering and machine learning integration in industrial quality assurance applications.

Rogers, Jeremy K. [Savannah River National Laborat↗

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↗