Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Information systems →Data mining”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Understanding and Improving Energy Efficiency of Regional Mobility Systems Leveraging System-Level Data

Increased congestion required urban Americans to travel 6.8 billion hours more and purchase 3.1 billion gallons of fuel for a congestion cost of $\$$153 billion, according to the 2019 Urban Mobility Report. How to effectively manage the regional mobility system and improve the energy efficiency presents a big challenge to public agencies. Recent years have witnessed massive multi-jurisdictional multi-modal system-level data from various sources, which provides an unprecedented opportunity to improve the mobility system and its energy efficiency. However, implications of system-level data for mobility and energy efficiency are unclear. Those system-level data sets are siloed, spatially and temporally sparse, biased, not unified, and lacking of insights for system management. Consequently, there is a real need to acquire, fuse, mine and learn from multi-source system-level data to prepare public agencies to deal more effectively with large-scale energy efficiency modeling, management and planning. This project proposes to intensively review inexpensive, replicable and openly-accessible data from multi-modal systems, develop a data-driven system-level modeling framework enabled and validated by data, identify the energy inefficiencies of mobility systems from infrastructure, vehicles, passenger systems, and quantify the benefits of system-level strategies to improve mobility/energy efficiency. In addition, this research develops models to effectively estimate energy consumption and emissions from various types of vehicles on the roadway networks, with high granularity and high fidelity. Traditional models often heavily rely on aggregated infrastructure or vehicle/passenger data, for example, the census survey, land-use, and traffic counts of one or several classes, which may lead to research gaps considering the emerging vehicle technologies. Those models do not contain individual vehicular information. We propose an integrated data-driven method that combines multiple network modeling components, featuring the utilization of state-wide vehicle registration data. The additional vehicle registration data improve the model performance, and produce high-resolution vehicle-specific estimates of emissions and network performance metrics. Two case studies on the Pittsburgh and Philadelphia regional network show that the proposed method can efficiently and effectively estimate the emissions of a large-scale network, and provide valuable information for evaluating common management strategies.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

NEWTS Integrated Dataset (version 1.0)

The National Energy Water Treatment and Speciation (NEWTS) Integrated Dataset v1.0 provides water researchers, community leaders, and regulators with a unified and standardized energy-related wastewater stream database. This resource is derived from 27 state and federal entities, and scientific publications, and contains more than 400,000 sample records, many of which also provide geospatial information. The dataset includes data for several different energy-related wastewater types including produced water, other oil and gas wastewaters, mine drainage, coal ash leachate, and power plant wastewater. The NEWTS Integrated Dataset was built to support environmentally prudent decision-making, explore treatment opportunities, and identify potential critical mineral sources. A subset of this novel resource is also featured on NETL NEWTS State-Level Database Dashboard. Additional data can be found in the NEWTS EDX Group and the NEWTS Federal Database Dashboard.

abandoned mine drainage↗
DOE OSTI2022

Flexible Siting Criteria and Staff Minimization for Micro-Reactors

The economic potential of micro-reactors is vast and underestimated. Commonly-emphasized applications include niche markets such as remote communities, mines and military bases. However, micro-reactors could be used as flexible energy generators also for larger markets, such as mobile and containerized agriculture and manufacturing facilities, district heating, micro-grids for data centers, sea ports, airports and hospitals. The implication is that micro-reactors may have to be deployed also in non-remote locations. Successful implementation of micro-reactors needs a navigable and predictable licensing process, technology-appropriate siting restrictions, risk-informed emergency and safety requirements, and practical operating and maintenance requirements. The primary goal of this project was to develop siting criteria that are tailored to micro-reactors deployable in densely-populated areas, e.g., urban environments. To achieve that goal, we compared the characteristics of the MIT research reactor (MITR) with those of leading micro-reactor concepts (e.g., eVinci, USNC, Aurora), and evaluated whether and how the MITR design basis (e.g., inherent safety features, engineered safety systems, source term, emergency planning and emergency operating procedures) and associated regulations may be applicable to these new micro-reactors as well. What makes MITR a unique analogue in this context is its small power rating (6 MWt) and physical size, mode of operations (24/7 with a somewhat more commercial flavor than typical university reactors), and especially its urban location. Of course significant differences exist, such as mission (power production vs. research) and the reactor design itself. Leveraging the MITR experience, this project was able to generate criteria that will allow micro-reactors to realize their full economic potential as flexible heat and electricity generators for a diverse portfolio of applications in non-remote locations. As such, the outcome of this project might encourage investment in and use of micro-reactors. A second goal of the project was to conceptualize a model of operations for micro-reactors that would minimize the staffing requirements, and thus reduce the cost of electricity and heat generated by these systems. Here too our approach was to systematically review the MITR experience and requirements, as well as survey the innovations in autonomous control technologies and monitoring (e.g., advanced sensors, drones, robotics, AI) that would permit a dramatic reduction in staffing at future micro-reactor installations. The scope of work was expanded after the start date to include also an evaluation of micro-reactor security, using the so-called consequence-based analysis, and the development of a methodology to perform dynamic risk assessment for micro-reactors, using system theory and modeling and simulation.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Case Study: Hybrid Carbon Conversion Using Low-Carbon Energy Sources in Coal-Producing States

The demand for more carbon efficient power sources and a decrease in natural gas prices has decreased the desire for coal power. This decrease in demand has led to massive job losses in coal mining regions over the past decade. The purpose of this project is to develop a hybrid energy system utilizing both a coal power plant and advanced reactor, which is competitive with natural gas by improving on profitability and decreasing carbon emissions. This report details the problem with a summary of the impact on the coal industry and the availability of renewable energy sources in the Appalachian region. Because of the geography of the region, variable renewable energy sources are not available without significant size and siting restrictions. However, biomass in the form of wood waste is abundant and can be used as a carbon neutral energy source. Combining biomass and coal processing, in addition to thermal power plants, can increase system profits and efficiency by providing peaking power and conversion opportunities for secondary markets. The electric load is based on publicly available demand data from Appalachian Power, which services the western Virginia and southern West Virginia in the Appalachian region. The demand information is combined by service, normalized, and scaled to an average demand of 1000 kW, which will be the basis for sizing the hybrid energy system. A traditional screening curve analysis for a coal plant and advanced reactor shows that the least cost design varies significantly based on the assumed discount rate and capital recovery period. An optimization program to size the design in TEAL based on the load curve gives 10 optimal designs, all with a negative resulting net present value (NPV) and a coal plant capacity of less than 15%. Including profits from selling captured carbon at a flat rate results in a positive NPV; however, the coal capacity factor only increases to about 40%. There are limitations with this optimization as well since the price of CO2 is likely to decrease as more is sold to the conversion market. The suggested design will combine coal power, an advanced reactor, and coal and biomass coprocessing to produce a variety of products that can be sold to the conversion market while increasing system efficiency. The analysis of conversion pathways for coal and biomass reveals that multiple options will need to be included in the analysis to produce the optimal system design. Three systems will be optimized and compared to determine the best design based on the figures of merit of total NPV and cost of carbon avoided. The first system will include a coal power plant and an advanced reactor that will sell electricity to the grid to meet demand and sell captured carbon to the conversion market. The second system adds a high-temperature steam electrolysis plant, which will utilize electricity during times of low demand to produce hydrogen and sell it to the conversion market. The third system adds biomass and coal processing with options for hydrocarbon oils, syngas to be produced for the conversion market, and electricity generation to power components within the system or provide peaking power. This analysis will be based on a new approach that combines traditional screening curve methods with a dispatch algorithm that optimizes the system based on the opportunity cost of different production options. The resulting optimization algorithm should provide results with less processing time than HERON’s decision tree method. The results from this analysis will determine an optimal design and reinforce the benefits of coal power when used in a hybrid energy system. The initial results show that the addition of a secondary market for carbon sales could result in a positive NPV and increases the capacity factor of the coal plant as compared to a design with only sales to the electricity market. The addition of more markets and additional coal consumption from biomass coprocessing could increase NPV further, replace carbon in other markets through the sale of biomass-derived hydrocarbons, and demonstrate the value of coal power technology.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2021

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2025

An Exploratory Data Mining Investigation for Constructing a Publicly Sourced Dataset of Foreign Hypersonic Tests

This document details a data mining exercise that resulted in an exploratory dataset of publicly reported foreign (non-US) hypersonic vehicle test events. Using a combination of targeted English language searches and country-specific queries, the study aggregates information from digital news media, official press releases, and social media posts. The resulting list of events captures the publicly available accounts of foreign hypersonic tests, although it does not represent an exhaustive record. Limitations such as inconsistent reporting, translation challenges, and the inherently provisional nature of open-source data are acknowledged. This dataset serves as an initial reference point for further inquiries into high-speed atmospheric phenomena and may facilitate future efforts to correlate these events with geophysical measurements.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2021

Informing selection of drugs for COVID-19 treatment through adverse events analysis

Coronavirus disease 2019 (COVID-19) is an ongoing pandemic and there is an urgent need for safe and effective drugs for COVID-19 treatment. Since developing a new drug is time consuming, many approved or investigational drugs have been repurposed for COVID-19 treatment in clinical trials. Therefore, selection of safe drugs for COVID-19 patients is vital for combating this pandemic. Our goal was to evaluate the safety concerns of drugs by analyzing adverse events reported in post-market surveillance. We collected 296 drugs that have been evaluated in clinical trials for COVID-19 and identified 28,597,464 associated adverse events at the system organ classes (SOCs) level in the FDA adverse events report systems (FAERS). We calculated Z-scores of SOCs that statistically quantify the relative frequency of adverse events of drugs in FAERS to quantitatively measure safety concerns for the drugs. Analyzing the Z-scores revealed that these drugs are associated with different significantly frequent adverse events. Our results suggest that this safety concern metric may serve as a tool to inform selection of drugs with favorable safety profiles for COVID-19 patients in clinical practices. Caution is advised when administering drugs with high Z-scores to patients who are vulnerable to associated adverse events.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2026

Robotics for Energy Infrastructure Construction on Earth and Beyond: Pilot Study Exploring Level 3-4 Semi-Autonomous Installation of a Reduced-Scale Photovoltaic Power Plant Prototype: Preprint

There is a growing need to build energy infrastructure at massive scale on both Earth and in space. On Earth, increasing electricity demand from applications such as AI data centers is driving rapid expansion of power systems, while in space, long-duration missions such as lunar operations require reliable and resilient energy infrastructure that can be deployed quickly. These needs outpace the capabilities of conventional construction methods. Robotic construction offers a path to faster, lower-cost, and more consistent deployment, yet most existing approaches focus on automating individual tasks rather than end-to-end assembly. The Industrialized Construction Innovation (ICI) team at the National Laboratory of the Rockies (NLR), in collaboration with the Colorado School of Mines, has been investigating robotics and automation strategies for rapid end-to-end energy infrastructure construction. This paper presents a pilot study demonstrating level 3-4 semi-autonomous, end-to-end robotic assembly of a reduced-scale photovoltaic power plant prototype under terrestrial conditions. The approach combines hardware redesign of photovoltaic components for robotic compatibility, discrete-event and physics-based robotic simulations in synthetic environments, and sim-to-real deployment to execute end-to-end robotic assembly of[NM1.1][NM1.2] tracking components, structural members, photovoltaic modules, and embedded electrical connections. The pilot identifies key limitations like tolerance management, perception and localization, end effector capability, fastening methods, and multi-physics simulation fidelity, that must be addressed to enable end-to-end robotic assembly of full-scale energy infrastructure. The study highlights how these insights inform scaling strategies for terrestrial energy infrastructure and adaptation to unstructured and extreme environments, including off-world scenarios such as robotic assembly of vertical tall lunar towers.

14 SOLAR ENERGY↗
DOE OSTI2020

A Model Tree Generator (MTG) Framework for Simulating Hydrologic Systems: Application to Reservoir Routing

Data-driven algorithms have been widely used as effective tools to mimic hydrologic systems. Unlike black-box models, decision tree algorithms offer transparent representations of systems and reveal useful information about the underlying process. A popular class of decision tree models is model tree (MT), which is designed for predicting continuous variables. Most MT algorithms employ an exhaustive search mechanism and a pre-defined splitting criterion to generate a piecewise linear model. However, this approach is computationally intensive, and the selection of the splitting criterion can significantly affect the performance of the generated model. These drawbacks can limit the application of MTs to large datasets. To overcome these shortcomings, a new flexible Model Tree Generator (MTG) framework is introduced here. MTG is equipped with several modules to provide a flexible, efficient, and effective tool for generating MTs. The application of the algorithm is demonstrated through simulation of controlled discharge from several reservoirs across the Contiguous United States (CONUS).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Intercomparison of Three Continuous Monitoring Systems on Operating Oil and Gas Sites

We compare continuous monitoring systems (CMS) from three different vendors on six operating oil and gas sites in the Appalachian Basin using several months of data. We highlight similarities and differences between the three CMS solutions when deployed in the field and compare their output to concurrent top-down aerial measurements and to site-level bottom-up inventories. Furthermore, we compare vendor-provided emission rate estimates to estimates from an open-source quantification algorithm applied to the raw CMS concentration data. This experimental setup allows us to separate the effect of the sensor platform (i.e., sensor type and arrangement) from the quantification algorithm. We find that 1) localization and quantification estimates rarely agree between the three CMS solutions on short time scales (i.e., 30 min), but temporally aggregated emission rate distributions are similar between solutions, 2) differences in emission rate distributions are generally driven by the quantification algorithm, rather than the sensor platform, 3) agreement between CMS and aerial rate estimates varies by CMS solution but is close to parity when CMS estimates are averaged across solutions, and 4) similar sites with similar bottom-up inventories do not necessarily have similar emission characteristics. These results have important implications for developing measurement-informed inventories and for incorporating CMS-inferred emission characteristics into emission mitigation efforts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Demonstration and performance of an online data selection algorithm for liquid argon time projection chambers using MicroBooNE

The MicroBooNE detector is a liquid argon time projection chamber (LArTPC) that produces three-dimensional images of particle interactions using ionization charge collected by anode wire plane arrays and scintillation light collected by a light detection system. In addition to testing long-standing experimental neutrino anomalies and performing measurements of neutrino interactions with argon nuclei using the Fermilab Booster Neutrino Beam, MicroBooNE aims to develop methodologies for rare beyond the Standard Model and off-beam physics searches. Looking ahead to the upcoming Deep Underground Neutrino Experiment (DUNE), with MicroBooNE serving as a valuable testbed, achieving high sensitivity and livetime for off-beam physics while satisfying data processing and storage constraints will require data-driven, intelligent, and online or real-time data selection techniques. These techniques are essential for reducing data rates and preserving rare signals with high accuracy. In this paper, we describe a fast data selection algorithm suitable for online execution to identify electrons from stopping cosmic ray muons in the MicroBooNE detector utilizing ionization charge information, and present its performance. This represents the first demonstration of online data selection in a LArTPC using real data and charge information exclusively and provides an important proof-of-principle for applying such techniques to other LArTPC experiments such as the Short-Baseline Near Detector and DUNE.

Abratenko, P. [Tufts U. (main)]↗
DOE OSTI2021

RAVEN Theory Manual

RAVEN is a software framework able to perform parametric and stochastic analysis based on the response of complex system codes. The initial development was aimed at providing dynamic risk analysis capabilities to the thermohydraulic code RELAP-7, currently under development at Idaho National Laboratory (INL). Although the initial goal has been fully accomplished, RAVEN is now a multi-purpose stochastic and uncertainty quantification platform, capable of communicating with any system code. In fact, the provided Application Programming Interfaces (APIs) allow RAVEN to interact with any code as long as all the parameters that need to be perturbed are accessible by input files or via python interfaces. RAVEN is capable of investigating system response and explore input space using various sampling schemes such as Monte Carlo, grid, or Latin hypercube. However, RAVEN strength lies in its system feature discovery capabilities such as: constructing limit surfaces, separating regions of the input space leading to system failure, and using dynamic supervised learning techniques. The development of RAVEN started in 2012 when, within the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program, the need to provide a modern risk evaluation framework arose. RAVEN’s principal assignment is to provide the necessary software and algorithms in order to employ the concepts developed by the Risk Informed Safety Margin Characterization (RISMC) program. RISMC is one of the pathways defined within the Light Water Reactor Sustainability (LWRS) program. In the RISMC approach, the goal is not just to identify the frequency of an event potentially leading to a system failure, but the proximity (or lack thereof) to key safety-related events. Hence, the approach is interested in identifying and increasing the safety margins related to those events. A safety margin is a numerical value quantifying the probability that a safety metric (e.g. peak pressure in a pipe) is exceeded under certain conditions. Most of the capabilities, implemented having RELAP-7 as a principal focus, are easily deployable to other system codes. For this reason, several side activates have been employed (e.g. RELAP5-3D, any MOOSE-based App, etc.) or are currently ongoing for coupling RAVEN with several different software. The aim of this document is to provide a set of commented examples that can help the user to become familiar with the RAVEN code usage.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Development of A High-Resolution Dataset for Solar Resource Adequacy Studies

High-resolution, long-term solar dataset is essential for characterizing the variability of solar energy resources and for informing strategies that ensure grid reliability and resilience in grid systems with high levels of solar energy integration. We present the development of a new 4-km, hourly Earth system dataset for the contiguous United States (CONUS), using a statistical downscaling approach that integrates the National Solar Radiation Database (NSRDB) with regional Earth system model projections. The new high-resolution Earth system dataset includes key variables - GHI, DNI, DHI, surface air temperature, and wind speed - under two future scenarios. Preliminary results show a reasonable agreement with NSRDB observations, with nBias less than 1% for GHI across CONUS. The dataset is expected to support in-depth analyses of extreme weather impacts and provide input to resource adequacy for future energy systems with diverse generation sources.

14 SOLAR ENERGY↗
DOE OSTI2021

Identifying schools at high-risk for elevated lead in drinking water using only publicly available data

Estimating the risk of lead contamination of schools' drinking water at the State level is a complex, important, and unexplored challenge. Variable water quality among water systems and changes in water chemistry during distribution affect lead dissolution rates from pipes and fittings. In addition, the locations of lead-bearing plumbing materials are uncertain. We tested the capability of six machine learning models to predict the likelihood of lead contamination of drinking water at the schools' taps using only publicly available datasets. The predictive features used in the models correspond to those with a proven correlation to the dominant, but commonly unavailable, factors that govern lead leaching: the presence of lead-bearing plumbing materials and water quality conducive to lead corrosion. By combining water chemistry data from public reports, socioeconomic information from the US census, and spatial features using Geographic Information Systems, we trained and tested models to estimate the likelihood of lead contaminated tap water in over 8,000 schools across California and Massachusetts. Our best-performing model was a Random Forest, with a 10-fold cross validation score of 0.88 for Massachusetts and 0.78 for California using the average Area Under the Receiver Operating Characteristic Curve (ROC AUC) metric. The model was then used to assign a lead leaching risk category to half of the schools across California (the other half was used for training). There was good agreement between the modeled risk categories and the actual lead leaching outcomes for every school; however, the model overestimated the lead leaching risk in up to 17% of the schools. This model is the first of its kind to offer a tool to predict the risk of lead leaching in schools at the State level. Further use of this model can help deploy limited resources more effectively to prevent childhood lead exposure from school drinking water.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2024

Development of a Data Overflow Protection System for Super-Kamiokande to Maximize Data from Nearby Supernovae

Neutrinos from very nearby supernovae, such as Betelgeuse, are expected to generate more than ten million events over 10 s in Super-Kamokande (SK). At such large event rates, the buffers of the SK analog-to-digital conversion board (QBEE) will overflow, causing random loss of data that are critical for understanding the dynamics of the supernova explosion mechanism. In order to solve this problem, two new data-acquisition (DAQ) modules were developed to aid in the observation of very nearby supernovae. The first of these, the SN module, is designed to save only the number of hit photomultiplier tubes during a supernova burst and the second, the Veto module, prescales the high-rate neutrino events to prevent the QBEE from overflowing based on information from the SN module. In the event of a very nearby supernova, these modules allow SK to reconstruct the time evolution of the neutrino event rate from beginning to end using both QBEE and SN module data. This paper presents the development and testing of these modules together with an analysis of supernova-like data generated with a flashing laser diode. We demonstrate that the Veto module successfully prevents DAQ overflows for Betelgeuse-like supernovae as well as the long-term stability of the new modules. During normal running the Veto module is found to issue DAQ vetos a few times per month resulting in a total dead-time less than 1 ms, and does not influence ordinary operations. Additionally, using simulation data we find that supernovae closer than 800 pc will trigger the Veto module, resulting in a prescaling of the observed neutrino data.

F20 Instrumentation and technique↗
DOE OSTI2025

Physics-Informed Neural Network (PINN) Prediction of Mixed Mass-Heat-Crystallization Limited Methane Hydrate Formation and Dissociation in Micro-Confinement

The creation and use of Physics-Informed Neural Networks (PINNs) for simulating the dynamics of methane hydrate formation and dissociation will be presented. The PINN framework's main benefit is its capacity to impose physical consistency with only a partial comprehension of the governing equations. This makes the algorithm especially useful for systems with little experimental evidence or a lack of theoretical knowledge. A strong basis for forecasting methane hydrate behavior over the verified operating ranges of 30.0-80.9 bar pressure and 1.0-4.0 K sub-cooling conditions is provided by the combination of conductive heat transfer equations and mixed mass-transfer–crystallization kinetics. PINNs were more accurate at predicting the mixed mass-heat-crystallization limited kinetics than conventional Artificial Neural Networks (ANNs), demonstrating remarkable predictive accuracy for methane hydrate production over the ANN model. The efficiency of incorporating physical limitations from first principles into machine learning frameworks for methane hydrate crystallizations is reinforced by these findings. For hydrate-related applications in energy generation, carbon sequestration, and climate modelling, our study establishes PINNs as a computational tool that is both scalable and efficient. The proven capacity to close the gap between conventional physics-based simulations and solely data-driven models creates new opportunities for expedited hydrate research and practical applications.

Hartman, Ryan L [NYU Tandon School of Engineering]↗
DOE OSTI2025

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↗