Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data analytics”

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 1,351 records · Page 75

HP-MDR: High-performance and Portable Data Refactoring and Progressive Retrieval with Advanced GPUs

Scientific applications produce vast amounts of data, posing grand challenges in the underlying data management and analytic tasks. Progressive compression is a promising way to address this problem, as it allows for on-demand data retrieval with significantly reduced data movement cost. However, most existing progressive methods are designed for CPUs, leaving a gap for them to unleash the power of today’s heterogeneous computing systems with GPUs.In this work, we propose HP-MDR, a high-performance and portable data refactoring and progressive retrieval framework for GPUs. Our contributions are four-fold: (1) We carefully optimize the bitplane encoding and lossless encoding, two key stages in progressive methods, to achieve high performance on GPUs; (2) We propose pipeline optimization and incorporate it with data refactoring and progressive retrieval workflows to further enhance the performance for large data process; (3) We leverage our framework to enable high-performance data retrieval with guaranteed error control for common Quantities of Interest; (4) We evaluate HP-MDR and compare it with state of the arts using five real-world datasets. Experimental results demonstrate that HP-MDR delivers an average 13.68 × and 6.31 × throughput in data refactoring and progressive retrieval tasks, respectively. It also leads to 11.22 × throughput for recomposing required data representations under Quantity-of-Interest error control and 6.04 × performance for the corresponding end-to-end data retrieval, when compared with state-of-the-art solutions.

Li, Yanliang [University of Oregon]↗

Faraday: A High-temperature Electrolysis Data Explorer

Faraday is a high-temperature electrolysis data visualization tool, which reveals the performance of various button cells under test conditions. These tests and the resulting analytics on their data constitute a state of the industry as the US Department of Energy pushes for the production of hydrogen. Faraday leverages the Idaho National Laboratory's DeepLynx data warehouse to standardize and query button cell data. Faraday programmatically accesses this data in DeepLynx by traversing the schema, represented by a custom ontology. The user interface queries DeepLynx for timeseries data associated with specific button cells in the warehouse, and renders them using JavaScript charts. Additional charting and data analysis techniques are made possible by an auxiliary Python server.

Woodruff, Nathan↗

Scalable, In-situ Data Clustering Data Analysis for Extreme Scale Scientific Computing (Final Report)

The objective of this project is to address challenges in the design and development of scalable in-situ data clustering and analytics algorithms and software. Our goal is to develop parallel software consisting of a set of spatio-temporal data clustering and anomaly detection functions, both of which are very important for large-scale analysis and have wide applicability for in-situ runs as well as post-processing analysis. Our design principles for in-situ analysis consider the following: (1) identify parts of the computation can be done close to the data within the nodes, while it is still in memory; (2) extract analysis components can (and should) be performed in remote staging and analysis nodes; (3) develop error-bound approximation methods for applications tolerable for small errors; (4) identify the type of derived distributions and statistics, for spatio-temporal data, that can be kept locally in order to both accelerate computations and meet energy constraints in subsequent iterations and phases; (5) use a self-describing data format so that data can be consistent and understood among local storage (memory and SSDs) and at staging and analysis nodes, thereby providing portability and flexibility; (6) develop service-oriented functions that can schedule in-situ and post-hoc analysis tasks based on the dynamic requirements of applications. Our development focus is to produce the parallel data analysis software/library that will be scalable, reusable, extensible, and generic for applications in different disciplines. The software will be able to run in-situ with the simulations as well as post-hoc analysis. This approach will satisfy many synergistic requirements for data intensive applications executed on data coming from instruments and experiments. In particular, the proposed multilevel approach is directly applicable to perform design tradeoffs for running part of the algorithms near the instruments and the rest on remote (analysis) systems.

97 MATHEMATICS AND COMPUTING↗

Sample IEEE123 Bus system for OEDI SI

Time series load and PV data from an IEEE123 bus system. An example electrical system, named the OEDI SI feeder, is used to test the workflow in a co-simulation. The system used is the IEEE123 test system, which is a well studied test system (see link below to IEEE PES Test Feeder), but some modifications were made to it to add some solar power modules and measurements on the system. The aim of this project is to create an easy-to-use platform where various types of analytics can be performed on a wide range of electrical grid datasets. The aim is to establish an open-source library of algorithms that universities, national labs and other developers can contribute to which can be used on both open-source and proprietary grid data to improve the analysis of electrical distribution systems for the grid modeling community. OEDI Systems Integration (SI) is a grid algorithms and data analytics API created to standardize how data is sent between different modules that are run as part of a co-simulation. The readme file included in the S3 bucket provides information about the directory structure and how to use the algorithms. The sensors.json file is used to define the measurement locations.

123 bus↗

Statistical Data Analyses of Trace Chemical, Biochemical, and Physical Analytical Signatures

Analytical and bioanalytical chemistry measurement results are most meaningful when interpreted using rigorous statistical treatments of the data. The same data set may provide many dimensions of information depending on the questions asked through the applied statistical methods. Three principal projects illustrated the wealth of information gained through the application of statistical data analyses to diverse problems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Building a FAIR data ecosystem for incorporating single-cell transcriptomics data into agricultural genome to phenome research

Introduction The agriculture genomics community has numerous data submission standards available, but the standards for describing and storing single-cell (SC, e.g., scRNA- seq) data are comparatively underdeveloped. Methods To bridge this gap, we leveraged recent advancements in human genomics infrastructure, such as the integration of the Human Cell Atlas Data Portal with Terra, a secure, scalable, open-source platform for biomedical researchers to access data, run analysis tools, and collaborate. In parallel, the Single Cell Expression Atlas at EMBL-EBI offers a comprehensive data ingestion portal for high-throughput sequencing datasets, including plants, protists, and animals (including humans). Developing data tools connecting these resources would offer significant advantages to the agricultural genomics community. The FAANG data portal at EMBL-EBI emphasizes delivering rich metadata and highly accurate and reliable annotation of farmed animals but is not computationally linked to either of these resources. Results Herein, we describe a pilot-scale project that determines whether the current FAANG metadata standards for livestock can be used to ingest scRNA-seq datasets into Terra in a manner consistent with HCA Data Portal standards. Importantly, rich scRNA-seq metadata can now be brokered through the FAANG data portal using a semi-automated process, thereby avoiding the need for substantial expert curation. We have further extended the functionality of this tool so that validated and ingested SC files within the HCA Data Portal are transferred to Terra for further analysis. In addition, we verified data ingestion into Terra, hosted on Azure, and demonstrated the use of a workflow to analyze the first ingested porcine scRNA-seq dataset. Additionally, we have also developed prototype tools to visualize the output of scRNA-seq analyses on genome browsers to compare gene expression patterns across tissues and cell populations. This JBrowse tool now features distinct tracks, showcasing PBMC scRNA-seq alongside two bulk RNA-seq experiments. Discussion We intend to further build upon these existing tools to construct a scientist-friendly data resource and analytical ecosystem based on Findable, Accessible, Interoperable, and Reusable (FAIR) SC principles to facilitate SC-level genomic analysis through data ingestion, storage, retrieval, re-use, visualization, and comparative annotation across agricultural species.

Genetics & Heredity↗

Telematics and Data Science: Informing Energy-Efficient Mobility

Fleets exploring the possibility of adding electric vehicles (EVs), battery electric vehicles (BEVs), and plug-in hybrid electric vehicles (PHEVs) seek an efficient, data-driven means to justify both expenditures for vehicle and charging infrastructure and the appropriate placement of them to help ensure the cost-effective adoption of these technologies. Exploring data collection and analytic methodologies across different telematics providers offers the opportunity to better understand the strengths, weaknesses, and possibilities for employing different methods of data collection, including smartphone-based telematics and more traditional telematics with hardware installed on a vehicle's onboard diagnostics port. This report presents results of five pilot programs that collected data from the operation of conventional light-duty fleet vehicles to generate recommendations for transitioning these fleet vehicles to EVs, implementing adequate charging infrastructure, and establishing management practices to maximize the benefits of these new fleet technologies.

33 ADVANCED PROPULSION SYSTEMS↗

Data Challenges in Multi-Sensor Data Science System for Monitoring a Solvent Extraction Process

Idaho National Laboratory (INL) is maintaining and gaining knowledge into the nuclear fuel cycle by building a test bed to allow researchers the opportunity to study nuclear fuel processing operations. This includes studying solvent extraction processes that use centrifugal contactors. As part of INL’s mission, the goal of this project is to develop a system that utilizes non-traditional measurement sources such as vibration, acoustics, current, light, flow, and temperature in conjunction with data-based, machine learning techniques that will allow for signal discovery. This multisensory data can support the development of safeguards by design, provide operator process awareness, and discover process anomalies. This poster will highlight some of the data collection and analytics challenges for the multi-sensor system as well as the mitigation strategies to build a robust system. Additionally, some preliminary data from the first testing campaign will be shown to help illustrate the data needs of the system.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Online Analytics for Remedy Support at DOE Environmental Management Sites

Environmental data is important for managing environmental restoration/waste site remediation, planning of monitoring efforts, addressing climate resilience, and engaging with stakeholders and regulators. A major challenge is how to manage the many different types and the large volume of environmental data in a way that allows practitioners and site managers to understand data implications and support decisions. The Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites (SOCRATES, https://www.pnnl.gov/projects/socrates) is a web application that provides data access, visualization, and rapid analytics to help make sense of environmental data, support remedy decisions, and communicate information. Development of SOCRATES has been funded through the DOE Richland Operations Office (RL) to support communication and decision making for the Hanford Site, thus is only tied into Hanford environmental data. However, the capabilities of SOCRATES are more broadly applicable to DOE-EM sites engaged in environmental remediation and management. This report describes the work to develop mechanisms for bringing non-Hanford data into SOCRATES so that other DOE-EM sites could make use of the visualization and analysis capabilities to support communication and decision making related to managing environmental restoration/waste site remediation, optimization/exit strategies for pump-and-treat systems, planning monitoring efforts, addressing climate resilience, and/or engaging with stakeholders and regulators. The background, approach, data transfer formats, examples, and next steps for this new SOCRATES-EM software are described in this report.

54 ENVIRONMENTAL SCIENCES↗

Technical Note: On the analytical proton dose evaluation in compounds and mixtures

Purpose: By combining the physical processes occurring due to the interaction of protons with matter, analytical theories published so far have provided acceptable models for calculating depth-dose distributions in homogeneous media. As a well-defined and comprehensive theory, the formula derived by Bortfeld models the dose transferred to the target in terms of the parabolic cylinder function. The model also includes three parameters with values specified for an initial proton energy and for the target material. These parameters are obtainable through the data gathered in nuclear data tables. The analytical studies using this interesting model are therefore restricted to those materials for which the data have been provided in these tables. This study aims to find general solutions for calculation of these parameters for a compound or mixture composed of an arbitrary choice of constituent elements. Methods: Inspired by formulas dedicated for calculating the range and the probability of undergoing nonelastic nuclear interactions for protons in desired compounds, the analytical methods for finding the three mentioned parameters are investigated. The accuracy of the methods suggested is examined through comparison of the results with those which are calculated using the data taken from nuclear data tables. By employing the calculated parameters using the derived formulas in the Bortfeld model, the dose distribution at depth in a chosen target is calculated. Results: For an arbitrary selection of compounds, the predictions of the analytical depth-dose model using these parameters have been found to closely match the results employing the parameters calculated using the data reported in nuclear data tables. Conclusions: The formulas presented are general, mathematically easy to handle, and valid for almost every compound or mixture including materials of interest for proton radiotherapy purposes, making the Bortfeld model more practical and advantageous.

61 RADIATION PROTECTION AND DOSIMETRY↗

Accelerating Science: A Computing Research Agenda

The emergence of "big data" offers unprecedented opportunities for not only accelerating scientific advances but also enabling new modes of discovery. Scientific progress in many disciplines is increasingly enabled by our ability to examine natural phenomena through the computational lens, i.e., using algorithmic or information processing abstractions of the underlying processes; and our ability to acquire, share, integrate and analyze disparate types of data. However, there is a huge gap between our ability to acquire, store, and process data and our ability to make effective use of the data to advance discovery. Despite successful automation of routine aspects of data management and analytics, most elements of the scientific process currently require considerable human expertise and effort. Accelerating science to keep pace with the rate of data acquisition and data processing calls for the development of algorithmic or information processing abstractions, coupled with formal methods and tools for modeling and simulation of natural processes as well as major innovations in cognitive tools for scientists, i.e., computational tools that leverage and extend the reach of human intellect, and partner with humans on a broad range of tasks in scientific discovery (e.g., identifying, prioritizing formulating questions, designing, prioritizing and executing experiments designed to answer a chosen question, drawing inferences and evaluating the results, and formulating new questions, in a closed-loop fashion). This calls for concerted research agenda aimed at: Development, analysis, integration, sharing, and simulation of algorithmic or information processing abstractions of natural processes, coupled with formal methods and tools for their analyses and simulation; Innovations in cognitive tools that augment and extend human intellect and partner with humans in all aspects of science.

97 MATHEMATICS AND COMPUTING↗

Fe 2 O 3 -Au hybrid nanoparticles for sensing applications via SERS analysis

Multifunctional iron oxide-gold hybrid nanostructures have been produced via solution chemistries and investigated for analyte detection. Gold nanoparticles of various shapes have been used for probing surface-enhanced Raman scattering (SERS) effects as they display unique optical properties in the visible-near IR region of the spectrum. When coupled with other nanoparticles, namely iron oxide nanoparticles, hybrid structures with increased functionality were produced. By exploiting their magnetic properties, nanogaps or “hot spots” were rationally created and evaluated for SERS enhancement studies. The “hot spots” were created by using a seeded reaction to increase the gold loading on the iron oxide support by 43% by weight. SERS Nanomaterials were evaluated for their ability to promote surface-enhanced Raman scattering of a model analyte, 4-mercaptophenol. The data shows an enhancement effect of the model analyte on gold decorated iron oxide nanoparticles.

36 MATERIALS SCIENCE↗

Analysis of X-ray images and spectra (aXis2000): A toolkit for the analysis of X-ray spectromicroscopy data

Spectromicroscopy refers to analytical methods that combine imaging and spectroscopy to provide detailed, spatially resolved analytical information about a sample, such as the type and quantitative spatial distributions of chemical components, geometric or magnetic alignment information, crystal structure, etc. The analysis of X-ray images and spectra (aXis2000) software described in this work provides a set of routines within a single, integrated, graphical-oriented package to read, display, manipulate and analyze spectromicroscopy data, with particular focus on soft X-ray spectromicroscopy methods such as scanning transmission X-ray microscopy (STXM), X-ray photoemission electron microscopy (XPEEM), scanning photoelectron X-ray microscopy (SPEM) and transmission X-ray microscopy (TXM). Here, this free software is described and compared to other software that can provide similar or complementary capabilities. Examples of spectromicroscopic analyses using advanced features of aXis2000 are provided.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

EVALUATION OF LOW TEMPERATURE ALUMINUM DISSOLUTION IN TANK 51

Liquid Waste Organization (LWO) identified aluminum dissolution as a method to mitigate the effect of having about 50% more solids in High Level Waste (HLW) sludge than previously planned. Previous aluminum dissolution performed in a HLW tank in 1982 was performed at approximately 85 C for 5 days, which became the baseline aluminum dissolution process. LWO initiated a project to modify a waste tank to meet these requirements. Subsequent to an alternative evaluation, LWO management identified an opportunity to perform aluminum dissolution on sludge destined for Sludge Batch 5, but within a limited window that would not allow time for any modifications for tank heating. A variation of the baseline process, dubbed Low Temperature Aluminum Dissolution (LTAD), was developed based on the constraint of available energy input in Tank 51 and the window of opportunity, but was not constrained to a minimum extent of dissolution, i.e. dissolve as much aluminum as possible within the time available. This process was intended to operate between 55 and 70 C, but for a significantly longer time than the baseline process. LTAD proceeded in parallel with the baseline project. The preliminary evaluation at the completion of LTAD focused on the material balance and extent of the aluminum dissolved. The range of values of extent of dissolution, 56% to 64%, resulted from the variation in liquid phase sample data available at the time. Additional solid phase data is available from a sample taken after LTAD to refine this range. This report provides additional detailed evaluation of the LTAD process based on analytical and field data and includes: a summary of the process chronology; a determination of an acceptable blending strategy for the aluminum-laden supernate stored in Tank 11; an update to the determination of aluminum dissolved using more complete sample results; a determination of the effect of LTAD on uranium, plutonium, and other metals; a determination of the rate of heat loss from a quiescent tank; and an evaluation of the aluminum dissolution rate model and actual dissolution rate. LTAD was successfully completed in Tank 51 with minimal waste tank changes. The following general conclusions may be drawn about the LTAD process: (1) Dissolution at about 60 C for 46 days dissolved 64% of the aluminum from the sludge slurry. (2) The aluminum-laden leach solution decanted to Tank 11 can be blended with a wide variety of supernates without risk of precipitating the dissolved aluminum based on thermodynamic chemical equilibrium models. (3) Uranium and plutonium leached into solution without corresponding leaching of iron or metal other than aluminum, but the total mass leached was a small fraction of the total uranium and plutonium in the sludge. (4) The concentration of uranium and plutonium in the leach solution was indistinguishable from other tank farm supernates, thus, the leach solutions can be managed relative to the risk of criticality like any other supernate. (5) A small amount of mercury leached into solution from the sludge causing the liquid phase concentration to increase 6 to 10 fold, which is consistent with the 4 to 14 fold increase observed during the 1982 aluminum dissolution demonstration. (6) Chromium did not dissolve during LTAD. (7) Chloride concentration increased in the liquid phase during LTAD due to chloride contamination in the 50% sodium hydroxide solution. (8) The rate of heat loss from Tank 51 at temperatures above 45 C appeared linear and predictable at 8E+7 cal/hr. (9) The rate of heat transfer from Tank 51 did not follow a simplified bulk heat transfer model. (10) Prediction of the aluminum dissolution rate was prone to error due to a lack of active specific surface area data of sludge particles. (11) The higher than expected dissolution rate during LTAD was likely due to smaller than expected particle sizes of most of the sludge particles. While evaluating the LTAD process, the dissolved salt solution from Tank 41 that was stored and sampled in Tank 49 was determined to be supersaturated relative to aluminum. Supersaturation in Tank 49 is not a risk to LTAD. However, storing and processing of this supernate carries a risk of solids precipitation, primarily in the form of gibbsite or boehmite. Blending with the supernate in Tank 11 neither increases nor decreases this risk. LTAD was initiated as an opportunity to substantially mitigate the planned increase in canister production and DWPF lifecycle after the realization of more sludge solids stored in the HLW tanks. As determined from the preliminary evaluation of LTAD, the direct benefit of the decanted liquid stored in Tank 11 represents 45 canisters at 34% waste loading with potential indirect benefits for much larger reductions. Application of an aluminum dissolution process to the remaining high aluminum content sludge will potentially reduce the planned canister production by several hundred canisters at 34%-38% waste loading.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Artificial Intelligence in Nuclear Safeguards; Evaluating Safeguards and Security Risks and Benefits for Advanced and Small Modular Reactor Deployments

Rapidly growing interest in advanced and small modular reactor (A/SMR) technologies presents challenges as well as opportunities for implementing international safeguards and security. A/SMR deployments are expected to be more numerous, more geographically dispersed, and more varied in their designs, placing new demands on the data systems and analytical tools used to support oversight (Alberti et al., 2023; Canadian Nuclear Safety Commission et al., 2024). Because of this variability, the importance and reliance on data systems for A/SMR deployments is expected to be higher than for previous reactor generations. Artificial Intelligence and Machine Learning (AI/ML) offer potential capabilities to address the high variability inherent in A/SMR technology. The beneficiaries of AI-assisted tools include facility operators, government regulators, IAEA inspectors, and A/SMR vendors. This report analyzes how AI/ML-assisted technologies can strengthen the implementation of IAEA safeguards and security measures. It also identifies AI-assisted tools to strengthen operator, facility, and regulator knowledge management practices and examines the potential risks AI/ML-based tools may introduce to IAEA safeguards and security efforts. It concludes with a set of hypothetical, standards-style requirements for AI/ML systems used in safeguards contexts, grounded in an inspector-centric view of system verification. Despite the potential benefits of AI/ML systems, understanding potential intentional and unintentional failure modes is critical for ensuring adequate protection of nuclear materials and facilities. Unique features of A/SMRs including sealed cores, remote and novel paradigms of operation, off-site reactor fabrication, novel fuel forms, and varied refueling requirements, introduce challenges for traditional safeguards technological approaches (Pensado et al., 2024; Federation of American Scientists, 2025). AI/ML systems deployed to address these challenges may introduce new risks requiring systematic evaluation rooted in both AI-specific risk frameworks, such as the NIST AI Risk Management Framework (NIST AI RMF), and established cyber risk management standards such as NIST SP 800-30 (National Institute of Standards and Technology [NIST], 2023; NIST, 2012).

97 MATHEMATICS AND COMPUTING↗

Industry case studies: Finance

This article, the third in a series on the U.S. Department of Energy and IDEA collaboration, focuses on financial strategies used by institutions to support district energy system modernization and decarbonization. It highlights how effective funding models, long-term cost analysis, and leadership support are critical to implementing large-scale infrastructure upgrades. The case studies show different approaches to financing. Ball State University demonstrates how life-cycle cost analysis and phased funding—supported by state funding, bonds, and grants—enabled a transition to geothermal energy. Penn State’s Hershey Medical Center emphasizes the importance of financial leadership, shifting from reactive budgeting to data-driven, proactive investment in infrastructure. The University of Washington highlights how comprehensive data collection and analytics can justify investments and even create self-sustaining funding mechanisms like green revolving funds. Overall, the article shows that combining strong financial planning, data-driven decision-making, and innovative funding approaches is essential for advancing sustainable district energy systems while managing high upfront costs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

IMG 4 version of the integrated microbial genomes comparative analysis system

The Integrated Microbial Genomes (IMG) data warehouse integrates genomes from all three domains of life, as well as plasmids, viruses and genome fragments. IMG provides tools for analyzing and reviewing the structural and functional annotations of genomes in a comparative context. IMG’s data content and analytical capabilities have increased continuously since its first version released in 2005. Since the last report published in the 2012 NAR Database Issue, IMG’s annotation and data integration pipelines have evolved while new tools have been added for recording and analyzing single cell genomes, RNA Seq and biosynthetic cluster data. Finally, different IMG datamarts provide support for the analysis of publicly available genomes (IMG/W: http://img.jgi.doe.gov/w), expert review of genome annotations (IMG/ER: http://img.jgi.doe.gov/er) and teaching and training in the area of microbial genome analysis (IMG/EDU: http://img.jgi.doe.gov/edu).

59 BASIC BIOLOGICAL SCIENCES↗

ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather

Abstract. Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning – when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create “ClimateNet” – an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification – i.e., segmentation – of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs, or “the background” at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, high-fidelity, and highly precise analytics of climate data using a curated expert-labeled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning.

54 ENVIRONMENTAL SCIENCES↗