Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “pipeline”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

A Data Processing Pipeline To Extract A Knowledge Graph From Heterogeneous Data For Socio-technical Analysis Of Critical Infrastructure Influence

The code is written in Python and consists of the following pipeline that is implemented in Apache Airflow. This pipeline intends to understand the companies that are directly or indirectly involved with a type of critical infrastructure system at some point in that system's lifecycle. The pipeline takes a configuration file that specifies a list of initial companies to consider, a geographic region of interest, and a set of SEC form types as well as other data sources (e.g. CrunchBase) from which to extract entities and relations. There are four main components to this pipeline as currently implemented: Entity Extraction, Network Construction, Analysis, and Visualization. First, Entity Extraction, is implemented as the `topear-extract_organizations` Apache Airflow workflow. Given an initial query that specifies a geographic region of interest and a time interval, the software will extract CI facilities of interest and organizations that have a direct influence relationship to those facilities (e.g. ownership). During the course of the LDRD, we focused on Electric Vehicle charging stations and this information is available via the Department of Energy (DOE) database on fueling stations maintained by NREL. Within the context of the DOE CESER project, we have focused on Battery Energy Storage Systems (BESS). Second, the Network Extraction component will iteratively construct a social network graph given the set of organizations and people extracted in the previous step. Organizations (and eventually People if desired) are then fed as a query to the `topgear-construct_social_network` Apache Airflow workflow which given a set of initial companies and data sets (e.g. SEC EDGAR form types, OpenCorporates, Crunchbase). This Airflow workflow will iteratively query such data sources to discover relationships with new organizations and people. For example, this module can iteratively query SEC EDGAR for metadata that documents the number of each type of form for the given set of companies and their location. This forms metadata represents a catalog of data sources from SEC EDGAR for the extracted social network knowledge graph. The pipeline then downloads these forms from the website and saves them in a build directory for further processing. These documents are then parsed for entities and relations. Again, we note that in additional to SEC data sources, this step can also pull in information on organizations via API services such as CrunchBase and OpenCorporates or bulk data sources. At the end of this step, the resultant social network, the Critical Infrastructure network, and the edges that encode relationships between organizations and CI facilities, form the Adversarial Socio-Technical Network (ASTN) that informs the analysis. Third, the Analysis component processes these generated ASTN. Previously, that has included the ability to compare prevalence of different vendors for a given infrastructure component type across different regions as well as identify common public and private investors across those vendors. This was demonstrated for EV Charging Stations across several different metropolitan areas within an IEEE PES GridEdge publication. More recently, we have looked at ways to identify infrastructure owners and operators of BESS with the most nameplate capacity across different states as well as other indictors of risk resulting from changes in ownership over time. Finally, the Visualization component consists of an HTML/CSS/JS framework by which users can interact geospatial, operational, and organizational relationships across a given portfolio of Critical Infrastructure facilities. The objective is to provide a library of UI/UX modules that can be repurposed for stakeholder-specific dashboards. All of the modules are related via a common event model that enables UI actions in one view to percolate across the other views.

Weaver, Gabriel [Idaho National Laboratory (INL), ↗
DOE OSTI2023

Abstract for CRADA between National Energy Technology Laboratory and Colonial Pipeline Company

The National Energy Technology Laboratory (NETL) and Colonial Pipeline Company (Participant) will collaborate in the field demonstration of optical fiber sensor systems developed at NETL on Participant’s fuel pipeline. The optical fiber sensor technologies are capable of distributed temperature and strain sensing, distributed acoustic sensing, and ultrasensitive acoustic sensing. Real-time monitoring of these parameters enables pipeline integrity monitoring, security monitoring, flow rate monitoring, etc. Successful demonstration on a real fuel pipeline at Participant’s facilities will validate the sensor technologies and installation methods at a real scale. This effort aligns with NETL’s mission in reliable and sustainable energy and reducing environmental effects due to pipeline failures.

42 ENGINEERING↗
DOE OSTI2023

Onshore U.S. Carbon Pipeline Deployment: Siting, Safety, and Regulation

Carbon capture, utilization, and storage technology has significant potential to reduce greenhouse gas emissions and mitigate the impact of climate change, particularly in hard-to-decarbonize industrial and commercial sectors. Unless utilization or storage occurs at the same location as carbon capture, which is rare, carbon must be transported from a point source to a utilization or storage site. Pipelines offer significant advantages for large-scale transportation of carbon dioxide over other methods. While studies show that reaching net-zero carbon emissions in the United States by 2050 will require between 29,000 and 66,000 miles of carbon pipelines, the U.S. had deployed fewer than 6,000 miles of carbon pipelines by 2022. Although closing this gap is important to achieving low-carbon goals, carbon pipelines operate in a complex and uncertain local, state and federal regulatory landscape and face public concerns about safety and siting. This report covers numerous regulatory issues surrounding carbon pipeline development, including the current narrow federal definition of carbon dioxide and the considerable variation in state and local governments’ laws and regulations. The report serves as a primer for regulators and stakeholders who seek to better understand the regulatory challenges and opportunities facing this critical infrastructure

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2022

Transport Affordable Clean Hydrogen Energy via Existing Pipeline Infrastructure (CRADA 573)

Our Nation’s vast network of oil pipelines span over 230,000 miles connecting remote energy producing regions to distant markets. The COVID-19 pandemic’s influence on oil prices intensified technical and economic vulnerabilities afflicting the Trans-Alaska Pipeline System (TAPS, operating below 25% capacity) that may soon resurface as energy demand shifts to low carbon sources. Through the opportunity afforded by the Arctic Advanced Manufacturing Program, I’ve toured the great State of Alaska learning about its culture, unique energy challenges, business ecosystem, research institutions, and regulatory agencies. With encouragement and support from dedicated Alaskans and my professional mentors, I’ve founded Mighty Pipeline for the purpose of developing and commercializing proprietary technology and hardware to convert oil pipelines into clean hydrogen energy transmission systems. Leveraging the advanced technical capabilities of Pacific Northwest National Laboratory, we’ve demonstrated proof-of-concept (TRL = 3) and are seeking pre-pilot development project opportunities to conduct hardware and system level tests. If we successfully achieve technical and regulatory milestones, Mighty Pipeline’s technology could be available to help facilitate bulk clean hydrogen energy export this decade.

08 HYDROGEN↗
DOE OSTI2026

Statistical and Machine Learning Approaches to Analyzing Pipeline Incidents in the United States (2010–2024)

This study applies machine learning methods to analyze natural gas pipeline incidents in the United States using the Pipeline and Hazardous Materials Safety Administration (PHMSA) Gas Distribution Incident Dataset (2010–2024). The dataset includes over 600 variables describing incident characteristics, infrastructure attributes, and contributing factors associated with unintentional gas releases. The objective is to assess whether these features can reliably predict the underlying cause of pipeline failures. Multinomial logistic regression and Random Forest models were developed to classify incident causes, including excavation damage, corrosion, equipment failure, and natural forces. Results show that excavation damage is both the most frequent and most predictable cause, with models achieving strong performance for this category. However, when excavation damage is excluded, model accuracy declines significantly, with some models performing near random levels. Across all approaches, severe class imbalance and limited variability in key predictors constrain predictive performance. Pipeline age and diameter emerge as the most influential variables, but they provide insufficient discriminatory power to distinguish among less frequent failure types. These findings indicate that non-excavation-related incidents are rare, heterogeneous, and weakly represented in the dataset, limiting the effectiveness of machine learning classification. Overall, this study highlights the structural limitations of the PHMSA dataset for predictive modeling and underscores the need for improved data balance and feature enrichment. The results reinforce excavation damage prevention as the most impactful strategy for reducing pipeline incidents.

03 NATURAL GAS↗
DOE OSTI2026

Adaptive Cybersecurity for Distributed Energy Resources (AdCyDER): Online Reinforcement Learning with Stackelberg-Optimized Defenses — Pipeline Architecture, Evaluation Methodology, and Findings from a Synthetic-Data Evaluation

This report documents the design and evaluation of an integrated online-learning pipeline developed within the AdCyDER project for Distributed Energy Resource (DER) cybersecurity. The pipeline couples a Reinforcement Learning (RL) attack classifier — which produces an attack-type probability distribution — with a Stackelberg game-theoretic (GT) defense selector that consumes those distributions alongside SME-encoded priors over (defense, attack) effectiveness pairings and perdefense costs to choose grid-health-preserving defenses. The objective is not attack classification per se but production of distributions that drive effective defense selection through the Stackelberg layer, learned from delayed grid-health feedback rather than labeled attack data. AdCyDER as a whole is broader than the work presented here; this report covers the specific RL/GT loop integration and its evaluation. We present the integrated pipeline (SCADA telemetry with Fronius inverter physics, Suricata IDS, time-windowed aggregation, per-facility LSTM classifier, Stackelberg optimizer, OpenC2 actuators), an experimental campaign of 28 eight-hour iterations across three baseline modes, and a pipeline-ordered diagnostic protocol. The protocol identifies two distinct failure modes within the loop: paired supervised ceilings on the same features establish that the deployed online RL classifier (macro F1 ≈ 0.07) sits at least 4.7× below a same-architecture supervised LSTM (≈ 0.34) and 10–11× below a linear feature-signal ceiling (≈ 0.70–0.79 depending on per-facility isolation), localizing the dominant failure to the training procedure; and the reward signal driving online updates carries weak directional coupling with classifier correctness in the methodology-expected direction (multi-lens convergent: top-decile P(true) records produce more frequent state changes and slightly larger improvements, top-vs-bot Cohen’s 𝑑 ≈ −0.19), but at effect magnitudes too small to drive gradient-based learning at the campaign sample size. The original learning hypothesis is not supported by the data. The primary contributions are the diagnostic methodology — proposed as a transferable falsification protocol for online RL/GT defense pipelines learning from delayed environmental reward — and the open, reproducible experimental infrastructure. We outline reward reformulation as the highest-priority aspirational next step given the underpowered-but-aligned Q6 reading, with hardware-in-the-loop evaluation as the broadest scope-expansion option.

Blakely, Benjamin [Argonne National Laboratory (AN↗
DOE OSTI2023

PhytoOracle: Scalable, modular phenomics data processing pipelines

As phenomics data volume and dimensionality increase due to advancements in sensor technology, there is an urgent need to develop and implement scalable data processing pipelines. Current phenomics data processing pipelines lack modularity, extensibility, and processing distribution across sensor modalities and phenotyping platforms. To address these challenges, we developed PhytoOracle (PO), a suite of modular, scalable pipelines for processing large volumes of field phenomics RGB, thermal, PSII chlorophyll fluorescence 2D images, and 3D point clouds. PhytoOracle aims to ( i ) improve data processing efficiency; ( ii ) provide an extensible, reproducible computing framework; and ( iii ) enable data fusion of multi-modal phenomics data. PhytoOracle integrates open-source distributed computing frameworks for parallel processing on high-performance computing, cloud, and local computing environments. Each pipeline component is available as a standalone container, providing transferability, extensibility, and reproducibility. The PO pipeline extracts and associates individual plant traits across sensor modalities and collection time points, representing a unique multi-system approach to addressing the genotype-phenotype gap. To date, PO supports lettuce and sorghum phenotypic trait extraction, with a goal of widening the range of supported species in the future. At the maximum number of cores tested in this study (1,024 cores), PO processing times were: 235 minutes for 9,270 RGB images (140.7 GB), 235 minutes for 9,270 thermal images (5.4 GB), and 13 minutes for 39,678 PSII images (86.2 GB). These processing times represent end-to-end processing, from raw data to fully processed numerical phenotypic trait data. Repeatability values of 0.39-0.95 (bounding area), 0.81-0.95 (axis-aligned bounding volume), 0.79-0.94 (oriented bounding volume), 0.83-0.95 (plant height), and 0.81-0.95 (number of points) were observed in Field Scanalyzer data. We also show the ability of PO to process drone data with a repeatability of 0.55-0.95 (bounding area).

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1980

Assessing the impact of pipeline construction on coniferous wetlands in central Michigan with aerial photography

The Remote Sensing Project at Michigan State University is using repetitive aerial photography to assess the impact of pipeline construction on coniferous wetlands in central Michigan. Preliminary results indicate that ponding, dieback, windthrow, and vegetation changes are readily detectable on medium-scale aerial photography. It is found that the major effect of the pipeline construction is the alteration of the water level, either by flooding or dessication. The most serious damage generally occurs when pipelines cross seepage and spiring wetland types; specific damage is related to the impoundment of the natural water flow, producing flooding on the upflow side of the pipeline and dessication of these wetlands below the pipeline rights-of-way.

Kittleson, K. M.↗
NASA NTRS2008

Orchestrator Telemetry Processing Pipeline

Orchestrator is a software application infrastructure for telemetry monitoring, logging, processing, and distribution. The architecture has been applied to support operations of a variety of planetary rovers. Built in Java with the Eclipse Rich Client Platform, Orchestrator can run on most commonly used operating systems. The pipeline supports configurable parallel processing that can significantly reduce the time needed to process a large volume of data products. Processors in the pipeline implement a simple Java interface and declare their required input from upstream processors. Orchestrator is programmatically constructed by specifying a list of Java processor classes that are initiated at runtime to form the pipeline. Input dependencies are checked at runtime. Fault tolerance can be configured to attempt continuation of processing in the event of an error or failed input dependency if possible, or to abort further processing when an error is detected. This innovation also provides support for Java Message Service broadcasts of telemetry objects to clients and provides a file system and relational database logging of telemetry. Orchestrator supports remote monitoring and control of the pipeline using browser-based JMX controls and provides several integration paths for pre-compiled legacy data processors. At the time of this reporting, the Orchestrator architecture has been used by four NASA customers to build telemetry pipelines to support field operations. Example applications include high-volume stereo image capture and processing, simultaneous data monitoring and logging from multiple vehicles. Example telemetry processors used in field test operations support include vehicle position, attitude, articulation, GPS location, power, and stereo images.

Powell, Mark↗
NASA NTRS2010

Kepler Science Operations Center Pipeline Framework

The Kepler mission is designed to continuously monitor up to 170,000 stars at a 30 minute cadence for 3.5 years searching for Earth-size planets. The data are processed at the Science Operations Center (SOC) at NASA Ames Research Center. Because of the large volume of data and the memory and CPU-intensive nature of the analysis, significant computing hardware is required. We have developed generic pipeline framework software that is used to distribute and synchronize the processing across a cluster of CPUs and to manage the resulting products. The framework is written in Java and is therefore platform-independent, and scales from a single, standalone workstation (for development and research on small data sets) to a full cluster of homogeneous or heterogeneous hardware with minimal configuration changes. A plug-in architecture provides customized control of the unit of work without the need to modify the framework itself. Distributed transaction services provide for atomic storage of pipeline products for a unit of work across a relational database and the custom Kepler DB. Generic parameter management and data accountability services are provided to record the parameter values, software versions, and other meta-data used for each pipeline execution. A graphical console allows for the configuration, execution, and monitoring of pipelines. An alert and metrics subsystem is used to monitor the health and performance of the pipeline. The framework was developed for the Kepler project based on Kepler requirements, but the framework itself is generic and could be used for a variety of applications where these features are needed.

Klaus, Todd C.↗
NASA NTRS2011

Time-Distance Helioseismology Data-Analysis Pipeline for Helioseismic and Magnetic Imager Onboard Solar Dynamics Observatory (SDO-HMI) and Its Initial Results

The Helioseismic and Magnetic Imager onboard the Solar Dynamics Observatory (SDO/HMI) provides continuous full-disk observations of solar oscillations. We develop a data-analysis pipeline based on the time-distance helioseismology method to measure acoustic travel times using HMI Doppler-shift observations, and infer solar interior properties by inverting these measurements. The pipeline is used for routine production of near-real-time full-disk maps of subsurface wave-speed perturbations and horizontal flow velocities for depths ranging from 0 to 20 Mm, every eight hours. In addition, Carrington synoptic maps for the subsurface properties are made from these full-disk maps. The pipeline can also be used for selected target areas and time periods. We explain details of the pipeline organization and procedures, including processing of the HMI Doppler observations, measurements of the travel times, inversions, and constructions of the full-disk and synoptic maps. Some initial results from the pipeline, including full-disk flow maps, sunspot subsurface flow fields, and the interior rotation and meridional flow speeds, are presented.

Sun: helioseismology↗
NASA NTRS2017

Kepler Planet Detection Metrics: Pixel-Level Transit Injection Tests of Pipeline Detection Efficiency for Data Release 25

This document describes the results of the fourth pixel-level transit injection experiment, which was designed to measure the detection efficiency of both the Kepler pipeline (Jenkins 2002, 2010; Jenkins et al. 2017) and the Robovetter (Coughlin 2017). Previous transit injection experiments are described in Christiansen et al. (2013, 2015a,b, 2016).In order to calculate planet occurrence rates using a given Kepler planet catalogue, produced with a given version of the Kepler pipeline, we need to know the detection efficiency of that pipeline. This can be empirically determined by injecting a suite of simulated transit signals into the Kepler data, processing the data through the pipeline, and examining the distribution of successfully recovered transits. This document describes the results for the pixel-level transit injection experiment performed to accompany the final Q1-Q17 Data Release 25 (DR25) catalogue (Thompson et al. 2017)of the Kepler Objects of Interest. The catalogue was generated using the SOC pipeline version 9.3 and the DR25 Robovetter acting on the uniformly processed Q1-Q17 DR25 light curves (Thompson et al. 2016a) and assuming the Q1-Q17 DR25 Kepler stellar properties (Mathur et al. 2017).

Pixel-Level Transit Injection↗
NASA NTRSDate not supplied

Updates in Developing a Prototype Science Pipeline and Full-Volume, Global Hyperspectral Synthetic Data Sets for NASA’s Earth System Observatory’s Upcoming Surface, Biology and Geology Mission

The Surface Biology and Geology (SBG) mission recently passed mission confirmation review and has entered phase A – design and development. SBG will acquire high resolution solar-reflected spectroscopy and thermal infrared observations at a data rate of ~2.5 TB/day and generate products at ~40 TB/day. Given that the per-day volume is greater than NASA’s total extant airborne hyperspectral data collection, collecting, processing, disseminating, and exploiting the SBG data present new challenges. To meet these challenges, we have developed a prototype science pipeline and a full-volume global hyperspectral synthetic data set to help prepare for SBG’s flight (see poster GC42D-0730). Our science pipeline is based on the science processing technology developed for NASA’s Kepler and TESS planet-hunting missions. The pipeline infrastructure, Ziggy, provides a scalable architecture for robust, repeatable, and replicable science and application products that can be run on a range of systems from a laptop to the cloud or a supercomputer. Ziggy is compliant with NASA Procedural Requirement (NPR) 7150.2C, is at a technical readiness level (TRL) of 7 and has been released to github.com/nasa/ziggy. We integrated Ziggy with EO-1/Hyperion workflows to build a prototype pipeline and ingested the 17-year mission archive that provides globally sampled visible through shortwave infrared spectra that are representative of SBG data types and volumes. We fully implemented the first stage and processed the entire 55 TB Hyperion data set from the raw data (Level 0) to top-of-the-atmosphere radiance (Level 1R). We are currently evaluating the ISOFIT atmospheric correction module to convert the L1R data to surface reflectance (Level 2) before reprocessing the full data set to L2. Crosschecks are being performed with RadCalNet as well as with coincident observations by AVIRIS. We are also investigating modern methods for georectifying the Hyperion scenes. Finally, we describe an analysis of the cost to conduct forward processing and reprocessing campaigns for SBG on HECC with dedicated compute and storage resources using the resurrected Hyperion pipeline as a proxy for full-volume SBG data. The analysis demonstrates that SBG L0 data can be processed to L2 on HECC with full reprocessing campaigns every two years for ~$2.6M over a 7-year lifespan. Moreover, 69% of the system capacity would be available for other activities, possibly enabling future open-source science activities, including algorithm development, L3+ processing, .etc.

ESD↗
NASA NTRSDate not supplied

Towards A Better Measurement of eta-Earth and Beyond Via Modernizing the Kepler Pipeline: An Update

The measurement of the occurrence of rocky habitable-zone planets orbiting Sun-like stars (eta-Earth), is a fundamental quantity for guiding our search for habitable exoplanets. Despite being launched 15 years ago, NASA’s Kepler mission remains responsible for finding the majority of all known exoplanet candidates relevant to eta-Earth, ushering in a new era of exoplanet demographics studies and continuing to drive planet occurrence rate calculations. However, the paucity of detections of likely rocky planets in the habitable zones of their host stars remains a limiting factor for estimating eta-Earth. We describe our five-year project for modernizing the Kepler planet detection and vetting pipeline in order to produce a more complete and reliable exoplanet catalog, which will lead to more accurate and precise measurements of eta-Earth. First, we are currently porting the original Kepler pipeline code from MATLAB to Python. We will then describe new stellar catalogs based on Gaia and ground-based imaging data, and ways to improve the pipeline detection and vetting algorithms. We will provide an update on the current state of this work. When completed, we will use this new pipeline and catalog to calculate updated estimates of eta-Earth. The full, updated pipeline code in Python, as well as all our inputs and results, will be made available to the public for detailed exoplanet occurrence-rate and demographics studies.

kepler↗
DOE OSTI2022

Reconstruction of Large Radius Tracks with the Exa.TrkX pipeline

Particle tracking is a challenging pattern recognition task at the Large Hadron Collider (LHC) and the High Luminosity-LHC. Conventional algorithms, such as those based on the Kalman Filter, achieve excellent performance in reconstructing the prompt tracks from the collision points. However, they require dedicated configuration and additional computing time to efficiently reconstruct the large radius tracks created away from the collision points. We developed an end-to-end machine learning-based track finding algorithm for the HL-LHC, the Exa.TrkX pipeline. The pipeline is designed so as to be agnostic about global track positions. In this work, we study the performance of the Exa.TrkX pipeline for finding large radius tracks. Trained with all tracks in the event, the pipeline simultaneously reconstructs prompt tracks and large radius tracks with high efficiencies. This new capability offered by the Exa.TrkX pipeline may enable us to search for new physics in real time.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Investigation of the Hydrogen Embrittlement of API 5L Natural Gas Pipeline Steels

Hydrogen ions produced during corrosion or through hydrogen blending into natural gas pipelines can lead to the degradation of ductility of metals used in these transmission pipelines. The effect of hydrogen on the mechanical properties of pipeline steels was studied for three grades of API 5L steels: X56, X65, and X100. These steels are either commonly used in or considered for use in natural gas transmission pipelines which are being considered for use in hydrogen blending. These steels were subjected to constant strain rate tensile testing after charging with electrochemically generated hydrogen. This presentation reports on work to extend the life of the natural gas pipeline network via understanding the effect of hydrogen embrittlement induced by corrosion processes.

Teeter, Lucas↗
DOE OSTI2025

Pilot-Scale Validation of Distributed Optical Fiber Sensors for Underground Pipeline Monitoring

Distributed fiber optic sensing is a cutting-edge technology that has found extensive applications in the monitoring of Ensuring the safety, integrity, and operational efficiency of underground product pipelines is vital for maintaining the nation’s critical infrastructure. Monitoring parameters such as hoop strain, pressure, and acoustic vibrations is key to detecting potential leaks, intrusions, or structural issues. Distributed optical fiber sensor (DOFS) systems provide a compelling solution for continuous, real-time monitoring over long distances. This paper details the development and pilot-scale implementation of DOFS systems for underground pipeline monitoring, evolving from a proof-of-concept stage. Multiple custom-designed DOFS interrogator units—such as optical frequency-domain reflectometry (OFDR), Brillouin optical time-domain analysis (BOTDA), and multimodal interferometer-based fiber acoustic sensors—were employed to measure key parameters like hoop strain, pressure, and acoustic vibrations. The underground product pipeline's outer diameter is 30 inches, the wall thickness is 1.28 inches, and the 3-foot depth. The fiber deployment strategies, and sensing data acquisition methods for these systems are discussed. The results demonstrate the effectiveness of DOFS in detecting hoop strain, temperature changes, and acoustic vibrations, showcasing their potential for real-time monitoring and enhancing pipeline safety.

distributed fiber sensing↗
DOE OSTI2025

Automated Image Segmentation and Processing Pipeline Applied to X–Ray Computed Tomography Studies of Pitting Corrosion in Aluminum Wires

Understanding pitting corrosion is critical, yet its kinetics and morphology remain challenging to study from X-ray computed tomography (XCT) due to manual segmentation barriers. To address this, an automated pipeline leveraging deep learning for efficient large-scale XCT analysis is developed, revealing new corrosion insights. The pipeline enables pit segmentation, 3D reconstruction, statistical characterization, and a topological transformation for visualization. Here, the pipeline is applied to 87 648 XCT images capturing commercial purity aluminum (1100 Al) wire exposed to sodium chloride (NaCl) salt particles over a period of 122 h. The pipeline achieves complete feature extraction and statistical quantification across the entire XCT dataset, leveraging distributed computing environment for high efficiency. Global growth kinetics such as high-level stepwise sigmoidal volume loss patterns and granular individual pit developments are both captured for 36 detected pits. By combining automation, computer vision, and extensive XCT datasets, this research accelerates precise corrosion assessment to enable materials science discoveries at scale.

36 MATERIALS SCIENCE↗