SEARCH · Engineering Papers

Results for “Human Performance Improvement”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Improved detection of low-frequency within-host variants from deep sequencing: A case study with human papillomavirus

Abstract High-coverage sequencing allows the study of variants occurring at low frequencies within samples, but is susceptible to false-positives caused by sequencing error. Ion Torrent has a very low single nucleotide variant (SNV) error rate and has been employed for the majority of human papillomavirus (HPV) whole genome sequences. However, benchmarking of intrahost SNVs (iSNVs) has been challenging, partly due to limitations imposed by the HPV life cycle. We address this problem by deep sequencing three replicates for each of 31 samples of HPV type 18 (HPV18). Errors, defined as iSNVs observed in only one of three replicates, are dominated by C→T (G→A) changes, independently of trinucleotide context. True iSNVs, defined as those observed in all three replicates, instead show a more diverse SNV type distribution, with particularly elevated C→T rates in CCG context (CCG→CTG; CGG→CAG) and C→A rates in ACG context (ACG→AAG; CGT→CTT). Characterization of true iSNVs allowed us to develop two methods for detecting true variants: (1) VCFgenie, a dynamic binomial filtering tool which uses each variant’s allele count and coverage instead of fixed frequency cut-offs; and (2) a machine learning binary classifier which trains eXtreme Gradient Boosting models on variant features such as quality and trinucleotide context. Each approach outperforms fixed-cut-off filtering of iSNVs, and performance is enhanced when both are used together. Our results provide improved methods for identifying true iSNVs in within-host applications across sequencing platforms, specifically using HPV18 as a case study.

Virology↗

DOE OSTI2021

Multi-channel Imager Algorithm (MIA): A novel cloud-top phase classification algorithm

The current Geostationary Operational Environmental Satellites (GOES-16 and 17) cloud-top phase classification algorithm is based primarily on empirical thresholds at multiple wavelengths that have varying absorption capabilities for water and ice. The performance of current GOES-16 cloud-top phase product largely depends on the accuracy of the selection of reflectance ratios. Here this study aims at presenting a novel cloud-top phase classification algorithm (the Multi-channel Imager Algorithm, MIA) that provides a more judicious selection of relationships between channels using a supervised K-mean clustering method on multi-channel Red-Green-Blue images. The K-mean clustering method works analogously to how human eyes separate different colors in a microphysical color rendering set of satellite images, which differentiates water, ice and unclassified thin clouds. For water phase, cloud-top temperature information is used to further distinguish supercooled water. To evaluate the performance of the MIA, an extensive comparison with Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), Moderate Resolution Imaging Spectroradiometer, and current GOES-16 cloud-top phase products is conducted, using CALIOP as the benchmark. Compared to the current GOES-16 cloud-top phase product, MIA demonstrates a substantial improvement in phase classification, where hit rate increases from 69% to 76% over the Continental United States and 58% to 66% over the full disk domain.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving the LLMs to align existing foundation models with scientific disciplines, concepts and goals. In this work, we present SciTune as a tuning framework to improve the ability of LLMs to follow scientific multimodal instructions. To test our methodology, we use a human-generated scientific instruction tuning dataset and train a large multimodal model LLaMA-SciTune that connects a vision encoder and LLM for science-focused visual and language understanding. LLaMA-SciTune significantly outperforms the state-of-the-art models in the generated figure types and captions in multiple scientific multimodal benchmarks. In comparison to the models that are fine-tuned with machine generated data only, LLaMA-SciTune surpasses human performance on average and in many sub-categories on the ScienceQA benchmark.

• Artificial intelligence (AI) / machine learning ↗

DOE OSTI2020

Process Development of the Vaporizing Foil Actuator Welding Technique

The industrial focus on continuous improvement for products is leading design engineers to consider multi-material design concepts more frequently. The design concepts use the advantages of each material while simultaneously minimizing the drawbacks. It also allows for the overall weight of the products to be reduced. Some traditional joining methods, though, struggle to join dissimilar material combinations. A technique known as vaporizing foil actuator welding, which was developed around ten years ago, is a solid-state joining method that has the potential to overcome the barriers to dissimilar material joining. The biggest drawbacks of vaporizing foil actuator welding are that it is still exclusively used in laboratory settings and early in the technology development process. As such, there is not enough confidence in the process for it to be transitioned to manufacturing environments yet. This work begins by analyzing the current state of the technology and identifying a roadmap to achieve a transition to manufacturing. The analysis found that increased confidence in the technology requires sample to sample repeatability to be improved. Beyond that, the process also needs to be fully automated before it can be considered as a viable technique for mass production. In order to further develop the technique, a fully automated work cell was constructed. By removing the human element from the process, this cell helped identify iii the aspects which contribute to process variability. The positioning of the vaporizing foil actuator was identified as the most important factor in process stability. A small set of samples were made in the automated cell with the addition of one component epoxy adhesive around the perimeter of the weld. These samples showed improved process repeatability compared with the samples made without adhesive. This indicates that small amounts of adhesive may be critical in using the process in industrial settings. Additionally, work was performed with manual positioning and adhesive dispensing. This work found that a hybrid joint behaves like traditional weld bonding, where the addition of adhesive makes the joint stronger than if either of the two joining methods were used on their own. To realize this performance with vaporizing foil actuator welding, though, the adhesive needs to be protected from burning during the rapid compression of air during the impact process.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Self-Supervised Cloud Classification

Abstract Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets. Significance Statement Marine clouds heavily influence Earth’s weather and climate, and improved understanding of marine clouds is required to improve our atmospheric modeling capabilities and physical understanding of the atmosphere. Recently, deep learning has emerged as a powerful research tool that can be used to identify and study specific marine cloud types in the vast number of images collected by Earth-observing satellites. While powerful, these approaches require hand-labeling of training data, which is prohibitively time intensive. This study evaluates a recently developed self-supervised deep learning method that does not require human-labeled training data for processing images of clouds. We show that the trained algorithm performs competitively with algorithms trained on hand-labeled data for image classification tasks. We also discuss potential downstream uses and demonstrate some exciting features of the approach including application to multiple satellite instruments, resilience against changing image brightness, and its learned internal representations of cloud types. The self-supervised technique removes one of the major hurdles for applying deep learning to very large atmospheric datasets.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Efforts to enhance reproducibility in a human performance research project

Background: Ensuring the validity of results from funded programs is a critical concern for agencies that sponsor biological research. In recent years, the open science movement has sought to promote reproducibility by encouraging sharing not only of finished manuscripts but also of data and code supporting their findings. While these innovations have lent support to third-party efforts to replicate calculations underlying key results in the scientific literature, fields of inquiry where privacy considerations or other sensitivities preclude the broad distribution of raw data or analysis may require a more targeted approach to promote the quality of research output. Methods: We describe efforts oriented toward this goal that were implemented in one human performance research program, Measuring Biological Aptitude, organized by the Defense Advanced Research Project Agency's Biological Technologies Office. Our team implemented a four-pronged independent verification and validation (IV&V) strategy including 1) a centralized data storage and exchange platform, 2) quality assurance and quality control (QA/QC) of data collection, 3) test and evaluation of performer models, and 4) an archival software and data repository. Results: Our IV&V plan was carried out with assistance from both the funding agency and participating teams of researchers. QA/QC of data acquisition aided in process improvement and the flagging of experimental errors. Holdout validation set tests provided an independent gauge of model performance. Conclusions: In circumstances that do not support a fully open approach to scientific criticism, standing up independent teams to cross-check and validate the results generated by primary investigators can be an important tool to promote reproducibility of results.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Raman-based sorting of microbial cells to link functions to their genes

In our recent work, we developed an optofluidic platform that allows a direct link to be made between the phenotypes (functions) and the genotypes (genes) of microbial cells within natural communities. By combining stable isotope probing, optical tweezers, Raman microspectroscopy, and microfluidics, the platform performs automated Raman-based sorting of taxa from within a complex community in terms of their functional properties. In comparison with manual sorting approaches, our method provides high throughput (up to 500 cells per hour) and very high sorting accuracy (98.3 ± 1.7%), and significantly reduces the human labour required. The system provides an efficient manner to untangle the contributions of individual members within environmental and host-associated microbiomes. In this News and Thoughts, we provide an overview of our platform, describe potential applications, suggest ways in which the system could be improved, and discuss future directions in which Raman-based analysis of microbial populations might be developed.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

Deep learning multiphysics network for imaging CO 2 saturation and estimating uncertainty in geological carbon storage

Multiphysics inversion exploits different types of geophysical data that often complement each other and aims to improve overall imaging resolution and reduce uncertainties in geophysical interpretation. Despite the advantages, traditional multiphysics inversion is challenging because it requires a large amount of computational time and intensive human interactions for preprocessing data and finding trade-off parameters. These issues make it nearly impossible for traditional multiphysics inversion to be applied as a real-time monitoring tool for geological carbon storage. In this paper, we present a deep learning (DL) multiphysics network for imaging CO 2 saturation in real time. The multiphysics network consists of three encoders for analysing seismic, electromagnetic and gravity data and shares one decoder for combining imaging capabilities of the different geophysical data for better predicting CO 2 saturation. The network is trained on pairs of CO 2 label models and multiphysics data so that it can directly image CO 2 saturation. Here we use the bootstrap aggregating method to enhance the imaging accuracy and estimate uncertainties associated with CO 2 saturation images. Using realistic CO 2 label models and multiphysics data derived from the Kimberlina CO 2 storage model, we evaluate the performance of the deep learning multiphysics network and compare its imaging results to those from the deep learning single-physics networks. Our modelling experiments show that the deep learning multiphysics network for seismic, electromagnetic, and gravity data not only improves the imaging accuracy but also reduces uncertainties associated with CO 2 saturation images. Our results also suggest that the deep learning multiphysics network for the non-seismic data (i.e., electromagnetic and gravity) can be used as an effective low-cost monitoring tool in between regular seismic monitoring.

58 GEOSCIENCES↗

DOE OSTI2024

Robustness of topological persistence in knowledge distillation for wearable sensor data

Topological data analysis (TDA) has shown great success in various applications involving wearable sensor data. However, there are difficulties in leveraging topological features in machine learning and wearable sensors because of the large time consumption and computational resources required to extract the features. To address this problem, knowledge distillation (KD) is utilized to generate a small model and accommodate topological features with persistence image (PI) representations from the raw time series data. Deploying topological knowledge in KD enables the student to achieve better performance compared to the one trained solely on raw time series data. However, it is not yet known if there are coherent characteristics for topological features in PI, which can aid in improving the performance during KD. In this paper, we investigate the suitability and challenges of utilizing topological features in KD for wearable sensor data, thereby contributing to the advancement of the field. Our study explores the impact of transferred topological features by comparing the Teacher-to-Student framework with Multiple Teachers-to-Student where teachers utilize both time series data and persistence images obtained by TDA as inputs. Additionally, we conduct a rigorous examination of topological knowledge effects by testing under various corruptions, knowledge types, and learning strategies in the context of human activity recognition tasks. Our analysis of topological features in KD presents the optimal strategy for incorporating these features. This study includes datasets of varying scales, window lengths, and activity classes, providing a comprehensive evaluation. Our results demonstrate that leveraging topological features in KD to enhance performance across databases.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Modeling the Sources and Transport Processes During Extreme Ammonia Episodes in the U.S. Corn Belt

Abstract Atmospheric ammonia (NH 3 ) is the primary form of reactive nitrogen (N r ) and a precursor of ammonium (NH 4 + ) aerosols. Ammonia has been linked to adverse impacts on human health, the loss of ecosystem biodiversity, and plays a key role in aerosol radiative forcing. The midwestern United States is the major NH 3 source in North America because of dense livestock operations and the high use of synthetic nitrogen fertilizers. Here, we combine tall‐tower (100 m) observations in Minnesota and Weather Research and Forecasting model coupled with Chemistry (WRF‐Chem) modeling to investigate high and low NH 3 emission episodes within the U.S. Corn Belt to improve our understanding of the distribution of emission sources and transport processes. We examined observations and performed model simulations for cases in February through November of 2017 and 2018. The results showed the following: (1) Peak emissions in November 2017 were enhanced by above‐normal air temperatures, implying a Q 10 (i.e., the change in NH 3 emissions for a temperature increase of 10°C) of 2.5 for emissions. (2) The intensive livestock emissions rom northern Iowa, approximately 400 km away from the tall tower, accounted for 17.6% of the abundance in tall‐tower NH 3 mixing ratios. (3) Ammonia mixing ratios in the innermost domain 3 frequently (i.e., 336 hr, 48% of November 2017) exceeded 5.3 ppb, an important air quality health standard. (4) In November 2017, simulated NH 3 net ecosystem exchange (the difference between NH 3 emissions and dry deposition) accounted for 60–65% of gross NH 3 emissions for agricultural areas and was 2.8–3.1 times the emissions of forested areas. (5) We estimated a mean annual NH 3 net ecosystem exchange of 1.60 ± 0.06 nmol · m −2 · s −1 for agricultural lands and −0.07 ± 0.02 nmol · m −2 · s −1 for forested lands. These results imply that future warmer fall temperatures will enhance agricultural NH 3 emissions, increase the frequency of dangerous NH 3 episodes, and enhance dry NH 3 deposition in adjacent forested lands.

Hu, Cheng↗

DOE OSTI2023

Federated benchmarking of medical artificial intelligence with MedPerf

Medical artificial intelligence (AI) has tremendous potential to advance healthcare by supporting and contributing to the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving both healthcare provider and patient experience. Unlocking this potential requires systematic, quantitative evaluation of the performance of medical AI models on large-scale, heterogeneous data capturing diverse patient populations. Here, to meet this need, we introduce MedPerf, an open platform for benchmarking AI models in the medical domain. MedPerf focuses on enabling federated evaluation of AI models, by securely distributing them to different facilities, such as healthcare organizations. This process of bringing the model to the data empowers each facility to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status and real-world deployment, our roadmap and, importantly, the use of MedPerf with multiple international institutions within cloud-based technology and on-premises scenarios. Finally, we welcome new contributions by researchers and organizations to further strengthen MedPerf as an open benchmarking platform.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Automated Fire Detection for Industrial Settings with Pretrained Convolutional Networks

Early fire detection in industrial environments is critical to preventing equipment damage, personal injury, and operational disruptions. Traditional smoke detectors, while effective, often experience delays due to the time required for smoke to reach sensors, allowing fires to spread. Manual fire watch operations and human surveillance of camera feeds are resource-intensive and prone to human error. To address these challenges, this paper explores the application of convolutional neural networks for automated fire detection, specifically in industrial settings. By leveraging 11 different pre-trained machine vision models from TensorFlow and enhancing them with transfer learning on a custom-built industrial fire dataset, we optimized fire detection performance. Here, we analyzed each machine vision model architecture in terms of its depth, width, and input image resolution, considering both resource requirements and detection accuracy. We further explored the option of combining multiple models into an ensemble classifier to evaluate whether the performance improvements could justify the much greater computational complexity and other practical impacts. A cost-benefit analysis is presented to evaluate the trade-offs between performance and computational expense. Our findings identify that EfficientNetV2L, specifically tailored for industrial applications, provides the optimal balance between costs involved in training and using the model versus the overall fire detection performance. Additionally, we present a qualitative analysis of model performance using the technique of gradient-based class activation mapping to provide explainability by visualizing model decisions.

artificial intelligence↗

DOE OSTI2020

Chapter 14: Sustainable Biomass Conversion Process Assessment

Process intensification and integration for sustainable design play an essential role in addressing and alleviating severe sustainable development challenges. It is prudent to evaluate a process design in its early stage development to ensure the process can achieve sustainability goals. The primary goal of a sustainability evaluation is to assess the impact of systems on areas sought to be protected and maintained over time, such as human well-being and ecosystems (Schaubroeck, T. and Rugani, B. (2017). A revision of what life cycle sustainability assessment should entail: towards modeling the net impact on human well-being. Journal of Industrial Ecology 21 (6): 1464-1477). Parenthetically, sustainable process design to convert biomass to fuels and chemicals plays an integral part in the bioeconomy sustainability. It is recognized that the integration of sustainability in process design is core to the mission in developing renewable fuels and should be considered a necessary practice in biorefinery design. This study demonstrates the use of Gauging Reaction Effectiveness for ENvironmental Sustainability of Chemistries with a multi-Objective Process Evaluator (GREENSCOPE) as a tool to help track progress on process sustainability performance attributed to conversion improvement. With the incorporation of a wide range of indicators, GREENSCOPE captures the multi-dimensional aspect of the process design and operation. As opposed to conventional techno-economic analysis and life cycle assessment (in which the focuses are limited to economic and environmental aspects), GREENSCOPE enables the consideration of process intensification and integration for sustainable design. A high-octane gasoline production from woody biomass feedstock is used as a case study to demonstrate the approach.

biomass↗

DOE OSTI2026

A prototype cooling blanket for mitigating occupant overheating risk in a hot indoor environment: Modeling and assessments

Conventional ways of cooling a room or an entire house for occupant thermal comfort during summer consume a significant amount of energy and are vulnerable to overheating risk during power outages that lead to loss of cooling system operations. This study investigates a low-power cooling blanket, as a Personal Cooling System (PCS), that covers the upper human body for direct cooling during a five-day heat wave in a single-family house. A modeling framework is developed for evaluating the thermal and energy performance of the cooling blanket, which builds upon the co-simulation of three models: a house energy model, a personal thermal comfort model, and a cooling blanket model. Simulation results show that under the power outage scenario, the cooling blanket can greatly reduce the occupant heat stress with a reduction of daily hours of exceedance (discomfort hours defined as TSV>2) by up to 17.2 h (a 95.3 % improvement from the baseline power outage without the blanket). The cooling blanket, equipped with an innovative electrocaloric heat pump (COP as high as 10.1) consumes 6.31 W and can be operated by a portable battery for several days. The cooling blanket consumes only 0.28 % of the electricity of a central air-conditioning system running to provide cooling for the whole house during the five-day heatwave period. The findings justify further research of electrocaloric wearable PCS as low-power effective cooling to ensure thermal survivability of occupants during extreme indoor environments.

Electrocaloric heat pump↗

DOE OSTI2023

A comparison of histopathology imaging comprehension algorithms based on multiple instance learning

Whole slide imaging (WSI), also called digital virtual microscopy, is a new imaging modality. It allows for the application of AI and machine learning methods to cancer pathology to help establish a means for the automatic diagnosis of cancer cases. However, designing machine-learning models for WSI is computationally challenging due to its required ultra-high resolution. The current state-of-the-art models use multiple instance learning (MIL). MIL is a weakly-supervised learning method in which the model uses an array of inferences from many smaller instances to make a final classification about the entire set. In the context of WSI, researchers divide the ultra-high-resolution image into many patches. The model then classifies the slide based on an array of inferences from the patches. Among several ways of making the final classification, attention-based mechanisms have resulted in superb accuracy scores. The Transformer, one attention-based algorithm, has reported substantial improvements for WSI comprehension tasks. In this project, we studied and compared several WSI comprehension algorithms. We used the following three datasets: CAMELYON16+17, TCGALung, and TCGA-Kidney. We found that attention-based MIL algorithms performed better than standard MIL algorithms for classifying WSI images, achieving a higher mean accuracy and AUC. However, none of the attention-based algorithms performed significantly better than the others, reporting accuracy scores that varied widely. Presumably, it is due to the limited availability of training samples in the data corpus. Since it is not easy to increase the samples from human subjects, some machine learning techniques like transfer learning could help mitigate this issue.

Saunders, Adam↗

DOE OSTI2025

As part of its commitment to advancing safety and reliability assessment methodologies, Argonne National Laboratory pioneered the use of an evaluation method called the Success Path Method (SPM) to improve risk management for offshore oil and gas operations. The development of the SPM at Argonne has been driven by the need to improve existing risk assessment methodologies by focusing on the steps necessary for success rather than failure modes alone. This is particularly important for industrial environments like offshore facilities that perform multiple functions under a continuously evolving set of operational conditions – such as water depth and temperature, currents, and weather conditions. In these dynamic environments, the traditional Probabilistic Risk Assessment (PRA) approach is far too complex as it focuses on what can go wrong – which comprises an infinite failure space that must be fully explored and understood. By shifting the focus to a finite space of success paths, the SPM enables operators and decision makers to prioritize a manageable number of steps that must go right to ensure success. Building on its five decades of experience in safety assessments for the nuclear industry, Argonne made major adaptations to existing risk assessment methods utilizing features similar to fault trees that are traditionally used in PRA to map all pathways in which the system can malfunction. In contrast, SPM identifies the components and processes that must function correctly to achieve specific outcomes – such as preventing the uncontrolled release of hydrocarbons during drilling operations. The SPM framework integrates equipment, procedures, software, processes, and human actions to ensure that physical barriers meet critical safety functions in dynamic operational conditions. This approach helps identify failure modes and improve operational risk management by narrowing the focus to key success elements, which in turn reduces uncertainty and helps users understand, manage, and respond to failures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Spatiotemporal features of traffic help reduce automatic accident detection time

Quick and reliable automatic detection of traffic accidents is of paramount importance to save human lives in transportation systems. However, automatically detecting when accidents occur has proven challenging, and minimizing the time to detect accidents (TTDA) by using traditional features in machine learning (ML) classifiers has plateaued. We hypothesize that accidents affect traffic farther from the accident location than previously reported. Therefore, leveraging traffic signatures from neighboring sensors that are adjacent to accidents should help improve their detection. We confirm this hypothesis by using verified ground-truth accident data, traffic data from radar detection system sensors, and light and weather conditions and show that we can minimize the TTDA while maximizing classification performance by considering spatiotemporal features of traffic. Specifically, we compare the performance of different ML classifiers (i.e, logistic regression, random forest, and XGBoost) when controlling for different numbers of neighboring sensors and TTDA horizons. We use data from interstates 75 and 24 in the metropolitan area that surrounds Chattanooga, TN. Our results show that the XGBoost classifier produces the best results by detecting accidents as quickly as 1.0 min after their occurrence with an area under the receiver operating characteristic curve of up to 83% and an average precision of up to 49%. We describe limitations, open challenges, and how the proposed framework can be used for quicker operational accident detection.

33 ADVANCED PROPULSION SYSTEMS↗