Search NASA⌕ Search

SEARCH · Search NASA

Results for “roadway lighting”

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.

Impact of Solid State Roadway Lighting on Melatonin in Humans

Introduction: In 2009, the World Health Organization identified vehicle crashes, both injury-related and fatal, as a public health hazard. Roadway lighting has long been used to reduce crashes and improve the safety of all road users. Ocular light exposure at night can suppress melatonin levels in humans. At sufficient light levels, all visible light wavelengths can elicit this response, but melatonin suppression is maximally sensitive to visible short wavelength light. With the conversion of roadway lighting to solid state sources that have a greater short wavelength spectrum than traditional sources, there is a potential negative health impact through suppressed melatonin levels to roadway users and those living close to the roadway. This paper presents data on the impact of outdoor roadway lighting on salivary melatonin in three cohorts of participants: drivers, pedestrians, and those experiencing light trespass in their homes. Methods: In an outdoor naturalistic roadway environment, healthy participants (N = 29) each being assigned to a cohort of either pedestrian, driver, or light trespass experiment, were exposed to five different solid state light sources with differing spectral emissions and one no lighting condition. Salivary melatonin measurements were made under an average roadway luminance of 1.0 cd/m2 (IES RP-18 Roadway Lighting Requirements for expressway roads) with a corneal melanopic Equivalent Daylight Illuminances (EDI) ranging from 0.22 to 0.86 lux. Results: The results indicate that compared to the no roadway lighting condition, the roadway light source spectral content did not significantly impact salivary melatonin levels in the participants in any of the cohorts. Conclusions: These data show that recommended levels of street lighting for expressway roads do not elicit an acute suppression of salivary melatonin and suggest that the health benefit of roadway lighting for traffic safety is not compromised by an acute effect on salivary melatonin.

60 APPLIED LIFE SCIENCES↗

Enhanced Lighting Signals for Safety and Efficiency - Experiments With Addressable LEDs

For enhanced roadway safety, clear and immediate visual cues are essential for preventing accidents between drivers and pedestrians. At intersections, however, the line of sight to other roadway users may be obstructed by vehicles and infrastructure. Additionally, adverse conditions, including low visibility, poor weather, or inadequate lighting can increase the potential for collisions. Distracted drivers and pedestrians can further exacerbate the risk of accidents, particularly when using a smartphone, rather than focusing on roadway surroundings. These issues demonstrate the need for infrastructure upgrades that enhance visibility and awareness at crosswalks. A potential solution is through enhanced lighting signals integrated into the roadway infrastructure. One such example is the use of addressable LEDs, individually controllable lights that can change color and brightness instantaneously through programmable microcontrollers. They can be installed and integrated into crosswalks to maintain visibility in conditions where pedestrians may be difficult to see, while also offering peripheral cues to pedestrians who may be distracted by their phones or other objects rather than the road. Such a system (as one example) that is integrated into a traffic intersection digital twin that tracks all roadway users accurately, has the potential to enhance visibility of vulnerable road users, and thus enhance safety. This paper examines the potential implementation and feasibility of this technology, as well as the safety benefits it could provide. Laboratory experiments with addressable LEDs reveal the capabilities and challenges of this technology for roadway infrastructure safety. These findings could pave the way for more integrated lighting in infrastructure for vehicles and pedestrians at intersections, merge and diverge locations, and other areas where complex interactions present safety hazards. Such lighting solutions, enabled by modern computation and communications, could enhance safety and efficiency in our transportation system and improve overall mobility.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Enhanced Lighting Signals for Safety and Efficiency - Experiments with Addressable LEDs

For enhanced roadway safety, clear and immediate visual cues are essential for preventing accidents between drivers and pedestrians. At intersections, however, the line of sight to other roadway users may be obstructed by vehicles and infrastructure. Additionally, adverse conditions, including low visibility, poor weather, or inadequate lighting can increase the potential for collisions. Distracted drivers and pedestrians can further exacerbate the risk of accidents, particularly when using a smartphone, rather than focusing on roadway surroundings. These issues demonstrate the need for infrastructure upgrades that enhance visibility and awareness at crosswalks. A potential solution is through enhanced lighting signals integrated into the roadway infrastructure. One such example is the use of addressable LEDs, individually controllable lights that can change color and brightness instantaneously through programmable microcontrollers. They can be installed and integrated into crosswalks to maintain visibility in conditions where pedestrians may be difficult to see, while also offering peripheral cues to pedestrians who may be distracted by their phones or other objects rather than the road. Such a system (as one example) that is integrated into a traffic intersection digital twin that tracks all roadway users accurately, has the potential to enhance visibility of vulnerable road users, and thus enhance safety. This paper examines the potential implementation and feasibility of this technology, as well as the safety benefits it could provide. Laboratory experiments with addressable LEDs reveal the capabilities and challenges of this technology for roadway infrastructure safety. These findings could pave the way for more integrated lighting in infrastructure for vehicles and pedestrians at intersections, merge and diverge locations, and other areas where complex interactions present safety hazards. Such lighting solutions, enabled by modern computation and communications, could enhance safety and efficiency in our transportation system and improve overall mobility.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Enhanced Safety of Heavy-Duty Vehicles on Highways through Automatic Speed Enforcement – A Simulation Study

Highway safety remains a significant concern, especially in mixed traffic scenarios involving heavy-duty vehicles (HDV) and smaller passenger cars. The vulnerability of HDVs following closely behind smaller cars is evident in incidents involving the lead vehicle, potentially leading to catastrophic rear-end collisions. Here, this paper explores how automatic speed enforcement systems, using speed cameras, can mitigate risks for HDVs in such critical situations. While historical crash data consistently demonstrates the reduction of accidents near speed cameras, this paper goes beyond the conventional notion of crash occurrence reduction. Instead, it investigates the profound impact of driver behavior changes within desired travel speed distribution, especially around speed cameras, and their contribution to the safety of trailing vehicles, with a specific focus on heavy-duty trucks in accident-prone scenarios. To conduct this analysis, we utilize SUMO, an open-source microscopic traffic simulator, enabling realistic simulations of real-world driving behaviors with and without speed cameras. The simulations also consider empirical distributions of desired headway gaps and reaction times exhibited by human drivers. This study offers a fresh perspective on highway safety by examining how the influence of automatic speed enforcement systems on driver behavior enhances the safety of HDV when faced with challenging situations. By shedding light on these dynamics, we contribute valuable insights to the ongoing research efforts on using technology to create safer roadways, ultimately promoting safer coexistence between heavy-duty and passenger vehicles.

33 ADVANCED PROPULSION SYSTEMS↗

Mapping the Ancient Maya Landscape from Space

This project uses new satellite and airborne imagery in combination with remote sensing, GIS, and GPS technology to understand the dynamics of how the Maya successfully interacted with their karst topographic landscape for several centuries in the northern Peten region of Guatemala. The ancient Maya attained one of the greatest population densities in human history in the tropical forest of the Peten, Guatemala, and it was in this region that the Maya civilization began, flourished, and abruptly disappeared for unknown reasons around AD 800. How the Maya were able to successfully manage water and feed this dense population is not known at this time. However, a recent NASA-funded project was the first to investigate large seasonal swamps (bajos) that make up 40 percent of the landscape. Through the use of remote sensing, ancient Maya features such as cities, roadways, canals and water reservoirs have been detected and verified through ground reconnaissance. The results of this research cast new light on the adaptation of the ancient Maya to their environment. Micro-environmental variation within the wetlands was elucidated and the different vegetational associations identified in the satellite imagery. More than 70 new archeological sites within and at the edges of the bajo were mapped and tested. Modification of the landscape by the Maya in the form of dams and reservoirs in the Holmul River and its tributaries and possible drainage canals in bajos was demonstrated. The recent acquisition of one-meter IKONOS imagery and high resolution STAR-3i radar imagery (2.5m backscatter/ 10m DEM), opens new possibilities for understanding how a civilization was able to survive for centuries upon a karst topographic landscape and their human-induced effects upon the local climate. This understanding is critical for the current population that is presently experiencing rapid population growth and destroying the landscape through non-traditional farming and grazing techniques, resulting in socioeconomic problems.

Sever, Tom↗

Landscape Archeology: Remote Sensing Investigation of the Ancient Maya in the Peten Rainforest of Northern Guatemala

Through the use of airborne and satellite imagery we are improving our ability to investigate ancient Maya settlement, subsistence, and landscape modification in this dense forest region. Today the area is threatened by encroaching settlement and deforestation. However, it was in this region that the Maya civilization began, flourished, and abruptly disappeared for unknown reasons in the 9th century AD. At the time of their collapse they had attained one of the highest population densities in human history. How the Maya were able to successfully manage water and feed this dense population is not well understood at this time. A NASA-funded project used remote sensing technology to investigate large seasonal swamps (bajos) that make up 40 percent of the landscape. Through the use of remote sensing, ancient Maya features such as sites, roadways, canals and water reservoirs have been detected and verified through ground reconnaissance. The results of this preliminary research cast new light on the adaptation of the ancient Maya to their environment. Microenvironmental variation within the wetlands was elucidated and the different vegetation associations identified in the satellite imagery. More than 70 new archeological sites within and at the edges of the bajo were mapped and tested. Modification of the landscape by the Maya in the form of dams and reservoirs in the Holmul River and its tributaries and possible drainage canals in bajos was demonstrated. The use of Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM), one-meter IKONOS satellite imagery, as well as high resolution airborne STAR-3i radar imagery--2.5 meter backscatter/10 meter Digital Elevation Model (DEM)--are opening new possibilities for understanding how a civilization was able to survive for centuries upon a karat topographic landscape. This understanding is critical for the current population that is currently experiencing rapid population growth and destroying the landscape through nontraditional farming and grazing techniques, resulting in socioeconomic problems.

Sever, Thomas L.↗

Optical traffic-sensing concept

Scaled-up optical proximity detector is versatile traffic sensor that replaces or augments existing systems such as inductive loops. Photosensor which does not depend on ambient light has several features that protect it against spurious or ambiguous inputs. It could be implemented in several forms to cope with different roadway conditions.

Johnston, A. R.↗

The Evolution and Development of the Lunar Regolith and Implications for Lunar Surface Operations and Construction

The lunar regolith consists of about 90% submillimeter particles traditionally termed lunar soil. The remainder consists of larger particles ranging up to boulder size rocks. At the lower size end, soil particles in the 10s of nanometer sizes are present in all soil samples. Lunar regolith overlies bedrock which consists of either lava flows in mare regions or impact-produced megaregolith in highland regions. Lunar regolith has been produced over billions of years by a combination of breaking and communition of bedrock by meteorite bombardment coupled with a variety of complex space weathering processes including solar wind implantation, solar flare and cosmic ray bombardment with attendant radiation damage, melting, vaporization, and vapor condensation driven by impact, and gardening and turnover of the resultant soil. Lunar regolith is poorly sorted compared to most terrestrial soils, and has interesting engineering properties including strong grain adhesion, over-compacted soil density, an abundance of agglutinates with sharp corners, and a variety of properties related to soil maturity. The NASA program has supported a variety of engineering test research projects, the production of bricks by solar or microwave sintering, the production of concrete, the in situ sintering and glazing of regolith by microwave, and the extraction of useful resources such as oxygen, hydrogen, iron, aluminum, silicon and other products. Future requirements for a lunar surface base or outpost will include construction of protective berms, construction of paved roadways, construction of shelters, movement and emplacement of regolith for radiation shielding and thermal control, and extraction of useful products. One early need is for light weight but powerful digging, trenching, and regolith-moving equipment.

McKay, David↗

Investigating the Impact of Temporal and Directional Traffic Distribution on Crash Frequencies

Safety Performance Functions (SPFs) are mathematical models that establish relationships between the frequency of various crash types and site-specific characteristics, serving as essential tools for traffic safety analysis and roadway design. Traditional SPFs, however, often overlook the temporal fluctuations in traffic flow (such as peak-hour surges) and directional imbalances between opposing traffic streams. These traffic patterns can exacerbate congestion, disrupt driver behavior, and create unexpected conflict points, potentially leading to increased crash frequencies and more severe accidents. In light of this gap, this study aims to explore the potential of incorporating K-factors (representing peak-hour traffic proportions) and D-factors (reflecting the imbalance of directional traffic) into the development of SPFs to assess whether these factors can effectively represent the impact of temporal and spatial traffic distribution on roadway safety. Using crash data from Pennsylvania urban-suburban collector roadways, it is found that the D-factor plays a significant role in predicting the frequency of total crashes, fatal + injury crashes, and angle crashes, with positive coefficient signs indicating that higher directional imbalances correspond to increased crash risks. Similarly, the K-factor emerges as a critical predictor for fatal + injury crashes and rear-end crashes, with negative coefficients suggesting that a more pronounced traffic peak is associated with a reduction in expected crash frequencies. These results highlight the importance of accounting for uneven traffic distribution in both time and direction when developing SPFs, offering deeper insights into crash patterns and supporting more effective safety interventions and roadway designs.

Xu, Guanhao [ORNL] (ORCID:0000000214326357)↗

Investigation of Atmospheric Effects in Image Transfer

Several computations on radiation emerging from the atmosphere for different aerosol models have been performed and the reflection matrix of a given surface was defined by incident light signature analyses. A two channel polarimeter is being constructed for measuring the Stokes parameters of reflected light. Surface albedo measurements were made in six wavelength ranges in the ultraviolet, visible, and near infrared spectral regions for six different vegetated surfaces, four soil surfaces, and two roadway surfaces. The effects of polarization changes on the intensity of projected images were studied by using a rotatable polarizer in front of an aerial camera lens.

Coulson, K. L.↗

Safe Operations at Roadway Junctions: Intelligent Roadway Infrastructure as Functional Interlocking

Automated vehicle (AV) technology is quickly maturing, and the corresponding infrastructure systems that evaluate traffic and communicate to vehicles requires sophisticated sensing and perception technologies, referred to as intelligent roadway infrastructure (IRI), to complement emerging AV capabilities. IRI provides signals to vehicles, indicating right-of-way for vehicles and communicating to approaching AVs that no other vehicle is failing to yield. This capability, denoted as safety-affirmative signaling, provides a green light or a green arrow as appropriate and affirms through communication links to connected vehicles when it is safe to proceed. About 36% of collisions occur at intersections, with most occurring upon left turns (22.2%) or crossing over (12.6%), and only a small percentage (1.2%) while turning right at an intersection. Of all intersection crashes about half (52.5%) of those vehicles were traveling through a signalized intersection 2. Safety-affirmative signaling would guarantee safety of AV fleet vehicles, by providing the interlocking principle, a term from automated train control that only allows progression through a railway intersection after affirming no opportunity for a crash exists. IRI through safety-affirmative signaling would bring performance and safety to complex roadway intersections where AV transit fleet service is most needed, as well as safety benefits to traditional, non-automated vehicles and vulnerable road users. The implementation of IRI has functional, programmatic, and technical challenges. Research work performed at the National Renewable Energy Laboratory (NREL) in an integrative approach encapsulating these themes, and termed infrastructure perception and control (IPC) is motivated by improved performance (travel time), improved safety (reduced collisions), and improved energy efficiency (less fuel burned and minimized production of greenhouse gases). IPC is intended not only for roadway and intersection applications but also in extension to inform complementary buildings and grid systems to enable better co-management, as vehicles and their charging needs become increasingly integrated into the built environment. The NREL IPC project presents an open-source framework, architecture, and supporting technology to implement IRI, addressing critical issues such as fusion of data, reliability, standardization of data interfaces, and confidence of detection. The framework is informed by previous experience in U.S. Department of Defense research technology, specifically in the use of radar to detect, identify, and track aerial threats. These principles combined with multi-sensor fusion provides for a complete digital twin with known and measurable confidence and accuracy from which safety-affirmative signaling can be developed and deployed.

ADVANCED PROPULSION SYSTEMS,MATHEMATICS AND COMPUT↗

An interactive driving simulation for driver control and decision-making research

Display techniques and equations of motion for a relatively simple fixed base car simulation are described. The vehicle dynamics include simplified lateral (steering) and longitudinal (speed) degrees of freedom. Several simulator tasks are described which require a combination of operator control and decision making, including response to wind gust inputs, curved roads, traffic signal lights, and obstacles. Logic circuits are used to detect speeding, running red lights, and crashes. A variety of visual and auditory cues are used to give the driver appropriate performance feedback. The simulated equations of motion are reviewed and the technique for generating the line drawing CRT roadway display is discussed. On-line measurement capabilities and experimenter control features are presented, along with previous and current research results demonstrating simulation capabilities and applications.

Allen, R. W.↗

Economic feasibility of in-motion wireless power transfer in a high-density traffic corridor

Electricity is expected to become a dominant power source in the transportation sector, but under a stationary recharging model, electric powered vehicles still suffer some disadvantages relative to conventional vehicles. Recent developments in wireless power transfer (WPT) technology can enable an alternative vehicle recharging model wherein power is supplied to vehicles while they are moving, mitigating the need for charging stops and high-capacity on-board energy storage. One of the greatest concerns associated with dynamic WPT is that the required infrastructure costs would be prohibitively high; however, the life-cycle costs and benefits of such a system have been under-researched. Here in this work, we apply a systems-level assessment to a case study of a WPT charging system located on the densely trafficked I-710 corridor in Los Angeles, California. Detailed cost estimates for electronics and implementation, high-fidelity energy consumption modeling, and survey-derived adoption projections are applied to evaluate scenarios of economic feasibility and environmental impact. Results show that a “1st-of-a-kind” system can achieve a payback in 20 years while maintaining operating cost advantages relative to petroleum fueling. System economics are shown to improve substantially with “nth-of-a-kind” capital costs. Discussion focuses on the effect of uptake trajectory on economic viability and detailed economics outcomes for light duty and heavy duty vehicles.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

LA100 Equity Strategies. Chapter 11: Truck Electrification for Improved Air Quality and Health

The LA100 Equity Strategies project integrates community guidance with robust research, modeling, and analysis to identify strategy options that can increase equitable outcomes in Los Angeles' clean energy transition. This report focuses on truck electrification as a means to improve air quality and health in traffic and air quality disadvantaged communities. It also identifies potential strategies to more equitably distribute air quality benefits from electrification of trucks, defined here as heavy-duty vehicles over 8,500 pounds (lbs) gross vehicle weight. Specifically, NREL analyzed 1) baseline air pollutant emissions, 2) emissions reductions associated with incremental increases in electrification of three types of heavy-duty trucks in 2035, and 3) resultant changes to air pollutant concentrations for selected census tracts along major roadways in disadvantaged and non-disadvantaged communities for comparison. In addition, NREL analyzed the impact of estimated pollutant concentrations on several health effects and the distribution of those health effects by disadvantaged community status. NREL's analysis is complemented by a University of California Los Angeles (UCLA) analysis of air quality benefits from transportation electrification, which included light-duty vehicles (Chapter 15) and evaluated regional air-quality changes across Los Angeles. Research was guided by input from the community engagement process, and associated equity strategies are presented in alignment with that guidance.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Cooperative Automated Cohort Driving on Connected Infrastructure, Arterial Roadways, and Highways: Final Project Demonstration and System-of-Systems Model Correlation

This project seeks to synergize vehicle automated driving and connectivity data to improve mobility and energy efficiency of groups of mixed vehicles operating in close proximity (vehicle cohort) on various infrastructure. A custom cellular communication network links vehicles operating as a cohort with infrastructure to a centralized system-of-systems digital twin with an AI-based optimal behavior planner. The data contained in this set are from final testing and technology demonstrations to U.S. Department of Energy staff at the American Center for Mobility. The data contain single-lane, single-light scenarios; multi-lane, multi-light arterial scenarios; and limited-access highway scenarios. All test cases were derived from simulations and replicated on the test track. The project employed two and four light-duty vehicles with connectivity and drive automation for the testing. The baseline scenario without connectivity was run under the control of the system-of-systems centralized planner but operating each vehicle with an intelligent driver model controlling the velocity, lane utilization, and vehicle gap. This was to ensure the highest compatibility with the simulation in terms of dynamic behavior. The connected cohort case utilized AI optimization to perform coordinated and cooperative control for energy, as well as safe, comfortable behavior for the cohort. The dataset is appropriately named with unconnected and connected designations, with comparisons sharing the same run index number. The included PowerPoint and PDF files describe the test setup and provide an overview of results from the project. ![image](de-EE0009209_March_2023_Data_Arterial_Scenario_Results.png)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Energy Optimization of Light and Heavy-Duty Vehicle Cohorts of Mixed Connectivity, Automation and Propulsion System Capabilities via Meshed V2V-V2I and Expanded Data Sharing (Final Scientific and Technical Report)

Vehicle connectivity and automated driving technologies individually have the potential to decrease energy consumption and/or increase safety on light, medium or heavy duty vehicles to varying degrees depending on the traffic infrastructure and specific driving scenarios. Due to advances in sensing, perception and computing power, research and development emphasis in the mobility sector has shifted away from connectivity. Prior research has shown that driving automation with the absence of connectivity can in certain circumstances increase energy consumption. The effectiveness of synergizing connectivity and driving automation technologies is the focus of this work, specifically applied to vehicle cohorts of mixed composition, light and heavy duty, and powertrains ranging from all electric to conventional internal combustion engine. The project team is led by Michigan Technological University (MTU) and partnered with AVL Mobility Technologies Inc. (AVL), Borg Warner (BW), Traffic Technology Services (TTS), American Center for Mobility (ACM) and Navistar (NAV). The main thrusts for the team are to develop a micro-traffic simulation environment with specific VD&PT system attributes and CAV capabilities, 2) field a vehicle test fleet of mixed classification, propulsion and CAV capacity, 3) develop artificial intelligence (AI) and machine learning (ML) based multi-agent optimization methods for various traffic infrastructures, 4) integrate the virtual environment and the optimization methods then deploy the system as a CAV hardware in the loop (HiL) for the vehicle test fleet and 5) conduct closed track and public road testing to validate simulation and demonstrated energy and mobility improvements at multiple scales. For a cohort of mixed vehicles, the team will demonstrate a reduction of energy consumption of 10-50% at intersection, arterial roadway and limited access highway scenarios through connectivity and automation in simulation and at a closed test track. The energy reduction objectives of the project are summarized in Table 1, indicating the infrastructure and over what distances are relevant considered. Single scenario energy reductions are not relevant and thus, the research team took the approach to vary parameters associated with the infrastructure, vehicle cohort composition and dynamic behavior to generate energy consumption distributions for both unconnected and connected scenarios.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Automated Announcements of Approaching Emergency Vehicles

Street intersections that are equipped with traffic lights would also be equipped with means for generating audible announcements of approaching emergency vehicles, according to a proposal. The means to generate the announcements would be implemented in the intersection- based subsystems of emergency traffic-light-preemption systems like those described in the two immediately preceding articles and in "Systems Would Preempt Traffic Lights for Emergency Vehicles" (NPO-30573), NASA Tech Briefs, Vol. 28, No. 10 (October 2004), page 36. Preempting traffic lights is not, by itself, sufficient to warn pedestrians at affected intersections that emergency vehicles are approaching. Automated visual displays that warn of approaching emergency vehicles can be helpful as a supplement to preemption of traffic lights, but experience teaches that for a variety of reasons, pedestrians often do not see such displays. Moreover, in noisy and crowded urban settings, the lights and sirens on emergency vehicles are often not noticed until a few seconds before the vehicles arrive. According to the proposal, the traffic-light preemption subsystem at each intersection would generate an audible announcement for example, emergency vehicle approaching, please clear intersection whenever a preemption was triggered. The subsystem would estimate the time of arrival of an approaching emergency vehicle by use of vehicle identity, position, and time data from one or more sources that could include units connected to traffic loops and/or transponders connected to diagnostic and navigation systems in participating emergency vehicles. The intersection-based subsystem would then start the announcement far enough in advance to enable pedestrians to leave the roadway before any emergency vehicles arrive.

Bachelder, Aaron↗

Identifying Vehicle Signals in Continuous Seismic Data Using Unsupervised Machine-Learning Techniques

Seismic sensors deployed near roadways effectively capture ground vibrations generated by passing vehicles. Although both traditional and machine‐learning algorithms have been utilized for analyzing such signals, independent validation of detected vehicle events remains limited. We applied two unsupervised machine‐learning algorithms, uniform manifold approximation and projection for dimension reduction, and hierarchical density‐based spatial clustering of applications with noise, to continuous seismic data collected along a road on the main campus of Oak Ridge National Laboratory. The algorithms identified seven distinct cluster labels across the entire dataset. By comparing these cluster labels with precipitation records from a nearby weather station and image‐derived labels from a local camera system, we identified one cluster associated with rainfall and another with vehicle activity. Our algorithms identified a greater number of vehicle‐related labels compared to the camera‐derived labels because seismic data are unaffected by poor lighting conditions. The arrival times of the newly detected vehicle signals corresponded well with the road’s speed limit, supporting our findings. Our algorithm outperformed the short‐term average/long‐term average method and k‐means clustering. Our results suggest that seismic data, when analyzed with machine‐learning algorithms, can complement existing vehicle monitoring systems, particularly under challenging environmental conditions.

Chai, Chengping [Oak Ridge National Laboratory (OR↗