Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “traffic estimation”

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 307 records · Page 17

Aircraft Conflict Analysis and Real-Time Conflict Probing Using Probabilistic Trajectory Modeling

Methods for maintaining separation between aircraft in the current airspace system have been built from a foundation of structured routes and evolved procedures. However, as the airspace becomes more congested and the chance of failures or operational error become more problematic, automated conflict alerting systems have been proposed to help provide decision support and to serve as traffic monitoring aids. The problem of conflict detection and resolution has been tackled from a number of different ways, but in this thesis, it is recast as a problem of prediction in the presence of uncertainties. Much of the focus is concentrated on the errors and uncertainties from the working trajectory model used to estimate future aircraft positions. The more accurate the prediction, the more likely an ideal (no false alarms, no missed detections) alerting system can be designed. Additional insights into the problem were brought forth by a review of current operational and developmental approaches found in the literature. An iterative, trial and error approach to threshold design was identified. When examined from a probabilistic perspective, the threshold parameters were found to be a surrogate to probabilistic performance measures. To overcome the limitations in the current iterative design method, a new direct approach is presented where the performance measures are directly computed and used to perform the alerting decisions. The methodology is shown to handle complex encounter situations (3-D, multi-aircraft, multi-intent, with uncertainties) with relative ease. Utilizing a Monte Carlo approach, a method was devised to perform the probabilistic computations in near realtime. Not only does this greatly increase the method's potential as an analytical tool, but it also opens up the possibility for use as a real-time conflict alerting probe. A prototype alerting logic was developed and has been utilized in several NASA Ames Research Center experimental studies.

Yang, Lee C.↗

En route Spacing Tool: Efficient Conflict-free Spacing to Flow-Restricted Airspace

This paper describes the Air Traffic Management (ATM) problem within the U.S. of flow-restricted en route airspace, an assessment of its impact on airspace users, and a set of near-term tools and procedures to resolve the problem. The FAA is committed, over the next few years, to deploy the first generation of modem ATM decision support tool (DST) technology under the Free-Flight Phase-1 (FFp1) program. The associated en route tools include the User Request Evaluation Tool (URET) and the Traffic Management Advisor (TMA). URET is an initial conflict probe (ICP) capability that assists controllers with the detection and resolution of conflicts in en route airspace. TMA orchestrates arrivals transitioning into high-density terminal airspace by providing controllers with scheduled times of arrival (STA) and delay feedback advisories to assist with STA conformance. However, these FFPl capabilities do not mitigate the en route Miles-In-Trail (MIT) restrictions that are dynamically applied to mitigate airspace congestion. National statistics indicate that en route facilities (Centers) apply Miles-In-Trail (MIT) restrictions for approximately 5000 hours per month. Based on results from this study, an estimated 45,000 flights are impacted by these restrictions each month. Current-day practices for implementing these restrictions result in additional controller workload and an economic impact of which the fuel penalty alone may approach several hundred dollars per flight. To mitigate much of the impact of these restrictions on users and controller workload, a DST and procedures are presented. The DST is based on a simple derivative of FFP1 technology that is designed to introduce a set of simple tools for flow-rate (spacing) conformance and integrate them with conflict-probe capabilities. The tool and associated algorithms are described based on a concept prototype implemented within the CTAS baseline in 1995. A traffic scenario is used to illustrate the controller's use of the tool, and potential display options are presented for future controller evaluation.

Green, S.↗

Optimal and suboptimal methods of satellite surveillance for traffic control of transoceanic flights.

Description of a system which uses two synchronous equatorial satellites. Aircraft location is determined by measuring the range of the aircraft to each satellite as well as aircraft altitude, and transmitting this information periodically to a ground station. There, the aircraft's geographic position at the time of transmission is computed. This information is then combined with past position measurements in a suboptimal filter to determine aircraft position and velocity (the velocity being used to estimate aircraft position between transmissions). The suboptimal filter is a simplification of the optimal Kalman filter. Except for altitude information, the system is independent of the aircraft navigation system.

Winter, H.↗

Exploration of the Theoretical Physical Capacity of the John F. Kennedy International Airport Runway System

A design study was completed to explore the theoretical physical capacity (TPC) of the John F. Kennedy International Airport (KJFK) runway system for a northflow configuration assuming impedance-free (to throughput) air traffic control functionality. Individual runways were modeled using an agent-based, airspace simulation tool, the Airspace Concept Evaluation System (ACES), with all runways conducting both departures and arrivals on a first-come first-served (FCFS) scheduling basis. A realistic future flight schedule was expanded to 3.5 times the traffic level of a selected baseline day, September 26, 2006, to provide a steady overdemand state for KJFK runways. Rules constraining departure and arrival operations were defined to reflect physical limits beyond which safe operations could no longer be assumed. Safety buffers to account for all sources of operational variability were not included in the TPC estimate. Visual approaches were assumed for all arrivals to minimize inter-arrival spacing. Parallel runway operations were assumed to be independent based on lateral spacing distances. Resulting time intervals between successive airport operations were primarily constrained by same-runway and then by intersecting-runway spacing requirements. The resulting physical runway capacity approximates a theoretical limit that cannot be exceeded without modifying runway interaction assumptions. Comparison with current KJFK operational limits for a north-flow runway configuration indicates a substantial throughput gap of approximately 48%. This gap may be further analyzed to determine which part may be feasibly bridged through the deployment of advanced systems and procedures, and which part cannot, because it is either impossible or not cost-effective to control. Advanced systems for bridging the throughput gap may be conceptualized and simulated using this same experimental setup to estimate the level of gap closure achieved.

Neitzke, Kurt W.↗

An Intercomparative Study of the Effects of Aircraft Emissions on Surface Air Quality

This study intercompares, among five global models, the potential impacts of all commercial aircraft emissions worldwide on surface ozone and particulate matter (PM (sub 2.5)). The models include climate-response models (CRMs) with interactive meteorology, chemical-transport models (CTMs) with prescribed meteorology, and models that integrate aspects of both. Model inputs are harmonized in an effort to achieve a consensus about the state of understanding of impacts of 2006 commercial aviation emissions. Models find that aircraft increase near-surface ozone (0.3 to 1.9 percent globally), with qualitatively similar spatial distributions, highest in the Northern Hemisphere. Annual changes in surface-level PM (sub 2.5) in the CTMs (0.14 to 0.4 percent) and CRMs (-1.9 to 1.2 percent) depend on differences in nonaircraft baseline aerosol fields among models and the inclusion of feedbacks between aircraft emissions and changes in meteorology. The CTMs tend to result in an increase in surface PM (sub 2.5) primarily over high-traffic regions in the North American midlatitudes. The CRMs, on the other hand, demonstrate the effects of aviation emissions on changing meteorological fields that result in large perturbations over regions where natural emissions (e.g., soil dust and sea spray) occur. The changes in ozone and PM (sub 2.5) found here may be used to contextualize previous estimates of impacts of aircraft emissions on human health.

Air quality↗

Prediction of Pushback Times and Ramp Taxi Times for Departures at Charlotte Airport

When optimizing the takeoff sequence and schedule for departures at busy airports, it is important to accurately predict the taxi times from gate to runway because those are used to calculate the earliest possible takeoff times. Several airports like Charlotte Douglas International Airport show relatively long taxi times inside the ramp area with large variations, with respect to the travel times in the airport movement area. Also, the pushback process times have not been accurately modeled so far mainly due to the lack of accurate data. The recent deployment of the integrated arrival, departure, and surface traffic management system at Charlotte airport by NASA enables more accurate flight data in the airport surface operations to be obtained. Taking advantage of this system, actual pushback times and ramp taxi times from historical flight data at this airport are analyzed. Based on the analysis, a simple, data-driven prediction model is introduced for estimating pushback times and ramp transit times of individual departure flights. To evaluate the performance of this prediction model, several machine learning techniques are also applied to the same dataset. The prediction results show that the data-driven prediction model is as good as the machine learning algorithms when comparing various prediction performance metrics.

Lee, Hanbong↗

Prediction of Pushback Times and Ramp Taxi Times for Departures at Charlotte Airport

When optimizing the takeoff sequence and schedule for departures at busy airports, it is important to accurately predict the taxi times from gate to runway because those are used to calculate the earliest possible takeoff times. Several airports like Charlotte Douglas International Airport show relatively long taxi times inside the ramp area with large variations, with respect to the travel times in the airport movement area. Also, the pushback process times have not been accurately modeled so far mainly due to the lack of accurate data. The recent deployment of the integrated arrival, departure, and surface traffic management system at Charlotte airport by NASA enables more accurate flight data in the airport surface operations to be obtained. Taking advantage of this system, actual pushback times and ramp taxi times from historical flight data at this airport are analyzed. Based on the analysis, a simple, data-driven prediction model is introduced for estimating pushback times and ramp transit times of individual departure flights. To evaluate the performance of this prediction model, several machine learning techniques are also applied to the same dataset. The prediction results show that the data-driven prediction model is as good as the machine learning algorithms when comparing various prediction performance metrics.

airport surface operations↗

Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning

One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. It affects the efficiency of the National Airspace System (NAS) and both surface and airspace operations can benefit from better understanding future runway configurations. In this paper, we present a comprehensive implementation of predictive models for runway configuration estimation from large volumes of historical data. Specifically, operational data from two full years (2018 and 2019) is collected, analyzed, and fused together to build the data product used in this work. The data set differs from prior work in the field in terms of its scope, resolution, and variety of factors collected and considered. Meteorological data is collected from two different sources – current weather conditions from METAR (Meteorological Terminal Aviation Routine Weather Report) and forecast weather conditions from Localized Aviation MOS Program (LAMP). Operational data from the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) related to scheduled and actual number of arrivals and departures, average taxi times, etc. are collected. NASA’s Sherlock Data Warehouse is used to identify critical information such as go-arounds, and other events that might impact RCM decision-making. All data is collected and aggregated over 15-minute intervals throughout the two years. This provides a resolution like the timescales that might be necessary for runway configuration management decision-making. A variety of supervised learning algorithms are tested including Support Vector Machine, Random Forest, Gradient Boosting, etc. including tuning of the model hyperparameters. The modeling process is applied and presented on two representative U.S. airports – Charlotte Douglas International Airport (KCLT) and Denver International Airport (KDEN). The two airports present different levels of complexity in terms of the total number of configurations used and provide a balanced perspective on the generalizability of the developed approach to other airports in the NAS. Initial results are promising (F1 score of 0.91 at KCLT and 0.83 at KDEN) for data in the test set. The final paper will contain a comprehensive comparison between different models and model building strategies as well as further refined results. Most important predictors for each airport will be identified along with a discussion and recommendations on adapting the framework to other scenarios.

Tejas G Puranik↗

Videopanorama Frame Rate Requirements Derived from Visual Discrimination of Deceleration During Simulated Aircraft Landing

In order to determine the required visual frame rate (FR) for minimizing prediction errors with out-the-window video displays at remote/virtual airport towers, thirteen active air traffic controllers viewed high dynamic fidelity simulations of landing aircraft and decided whether aircraft would stop as if to be able to make a turnoff or whether a runway excursion would be expected. The viewing conditions and simulation dynamics replicated visual rates and environments of transport aircraft landing at small commercial airports. The required frame rate was estimated using Bayes inference on prediction errors by linear FRextrapolation of event probabilities conditional on predictions (stop, no-stop). Furthermore estimates were obtained from exponential model fits to the parametric and non-parametric perceptual discriminabilities d' and A (average area under ROC-curves) as dependent on FR. Decision errors are biased towards preference of overshoot and appear due to illusionary increase in speed at low frames rates. Both Bayes and A - extrapolations yield a framerate requirement of 35 < FRmin < 40 Hz. When comparing with published results [12] on shooter game scores the model based d'(FR)-extrapolation exhibits the best agreement and indicates even higher FRmin > 40 Hz for minimizing decision errors. Definitive recommendations require further experiments with FR > 30 Hz.

deceleration perception↗

In-Flight Evaluation of the Traffic Aware Planner on the NASA HU-25A Guardian Aircraft

NASA’s Traffic Aware Planner (TAP) software is a research-prototype decision support tool that provides pilots with time- and fuel-saving route recommendations that optimize their current trajectory. The software runs on a first-of-a-kind system architecture onboard three aircraft in revenue service conducting operational evaluations with a major domestic airline. Therefore, significant NASA-internal testing is required prior to releasing the software to the partner airline. This paper describes a flight test plan that exercises the functionality of the TAP software in a representative operational environment, describes the system architecture developed and implemented for the NASA Langley HU-25A Guardian aircraft to support the test objectives, presents outcomes of the flight test campaign, and discusses use cases that demonstrate the value of flight testing for this activity.Research into flight path optimization of transport aircraft conducted by the National Aeronautics and SpaceAdministration (NASA) has produced an operational concept known as Traffic Aware Strategic Aircrew Requests(TASAR) [1, 2]. This near-term concept [3] provides the aircrew with a flight deck decision support tool known asthe Traffic Aware Planner (TAP). The TAP software leverages a growing number of information sources on the flightdeck to make time- and fuel-saving route optimization recommendations to the aircrew while en route. The aircrewcan then use the suggestions provided by the tool to make route change requests with a greater likelihood of acceptanceby air traffic control (ATC). Since TASAR is a concept intended for the current operational environment, it isintentionally designed to have no safety-critical impact or require any changes to current Federal AviationAdministration (FAA) rules and procedures [4, 5].The research prototype TAP system [6–8], explained further in Section III.C, continually incorporates up-to-dateaircraft state data from onboard avionics, as well as the latest position of surrounding traffic, the most recent windforecast, and the most recent convective weather forecast, in order to calculate candidate trajectory modifications thatimprove upon the current active route. These trajectories account for user-selectable objective functions [3] of reducedfuel burn, reduced flight time, or an airline-derived combination of factors known as trip cost. Previous analyses andsimulations have estimated substantial savings for airlines employing this technique within the U.S. National AirspaceSystem (NAS) [9–11]. Operational evaluations with Alaska Airlines seek to validate these projected benefits usingmeasured data while simultaneously providing benefits to the airline [12, 13].The TAP software has undergone a number of human-in-the-loop simulations [14] and flight test activities[15–17] in order to validate the operational concept, evaluate human factors considerations (e.g., workload, usability,distraction, etc.), and to assess the ability of the software to function in a representative operational environment (e.g.,connected to live avionics data, using in-flight internet connectivity, etc.). However, these simulations and flight testcampaigns did not account for the hardware architecture implemented on the three aircraft for Alaska Airlines’operational evaluations of the TAP software. Therefore, a need was identified to thoroughly test the functionality ofthe software in a similar hardware architecture to that of the partner airline’s aircraft. Information regarding testapparatus and environments used to evaluate TAP prior to testing on the HU-25A can be found in reference [18].A campaign of flight trials on a NASA aircraft, the HU-25A Guardian, was conducted to ensure that the researchprototype TAP system functions well in a configuration similar to the Alaska Airlines aircraft prior to deployment.This airborne, networked environment enables an assessment of the operational factors unique to the flight environment. Additionally, this activity evaluated the effectiveness and benefit of new TAP functionality andoperation in a relevant flight environment while allowing the rapid prototyping of new concepts and features.This paper is organized as follows: Section II discusses the details of the flight test plan, flight profiles, and theduties of personnel involved with conducting flight operations. Section III describes the test platform, avionicsequipage, and system architecture. Section IV presents a discussion of results, and Section V contains concludingremarks.

Underwood, Matthew C.↗

Crowd cluster data in the USA for analysis of human response to COVID-19 events and policies

We provide data on daily social contact intensity of clusters of people at different types of Points of Interest (POI) by zip code in Florida and California. This data is obtained by aggregating fine-scaled details of interactions of people at the spatial resolution of 10 m, which is then normalized as a social contact index. We also provide the distribution of cluster sizes and average time spent in a cluster by POI type. This data will help researchers perform fine-scaled, privacy-preserving analysis of human interaction patterns to understand the drivers of the COVID-19 epidemic spread and mitigation. Current mobility datasets either provide coarse-level metrics of social distancing, such as radius of gyration at the county or province level, or traffic at a finer scale, neither of which is a direct measure of contacts between people. We use anonymized, de-identified, and privacy-enhanced location-based services (LBS) data from opted-in cell phone apps, suitably reweighted to correct for geographic heterogeneities, and identify clusters of people at non-sensitive public areas to estimate fine-scaled contacts.

60 APPLIED LIFE SCIENCES↗

AIS-based characterization of navigation conflicts along the US Atlantic Coast prior to development of wind energy

This study characterizes navigation conflicts in a region with a large traffic volume along the US Atlantic Coast, utilizing Automated Identification System (AIS) data for 2010. The region includes areas proposed for wind energy development. The characterization could be useful in evaluating the effect of offshore wind areas on navigation conflicts. The study processes the AIS data to provide pairwise comparisons of vessel interactions (encounters and near-misses) as they occurred. Using the vessel encounter data, analyses are made using a ‘blind’ vessel assumption to evaluate the potential for both near-misses and collisions. Then statistical analyses are made to estimate the point values and uncertainty for each type of encounter (crossing, head-on, overtaking). Examination of the frequency/number of collisions from actual observations is made. The examination of actual near-misses, potential near-misses, and potential collisions provides comparable results in the number of near-misses and collisions. The potential near-miss analyses include an examination of the timing of responses made by vessels to prevent near-misses. This informed the statistical analysis but may also have utility in the simulation of navigation conflicts.

99 GENERAL AND MISCELLANEOUS↗

Non-urban mobile radio market demand forecast

A national nonmetropolitan land mobile traffic model for 1990-2000 addresses user classes, density classes, traffic mix statistics, distance distribution, geographic distribution, price elasticity, and service quality elasticity. Traffic demands for business, special industrial, and police were determined on the basis of surveys in 73 randomly selected nonurban counties. The selected services represent 69% of total demand. The results were extrapolated to all services in the non-SMSA areas of the contiguous United States. Radiotelephone services were considered separately. Total non-SMSA mobile radio demand (one way) estimates are given. General functional requirements include: hand portability, privacy, reduction of blind spots, two way data transmission, position location, slow scan imagery.

Castruccio, P. A.↗

Real Time Volcanic Cloud Products and Predictions for Aviation Alerts

Volcanic eruptions can inject significant amounts of sulfur dioxide (SO2) and volcanic ash into the atmosphere, posing a substantial risk to aviation safety. Ingesting near-real time and Direct Readout satellite volcanic cloud data is vital for improving reliability of volcanic ash forecasts and mitigating the effects of volcanic eruptions on aviation and the economy. NASA volcanic products from the Ozone Monitoring Insrument (OMI) aboard the Aura satellite have been incorporated into Decision Support Systems of many operational agencies. With the Aura mission approaching its 10th anniversary, there is an urgent need to replace OMI data with those from the next generation operational NASA/NOAA Suomi National Polar Partnership (SNPP) satellite. The data provided from these instruments are being incorporated into forecasting models to provide quantitative ash forecasts for air traffic management. This study demonstrates the feasibility of the volcanic near-real time and Direct Readout data products from the new Ozone Monitoring and Profiling Suite (OMPS) ultraviolet sensor onboard SNPP for monitoring and forecasting volcanic clouds. The transition of NASA data production to our operational partners is outlined. Satellite observations are used to constrain volcanic cloud simulations and improve estimates of eruption parameters, resulting in more accurate forecasts. This is demonstrated for the 2012 eruption of Copahue. Volcanic eruptions are modeled using the Goddard Earth Observing System, Version 5 (GEOS-5) and the Goddard Chemistry Aerosol and Radiation Transport (GOCART) model. A hindcast of the disruptive eruption from Iceland's Eyjafjallajokull is used to estimate aviation re-routing costs using Metron Aviation's ATM Tools.

Volcanic ash↗

Aircraft Trajectory Design Based on Reducing the Combined Effects of Carbon-Dioxide, Oxides of Nitrogen and Contrails

Aircraft operations need to meet the combined requirements of safety, efficiency, capacity and reduced environmental impact. Aircraft routes can be made efficient by flying wind optimal routes. However, the desire to reduce the impact of aviation emissions and contrails may result in trajectories, which deviate from wind optimal trajectories leading to extra fuel use. The lifetime associated with different emissions and contrails varies from a few hours to several hundred years. The impact of certain gases depends on the amount and location of the emission, and the decision-making horizon, in years, when the impact is estimated. The Absolute Global Temperature Potential (AGTP) is used as a metric to measure the combined effects of emissions and contrails. This paper extends earlier work by the authors to include the effect of oxides of nitrogen in the development of aircraft trajectories to reduce the combined effects of carbon dioxide, oxides of nitrogen (NOX) and contrails. The methodology is applied to air traffic in the continental US. The paper shows the trade-offs between reducing emissions and the cost of extra fuel using a fuel sensitivity index, defined as the reduction in AGTP per kg of fuel. The paper shows the performance of the optimization strategy for decision intervals of 10, 25 and 100 years. Based on the simplified models, the inclusion of NOX emissions has a slight influence on the minimal climate impact trajectories when the decision horizons are around 25 years.

air trafic optimization↗

Aircraft Trajectory Design Based on Reducing the Combined Effects of Carbon-di-oxide, Nitrogen and Contrails

Aircraft operations need to meet the combined requirements of safety, efficiency, capacity and reduced environmental impact. Aircraft routes can be made efficient by flying wind optimal routes. However, the desire to reduce the impact of aviation emissions and contrails may result in trajectories, which deviate from wind optimal trajectories leading to extra fuel use. The lifetime associated with different emissions and contrails varies from a few hours to several hundred years. The impact of certain gases depends on the amount and location of the emission, and the decision-making horizon, in years, when the impact is estimated. The Absolute Global Temperature Potential (AGTP) is used as a metric to measure the combined effects of emissions and contrails. This paper extends earlier work by the authors to include the effect of oxides of nitrogen in the development of aircraft trajectories to reduce the combined effects of carbon dioxide, oxides of nitrogen (NOX) and contrails. The methodology is applied to air traffic in the continental US. The paper shows the trade-offs between reducing emissions and the cost of extra fuel using a fuel sensitivity index, defined as the reduction in AGTP per kg of fuel. The paper shows the performance of the optimization strategy for decision intervals of 10, 25 and 100 years. Based on the simplified models, the inclusion of NOX emissions has a slight influence on the minimal climate impact trajectories when the decision horizons are around 25 years.

Sridhar, Banavar↗

Assessing variation in faecal glucocorticoid concentrations in gray whales exposed to anthropogenic stressors

Understanding how individual animals respond to stressors behaviourally and physiologically is a critical step towards quantifying long-term population consequences and informing management efforts. Glucocorticoid (GC) metabolite accumulation in various matrices provides an integrated measure of adrenal activation in baleen whales and could thus be used to investigate physiological changes following exposure to stressors. In this study, we measured GC concentrations in faecal samples of Pacific Coast Feeding Group (PCFG) gray whales (Eschrichtius robustus) collected over seven consecutive years to assess the association between GC content and metrics of exposure to sound levels and vessel traffic at different temporal scales, while controlling for contextual variables such as sex, reproductive status, age, body condition, year, time of year and location. We develop a Bayesian Generalized Additive Modelling approach that accommodates the many complexities of these data, including non-linear variation in hormone concentrations, missing covariate values, repeated samples, sampling variability and some hormone concentrations below the limit of detection. Estimated relationships showed large variability, but emerging patterns indicate a strong context-dependency of physiological variation, depending on sex, body condition and proximity to a port. Our results highlight the need to control for baseline hormone variation related to context, which otherwise can obscure the functional relationship between faecal GCs and stressor exposure. Therefore, extensive data collection to determine sources of baseline variation in well-studied populations, such as PCFG gray whales, could shed light on cetacean stress physiology and be used to extend applicability to less-well-studied taxa. GC analyses may offer greatest utility when employed as part of a suite of markers that, in aggregate, provide a multivariate measure of physiological status, better informing estimates of individuals’ health and ultimately the consequences of anthropogenic stressors on populations.

59 BASIC BIOLOGICAL SCIENCES↗

A General Spatiotemporal Imputation Framework for Missing Sensor Data

Many applications from precision agriculture, environmental monitoring and transportation networks rely on data collected across space and time over a large geographic area. Missing data poses a significant challenge for any data-driven inference and control tasks. Data imputation or the estimation of missing data can help fill these gaps by utilizing inherent spatial relationships and temporal patterns. A variety of spatiotemporal imputation models have been developed to address missing data in spatiotemporal datasets. However, these classical methods rely on the assumption that the underlying data follows a smooth trend and fail to provide accurate estimates when there is a large number of missing points in the data. Even though there are machine learning driven tensor completion approaches such as convolutional neural network based tensor completion (CoSTCo) that capture the non-linear relationships in the dataset, the transductive nature makes the algorithm less scalable. Thus, existing approaches for estimating the missing information do not effectively capture all dimensions of the spatiotemporal data structure, resulting in erroneous predictions and poor performance. The main contributions of this paper are: (1) We propose a novel inductive framework (G-LSTM) for missing data imputation that integrates a graph neural network with LSTMs to effectively capture both spatial and temporal dependencies. (2) Experimental results on a traffic dataset demonstrate that the proposed GNN integrated with an LSTM framework achieves improved imputation and maintains steady performance even when there are extreme missing conditions in comparison with the state-of-the-art imputation framework (i.e, CoSTCo). (3) The simulation results on a traffic network show up to 69% reduction in mean absolute error and 61% reduction in root mean square error when compared to CoSTCo.

Tharzeen, Aabila↗