Travel Time Estimation Research Articles

Estimating travel time in the Helsinki region utilising sequential Bayesian inference

This paper explores application of Bayesian inference (BI) to dynamic travel time estimation in the Helsinki region. Accurate travel time prediction is crucial in a wide range of fields, including departure time and routing. Limited real-time data challenge modelling accuracy. To address this, this paper utilises BI, particularly sequential Bayesian inference (SBI) for evolving observed values. Incorporating 2018 real-time data and 2015 information as prior knowledge, travel time distribution will be updated. Validation yields a 4.0% mean absolute error between the updated 2018 distribution and actual travel time. Also, using the 2015 posterior distribution as prior by way of SBI yields a 4.6% mean absolute error. Results highlight that SBI is an effective tool for updating distributions. This paper underscores potential of BI in addressing data scarcity and enhancing accuracy of transportation models. By supplying precise travel time estimates, this approach benefits congestion relief and travel planning. With evolving travel time data, BI promises to advance transportation modelling.

Analysis the Reliability of Travel Time in Urban Corridors in Baghdad City

Travel-time reliability is a crucial performance measure for transportation systems. This research aims to estimate travel time and predict delay time on three routes in Baghdad city using GPS devices: Safi Al-Den Street, Palestine Street, and the Army Channel Expressway. The study was conducted northward from 7:00 a.m. to 9:00 p.m. Reliability indices for the first and second routes with signalized intersections, including buffer index, travel time index, and 95th percentile travel time, were determined. Safi Al-Den Street's buffer time index for links 1 to 3 is approximately 44.75%, 39.87%, and 39.12%, respectively. The highest travel time index value is observed in link 3 at 8.9%. Link 1 has the longest 95% travel time at 659 seconds. Palestine Street shows a high buffer time index in links 1 and 3 at around 32.39% and 24.65%, respectively. The highest travel time index is in link 3 at 6.84%, attributed to congestion from increased educational, medical, and commercial trips. The longest 95% travel time is 430 seconds in link 7. This study offers valuable insights into the reliability of travel time in urban corridors in Baghdad city, aiding transportation planners and engineers in making informed decisions on traffic management, infrastructure development, and policy-making.

Method on Estimation of Travel Time Saving Benefit According to Smart Expressway Construction for Automated Vehicles

Method on Estimation of Travel Time Saving Benefit According to Smart Expressway Construction for Automated Vehicles

Travel Time Estimation of Sharada Road in Kano

Travel Time Estimation of Sharada Road in Kano

Congestion-aware Spatio-Temporal Graph Convolutional Network-based A* Search Algorithm for Fastest Route Search

The fastest route search, which is to find a path with the shortest travel time when the user initiates a query, has become one of the most important services in many map applications. To enhance the user experience of travel, it is necessary to achieve accurate and real-time route search. However, traffic conditions are changing dynamically, and the frequent occurrence of traffic congestion may greatly increase travel time. Thus, it is challenging to achieve the above goal. To deal with it, we present a congestion-aware spatio-temporal graph convolutional network-based A* search algorithm for the task of fastest route search. We first identify a sequence of consecutive congested traffic conditions as a traffic congestion event. Then, we propose a spatio-temporal graph convolutional network that jointly models the congestion events and changing travel time to capture their complex spatio-temporal correlations, which can predict the future travel-time information of each road segment as the basis of route planning. Further, we design a path-aided neural network to achieve effective origin-destination (OD) shortest travel-time estimation by encoding the complex relationships between OD pairs and their corresponding fastest paths. Finally, the cost function in the A* algorithm is set by fusing the output results of the two components, which is used to guide the route search. Our experimental results on the two real-world datasets show the superior performance of the proposed method.

Measuring geographic access to emergency obstetric care: a comparison of travel time estimates modelled using Google Maps Directions API and AccessMod in three Nigerian conurbations.

Google Maps Directions Application Programming Interface (the API) and AccessMod tools are increasingly being used to estimate travel time to healthcare. However, no formal comparison of estimates from the tools has been conducted. We modelled and compared median travel time (MTT) to comprehensive emergency obstetric care (CEmOC) using both tools in three Nigerian conurbations (Kano, Port-Harcourt, and Lagos). We compiled spatial layers of CEmOC healthcare facilities, road network, elevation, and land cover and used a least-cost path algorithm within AccessMod to estimate MTT to the nearest CEmOC facility. Comparable MTT estimates were extracted using the API for peak and non-peak travel scenarios. We investigated the relationship between MTT estimates generated by both tools at raster celllevel (0.6 km resolution). We also aggregated the raster cell estimates to generate administratively relevant ward-level MTT. We compared ward-level estimates and identified wards within the same conurbation falling into different 15-minute incremental categories (<15/15-30/30-45/45-60/+60). Of the 189, 101 and 375 wards, 72.0%, 72.3% and 90.1% were categorised in the same 15- minute category in Kano, Port-Harcourt, and Lagos, respectively. Concordance decreased in wards with longer MTT. AccessMod MTT were longer than the API's in areas with ≥45min. At the raster cell-level, MTT had a strong positive correlation (≥0.8) in all conurbations. Adjusted R2 from a linear model (0.624-0.723) was high, increasing marginally in a piecewise linear model (0.677-0.807). In conclusion, at <45-minutes, ward-level estimates from the API and AccessMod are marginally different, however, at longer travel times substantial differences exist, which are amenable to conversion factors.

Bi-scale car-following model calibration based on corridor-level trajectory

The precise estimation of macroscopic traffic parameters, such as travel time and fuel consumption, is essential for the optimization of traffic management systems. Despite its importance, the comprehensive acquisition of vehicle trajectory data for the calculation of these macroscopic measures presents a challenge. To bridge this gap, this study aims to calibrate car-following models capable of predicting both microscopic measures and macroscopic measures. We conduct a numerical analysis to trace the cumulative process of model prediction errors across various measurements, and our findings indicate that macroscopic measures encapsulate the accumulation of model errors. By incorporating macroscopic measures into vehicle model calibration, we can mitigate the impact of noise on microscopic data measurements. We compare three car-following model calibration methods: MiC (using microscopic measurements), MaC (using macroscopic measurements), and BiC (using both microscopic and macroscopic measurements)—utilizing real-world trajectory data. The BiC method emerges as the most successful in reconstructing vehicle trajectories and accurately estimating travel time and fuel consumption, whereas the MiC method leads to overfitting and inaccurate macro-measurement predictions. This study underscores the importance of bi-scale calibration for precise traffic and energy consumption predictions, laying the groundwork for future research aimed at enhancing traffic management strategies.

Analysis of Intercity Transportation Network Efficiency Using Flow-Weighted Time Circuity: A Case Study of Seven Major City Clusters in China

Enhancing the efficiency of intercity transportation networks is crucial for sustainable regional transport development, significantly impacting travel behaviors and energy consumption. The transportation infrastructure within the city cluster is rapidly developing to accommodate the increasing traffic demand, necessitating substantial investments. It is imperative to investigate the effectiveness of intercity traffic within urban clusters, to evaluate the influence of transportation infrastructure enhancements on regional traffic efficiency. Circuity is a conventional metric used to assess the efficiency of transportation networks, primarily emphasizing distance, while overlooking factors such as travel time and traffic flow. In this study, the concept of circuity has been redefined in terms of travel time and has been referred to as the transportation network travel speed. Subsequently, the amalgamation of travel speed within the transportation network and traffic flow culminates in the proposition of Flow-Weighted Time Circuity (FWTC). Real-time intercity navigation data, offering accurate travel time estimations, are utilized to analyze the spatial distribution of intercity transport efficiency in the seven major city clusters of China, via both automobile and train modes of transportation. The results indicate that (1) as the travel distance extends, the speed of transportation within the network typically increases, albeit with increasing fluctuations, especially in the case of intercity train travel; (2) concerning the efficiency of intercity automobile travel, most city clusters demonstrate satisfactory performance, with the exception of the Guanzhong Plain. The Yangtze River Delta and Beijing–Tianjin–Heibei regions stand out for their superior performance. In terms of intercity train efficiency, the Yangtze River Delta, Beijing–Tianjin–Heibei, and Mid-Yangtze River regions exhibit higher levels of efficiency in intercity train transportation, while the Guanzhong Plain city cluster falls behind in this aspect. On the whole, the efficiency of intercity travel using automobiles surpasses that of train travel, indicating a pressing need for improvement in the latter.

Revisiting the Thornthwaite Mather procedure for baseflow and groundwater storage predictions in sloping and mountainous regions

Hillslope aquifers regulate streamflow and are a critical potable and irrigation water source, especially in developing countries. Knowing recharge and baseflow is essential for managing these aquifers. Methods using available data to calculate recharge and baseflow from aquifers are not valid for uplands. This paper adapts the Thornthwaite and Mather (T-M) procedure from plains to sloping and mountainous regions by replacing the linear reservoir with a zero-order aquifer. The revised T-M procedure was tested over four years in two contrasting watersheds in the humid Ethiopian highlands: the 57 km2 Dangishta with a perennial stream and the nine km2 Robit Bata, where the flow ceased four months after the end of the rain phase. The monthly average groundwater tables were predicted with an accuracy ranging from satisfactory to good for both watersheds. Baseflow predictions were “very good” after considering the evaporation from shallow groundwater in the valley bottom during the dry phase in Dangishta. We conclude that the T-M procedure is ideally suited for calculating recharge, baseflow and groundwater storage in upland regions with sparse hydrological data since the procedure uses as input only rainfall and potential evaporation data that are readily available together with an estimate of the aquifer travel time.

Urban Origin–Destination Travel Time Estimation Using K-Nearest-Neighbor-Based Methods

Improving the estimation of origin–destination (O-D) travel times poses a formidable challenge due to the intricate nature of transportation dynamics. Current deep learning models often require an overwhelming amount of data, both in terms of data points and variables, thereby limiting their applicability. Furthermore, there is a scarcity of models capable of predicting travel times with basic trip information such as origin, destination, and starting time. This paper introduces novel models rooted in the k-nearest neighbor (KNN) algorithm to tackle O-D travel time estimation with limited data. These models represent innovative adaptations of weighted KNN techniques, integrating the haversine distance of neighboring trips and incorporating correction factors to mitigate prediction biases, thereby enhancing the accuracy of travel time estimations for a given trip. Moreover, our models incorporate an adaptive heuristic to partition the time of day, identifying time blocks characterized by similar travel-time observations. These time blocks facilitate a more nuanced understanding of traffic patterns, enabling more precise predictions. To validate the effectiveness of our proposed models, extensive testing was conducted utilizing a comprehensive taxi trip dataset sourced from Santiago, Chile. The results demonstrate substantial improvements over existing state-of-the-art models (e.g., MAPE between 35 to 37% compared to 49 to 60% in other methods), underscoring the efficacy of our approach. Additionally, our models unveil previously unrecognized patterns in city traffic across various time blocks, shedding light on the underlying dynamics of urban mobility.

Geographical accessibility to functional emergency obstetric care facilities in urban Nigeria using closer-to-reality travel time estimates: a population-based spatial analysis

Better accessibility for emergency obstetric care facilities can substantially reduce maternal and perinatal deaths. However, pregnant women and girls living in urban settings face additional complex challenges travelling to facilities. We aimed to assess the geographical accessibility of the three nearest functional public and private comprehensive emergency obstetric care facilities in the 15 largest Nigerian cities via a novel approach that uses closer-to-reality travel time estimates than traditional model-based approaches. In this population-based spatial analysis, we mapped city boundaries, verified and geocoded functional comprehensive emergency obstetric care facilities, and mapped the population distribution for girls and women aged 15-49 years (ie, of childbearing age). We used the Google Maps Platform's internal Directions Application Programming Interface to derive driving times to public and private facilities. Median travel time and the percentage of women aged 15-49 years able to reach care were summarised for eight traffic scenarios (peak and non-peak hours on weekdays and weekends) by city and within city under different travel time thresholds (≤15 min, ≤30 min, ≤60 min). As of 2022, there were 11·5 million girls and women aged 15-49 years living in the 15 studied cities, and we identified the location and functionality of 2020 comprehensive emergency obstetric care facilities. City-level median travel time to the nearest comprehensive emergency obstetric care facility ranged from 18 min in Maiduguri to 46 min in Kaduna. Median travel time varied by location within a city. The between-ward IQR of median travel time to the nearest public comprehensive emergency obstetric care varied from the narrowest in Maiduguri (10 min) to the widest in Benin City (41 min). Informal settlements and peripheral areas tended to be worse off compared to the inner city. The percentages of girls and women aged 15-49 years within 60 min of their nearest public comprehensive emergency obstetric care ranged from 83% in Aba to 100% in Maiduguri, while the percentage within 30 min ranged from 33% in Aba to over 95% in Ilorin and Maiduguri. During peak traffic times, the median number of public comprehensive emergency obstetric care facilities reachable by women aged 15-49 years under 30 min was zero in eight (53%) of 15 cities. Better access to comprehensive emergency obstetric care is needed in Nigerian cities and solutions need to be tailored to context. The innovative approach used in this study provides more context-specific, finer, and policy-relevant evidence to support targeted efforts aimed at improving comprehensive emergency obstetric care geographical accessibility in urban Africa. Google.

Comparison of Geometric-based Travel Time Prediction between Cars and Trucks

Travel time can be estimated using various approaches, such as historical data, traffic data, machine learning, and road geometry. In this paper, our focus is on prediction based on road geometry. By utilizing the curvature data of a road computed from GPS data, it is possible to determine the design speed of a specific road section. This information can then be used to estimate the time it would take to travel that particular stretch of road. For this paper, we test the algorithm on a 1.7km road in Kulim, Kedah, and observe its reliability of prediction for cars and trucks. While it provides accurate predictions for cars, it produces higher errors for trucks, implying that the approach is more suitable for cars than heavier vehicles. Insights gained from this research can inform future efforts to refine prediction models and enhance the accuracy and reliability of travel time estimation based on road geometry, especially for heavy vehicles.

Integrating singular value decomposition with deep learning for enhanced travel time estimation in multimodal freight transportation networks

AbstractMultimodal freight transport allows switching among various modes of transportation to efficiently utilize transport facilities. A multimodal transport system incorporates geographical scales from global to local. Travel time estimation in a multi‐modal cargo transportation network is essential for enhancing supply chain (SC) and logistics operations. Accurate travel time prediction is of great importance for cargo transportation, as it enables SC participants to increase logistics efficiency and quality. It requires adequate input data, which can be generated. In recent times, the machine learning (ML) algorithm has been well‐suited to resolve complex and nonlinear relationships in the collected tracking data. This study designs a deep learning‐powered travel time estimation in multimodal freight transportation networks (DLTTE‐MFTN) technique. The goal of the DLTTE‐MFTN technique is to estimate the travel time using a hyperparameter‐tuned ensemble learning approach. To achieve this, the DLTTE‐MFTN method initially undergoes data pre‐processing to convert the input raw data into a useful format. In addition, the singular value decomposition (SVD) model can be applied for feature dimensionality reduction in multimodal transport data, considerably improving travel time prediction. Besides, the DLTTE‐MFTN method estimates travel time using an ensemble of three DL approaches including one‐dimensional convolutional neural network (1D‐CNN), stacked autoencoder (SAE) attention, and recurrent neural network (RNN). Finally, the hyperparameter tuning of the DL models takes place using the whale optimization algorithm (WOA). The performance analysis of the DLTTE‐MFTN method takes place using the Kaggle dataset. The experimental results stated that the DLTTE‐MFTN technique attains superior performance over other ML and DL models.

Fuzing multiple erroneous sensors to estimate travel time

Estimating accurate travel time information is one of the fundamental tasks in controlling city traffic. In general, fuzing multiple sensors can generate more accurate information to measure traffic flow characteristics than using each one separately. However, in addition to the cost of installing a new sensor system, the costly steps of data cleaning and preparation are required before using a new sensor; therefore, it is essential to estimate the marginal benefit of adding a new sensor vs its marginal cost. Three datasets are generated and analyzed in this study, namely a Hypothetical Ground Truth (HGT), an Erroneous Ground Truth (EGT), and a set of Erroneous Sensors (E-Sensors). This study also challenges the assumption of an error-free Ground Truth (GT). By computing the optimal number of detections to approximate the GT, the effect of (endogenous) error in the fusion procedure is evaluated. Furthermore, by fuzing the E-Sensors that had different levels of (exogenous) error, it is revealed that the error level has a limited effect on the result of fusion. Multiple sets of E-Sensors are assessed and the RMSE values between using Erroneous Ground Truth and Hypothetical Ground Truth are measured, which shows a significant difference. Additionally, the effect of increasing the number of sensors in estimating the travel time is investigated, which shows that adding a new sensor can improve fusion accuracy if the accuracy of the added sensor is better than a given threshold. Moreover, the optimal number of detections to approximate the ground truth is studied. Real traffic data is also used to validate the results.

Equilibrium condition-based optimization models for network-wide travel time estimation using limited observed data

This paper presents a series of optimisation models to estimate network-wide travel times under equilibrium conditions. The proposed models estimate the upper and lower bounds (ULB) of the maximum total travel time (MTTT), path travel time (PTT), and link travel time (LTT). The uncertainty range of travel time is obtained by subtracting the upper bound of travel time from the corresponding lower bound. To minimise the uncertainty ranges of the estimated travel times, the relationship of PTTs is introduced as a generalised equilibrium condition. Numerical experiments show that adopting the equilibrium condition can minimise the uncertainty ranges of the travel time estimation. The proposed method can also more accurately estimate the travel times even when the observed data are limited in the entire network. These findings provide a basis for further research on the travel time observability problem of travel time estimation for the whole territory of the network.

Automatic Identification System-Based Prediction of Tanker and Cargo Estimated Time of Arrival in Narrow Waterways

In maritime logistics, accurately predicting the Estimated Time of Arrival (ETA) of vessels is pivotal for optimizing port operations and the global supply chain. This study proposes a machine learning method for predicting ETA, drawing on historical Automatic Identification System (AIS) data spanning 2018 to 2020. The proposed framework includes a preprocessing module for extracting, transforming, and applying feature engineering to raw AIS data, alongside a modeling module that employs an XGBoost model to accurately estimate vessel travel times. The framework’s efficacy was validated using AIS data from the Port of Houston, and the results indicate that the model can estimate travel times with a Mean Absolute Percentage Error (MAPE) of just 5%. Moreover, the model retains consistent accuracy in a simplified form, pointing towards the potential for reduced complexity and increased generalizability in maritime ETA predictions.

Gct-TTE: graph convolutional transformer for travel time estimation

This paper introduces a new transformer-based model for the problem of travel time estimation. The key feature of the proposed GCT-TTE architecture is the utilization of different data modalities capturing different properties of an input path. Along with the extensive study regarding the model configuration, we implemented and evaluated a sufficient number of actual baselines for path-aware and path-blind settings. The conducted computational experiments have confirmed the viability of our pipeline, which outperformed state-of-the-art models on both considered datasets. Additionally, GCT-TTE was deployed as a web service accessible for further experiments with user-defined routes.

The impact of transportation mode, socioeconomic deprivation and rurality on travel times to radiotherapy and surgical services for patients with prostate cancer: A national population-based evaluation

BackgroundThe distances that patients have to travel can influence their access to cancer treatment. We investigated the determinants of travel time, separately for journeys by car and public transport, to centres providing radical surgery or radiotherapy for prostate cancer. MethodsUsing national cancer registry records linked to administrative hospital data, we identified patients who had radical surgery or radiotherapy for prostate cancer between January 2017 and December 2018 in the English National Health Service. Estimated travel times from the patients’ residential area to the nearest specialist surgical or radiotherapy centre were estimated for journeys by car and by public transport. ResultsWe included 13,186 men who had surgery and 26,581 who had radiotherapy. Estimated travel times by public transport (74.4 mins for surgery and 69.4 mins for radiotherapy) were more than twice as long as by car (33.4 mins and 29.1mins, respectively). Patients living in more socially deprived neighbourhoods in rural areas had the longest travel times to the nearest cancer treatment centres by car (62.0 mins for surgery and 52.1 mins for radiotherapy). Conversely patients living in more affluent neighbourhoods in urban conurbations had the shortest (18.7 mins for surgery and 17.9 mins for radiotherapy). ConclusionTravel times to cancer centres vary widely according to mode of transport, socioeconomic deprivation, and rurality. Policies changing the geographical configuration of cancer services should consider the impact on the expected travel times both by car and by public transport to avoid enhancing existing inequalities in access to treatment and patient outcomes.

Optimization of new fire department location using an improved GIS algorithm for firefighters travel time estimation

PurposeThe rapid development of urban areas in Sleman District, Indonesia, has created new challenges for firefighting response services. One of the primary challenges is to identify the optimal locations for new fire stations, to improve service quality and maximize service coverage within the specified time.Design/methodology/approachThis paper proposes a method for precisely calculating travel time that integrates delay time caused by traffic lights, intersections and congestion. The study highlights the importance of precise calculation of travel time in order to provide a more accurate understanding of the service area covered by the fire stations. The proposed method utilizes network analysis in ArcGIS, the analytical hierarchy process (AHP) and simple additive weighting (SAW) to accurately calculate travel time and to identify the best locations for new fire stations. The identification of new site was based on service safety, service quality, service costs and demographic factors and applied to the Sleman district in Indonesia.FindingsThe results showed that the total area covered by old and new fire stations decreased from 61% to 31.8% of the study area when the adjusted default speed scenario was implemented.Practical implicationsThe results indicated that the default speed scenario could provide misleading information about the service area, while the adjusted default speed scenario improved service quality and maximized service coverage.Originality/valueThe proposed method provides decision-makers with an effective tool to make informed decisions on optimal locations for new fire stations and thus enhance emergency response and public safety.

Urban Arterial Traffic Volume and Travel Time Estimation with Use of Data Driven Models

In recent years, the development of technology and the availability of large amounts of data have transformed the way transport systems are managed, particularly through the forecasting of traffic conditions. This work aims to develop traffic prediction models, with a specific focus on traffic volume and travel time of an urban arterial. These models are based on Machine Learning algorithms, which find frequent application in the literature for various forecasting tasks. The traffic data that were utilized in the development process were sourced from a road section of Alexandras Av. in Athens. According to the results, the models are capable of accurate predictions with an acceptable fit to the data. Finally, a comparison is drawn between Machine Learning models, the BPR Volume-Delay function, and a BPR-ML hybrid approach. Ultimately, the findings reveal that Machine Learning methods exhibit superior forecasting capabilities.