Travel Time Prediction Research Articles

A novel modelling framework for real-time prediction of path travel times using both traffic and weather data

The problems of path travel time predictions have been studied over decades. Traditional approaches to this challenge have relied on different traffic data. However, in metropolitan cities with frequent rainfall, there is a need to consider the weather effects on real-time prediction of path travel times. Hence, this research integrates traffic data with weather data, including rainfall intensity data and weather forecast data to consider the temporal relationships between weather data and path travel times. The proposed modelling framework is evaluated with data from a major expressway and an urban arterial road in Hong Kong. Results unequivocally demonstrate that incorporating weather data significantly boosts prediction accuracy. This study also examines the impact of different frequencies on weather data, as well as weather forecast correctness, on prediction accuracy. Finally, the applicability of the proposed modelling framework has been verified without and with the input of ground truth on path travel times.

Estimation of vessel link-level travel time distribution: A directed network-driven approach

Accurate vessel travel time estimation is essential for operational efficiency and route optimization. Despite the prevalent use of the automatic identification system (AIS) in garnering multifaceted real-time data, ambiguities and inaccuracies in travel time predictions persist. It leads to planning uncertainties, inefficient resource allocations, and heightened operational costs in maritime logistics. To addresses these issues, this paper proposed a nuanced method to enhance the precision and reliability of vessel travel time estimations. Firstly, a directed maritime network is constructed by extracting essential information from AIS-based historical vessel trajectories. This lays the foundation for the subsequent analytical processes. Secondly, the non-parametric kernel density estimation (KDE) is applied to this constructed network, enabling the estimation of vessel travel time distributions across various network links. The non-parametric KDE is used in combination with AIS data, which improves the specificity and accuracy of the travel time estimations at the link level. Finally, this paper employs cellular automata (CA) simulations to validate the accuracy of the KDE-based estimations. Comparison between the simulation results and real-world data reveals a high degree of accuracy in the proposed method, confirming its applicability and effectiveness in estimating vessel travel times.

Cross regional online food delivery: Service quality optimization and real-time order assignment

Online food delivery (OFD) represents a rapidly evolving e-business application that leverages cloud computing data centers, playing a crucial role in meeting the demands of urban lifestyles. With diverse order fulfillment features and increasing expectations for service quality, the task of effectively assigning riders for timely long-distance, cross-regional deliveries presents a significant engineering challenge. Previous studies often relied on traditional rider allocation methods that fail to account for varying capacities, or they utilized non-intelligent systems that did not adequately address fluctuating order demands and service delays. In this study, we introduce a robust Mixed Integer Linear Programming (MILP) optimization framework designed to minimize the total service time and delivery cost for cross-regional orders. This framework divides a large OFD area into multiple regions and utilizes both transfer vehicles and riders to optimize deliveries. To enhance the predictive accuracy of our model, we incorporate advanced machine learning techniques. Specifically, we employ the Long Short-Term Memory (LSTM) model to forecast regional order demands accurately, reflecting the dynamic nature of the marketplace. Additionally, Extreme Gradient Boosting (XGBoost) is tailored to dynamically predict travel times from restaurants to customer locations, facilitating more precise scheduling and resource allocation within the MILP framework. These machine learning techniques significantly bolster the MILP framework by providing detailed, accurate predictions that improve decision-making processes and adaptability to real-time conditions. Acknowledging the complexity of this optimization problem, we further enhance our approach by integrating a meta-heuristic algorithm, Adaptive Large Neighbor Search (ALNS), which efficiently assigns orders to the appropriate transfer vehicles and riders within polynomial time. Our Cross Regional Online Food Delivery (XROFD) system is meticulously designed to optimize both customer satisfaction and rider incentives. Simulation experiments confirm that the XROFD system not only reduces service times and delivery costs but also markedly enhances customer satisfaction and provides superior incentives for riders, outperforming existing state-of-the-art methods.

Vehicle routing Problem for cold chain logistics based on data fusion technology to predict travel time

Vehicle routing Problem for cold chain logistics based on data fusion technology to predict travel time

Accounting for taxi service conditions in estimating route travel time from floating car data using Markov chain model

Recognising the variations in driving behaviour between taxis in the empty and carry conditions is pivotal for enhancing the accuracy of route travel time estimations using floating car data. However, existing methods largely overlook this distinction. In light of this, this study aims to harness these variations for more precise estimations. Utilising taxi data, we segmented the information by service conditions and executed distinct estimations for each segment. The route travel time was deduced through convolutional operation, complemented by a Markov chain model to discern correlations between travel times across various links. Our innovative approach realised a substantial enhancement in accuracy. Notably, when accounting for distinct service conditions, there was a reduction of 51.44% in mean absolute error and a 46.83% decline in maximum percentage error. By providing more accurate and reliable travel time predictions, our methodology enables better-informed traffic management decisions. Accurate travel time estimations are essential for optimising traffic signal timings, planning efficient routing strategies, and managing road network usage. These improvements in traffic management can lead to smoother traffic flow, reduced travel times, and ultimately, diminished congestion in urban areas.

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.

Waveform modelling of hydroacoustic teleseismic earthquake records from autonomous Mermaid floats

SUMMARY We present a computational technique to model hydroacoustic waveforms from teleseismic earthquakes recorded by mid-column Mermaid floats deployed in the Pacific, taking into consideration bathymetric effects that modify seismo-acoustic conversions at the ocean bottom and acoustic wave propagation in the ocean layer, including reverberations. Our approach couples axisymmetric spectral-element simulations performed for moment-tensor earthquakes in a 1-D solid Earth to a 2-D Cartesian fluid–solid coupled spectral-element simulation that captures the conversion from displacement to acoustic pressure at an ocean-bottom interface with accurate bathymetry. We applied our workflow to 1129 seismograms for 682 earthquakes from 16 Mermaids (short for Mobile Earthquake Recording in Marine Areas by Independent Divers) owned by Princeton University that were deployed in the Southern Pacific as part of the South Pacific Plume Imaging and Modeling (SPPIM) project. We compare the modelled synthetic waveforms to the observed records in individually selected frequency bands aimed at reducing local noise levels while maximizing earthquake-generated signal content. The modelled waveforms match the observations very well, with a median correlation coefficient of 0.72, and some as high as 0.95. We compare our correlation-based traveltime measurements to measurements made on the same data set determined by automated arrival-time picking and ray- traced traveltime predictions, with the aim of opening up the use of Mermaid records for global seismic tomography via full-waveform inversion.

Expressway Vehicle Arrival Time Estimation Algorithm Based on Electronic Toll Collection Data

Precise travel time prediction benefits travelers and traffic managers by enabling anticipation of future roadway conditions, thus aiding in pre-trip planning and the development of traffic control strategies. This approach contributes to reducing travel time and alleviating traffic congestion issues. To achieve real-time state perception of vehicles on expressways, we propose an algorithm to estimate the arrival time of vehicles in the next segment using Electronic Toll Collection (ETC) data. Firstly, the characteristics of ETC data and GPS data are meticulously described. We devise algorithms for data cleaning and fusion, subsequently segmenting the vehicle journey into multiple sub-segments. In the following step, feature vectors are constructed from the fused data to detect service areas and analyze the expressway segment characteristics, vehicle traits, and the influence of service areas. Finally, an algorithm utilizing LightGBM is introduced for estimating the arrival time of vehicles at various segments, corroborated by empirical tests using authentic traffic data. The MAE of the algorithm is recorded as 20.1 s, with an RMSE of 32.6 s, affirming its efficacy. The method proposed in this paper can help optimize transportation systems for improving efficiency, alleviating congestion, reducing emissions, and enhancing safety.

Short-Term and Long-Term Travel Time Prediction Using Transformer-Based Techniques

In the evolving field of Intelligent Transportation Systems (ITSs), accurate and reliable traffic prediction is essential in enhancing management and planning capabilities. Accurately predicting traffic conditions over both short-term and long-term intervals is vital for the practical application of ITS. The integration of deep learning into traffic prediction has proven crucial in advancing traffic prediction beyond traditional approaches, particularly in analyzing and forecasting complex traffic scenarios. Despite these advancements, the existing methods are unable to effectively handle both short-term and long-term traffic patterns given their complex nature, revealing a need for more comprehensive forecasting solutions. To address this need, we propose a new approach named the Short-Term and Long-Term Integrated Transformer (SLIT). SLIT is a Transformer-based encoder–decoder architecture, designed for the effective prediction of both short-term and long-term travel time durations. The architecture integrates the Enhanced Data Preprocessing (EDP) with the Short-Term and Long-Term Integrated Encoder–Decoder (SLIED). This harmonious combination enables SLIT to effectively capture the complexities of traffic data over varying time horizons. Extensive evaluations on a large-scale real-world traffic dataset demonstrate the excellence of SLIT compared with existing competitive methods in both short- and long-term travel time predictions across various metrics. SLIT exhibits significant improvements in prediction results, particularly in short-term forecasting. Remarkable improvements are observed in SLIT, with enhancements of up to 9.67% in terms of all evaluation metrics across various time horizons. Furthermore, SLIT demonstrates the capability to analyze traffic patterns across various road complexities, proving its adaptability and effectiveness in diverse traffic scenarios with improvements of up to 10.83% in different road conditions. The results of this study highlight the high potential of SLIT in significantly enhancing traffic prediction within ITS.

Mapping disparities in head and neck cancer care: Geospatial analysis of social vulnerability and healthcare access in the US.

e23112 Background: Ensuring equitable access to head and neck (H&N) cancer care across the US is vital for optimal patient outcomes. This study explores the impact of social vulnerability on disparities in access to H&N multidisciplinary specialist care by US region and metro status. Methods: Oncologists and a subset of H&N cancer specialist practice locations were extracted from the National Provider Index, American Society of Clinical Oncology, and US News and World Report. Travel time using the fastest transportation mode from population-weighted county centroids to the nearest H&N cancer specialist (surgical, radiation, or medical oncologist) was computed using Travel Time API. Cancer data were obtained from United States Cancer Statistics and Surveillance, Epidemiology, and End Results (SEER). Regression analysis assessed impact of aspects of social vulnerability from the Social Vulnerability Index (SVI) on travel time. A disparity index incorporating travel time, county-level H&N cancer incidence, and SVI was developed to quantify disparities at the county-level. Results: In total, 18,241 medical, 6,387 radiation, and 2,564 surgical oncologists were identified, of which 346 medical, 308 radiation, and 453 surgical oncologists self-identified as H&N specialists. Regression analysis indicated that low household income and lack of insurance within counties significantly increased travel time ( p < .001) after controlling for US region, metro status, cancer rate, and other county-level factors. The disparity index identified counties with highest and lowest disparity (Table 1). Conclusions: Key findings highlight specific counties with higher vulnerability, primarily rural counties in the West and Southeast, and underscores the influence of social vulnerability on access to care. After accounting for US region and metro status, aspects of social vulnerability still predict travel time, with low household income and lack of insurance being the most impactful. Identified disparities in care may provide targets for interventions and policies aimed at reducing access inequalities, such as outreach programs and allocation of resources to underserved areas. [Table: see text]

Periodic Transformer Encoder for Multi-Horizon Travel Time Prediction

In the domain of Intelligent Transportation Systems (ITS), ensuring reliable travel time predictions is crucial for enhancing the efficiency of transportation management systems and supporting long-term planning. Recent advancements in deep learning have demonstrated the ability to effectively leverage large datasets for accurate travel time predictions. These innovations are particularly vital as they address both short-term and long-term travel demands, which are essential for effective traffic management and scheduled routing planning. Despite advances in deep learning applications for traffic analysis, the dynamic nature of traffic patterns frequently challenges the forecasting capabilities of existing models, especially when forecasting both immediate and future traffic conditions across various time horizons. Additionally, the area of long-term travel time forecasting still remains not fully explored in current research due to these complexities. In response to these challenges, this study introduces the Periodic Transformer Encoder (PTE). PTE is a Transformer-based model designed to enhance traffic time predictions by effectively capturing temporal dependencies across various horizons. Utilizing attention mechanisms, PTE learns from long-range periodic traffic data for handling both short-term and long-term fluctuations. Furthermore, PTE employs a streamlined encoder-only architecture that eliminates the need for a traditional decoder, thus significantly simplifying the model’s structure and reducing its computational demands. This architecture enhances both the training efficiency and the performance of direct travel time predictions. With these enhancements, PTE effectively tackles the challenges presented by dynamic traffic patterns, significantly improving prediction performance across multiple time horizons. Comprehensive evaluations on an extensive real-world traffic dataset demonstrate PTE’s superior performance in predicting travel times over multiple horizons compared to existing methods. PTE is notably effective in adapting to high-variability road segments and peak traffic hours. These results prove PTE’s effectiveness and robustness across diverse traffic environments, indicating its significant contribution to advancing traffic prediction capabilities within ITS.

Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing

Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing

Traffic state estimation from vehicle trajectories with anisotropic Gaussian processes

Accurately monitoring road traffic state is crucial for various applications, including travel time prediction, traffic control, and traffic safety. However, the lack of sensors often results in incomplete traffic state data, making it challenging to obtain reliable information for decision-making. This paper proposes a novel method for imputing traffic state data using Gaussian processes (GP) to address this issue. We propose a kernel rotation re-parametrization scheme that transforms a standard isotropic GP kernel into an anisotropic kernel, which can better model the congestion propagation in traffic flow data. The model parameters can be estimated by statistical inference using data from sparse probe vehicles or loop detectors. Moreover, the rotated GP method provides statistical uncertainty quantification for the imputed traffic state, making it more reliable. We also extend our approach to a multi-output GP, which allows for simultaneously estimating the traffic state for multiple lanes. We evaluate our method using real-world traffic data from the Next Generation simulation (NGSIM) and HighD programs, along with simulated data representing a traffic bottleneck scenario. Considering current and future mixed traffic of connected vehicles (CVs) and human-driven vehicles (HVs), we experiment with the traffic state estimation (TSE) scheme from 5% to 50% available trajectories, mimicking different CV penetration rates in a mixed traffic environment. We also test the traffic state estimation when traffic flow information is obtained from loop detectors. The results demonstrate the adaptability of our TSE method across different CV penetration rates and types of detectors, achieving state-of-the-art accuracy in scenarios with sparse observations.

Dynamic measurements of geographical accessibility considering traffic congestion using open data: a cross-sectional assessment for haemodialysis services in Cali, Colombia

Many cities with traffic congestion lack accessibility assessments accounting for traffic congestion and equity considerations but have disaggregated georeferenced municipal-level open data on health services, populations, and travel times big data. We convened a multistakeholder intersectoral collaborative group that developed a digital, web-based platform integrating open and big data to derive dynamic spatial-temporal accessibility measurements (DSTAM) for haemodialysis services. We worked with stakeholders and data scientists and considered people's places of residence, service locations, and travel time to the service with the shortest travel time. Additionally, we predicted the impacts of strategically introducing haemodialysis services where they optimise accessibility. Cross-sectional analyses of DSTAM, accounting for traffic congestion, were conducted using a web-based platform. This platform integrated traffic analysis zones, public census and health services datasets, and Google Distance Matrix API travel-time data. Predictive and prescriptive analytics identified optimal locations for new haemodialysis services and estimated improvements. Primary outcomes included the percentage of residents within a 20-min car drive of a haemodialysis service during peak and free-flow traffic congestion. Secondary outcomes focused on optimal locations to maximise accessibility with new services and potential improvements. Findings were disaggregated by sociodemographic characteristics, providing an equity perspective. The study in Cali, Colombia, used geographic and disaggregated sociodemographic data from the adjusted 2018 Colombian census. Predicted travel times were obtained for two weeks in2020. There were substantial traffic variations. Congestion reduced accessibility, especially among marginalised groups. For 6-12 July, free-flow and peak-traffic accessibility rates were 95.2% and 45.0%, respectively. For 23-29 November, free-flow and peak traffic accessibility rates were 89.1% and 69.7%. The locations where new services would optimise accessibility had slight variation and would notably enhance accessibility and health equity. Establishing haemodialysis services in targeted areas has significant potential benefits. By increasing accessibility, it would enhance urban health and equity. No external or institutional funding was received.

Predicting Bus Travel Time in Cheonan City Through Deep Learning Utilizing Digital Tachograph Data

Urban transportation systems are increasingly burdened by traffic congestion, a consequence of population growth and heightened reliance on private vehicles. This congestion not only disrupts travel efficiency but also undermines productivity and urban resident’s overall well-being. A critical step in addressing this challenge is the accurate prediction of bus travel times, which is essential for mitigating congestion and improving the experience of public transport users. To tackle this issue, this study introduces the Hybrid Temporal Forecasting Network (HTF-NET) model, a framework that integrates machine learning techniques. The model combines an attention mechanism with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers, enhancing its predictive capabilities. Further refinement is achieved through a Support Vector Regressor (SVR), enabling the generation of precise bus travel time predictions. To evaluate the performance of the HTF-NET model, comparative analyses are conducted with six deep learning models using real-world digital tachograph (DTG) data obtained from intracity buses in Cheonan City, South Korea. These models includes various architectures, including different configurations of LSTM and GRU, such as bidirectional and stacked architectures. The primary focus of the study is on predicting travel times from the Namchang Village bus stop to the Dongnam-gu Public Health Center, a crucial route in the urban transport network. Various experimental scenarios are explored, incorporating overall test data, and weekday and weekend data, with and without weather information, and considering different route lengths. Comparative evaluations against a baseline ARIMA model underscore the performance of the HTF-NET model. Particularly noteworthy is the significant improvement in prediction accuracy achieved through the incorporation of weather data. Evaluation metrics, including root mean squared error (RMSE), mean absolute error (MAE), and mean squared error (MSE), consistently highlight the superiority of the HTF-NET model, outperforming the baseline ARIMA model by a margin of 63.27% in terms of the RMSE. These findings provide valuable insights for transit agencies and policymakers, facilitating informed decisions regarding the management and optimization of public transportation systems.

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.

An instance-based transfer learning model with attention mechanism for freight train travel time prediction in the China–Europe railway express

Since the inception of the China–Europe Railway Express (CRE), rail transportation has emerged as a predominant means of transporting goods across international borders. The quality and reliability of railway transport services are constrained by the precision of train travel times. However, the real-time data available for the CRE trains is rather limited due to the volume and duration of operations, which increases the difficulty of forecasting CRE train travel times. In order to enhance the accuracy of predictions, a novel two-stage transfer learning model with the Long Short-Term Memory attention (T.R2_LSTM_A) is introduced in this study. By incorporating attention mechanisms, the Long Short-Term Memory networks (LSTM) module, the two-stage TrAdaBoost.R2 algorithm, and transfer learning (TL), the model captures the inherent characteristics of time series data and attains a high level of accuracy in predictions. This approach effectively mitigates the limitations of current transfer learning methods, which are primarily caused by insufficient sample data. In the model, an instance-based TL method is utilized to address the shortcomings of insufficient data, and an attention-based LSTM is selected as a base learner to overcome the thorny issues of gradient disappearance and explosion. Additionally, LSTM Attention (LSTM_A), a novel attention mechanism, is introduced to improve the ability of the proposed model to capture complicated characteristics. The T.R2_LSTM_A model is systemically evaluated and shown to be superior to Random Forest (RF), Support Vector Regression (SVR), LSTM, convolution-based LSTM (CLSTM), AdaBoost_LSTM, LSTM with attention mechanism (LSTM_Attention), and TrAdaBoost.R2_RF (T.R2_RF) for predicting train travel time, using a real-life case study of CRE. The MSE, RMSE, MAPE, and MAE values for the T.R2_LSTM_A model are equal to 5.572, 2.361, 2.578, and 1.767, respectively. These values surpass those of other widely used prediction methods, indicating that the T.R2_LSTM_A model is well-suited for predicting train travel times in the CRE.

Development of Travel Time Prediction Models Using Statistical and GEP Techniques for Public Transportation Bus Routes in Amman-Jordan

Development of Travel Time Prediction Models Using Statistical and GEP Techniques for Public Transportation Bus Routes in Amman-Jordan

Every Second Counts: A Comprehensive Review of Route Optimization and Priority Control for Urban Emergency Vehicles

Emergency vehicles (EMVs) play an important role in saving human lives and mitigating property losses in urban traffic systems. Due to traffic congestion and improper priority control strategies along the rescue route, EMVs may not be able to arrive at rescue spots on time, which also increases traffic risk and has a negative impact on social vehicles (SVs). The greater the negative impact on SVs, such as increased delay times and queue length, the more profound the negative impacts on urban environmental sustainability. Proper rescue route selection and priority control strategies are essential for addressing this problem. Consequently, this paper systematically reviews the studies on EMV routing and priority control. First, a general bibliometric analysis is conducted using VOSviewer. This study also classifies the existing studies into three parts: EMV travel time prediction (EMV-TTP), EMV routing optimization (EMV-RO), and EMV traffic priority control (EMV-TPC). Finally, this study provides future research suggestions on five aspects: 1. uncovering authentic demand characteristics through EMV data mining, 2. incorporating the distinct characteristics of EMV in EMV-RO models, 3. implementing active EMV-TPC strategies, 4. concentrating more on the negative impacts on SVs, and 5. embracing the emerging technologies in the future urban traffic environment.

Prediction Intervals for Bus Travel Time Based on Road Segment Sharing, Multiple Routes’ Driving Style Similarity, and Bootstrap Method

Providing accurate information about bus travel times can help passengers plan their itinerary and reduce waiting time. However, due to various uncertainty factors and the sparsity of single-route data, traditional travel time predictions cannot accurately describe the credibility of the prediction results, which is not conducive to passengers waiting based on the predicted results. To address the above issues, this paper proposes a bus travel time prediction intervals model based on shared road segments, multiple routes’ driving style similarity, and the bootstrap method. The model first divides the predicted route into segments, dividing adjacent stations shared by multiple routes into one section. Then, the hierarchical clustering algorithm is used to group all drivers in multiple bus routes in this section according to their driving styles. Finally, the bootstrap method is used to construct a bus travel time prediction interval for different categories of drivers. The travel time data sets of Shenyang 239, 134, and New Area Line 1 were selected for experimental verification. The experimental results indicate that the quality of the prediction interval constructed using a data set fused with multiple routes is better than that constructed using a single-route data set. In the two cases studied, the MPIW of the three time periods decreased by 101.04 s, 151.72 s, 33.87 s, and 126.58 s, 127.47 s, 17.06 s, respectively.