1. Executive summary

This document reports the accuracy of the TomTom Historical Traffic Volumes hourly estimates for 2025. Sections 2 to 6 describe the product and how we validate it and are the same in every year’s document; Section 7 and the key findings below are specific to 2025.

We measured accuracy against independent ground-truth traffic counts from permanent loop detectors and similar counting infrastructure in seven countries (Belgium, Netherlands, New Zealand, Norway, Sweden, United Kingdom, and United States) for 2025. The per-country metrics in this document come from k-fold cross-validation, which tests the model on data it was not trained on (Section 5). For markets beyond these seven countries, Section 6 describes the complementary leave-one-country-out (LOCO) validation, whose pooled results for 2025 are reported in Section 7.8. A market is a country where the product is available.

Key findings:

• The United Kingdom delivers the most accurate hourly estimates in this assessment: an all-roads MAPE of 7.7% in day hours, close to its AADT level, and 15.2% at night, with an unbiased median error by day and a night SQV of 0.92 (Very good).
• Across the seven countries, the day-hour all-roads MAPE ranges from 7.7% (United Kingdom) to 18.6% (Norway), with five countries between 7.7% and 11.8%; the night-hour figure runs from 15.2% to 28.9%, and every country reaches at least the Good SQV tier at night (0.89 to 0.92).
• Norway carries the highest day-hour MAPE of the group (18.6%) and the widest 95th percentile APE (50.0%) yet a Good SQV of 0.87; its high-volume rows rest on only three counters, so read them as indicative.
• For markets without local counter data, the pooled leave-one-country-out results (Section 7.8) give a day-hour MAPE from 14.7% on high-volume roads to 26.4% on low-volume roads, above the k-fold figures of every country in this assessment; the day-hour SQV is Insufficient on high-volume roads (0.71) and Acceptable on medium-volume roads (0.79), while low-volume roads stay Good (0.86) and every night-hour band reaches Fair or better.
• Percentage errors are consistently higher on low-volume roads in every country, but on such roads they correspond to small absolute vehicle counts; Section 8 provides guidance on interpreting these values.

2. Introduction

How many vehicles pass a road segment in a given hour? TomTom Historical Traffic Volumes estimates exactly that, for each road segment. We apply machine learning to probe data: the position and speed reports that millions of connected vehicles send (Sekuła et al., 2018; Zhan et al., 2017). The estimates for individual hours cover the roads with significant probe coverage, by road class and country (Section 3.5). A road class is the functional class of a road in the map, such as motorway, major road or local street.

Historical Traffic Volumes delivers three quantities: AADT, AAWHT and hourly volumes. The product introduction defines them. This document covers the hourly volumes; AADT and AAWHT are documented in the Annual averages section of this documentation.

The hour-by-hour estimates reach back to 2024 and forward to about 72 hours before the present. We improve the model continuously, and an improved model can recompute past periods, so a published figure for a past period can improve after publication (Section 9).

Traffic volume data informs decisions with real consequences:

• Where to open a new store
• How to allocate infrastructure budgets
• How to assess road safety risk
• Whether the surrounding road network can support a proposed development
• Whether a new lane, a closure or another change to a road altered traffic, comparing the period before with the period after

Every one of those decisions rests on a volume number, so the useful question is not whether the data is reliable but how far off it can be on the roads you care about. This document answers that in vehicles, in percentages and as quality scores.

Traditional counting methods give precise counts at a small number of fixed points (Federal Highway Administration, 2022). TomTom Historical Traffic Volumes estimates the volume across the road network of a covered market (Section 3.5 gives the coverage of the hourly estimates). An estimate carries uncertainty, so we measure that uncertainty with the metrics defined in Section 4. With those numbers, customers can decide where and how to use the data.

We validate against counters: permanent loop detectors and similar counting stations whose independent ground-truth counts played no part in model training. The accuracy metrics in this document measure the gap between our estimates and those reference counts; a smaller gap means a more accurate estimate. Where results fall short of the quality thresholds in Section 4.4, we say so and give the available context.

3. How the model works

Turning raw reports from connected vehicles into reliable, network-wide volume estimates takes a sequence of steps, and each step solves a distinct problem. Unlike traditional counting methods, the product needs no physical equipment at each measurement point. We collect probe observations (Section 3.1), estimate the penetration rate (Section 3.2) and convert probe observations into volume estimates: first the typical values (Section 3.3), then the values for specific hours (Section 3.4). Section 3.5 states where the hourly estimates are available.

3.1 From connected vehicles to traffic observations

Our primary data source is floating-car data: GPS and telematics signals from connected vehicles (Herrera et al., 2010). Each signal is a probe observation; together, the signals form the probe data. Connected vehicles include:

• In-vehicle navigation systems
• Smartphones running navigation apps
• Connected commercial vehicles

The signals arrive passively and continuously from millions of devices worldwide. For each road segment, they form a continuous stream of speed and passage observations.

Probe observations are not traffic volumes, though. Only a fraction of the vehicles on a given road are connected and contributing data. We call this fraction the penetration rate. It varies by road type, geography and time of day, so converting probe observations into total volume estimates means accounting for that variation.

3.2 Estimating the penetration rate without counters

A probe count becomes a traffic volume only once we know the penetration rate: the share of vehicles on that road that report probe data. Permanent counters measure it directly, but they exist on a small fraction of roads, and in many markets on none. A method that needs counters everywhere cannot scale. Ours needs them only once, to learn.

The key is congestion. When a road operates at or near capacity (Transportation Research Board, 2022), physics constrains it: the relationship between the speed vehicles drive and the number of vehicles the road carries becomes tight and predictable, as the fundamental diagram of traffic flow describes (Greenshields, 1935; Treiber & Kesting, 2013). From probe speeds, read together with the road’s attributes, we can then estimate how many vehicles the road carries. We train a capacity model on roads with counters to learn this speed-to-flow relationship, together with map attributes such as road class, urban or rural context and lane configuration. Because the same congestion physics applies wherever a road runs near capacity (Kerner, 2004), the model transfers to roads that have never had a counter.

On any congested road we then hold two independent numbers: the total flow the capacity model estimates from speeds, and the probe flow we count directly. Their ratio is the penetration rate. Wherever probes meet congestion, we obtain a penetration-rate estimate, far beyond counter locations (Eisinga & Lorkowski, 2025). Individual estimates are noisy, so we aggregate them by region and road type into summaries that resist noise and fill the remaining gaps from similar surroundings. The result is a consistent picture of probe representativeness across countries and road classes. Roads that never congest inherit the estimate of their region and road type.

3.3 From penetration rate to typical volumes

The regional penetration picture tells us roughly what share of traffic the probes capture around a road. The volume model turns that into an estimate for the specific road. We train it on real ground truth: permanent counters, where they exist. From those counts it learns how the regional penetration rate, the observed probe data and the road’s own attributes combine into the volume of one road, in effect refining the regional penetration rate down to each segment. Once trained, it needs no counters. It runs wherever probe data and a map exist, which is what makes the product scalable to new regions, and why Section 6 tests it on countries it has never seen.

A motorway and a residential street sit at opposite ends of a wide range: among the counters the model learns from, the quietest carry fewer than 500 vehicles a day and the busiest more than 125,000. The relationship between a road’s attributes, its probe activity and its traffic load is not the same at the two ends. The estimate has to hold across that whole range. So we train the model on counters across the full range of volumes, and we judge it on the same range, separately for high-, medium- and low-volume roads in every validated country. The Annual averages section of this documentation reports those results for AADT; Section 7 of this document reports them for the hourly estimates.

The volume model produces the typical values first: AADT, annual average daily traffic, one value per road segment and year, and AAWHT, annual average week-hour traffic, 168 values per segment and year, one for each hour of each day of the week. Section 3.4 describes how the estimate for one specific hour builds on them.

3.4 From typical hours to specific hours

AADT and AAWHT describe typical conditions. Customers usually want to know about one road on one day at one hour — last Tuesday at 8am, for example.

The model produces these estimates by starting from the typical value for that road, that day of the week and that hour, and adjusting it by how busy the road was in the period being estimated, as observed in probe data. A road that was quieter than on a typical Tuesday morning receives a lower estimate; a road that was busier receives a higher one.

The set of vehicles contributing probe data is not fixed: sources are added and removed over time, and the number of reporting vehicles varies from road to road. A method that read absolute probe counts would mistake fewer reporting vehicles for less traffic. The model therefore measures the adjustment as a relative change in probe activity: it compares the period being estimated with a reference measured on the same basis as that period, so that a change in the number of reporting vehicles does not read as a change in traffic.

Where too few vehicles report on a road class in a country for hourly estimates to be reliable, the model produces no hourly estimate; Section 3.5 describes the coverage of the hourly estimates.

3.5 Coverage of the hourly estimates

TomTom Historical Traffic Volumes has two products with two footprints. The annual averages, AADT and AAWHT, cover most roads of the network. The hourly estimates described in Section 3.4 need enough reporting vehicles, so they cover the roads with significant probe coverage, by road class and country. Where too few vehicles report on a road class in a country for the hourly estimates to be reliable, we publish none for it. This is a deliberate choice: a published but unreliable estimate would be used as if it were sound, and we prefer a gap to a number that looks sound but is not.

Coverage therefore differs by road class within a country. Larger roads carry more traffic, and with it more reporting vehicles, so hourly estimates are available on major roads in more countries than on minor roads. The Market coverage page of the Hourly section lists, for each country, the road classes with hourly estimates.

That list grows. We are extending the hourly model to the roads it does not yet cover: roads where low volumes mean few reporting vehicles and a sampling error in the probe signal. We improve the model continuously, and further releases also regenerate historical data, so coverage and accuracy improve for past periods too. The Market coverage page shows the current state. Earlier periods can carry hourly estimates on roads that the current list does not include.

4. How we measure accuracy

One number cannot show both the typical error and its spread, so we report a set of complementary metrics. Each one highlights a different aspect of performance, and every one is measured against independent ground-truth counts. The unit of analysis is the segment-hour: one road segment in one hour on one date. Every metric in this document is computed across segment-hours, so a road segment contributes one value per counted hour, not one value per segment.

4.1 Mean absolute percentage error (MAPE)

MAPE measures the average size of the prediction error relative to the observed count, as a percentage. A MAPE of 10% means that estimates differ from actual counts by 10% on average. MAPE treats errors of all sizes equally, and it is a commonly reported accuracy measure in traffic estimation.

On quiet roads and in quiet hours, a high percentage error can mean a small difference in vehicles (Hyndman & Koehler, 2006). A road carrying 40 vehicles in an hour, with a MAPE of 15%, has a typical absolute error of 6 vehicles in that hour. For most planning and analytical purposes, a difference of that size is negligible. This is one reason Section 7 reports day and night hours separately: night volumes are low, so percentage errors rise, while the MAE column shows the error in vehicles. So read MAPE values for low-volume roads alongside the absolute volumes that matter for your use case.

4.2 Median percentage error

The median percentage error is the middle value of all signed errors: positive when our estimate exceeds the actual count, negative when it falls short. A value close to zero shows that the model has no strong tendency to over- or under-count. Low bias matters for applications such as aggregated network analysis or vehicle kilometers traveled (VKT) calculations, because systematic errors add up across many road segments.

4.3 68th and 95th percentile absolute percentage error

These percentiles describe how the errors spread across segment-hours. The 68th percentile corresponds roughly to one standard deviation in a normal distribution: about 68% of segment-hours have an error at or below it. The 95th percentile captures the upper range, the error level of the most challenging segment-hours. Together with MAPE, the percentiles show how the error is distributed, not only its average.

4.4 Scalable Quality Value (SQV)

A percentage error looks large on a quiet road and an absolute error looks large on a busy one. The Scalable Quality Value (Friedrich et al., 2019) handles both cases. It generalizes the GEH statistic used in transport model validation (Department for Transport, 2026). It is a bounded, scale-independent quality metric with a score between 0 and 1, where 1 is a perfect match. It measures the error against a yardstick that grows with the square root of the count, so it tolerates a larger percentage error on quiet roads, where a few vehicles make a large percentage, and a larger absolute error on busy roads. It then maps the result to a bounded score. SQV is therefore consistent across the full range of traffic volumes. The formula is

SQV = 1 / (1 + sqrt((M − C)² / (f × C)))

where M is the modeled value, C is the observed count and f is a scaling factor set by the order of magnitude of the quantity: 1,000 for hourly volumes and 10,000 for daily volumes. An error of zero gives a score of 1; the larger the error relative to the count, the lower the score. For example, an hourly estimate of 1,100 vehicles against a count of 1,000 scores about 0.91. We report SQV as its 15th percentile across all segment-hours in each group: at least 85% of the segment-hours in the group perform better than the stated value. The quality thresholds below come from Friedrich et al. (2019):

4.5 Mean absolute error (MAE)

MAE measures the average absolute difference between predicted and observed volumes, in vehicles per hour. We report it for hourly volumes. Unlike the percentage-based metrics, it answers the question in traffic units: by how many vehicles per hour is a typical estimate off? An MAE of 30 means that hourly estimates differ from actual counts by 30 vehicles on average.

MAE complements MAPE (Section 4.1). Because MAE is measured in the same units as the traffic itself, the small denominators of quiet roads and quiet hours do not inflate it, although a difference of a few vehicles there registers as a large percentage error. The reverse also holds: high-volume roads dominate MAE, because the same relative error there means many more vehicles. MAE values are therefore most meaningful when compared within a volume category or road class, and read alongside the percentage-based metrics.

5. Validation approach: K-fold cross-validation

The per-country accuracy metrics in this document come from k-fold cross-validation. The method tests the model on data it was not trained on, which gives a realistic measure of real-world performance.

We divide the counter-equipped road segments used in training into five groups, called folds (Roberts et al., 2017). In each round, we hold one fold back entirely, train the model on the remaining folds and evaluate it against the held-back segments. This repeats until every fold has served as the test set. We then aggregate the accuracy figures across all rounds, so every validation counter contributes to the reported results without ever training the model it is evaluated against.

K-fold cross-validation is standard practice in machine learning (Hastie et al., 2009): it prevents overfitting to one test set, uses all available ground-truth data and gives a reliable estimate of how well the model generalizes.

We report results for three volume categories. The volume category is a different grouping from road class (Section 1):

• High-volume roads: 55,000 or more vehicles per day (AADT)
• Medium-volume roads: 5,000–54,999 vehicles per day
• Low-volume roads: fewer than 5,000 vehicles per day

For the hourly estimates, a counter’s volume category is set by its annual average daily traffic derived from its own counts, not by the volume of the hour being scored.

An All roads row gives the aggregated metrics across all counters, regardless of volume category; the LOCO tables in Section 7.8 report the three volume categories only. The hourly results are measured per segment-hour against the counter’s count for that hour, and the held-back counters play no part in any step that produces the hourly volume. Section 7 reports separate results for day hours (6am–11pm) and night hours (11pm–6am).

K-fold cross-validation needs ground-truth counting data for every country in the validation set. For markets without counter data, Section 6 describes the complementary leave-one-country-out (LOCO) approach we use to estimate accuracy.

6. Leave-one-country-out (LOCO) validation

TomTom Historical Traffic Volumes is available in many markets with no permanent counting infrastructure. K-fold cross-validation (Section 5) needs ground-truth data, so it cannot be applied directly there. Leave-one-country-out (LOCO) validation fills that gap: in countries that do have counters, it measures how the model performs in a country it has never seen, and uses that result as the accuracy estimate for a market without counters (Roberts et al., 2017). This transfer assumes that the held-out countries resemble the unseen market in road network structure and probe coverage.

6.1 How LOCO validation works

In LOCO validation, we exclude one country entirely from model training. We train the model on all remaining countries and then evaluate it against the held-out country with the counter data available there. This repeats for each country in turn, so every country serves once as an unseen test market. We report the results jointly for all held-out countries in a year rather than per country, so they describe the accuracy to expect in a market the model has never seen, not the accuracy of any one country.

LOCO simulates deployment in a market where the model has never seen local data. Its results therefore estimate performance in new markets, where the model relies entirely on what it has learned from other countries.

6.2 Why LOCO matters for customers

If you use TomTom Historical Traffic Volumes in a market beyond the seven countries in Section 7, the LOCO results in Section 7.8 are your primary quality basis. The model learns traffic patterns that carry across countries: road network structure, speed-flow relationships, penetration-rate dynamics. Those learned patterns are what the model carries into a market it has never seen. The LOCO results show how much of its accuracy travels with them.

6.3 Where the LOCO results are reported

The LOCO results for 2025 are reported in Section 7.8, next to the per-country k-fold results and in the same tables and metrics, pooled across all countries held out from training. Because the held-out countries are evaluated jointly, the figures describe the accuracy to expect in a market the model has never seen rather than any specific market. They extend the k-fold results in Section 7 to every market where the product is available.

7. Results (2025)

The tables below give the hourly accuracy results for each of the seven countries in the 2025 k-fold validation, followed by the pooled leave-one-country-out (LOCO) results for countries held out from training (Section 6). Section 4.4 defines the quality tiers for the SQV (15th Pct) values.

7.1 Belgium

Day hours (06:00–23:00)

Night hours (23:00–06:00)

Belgium’s night-time hourly MAPE rises to 20.6%, but the corresponding MAE of roughly 29 vehicles shows the inflation stems from the low absolute volumes carried at night rather than from a loss of accuracy in absolute terms; the night SQV in fact improves to 0.91.

7.2 Netherlands

Day hours (06:00–23:00)

Night hours (23:00–06:00)

A slight negative median percentage error recurs in the Netherlands’ hourly breakdown, indicating a mild systematic underestimation. As elsewhere, night-time percentage errors are elevated while the night MAE of roughly 29 vehicles stays small and the night SQV reaches 0.92.

7.3 New Zealand

Day hours (06:00–23:00)

Night hours (23:00–06:00)

New Zealand’s night-time hourly MAPE rises to 28.8% while the night MAE stays near 26 veh/h, the usual signature of low overnight volumes inflating percentage-based errors.

7.4 Norway

Day hours (06:00–23:00)

Night hours (23:00–06:00)

Norway’s high band contains only 3 counters, so its rows, including the Insufficient daytime hourly SQV of 0.69, rest on too small a sample to be conclusive. Night-time hourly MAPE reaches 28.9%, a low-volume effect, with a night MAE of only about 13 vehicles.

7.5 Sweden

Day hours (06:00–23:00)

Night hours (23:00–06:00)

Sweden’s hourly estimates are close to unbiased, with a median percentage error of -0.6% in both day and night hours, and its day-hour all-roads MAPE of 11.3% stays within four percentage points of its AADT level. The day-hour SQV of 0.85 sits exactly on the Good threshold, and the night SQV improves to 0.89 while the night MAPE rises to 21.0%, the usual signature of low overnight volumes. The low-volume band rests on 37 counters, so its night MAPE of 34.0%, with a MAE of only 6.8 vehicles per hour, is indicative rather than conclusive.

7.6 United Kingdom

Day hours (06:00–23:00)

Night hours (23:00–06:00)

The United Kingdom’s hourly performance stays close to the AADT level during the day (MAPE 7.7%), and the night SQV remains Very good at 0.92.

7.7 United States

Day hours (06:00–23:00)

Night hours (23:00–06:00)

The United States’ hourly results follow the familiar day/night pattern, with the night SQV (0.89) above the daytime value (0.84) and the night MAPE inflation explained by low night volumes, the night MAE being roughly 54 vehicles against about 150 by day.

7.8 Unseen countries (LOCO)

Day hours (06:00–23:00)

Night hours (23:00–06:00)

Pooled across the countries withheld from training, hourly MAPE runs from 14.7% in the high band by day to 36.6% in the low band at night, where an MAE of 9.1 veh/h shows that low overnight volumes inflate the percentage figures; night-time SQV reaches Fair or better in every band.

8. What the results mean for your use case

8.1 For business decision-makers and analysts

Traffic volume data informs strategic decisions (Section 2). For most analytical applications, the question comes down to one thing: is the error range acceptable for the decision at hand?

A practical guide: a MAPE of 10% on a road carrying 2,000 vehicles in an hour means that estimates differ from the true figure by about 200 vehicles on average, and the 68th and 95th percentile columns in Section 7 show how wide the error gets on a single road. For retail site selection, insurance risk modeling or transport infrastructure planning, an error of this size is usually acceptable. For applications that need precise capacity calculations, such as junction design or traffic signal optimization, we recommend adding local count data to the volume estimates where it is available and practicable. For comparisons across time, such as a before-and-after study, Section 9 explains how to read a difference between two periods against the stated accuracy, and how model improvements reach past periods.

Low-volume roads (under 5,000 vehicles per day) tend to show higher MAPE values (Das & Tsapakis, 2020). On roads with very low volumes, and in quiet hours such as the night, a higher percentage error still means a small number of vehicles — the worked example in Section 4.1 (a MAPE of 15% on a road carrying 40 vehicles in an hour, 6 vehicles) shows the scale. For use cases that depend on individual low-volume rural roads, treat the estimates as indicative and validate them against available count data where precision matters.

8.2 For data scientists and transport modelers

The SQV 15th percentile is a conservative quality indicator (Section 4.4 explains how to read it). When you integrate TomTom Historical Traffic Volumes into a transport model, the SQV shows which road categories you can use with confidence and where extra validation against local counts is advisable.

For road categories with SQV values at or above 0.80 (Fair or better), the data is suitable for transport models and analytical workflows that need segment-level accuracy. For categories between 0.75 and 0.79 (Acceptable), use the data for aggregate and indicative purposes and validate individual segments against local counts. For categories below 0.75 (Insufficient), treat the data as indicative and apply extra quality filters or local calibration where precision is required.

Where the median percentage error (bias) of a category is close to zero, aggregate measures such as total vehicle kilometers traveled across a network, or the average hourly volume for a road class, are reliable even where individual segments carry errors. Where a category shows a negative median percentage error (a tendency to under-predict), account for it in applications where absolute volume totals matter.

9. Updates, versions and comparability

9.1 Estimates are updated

TomTom Historical Traffic Volumes is a modeled product. We improve the model continuously, and an improved model can recompute the periods we have already published. A figure for a past period can therefore improve after publication: the recomputed estimate reflects a better model, while the traffic that occurred is unchanged. Regenerating the history in this way keeps a series internally consistent, because every period in it comes from the same model.

The set of contributing data sources also changes over time, as sources are added and removed, and such a change can affect where hourly estimates are available (Section 3.5).

9.2 Comparing periods

Every estimate in this product is a measurement with a stated accuracy: the quality figures in Section 7 give it for each country, and pooled for unseen markets, by road category and time of day. A comparison between two periods, in a before-and-after study, a year-over-year trend or network monitoring, is a comparison between two such measurements.

The two products behave differently over time. AADT and AAWHT aggregate a year of observations, so short-term variation in the probe data largely averages out, and they are the natural basis for year-over-year comparison. The hourly estimates are designed to absorb changes in the contributing fleet (Section 3.4). Where a large change in data sources still shifts their accuracy or coverage, up or down, the published quality figures show it.

Our guidance: read a difference between two periods against the accuracy figures published for both periods. When we regenerate the history, refresh both periods, so that they come from the same model.

We will extend this guidance as the product evolves.

10. Summary

This document reports the accuracy of the TomTom Historical Traffic Volumes hourly estimates for 2025, measured against independent ground-truth counts in seven countries by k-fold cross-validation, and for markets beyond them by leave-one-country-out (LOCO) validation.

In the 2025 assessment the United Kingdom leads with an all-roads hourly MAPE of 7.7% in day hours, and five of the seven countries keep their day-hour MAPE under 12%; Norway (18.6%) and New Zealand (16.3%) sit higher. Night hours raise the percentage errors to between 15.2% and 28.9%, yet the night SQV reaches the Good or Very good tier in every country, because the absolute errors overnight remain small. Median percentage errors stay within a few percent of zero in both periods, so aggregate network-level measures can be used with confidence.

For countries held out from training, the pooled LOCO results give a day-hour MAPE between 14.7% and 26.4% depending on road category (SQV 0.71 to 0.86), the accuracy to expect where the model has no local training data. Readers using segment-level data should consult the band-level tables and the guidance in Section 8.2.

On low-volume roads, MAPE values tend to be higher in percentage terms; as Section 4.1 explains, the difference in vehicles on these roads is typically small.

For markets beyond the seven countries in this k-fold validation, the pooled leave-one-country-out (LOCO) results in Section 7.8 provide the accuracy basis (Section 6).

We publish the results for every validated country, including where they fall short of the quality thresholds in Section 4.4. With this document, customers have what they need to use TomTom Historical Traffic Volumes with a clear view of both its accuracy and its limits.

11. References

Das, S., & Tsapakis, I. (2020). Interpretable machine learning approach in estimating traffic volume on low-volume roadways. International Journal of Transportation Science and Technology, 9(1), 76–88. https://doi.org/10.1016/j.ijtst.2019.09.004

Department for Transport. (2026). TAG Unit M3.1: Highway Assignment Modelling (May 2026). Transport Analysis Guidance. https://www.gov.uk/government/publications/webtag-tag-unit-m3-1-highway-assignment-modelling

Eisinga, K., & Lorkowski, S. (2025). Network-Wide Traffic Volume Estimation Based on Probe Vehicle Data. Transportation Research Record, 2679(4), 264–277. https://doi.org/10.1177/03611981241289408

Federal Highway Administration. (2022). Traffic Monitoring Guide (Version 1.0, December 2022). U.S. Department of Transportation. https://www.fhwa.dot.gov/policyinformation/tmguide/tmg_2022/

Friedrich, M., Pestel, E., Schiller, C., & Simon, R. (2019). Scalable GEH: A Quality Measure for Comparing Observed and Modeled Single Values in a Travel Demand Model Validation. Transportation Research Record, 2673(4), 722–732. https://doi.org/10.1177/0361198119838849

Greenshields, B. D. (1935). A study of traffic capacity. Highway Research Board Proceedings, 14, 448–477. https://onlinepubs.trb.org/Onlinepubs/hrbproceedings/14/14P1-023.pdf

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7

Herrera, J. C., Work, D. B., Herring, R., Ban, X., Jacobson, Q., & Bayen, A. M. (2010). Evaluation of traffic data obtained via GPS-enabled mobile phones: The Mobile Century field experiment. Transportation Research Part C: Emerging Technologies, 18(4), 568–583. https://doi.org/10.1016/j.trc.2009.10.006

Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688. https://doi.org/10.1016/j.ijforecast.2006.03.001

Kerner, B. S. (2004). The Physics of Traffic. Springer. https://doi.org/10.1007/978-3-540-40986-1

Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J. J., Schröder, B., Thuiller, W., Warton, D. I., Wintle, B. A., Hartig, F., & Dormann, C. F. (2017). Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 40(8), 913–929. https://doi.org/10.1111/ecog.02881

Sekuła, P., Marković, N., Vander Laan, Z., & Farokhi Sadabadi, K. (2018). Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study. Transportation Research Part C: Emerging Technologies, 97, 147–158. https://doi.org/10.1016/j.trc.2018.10.012

Transportation Research Board. (2022). Highway Capacity Manual 7th Edition: A Guide for Multimodal Mobility Analysis. National Academies Press. https://doi.org/10.17226/26432

Treiber, M., & Kesting, A. (2013). Traffic Flow Dynamics: Data, Models and Simulation. Springer. https://doi.org/10.1007/978-3-642-32460-4

Zhan, X., Zheng, Y., Yi, X., & Ukkusuri, S. V. (2017). Citywide Traffic Volume Estimation Using Trajectory Data. IEEE Transactions on Knowledge and Data Engineering, 29(2), 272–285. https://doi.org/10.1109/TKDE.2016.2621104