This thesis discusses travel time prediction of vehicles on roads based on the methods of machine learning. It describes theory of travel times and summarizes scientific papers dealing with this topic. Within the thesis, analysis of real travel time data was done and the features to be used in prediction models were engineered. Finally, the complex prediction system was designed and implemented and has been tested in production environment.

The Sustainable Water Interactive for Tomorrow (SWIFT) project in eastern Virginia is a Managed Aquifer Recharge project designed to alleviate the depletion of the Potomac Aquifer System due to unsustainable groundwater withdrawals. At the SWIFT Research Center (SWIFTRC) in Nansemond, VA, a pilot testing well (TW-1) has been implemented to help determine the feasibility of full-scale implementation. The pumping data from TW-1 and observation head data from surrounding monitoring wells (MW) at the SWIFTRC were used to calculate hydrogeological parameters (transmissivity, hydraulic conductivity, specific storage, and storage coefficient). Two sets of data were analyzed from before and after TW-1 was rehabilitated to account for the change in the flow distribution to each screen in TW-1. Comparing the results to past literature, the calculated (Theis and Cooper-Jacob methods) hydraulic conductivity/transmissivity values are within the same order of magnitude. Using borehole logs as well as apparent conductance and resistivity logs, multiple single and multi-layered models for both the upper and middle Potomac aquifers were produced with MODFLOW. Parameter estimation using MODFLOW and PEST and the two sets of observation data resulted in hydrogeological parameters similar to those calculated using Theis and Cooper-Jacob methods. The change in the hydraulic conductivity and specific storage between the pre and post rehabilitation flow distributions is proportional to that change in the flow distribution. For future modeling of the aquifer system, the hydrogeological parameters from the model using the 4/26/19 data set with the post rehabilitation flow distribution is recommended. Drawdown results from a multi-layered MODFLOW model were compared to results using the Theis method using both the Theis-calculated and MODFLOW-PEST modeled hydrogeological parameters. The results were nearly identical except for the Upper Potomac Aquifer (UPA) layer 1, as the model has a large change in aquifer thickness with distance from TW-1 that the Theis-based calculations do not consider. Travel times from the monitoring wells to TW-1 were calculated with the single and multi-layered models pumping 700 GPM from TW-1. Travel times from the SWIFT MW within the UPA sublayers ranged from 204 to 597 days depending on the sublayer, while travel times from the USGS MW within the UPA sublayers ranged from 2,395 to 7,859 days. For the single layer model of the UPA, the travel time from the SWIFT MW to TW-1 was 372 days while the travel time from the USGS MW was 4,839 days. Travel times from the SWIFT MW within the MPA sublayers were 416 and 1,195 days, while travel times from the USGS MW within the MPA sublayers were 4,339 and 11,245 days. For the single layer model of the MPA, the travel time from the SWIFT MW to TW-1 was 743 days while the travel time from the USGS MW was 7,545 days. / Master of Science / The Sustainable Water Interactive for Tomorrow (SWIFT) project in eastern Virginia is a project designed to help slow the depletion of the Potomac Aquifer System due to unsustainable groundwater withdrawals. At the SWIFT Research Center (SWIFTRC) in Nansemond, VA, a testing well (TW-1) has been implemented to help determine if the full-scale implementation of the SWIFT project is feasible. The pumping data from TW-1 and observation head data from surrounding monitoring wells (MW) at the SWIFTRC were used to calculate hydrogeological parameters (transmissivity, hydraulic conductivity, specific storage, and storage coefficients). These parameters help describe the behavior of the aquifer system. Two sets of data were analyzed from before and after TW-1 was rehabilitated to account for the change in the flow distribution within TW-1. Comparing the results to past literature, the calculated (using analytical methods, Theis and Cooper-Jacob methods) hydraulic conductivity/transmissivity values are within the same order of magnitude. Using data from the boreholes, multiple single and multi-layered models for both the upper and middle Potomac aquifers were produced with MODFLOW, a groundwater modeling software. Estimating parameters using observation data within MODFLOW resulted in hydrogeological parameters similar to those calculated using the Theis and Cooper-Jacob methods. The change in the hydraulic conductivity and specific storage between the pre and post rehabilitation flow distributions within TW-1 is proportional to that change in the flow distribution. For future modeling of the aquifer system, the hydrogeological parameters from the model using the 4/26/19 (most recent) data set with the post rehabilitation (more current) flow distribution is recommended. Drawdown (decrease in the water table) results from a multi-layered MODFLOW model were compared to results using the Theis method using both the Theis-calculated and MODFLOW modeled hydrogeological parameters. The results were nearly identical except for the Upper Potomac Aquifer (UPA) layer 1, as the model has a large change in aquifer thickness with distance from TW-1 that the Theis-based calculations do not consider. The time it took for a particle of water to travel from the monitoring wells to TW-1 were calculated with the single and multi-layered models pumping 700 GPM from TW-1. Travel times from the SWIFT MW within the UPA sublayers ranged from 204 to 597 days depending on the sublayer, while travel times from the USGS MW within the UPA sublayers ranged from 2,395 to 7,859 days. For the single layer model of the UPA, the travel time from the SWIFT MW to TW-1 was 372 days while the travel time from the USGS MW was 4,839 days. Travel times from the SWIFT MW within the MPA sublayers were 416 and 1,195 days, while travel times from the USGS MW within the MPA sublayers were 4,339 and 11,245 days. For the single layer model of the MPA, the travel time from the SWIFT MW to TW-1 was 743 days while the travel time from the USGS MW was 7,545 days.

<p>When establishing a groundwater protection area it is of great interest to be able to estimate the transit time of the groundwater from different places of the aquifer to the withdrawal well. These estimates can be uncertain due to heterogeneities in the aquifer. As a part of the work to develop methods for a more certain delineation of protection areas, a tracer test was performed in an esker located 25 kilometres NW of the town Uppsala.</p><p>The purpose of this master thesis was to perform, describe and evaluate the tracer test. Travel times from the tracer test should then enable comparison against stochastic simulated travel times of the groundwater in the area.</p><p>Three dyes (rhodamine WT, uranine and naphtionate) and a salt (NaBr) were used in the tracer test. The tracers were injected in four different wells located 25 meters from a pumping well. The pumping well was pumped at a rate of 1.7 L/s and water samples were collected from the pumped water. The calculated mass recovery was large for bromide (101 %) but considerably lower for the dyes rhodamine WT (70 %), uranine (61 %) and Naphthionate (19 %). The low mass recovery for the dyes is probably due to degradation and maybe also adsorption.</p><p>An analytical solution to the advection – dispersion equation in one dimension for radial converging flow was used for the interpretation of the breakthrough curves. Smallest and largest transit time that was received from the model fitting was 1,9 days and 5,1 days respectively and without exception large longitudinal dispersivities (9-35 m). Point dilution tests were performed in the injection wells in order to determine the ground water flow at these wells. The tests gave information about the magnitude of the ground water flow, differences between the wells and the flow change at pumping.</p><p>Travel times were estimated from the received breakthrough curves and the travel time distributions can be used for comparison against stochastic simulated travel times of the groundwater.</p> / <p>Vid utformningen av skyddsområden för grundvattentäkter är det av stor vikt att kunna uppskatta grundvattnets transporttid (uppehållstid) från olika partier av akviferen till uttagsplatsen. Dessa bedömningar har en tendens att bli osäkra på grund av heterogeniteter i akviferen. Som ett led i arbetet att utveckla metoder för en säkrare avgränsning av skyddsområden genomfördes ett spårämnesförsök i en isälvsavlagring (Järlåsaåsen) belägen cirka 2,5 mil nordväst om Uppsala.</p><p>Syftet med examensarbetet var att genomföra, beskriva och utvärdera spårämnesförsöket. Bestämda transporttider från spårämnesförsöket skulle sedan kunna användas för jämförelse med stokastiskt simulerade transporttider för grundvattnet i området.</p><p>Tre färgspårämnen (rhodamin WT, uranin och naphtionat) och ett salt (NaBr) användes vid spårämnesförsöken. Spårämnena injicerades i fyra olika grundvattenrör belägna 25 meter från en uttagsbrunn. Pumpflödet ur uttagsbrunnen var 1,7 L/s och med en automatprovtagare togs vattenprover från det uppumpade vattnet. Resultatet från massbalansberäkningarna visade på att all injicerad bromid återfanns i uttagsbrunnen, men andelen återfunnen spårämnesmassa var betydligt lägre för färgspårämnena rhodamin WT (70 %), uranin (61 %) och naphtionat (19 %). Den låga andelen återfunnen massa beror troligtvis främst på nedbrytning och kanske även på adsorption.</p><p>En analytisk lösning till advektions- dispersionsekvationen i en dimension för radiellt konvergerande strömning användes vid utvärderingen av genombrottskurvorna. En minsta och största uppehållstid på 1,9 dygn respektive 5,1 dygn och överlag oväntat stora dispersiviteter (9 – 35 m) erhölls från kurvanpassningen. Den första ankomsttiden till uttagsbrunnen hade ett minsta och största värde på 3,8 respektive 13 timmar. Utspädningsförsök genomfördes också för att bestämma storleken på flödet vid injektionsrören. Dessa försök gav en bild av flödets storlek, skillnader mellan de olika injektionsrören och flödets förändring vid pumpning.</p><p>De bestämda transporttiderna visar på relativt stora tidsskillnader och ett heterogent försöksområde. Transporttidsfördelningarna utgör också ett underlag för en jämförelse mot stokastiskt simulerade transporttider av grundvattnet.</p>

Research in the field of travel time measurement using Bluetooth technology has been an area of great interest in recent years as transportation professionals strive to increase the cost-effectiveness, accuracy, anonymity, and safety of travel time data collection methods. Commonly used travel time data collection methods include the use of inductive loops, video cameras, and probe vehicles. However, Bluetooth, a globally accepted wireless technology, serves as the medium being utilized by more and more transportation consultants, public agencies, and academics in the collection of travel time data. This study seeks to develop a methodology for measuring travel times on arterial roads using Bluetooth technology. A literature review of general travel time methods and Bluetooth travel time methods was conducted to provide the context for a Bluetooth field deployment development and implementation. The study presents the deployment plan and data analysis of a case study conducted on Spring Street in Atlanta, Georgia. Variable heights, Bluetooth to Bluetooth interference, and detection of Bluetooth devices in probe vehicles are investigated and recommendations are suggested for future Bluetooth travel time studies.

In this thesis, the vehicle routing problem with stochastic, and time dependent, travel times is studied. The stochastic travel times are estimated from historical drive data. The variation of the drive times, as well as that of the variance, during the day was modeled.   The purpose of the thesis was to propose a method of handling the congestion related traffic impediments in an urban setting. Since the majority of times of delivery in the empirical test cases studied correlate with the time period of high traffic load, an efficient and robust handling of such traffic scenarios is of high importance.  It is shown that the stochastic models will shift the estimated arrivals to customers from the more volatile early and late extremes to more central regions of the time window. Previously delivered routes were evaluated both with the standard algorithm and the proposed stochastic algorithm. The difference between the actual drive times and the calculated drive times were analyzed by studying the correlation of the drive times between each customer in the route. It was shown that the routes of the proposed stochastic method increased this correlation. The drive times between nodes where also perturbed with a Gamma distributed noise. The results from the stochastic algorithm showed higher resilience to this disturbance than did the deterministic models. / I detta examensarbete har fordonsruttningsproblemet, VRP, med stokastiska och tidsberonds körtider behandlöats. De stokastiska körtiderna har estimerats från tidigare insamlad hasighetsdata. Modeller för körtidernas och variansernas förändring under dagen har tagits fram.   Syftet med examensarbetet var att föreslå en metod för hur påverkan på körtider av förutsägbar trafikträngsel i en urban trafikmiljö kan hanteras. Eftersom huvuddelen av alla leveranser sammanfaller med de tider på dygnet då trafikbelastning är som högst, ar är en effektiv och robust metod för att hantera sådana störningar av stor vikt. Det visas att den stokastiska modellen kommer att förflyttar ankomster från början och slutet av tidsfönstret till den mer okänsliga mittregionen. Tidigare, utförda leveranser studerades både med den ursprungliga deterministiska modellen och här framtagna stokastiska modellen. Skillnaden mellan de två analyserades genom att studera korrelationen mellan körtiderna som de beräknats av de två modellerna och de upmätta tiderna som de loggats av leveransfordonen. Det visas att korrelationen mellan körtiderna mellan de stokastiska körtiderna och de verkliga körtiderna är högre än korrelationen mellan de deterministiska körtiderna och de verkliga. Rutterna som föreslagits av den stokastiska modellen var också mer tlig mot störningar.

Porozumění chování silniční dopravy je klíčem pro její efektivní řízení a organizaci. Tato úloha se stává čím dál více důležitou s rostoucími požadavky na dopravu a počtem registrovaných vozidel. Informace o dopravní situaci je důležitá pro řidiče a osoby zodpovědné za její řízení. Naštěstí v posledních několika dekádách došlo k značnému rozvoji technologií pro monitorování dopravní situace. Stacionární senzory, jako jsou indukční smyčky, radary, kamery a infračervené senzory, mohou být nainstalovány na důležitých místech. Zde jsou schopny měřit různé mikroskopické a makroskopické dopravní veličiny. Bohužel mnohá měření obsahují nekorektní data, která není možné použít při dalším zpracování, například pro predikci dopravy a její inteligentní řízení. Tato nekorektní data mohou být způsobena poruchou zařízení nebo problémy při přenosu dat. Z tohoto důvodu je důležité navrhnout obecný framework, který je schopný doplnit chybějící data. Navíc by tento framework měl být také schopen poskytovat krátkodobou predikci budoucího stavu dopravy. Tato práce se především zabývá vybranými problémy v oblasti doplnění chybějících dopravních dat, predikcí dopravy v krátkém časovém horizontu a predikcí dojezdových dob. Navrhovaná řešení jsou založena na kombinaci současných metod strojového učení, například Support vector regression (SVR) a multikriteriálních evolučních algoritmů. SVR má mnoho meta-parametrů, které je nutné dobře nastavit tak, aby byla dosažena co nejkvalitnější predikce. Kvalita predikce SVR dále silně závisí na výběru vhodné množiny vstupních proměnných. V této práci používáme multiktriteriální optimalizaci pro optimalizaci SVR meta-parametrů a množiny vstupních proměnných. Multikriteriální optimalizace nám umožňuje získat mnoho Pareto nedominovaných řešení. Mezi těmito řešeními je možné dynamicky přepínat dle toho, jaká data jsou aktuálně k dispozici tak, aby bylo dosaženo maximální kvality predikce. Metody navržené v této práci jsou především vhodné pro prostředí s velkým množstvím chybějících hodnot v dopravních datech. Tyto metody jsme ověřili na reálných datech a porovnali jejich výsledky s metodami, které jsou v současné době používány. Navržené metody poskytují lepší výsledky než stávající metody, a to především ve scénářích, kde se vyskytuje mnoho chybějících hodnot v dopravních datech.

La représentation des temps de parcours est un enjeu influençant la qualité de l’information transmise aux usagers des réseaux de transport. En particulier, la congestion constitue un inconvénient majeur dont la prise en compte n’est pas toujours maîtrisée au sein des calculateurs d’itinéraires. De même, les évènements comme les réductions de capacité, les perturbations climatiques, ou encore les pics de fréquentation incitent à dépasser la définition statique des temps de parcours. Des travaux antérieurs se sont focalisés sur des temps dynamiques, i.e. dépendants de la date de départ, de manière à affiner le détail de la représentation, et à prendre notamment en compte le caractère périodique des congestions. La considération d’informations en temps réel est aussi une amélioration indéniable, que ce soit lors de la préparation du trajet, ou lorsqu’il s’agit de s’adapter à des perturbations rencontrées en cours de route. Ceci dit, aussi fines qu’elles soient dans les calculateurs disponibles, ces modélisations présentent un inconvénient majeur : elles ne prennent pas en compte toutes les facettes de la variabilité des temps de parcours. Cette variabilité est très importante, en particulier si l’on considère le niveau d’aversion au risque des usagers. En outre, dans un réseau multimodal, les correspondances éventuelles rendent encore plus critique l’incertitude associée aux temps de parcours. En réponse à ces enjeux, les présents travaux de thèse ont ainsi été consacrés à l’étude de temps de parcours stochastiques, i.e. vus comme des variables aléatoires distribuées.Dans une première étape, nous nous intéressons à la modélisation statistique des temps de parcours et à la quantification de leur variabilité. Nous proposons l’utilisation d’un système de lois développé dans le domaine de l’hydrologie, la famille des lois de Halphen. Ces lois présentent les caractéristiques typiques des distributions de temps de parcours, elles vérifient par ailleurs la propriété de fermeture par l’addition sous certaines hypothèses afférentes à leurs paramètres. En exploitant les ratios de moments associés aux définitions de ces lois de probabilité, nous mettons également au point de nouveaux indicateurs de fiabilité, que nous confrontons avec la palette d’indicateurs classiquement utilisés. Cette approche holistique de la variabilité des temps de parcours nous semble ainsi ouvrir de nouvelles perspectives quant au niveau de détail de l’information, notamment à destination des gestionnaires de réseaux.Par la suite, nous étendons le cadre d’analyse aux réseaux, en utilisant les résultats obtenus à l’étape précédente. Différentes lois de probabilité sont ainsi testées dans le cadre de la recherche du plus court chemin stochastique. Cette première étude nous permet de dresser un panorama des chemins identifiés en fonction du choix de modélisation. S’il est montré que le choix du modèle est important, il s’agit surtout d’affirmer que le cadre stochastique est pertinent. Ensuite, nous soulevons la relative inefficacité des algorithmes de recherche du plus court chemin stochastique, ceux-ci nécessitant des temps de calcul incompatibles avec un passage à l’échelle industrielle. Pour pallier cette difficulté, un nouvel algorithme mettant en oeuvre une technique d’accélération tirée du cadre déterministe est développé dans la dernière partie de la thèse. Les résultats obtenus soulignent la pertinence de l’intégration de modèles stochastiques au sein des calculateurs d’itinéraires. / The travel time representation has a major impact on user-oriented routing information. In particular, congestion detection is not perfect in current route planners. Moreover, the travel times cannot be considered as static because of events such as capacity drops, weather disturbances, or demand peaks. Former researches focused on dynamic travel times, i.e. that depend on departure times, in order to improve the representation details, for example concerning the periodicity of congestions. Real-time information is also a significant improvement for users aiming to prepare their travel or aiming to react to on-line events. However these kinds of model still have an important drawback : they do not take into account all the aspects of travel time variability. This dimension is of huge importance, in particular if the user risk aversion is considered. Additionally in a multimodal network, the eventual connections make the travel time uncertainty critical. In this way the current PhD thesis has been dedicated to the study of stochastic travel times, seen as distributed random variables.In a first step, we are interested in the travel time statistical modeling as well as in the travel time variability. In this goal, we propose to use the Halphen family, a probability law system previously developed in hydrology. The Halphen laws show the typical characteristics of travel time distributions, plus they are closed under addition under some parameter hypothesis. By using the distribution moment ratios, we design innovative reliability indexes, that we compare with classical metrics. This holistic approach appears to us as a promising way to produce travel time information, especially for infrastructure managers.Then we extend the analysis to transportation networks, by considering previous results. A set of probability laws is tested during the resolution of the stochastic shortest path problem. This research effort helps us to describe paths according to the different statistical models. We show that the model choice has an impact on the identified paths, and above all, that the stochastic framework is crucial. Furthermore we highlight the inefficiency of algorithms designed for the stochastic shortest path problem. They need long computation times and are consequently incompatible with industrial applications. An accelerated algorithm based on a deterministic state-of-the-art is provided to overcome this problem in the last part of this document. The obtained results let us think that route planners might include travel time stochastic models in a near future.

When establishing a groundwater protection area it is of great interest to be able to estimate the transit time of the groundwater from different places of the aquifer to the withdrawal well. These estimates can be uncertain due to heterogeneities in the aquifer. As a part of the work to develop methods for a more certain delineation of protection areas, a tracer test was performed in an esker located 25 kilometres NW of the town Uppsala. The purpose of this master thesis was to perform, describe and evaluate the tracer test. Travel times from the tracer test should then enable comparison against stochastic simulated travel times of the groundwater in the area. Three dyes (rhodamine WT, uranine and naphtionate) and a salt (NaBr) were used in the tracer test. The tracers were injected in four different wells located 25 meters from a pumping well. The pumping well was pumped at a rate of 1.7 L/s and water samples were collected from the pumped water. The calculated mass recovery was large for bromide (101 %) but considerably lower for the dyes rhodamine WT (70 %), uranine (61 %) and Naphthionate (19 %). The low mass recovery for the dyes is probably due to degradation and maybe also adsorption. An analytical solution to the advection – dispersion equation in one dimension for radial converging flow was used for the interpretation of the breakthrough curves. Smallest and largest transit time that was received from the model fitting was 1,9 days and 5,1 days respectively and without exception large longitudinal dispersivities (9-35 m). Point dilution tests were performed in the injection wells in order to determine the ground water flow at these wells. The tests gave information about the magnitude of the ground water flow, differences between the wells and the flow change at pumping. Travel times were estimated from the received breakthrough curves and the travel time distributions can be used for comparison against stochastic simulated travel times of the groundwater. / Vid utformningen av skyddsområden för grundvattentäkter är det av stor vikt att kunna uppskatta grundvattnets transporttid (uppehållstid) från olika partier av akviferen till uttagsplatsen. Dessa bedömningar har en tendens att bli osäkra på grund av heterogeniteter i akviferen. Som ett led i arbetet att utveckla metoder för en säkrare avgränsning av skyddsområden genomfördes ett spårämnesförsök i en isälvsavlagring (Järlåsaåsen) belägen cirka 2,5 mil nordväst om Uppsala. Syftet med examensarbetet var att genomföra, beskriva och utvärdera spårämnesförsöket. Bestämda transporttider från spårämnesförsöket skulle sedan kunna användas för jämförelse med stokastiskt simulerade transporttider för grundvattnet i området. Tre färgspårämnen (rhodamin WT, uranin och naphtionat) och ett salt (NaBr) användes vid spårämnesförsöken. Spårämnena injicerades i fyra olika grundvattenrör belägna 25 meter från en uttagsbrunn. Pumpflödet ur uttagsbrunnen var 1,7 L/s och med en automatprovtagare togs vattenprover från det uppumpade vattnet. Resultatet från massbalansberäkningarna visade på att all injicerad bromid återfanns i uttagsbrunnen, men andelen återfunnen spårämnesmassa var betydligt lägre för färgspårämnena rhodamin WT (70 %), uranin (61 %) och naphtionat (19 %). Den låga andelen återfunnen massa beror troligtvis främst på nedbrytning och kanske även på adsorption. En analytisk lösning till advektions- dispersionsekvationen i en dimension för radiellt konvergerande strömning användes vid utvärderingen av genombrottskurvorna. En minsta och största uppehållstid på 1,9 dygn respektive 5,1 dygn och överlag oväntat stora dispersiviteter (9 – 35 m) erhölls från kurvanpassningen. Den första ankomsttiden till uttagsbrunnen hade ett minsta och största värde på 3,8 respektive 13 timmar. Utspädningsförsök genomfördes också för att bestämma storleken på flödet vid injektionsrören. Dessa försök gav en bild av flödets storlek, skillnader mellan de olika injektionsrören och flödets förändring vid pumpning. De bestämda transporttiderna visar på relativt stora tidsskillnader och ett heterogent försöksområde. Transporttidsfördelningarna utgör också ett underlag för en jämförelse mot stokastiskt simulerade transporttider av grundvattnet.

Vast application of ITS and the availability of numerous on-road detection devices has resulted in variety of alternative data sources to be exploited and used in the field of traffic modelling. In this thesis, historical travel times, as an alternative data source, is employed on the developed method to perform dynamic network loading. The developed method, referred to as DNLTT, uses the share of each route available in the route choice set from the initial demand, as well as link travel times to perform the network loading. The output of the algorithm is time-dependent link flows. DNLTT is applied on Stockholm transportation network, where it is expected to have variation in link travel times in different time-periods, due to network congestion. In order to calculate the route shares, a time-sliced OD matrix is used. The historical travel times and the routes in the route choice set are extracted from an existing route planning tool. An available logit model, which considers the route travel time as the only logit parameter, is used for the route share calculation and the network loading is performed according to 2 different methods of DNLTT and DL. The evaluation of results is done for a toy network, where there happen different network states in different time-periods. Furthermore, the model output from Stockholm case study is analyzed and evaluated. The dynamic behavior of DNLTT is studied by analysis of link flows in different time-periods. Furthermore, the resulting link flows from both network loading methods are compared against observed link flows from radar sensors and the statistical analysis of link flows is performed accordingly. DNLTT exhibits a better performance on the toy network compared to DL, where the increasing link travel times cause the link flows to decline in different time-periods. However, the output of the developed method does not resemble the observed link flows for the investigated links in Stockholm case study. It is strongly believed, that the performance of DNLTT on the investigated transportation network potentially improves, in case the historical travel times better resemble the network dynamics. In addition to a more reliable data set, an OD adjustment process in all the time-periods is believed to generate better model output.

Master thesis deals with possibilities of predicting traffic situation on the macroscopic level using data, that were recorded using traffic sensors. This sensors could be loop detectors, radar detectors or cameras. The main problem discussed in this thesis is the travel time of cars. A method for travel time prediction was designed and implemented as a part of this thesis. Data from real traffic were used to test the designed method. The first objective of this thesis is to become familiar with the prediction methods that will be used. The main objective is to use the acquired knowledge to design and to implement an aplication that will predict required traffic variables.