Search

The development of car fleet plays major part when considering the emissions resulted from passenger car use. Globally, there are many different methods and models for car fleet development estimation, but majority of these represent the results only on national level. In Finland, existing models do not note differences between area types. In this paper, we introduce car fleet model (SALAMA), which can be used to estimate car fleet development for both national and regional levels in Finland. Model allows to alter different variables (such as car fleet development speed, car ownership level and probability to change driving power) to examine, how different policy changes would affect the car fleet development. The paper depicts the Finnish baseline scenario compared to the effects of faster (30% faster than baseline) and slower (30% slower than baseline) fleet development speed scenarios. On the baseline scenario, model estimates 320 000 electric cars (both BEV and PHEV) in 2030 and 830 000 in 2040. For faster scenarios, model estimates 100 000 and 250 000 electric cars more in respective years, while slower scenario produces 80 000 and 180 000 electric cars less compared to baseline scenario. In addition, the model shows that there are clear differences between area types. For example, the share of electric car increases faster in urban areas than in rural areas. • Car fleet development model for Finland is presented. • Model produces results for both national and regional level. • Baseline scenario estimates a total of 830 000 BEV and PHEV in 2040 • Fast scenario estimates a total of 1 100 000 BEV and PHEV in 2040 • Fast fleet development alone will not fulfil 2030 EU emission reduction targets. [ABSTRACT FROM AUTHOR]

Time series characterized by periodic fluctuations are widespread in reality behavioural systems, and accurate forecasting of them has important practical application value. In this paper, based on the idea of discrete grey model, dual interaction effects and the nonlinear characteristics of the system are considered under the perspective of dual processing, and the fluctuating trend of the periodic sequence is portrayed through the introduction of the periodic dummy variable, and at the same time, combined with the extended periodic rolling time window method, the rolling discrete grey periodic power model with the interaction effect under dual processing is proposed, namely DIE-RDGM(1,1, T) α model. Differential evolution algorithm (DE) are employed to determine the optimum power index. Finally, the new model was compared with nine other forecasting models by three instances and applied to the problem of agricultural drought forecasting in Zhoukou City and Anyang City, Henan Province. The results show: (1) The new model has demonstrated strong competitiveness, confirming its rationality, validity, and superiority. (2) The DE is suitable for power index optimization search. (3) The new model can better describe the periodic change rule of seasonal-scale soil moisture in the two cities, and the forecast results are consistent with the actual drought conditions. [ABSTRACT FROM AUTHOR]

The rapid adoption of electric vehicles (EVs) has led to dramatic increase in charging demands that poses great challenges for efficient charging infrastructure rollout and operation. It is crucial to accurately assess charging demand in urban areas to optimize the siting and sizing of charging infrastructure. This paper proposes a novel urban charging load forecasting model for private passenger EVs based on massive operating data of EVs in Beijing. First, the characteristics of travel patterns for private passenger EVs, urban road network, functional area distribution and charging infrastructure distribution within the entire Beijing area are identified. Then a charging load forecasting model that can simultaneously simulate trip chains for EVs is constructed by considering the occupancy states of public charging piles and the interactions among different EVs. Finally, the effectiveness of the proposed charging load forecasting model is verified based on comprehensive test data. Our findings imply that the number of EVs at recharge and the charging power can be reliably predicted with the accuracy of over 84.73 % and 81.92 %, respectively. It provides the foundation for optimal charging infrastructure planning and charging scheduling. [ABSTRACT FROM AUTHOR]

Considering the increasing number of vehicles used for a variety of purposes, the demand for accurate traffic services is also rising. Most drivers use traffic services to find a path through the city and get an estimation of how long the trip will take. Due to a large number of factors affecting driving in urban areas the task of predicting the estimated time of arrival is not trivial. In this paper we discuss different methods used for trip duration prediction and compare their performances. We use a real urban traffic data set for testing, and also make this data set public to stimulate future research. [ABSTRACT FROM AUTHOR]

• Validating a multi-reservoir MFD model compared to real data. • Calibrating crucial input of the MFD model with real data. • Highlighting the role of the total active network length to scale-up observations from loop sensors. • Designing flow optimization methods to estimate a reliable path flow. distribution, possibly far from Wardrop's principle. Aggregated traffic flow models based on the Macroscopic Fundamental Diagram (MFD), also known as multi-reservoir or multi-region MFD models, have been developed for more than a decade for various applications. While being very appealing for simulating traffic dynamics at a city level, the outputs of these models were rarely confronted with real data measurements. Thus, this paper focuses on calibration and validation of an MFD simulation for a city partitioned into multiple reservoirs. The traffic predictions from the MFD simulation (total accumulation and mean speed) are compared with real data from loop and probe sensors. The questions addressed in this study include the influence of the city partitioning, the MFD and average trip length estimation, and the path flow distribution among reservoirs. This study is carried on the network of Lyon, France, composed by around 27,000 links that extend over an urban area of 80 km2. Two different partitioning cases are defined and compared, with respectively 5 and 10 reservoirs. Our results notably show that the proper estimation of three elements is critical for accurate traffic state prediction: (i) the total "active" network length of each reservoir, (ii) the regional trip lengths in the reservoirs, and (iii) the path flow distribution at the regional network level. While the network equilibrium found in the 5-reservoir partitioning can be roughly approximated with Wardrop's principle, the 10-reservoir case is more complex and requires to design ad-hoc optimization process to derive regional path flow distributions that fit the data. The global equilibrium found in this latter case turns out to be hardly predictable with any traffic equilibrium principle. [ABSTRACT FROM AUTHOR]

Investigating downstream freight demand is a prerequisite to accomplishing the overall strategic implementation of transportation systems. Machine learning has recently become widely applied in order to support decision-making in several logistic operational levels: travel/arrival time prediction, occupancy forecasting of logistic spaces, route optimization and so on. Nevertheless, strategic decision-making often overlooks flow tendencies forecasting. Targeting this perspective, the present paper aims at proposing an urban zoning approach based on time series forecasting of supply chain demand through clustering customers. To conduct our approach, we have selected a set of machine learning algorithms that are believed to be robust according to the literature and the achieved accuracy benchmarks. Considering real-life data-based computational results, a number of analytical insights are illustrated. [ABSTRACT FROM AUTHOR]

Predicting taxi demands in large cities can help in better traffic management as well as ensure better commuter satisfaction for an intelligent transportation system. However, the traffic demands across different locations have varying spatio-temporal correlations that are difficult to model. Despite the ability of the existing Deep Neural Network (DNN) models to capture the non-linearity in spatial and temporal characteristics of the demand time-series, capturing spatio-temporal characteristics in different real-world scenarios like varying historic and prediction time frame, spatio-temporal variations due to noise or missing data, etc. still remain a big challenge for the state-of-the-art models. In this paper, we introduce En coder- App ro X imator (EnAppX), an encoder–decoder DNN-based model that uses Chebyshev function approximation in the decoding stage for taxi demand times-series prediction and can better estimate the time-series in the presence of large spatio-temporal variations. Opposed to any existing state-of-the-art model, the proposed model approximates complete spatio-temporal characteristics in the frequency domain which in turn enables the model to make a robust and improved prediction in different scenarios. Validation over two real-world taxi datasets from different cities shows a considerable improvement of around 23% in RMSE scores compared to the state-of-the-art baseline model. Unlike several existing state-of-the-art models, EnAppX also produces improved prediction accuracy across two regions for both to and fro demands. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a combined method for short-term forecasting of detector counts in urban networks and subsequent traffic demand estimation using the forecasted counts as constraints to estimate origin–destination (OD) flows, route and link volumes. The method is intended to be used in the framework of an adaptive traffic control strategy with consecutive optimization intervals of 15min. The method continuously estimates the forthcoming traffic demand that can be used as input data for the optimization. The forecasting uses current and reference space–time-patterns of detector counts. The reference patterns are derived from data collected in the past. The current pattern comprises all detector counts of the last four time intervals. A simple but effective pattern matching is used for forecasting. The subsequent demand estimation is based on the information minimization model that has been integrated into an iterative procedure with repeated traffic assignment and matrix estimation until a stable solution is found. Some enhancements including the improvement of constraints, redundancy elimination of these constraints and a travel time estimation based on a macroscopic simulation using the Cell Transmission Model have been implemented. The overall method, its modules and its performance, which has been assessed using artificially created data for a real sub-network in Hannover, Germany, by means of a microsimulation with Aimsun NG, are presented in this paper. [Copyright &y& Elsevier]

• This paper hybridizes phase space reconstruction and weighted local constant method for short-term load forecasting. • The proposed model has good dynamic characteristics and adaptability; can capture changes in time, and can respond quickly. • Experimental results reveal that the proposed model has better forecasting accuracy than other alternative model. To forecast accurately the electric load of a city at the weekend, aiming at the problems of nonlinearity and model interpretability in power behavior, a local constant first-order weighted forecasting model is developed. First of all, the values of the electric load are reconstructed in phase space, stability analysis can effectively describe the operation mechanism and law of weekend power. Then, the weights of neighbors are used in the first-order local forecasting model, and the nearest neighbors are used in grid optimization. The forecasted values are then separated to be the phase forecasting points in terms of the spatial dimension of the electric loads and the lags of the time delay obtained in the training stage. Numerical experimental results of samples at different scales show the following: (1)The forecasting performance of the proposed model is better than other models in the forecasting errors in this work (among three types of measurements: root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE)); (2) the significance test (KSPA) also confirmed the universality and consistency of the method, and the effective diagnosis and statistical analysis of the weekend power mechanism are helpful to promote weekend power management and commercial design. [ABSTRACT FROM AUTHOR]

Following a federal policy statement in 2010 supporting bicycle and pedestrian accommodation in federal-aid transportation projects, many cities across the US have implemented Complete Streets principles and invested in developing better-planned infrastructure that can be safely accessed by a diversity of modes of transportation by all types of users, in a mix of land uses. However, most of the travel demand forecasting models and planning tools used in practice are not sensitive to changes in demand for non-motorized modes such as walking and cycling in response to road infrastructure improvements. Hence, there is a need for models and tools that are capable of evaluating impacts of infrastructure changes that include Complete Streets implementations on the travel behavior, and estimate shifts in mode choices from motorized to non-motorized modes. This paper proposes a specific data collection plan, a multi-modal choice model, and strategies to update traditional trip-based transportation models to forecast rates of non-motorized trips for evaluating Complete Streets plans at a higher level. Concretely, we estimate elasticities to Level of Traffic Stress, which defines the comfort or discomfort experienced by walkers and bikers, segmented by income levels and trip purposes. We then use them to compute the new non-motorized mode shares that would be achieved by improving CS attributes leading to lower levels of traffic stress. The proposed modeling framework has been successfully applied to the Maryland Statewide Transportation Model, producing reliable non-motorized trip rates, and can be extended to other methodological frameworks used by public agencies. [ABSTRACT FROM AUTHOR]

Abstract: New technologies enable new urban patterns and new connections within and between cities. This paper reviews new and emerging technologies that are impacting cities internally and in their relations within larger networks. Policy and social attitudes also must change to incorporate and integrate new technologies. Forecasts and visions of urban futures are now more complicated by new technologies and by the global networks within which urban economies and urban dwellers operate. [Copyright &y& Elsevier]

Abstract: In this paper, a hybrid model which combines Extended Kalman Filter (EKF) and Genetic Programming (GP) for forecasting of water demand in Tehran is developed. The initial goal of the current work is forecasting monthly water demand using GP for achieving an explicit optimum formula. In the proposed model, the EKF is applied to infer latent variables in order to make a forecasting based on GP results of water demand. The available dataset includes monthly water consumption of Tehran, the capital of Iran, from 1992 to 2002. Five best formulas based on GP results on this dataset are presented. In these models, the first five to three lags of observed water demand are used as probable and independent inputs. For each model, sensitivity of the results for each input is measured mathematically. A model with the most compatibility of the computed versus the observed water demand is used for filtering based on EKF method. Results of GP and hybrid models of EKFGP demonstrate the visible effect of observation precision on water demand prediction. These results can help decision makers of water resources to reduce their risks of online water demand forecasting and optimal operation of urban water systems. [Copyright &y& Elsevier]

[Display omitted] • First LUR models for UFP on a national scale. • Combining targeted mobile monitoring with long-term regional background monitoring. • Different algorithms predicted external measurements well and correlated highly. • Deconvolution can improve large-area exposure assessment. • Models will be applied in Dutch nation-wide health studies. Large nation- and region-wide epidemiological studies have provided important insights into the health effects of long-term exposure to outdoor air pollution. Evidence from these studies for the long-term effects of ultrafine particles (UFP), however is lacking. Reason for this is the shortage of empirical UFP land use regression models spanning large geographical areas including cities with varying topographies, peri -urban and rural areas. The aim of this paper is to combine targeted mobile monitoring and long-term regional background monitoring to develop national UFP models. We used an electric car to monitor UFP concentrations in selected cities and towns across the Netherlands over a 14-month period in 2016–2017. Routes were monitored 3 times and concentrations were averaged per road segment. In addition, we used kriging maps based on regional background monitoring (20 sites; 3 × 2 weeks) over the same period to assess annual average regional background concentrations. All road segments were used to model spatial variation of UFP with three different land-use (regression) approaches: supervised stepwise regression, LASSO and random forest. For each approach, we also tested a deconvolution method, which segregates the average concentration at each road segment into a local and background signal. Model performance was evaluated with short-term (400 sites across the Netherlands; 3 × 30 minutes) and external longer-term measurements (42 sites in two major cities; 3 × 24 hours). We also compared predictions of all six models at 1000 random addresses spread over the country. We found similar predictive performance for the six models, with validation R2 values from 0.25 to 0.35 for short-term measurements and 0.52 to 0.60 for longer-term external measurements. Models with and without deconvolution had similar predictive performance. All models based on the deconvolution method included a regional background kriging map as important predictor. Correlations between predictions at random addresses were high with Pearson correlations from 0.84 to 0.99. Models overestimated exposure at the short-term and long-term sites by about 20–30% in all cases, with small differences between regions and road types. We developed robust nation-wide models for long-term UFP exposure combining mobile monitoring with long-term regional background monitoring. Minor differences in predictive performance between different algorithms were found, but the deconvolution approach is considered more physically realistic. The models will be applied in Dutch nation-wide health studies. [ABSTRACT FROM AUTHOR]

Exposure to air pollution has a significant impact on the health of urban populations, so the improvement of methods that model the concentrations of air pollutants within complex urban areas is important in health studies to adequately asses the exposure of the population. This paper presents several hybrid, high-resolution models to simulate the variability of ambient NO 2 concentrations in Seoul, the capital of South Korea. These models combine the Community Multiscale Quality (CMAQ) as a regional photochemical model with a fine scale model of either the California Puff dispersion model (CALPUFF) or the land use regression model (LUR). We compared high-resolution estimates of the spatial NO 2 concentration from four different hybrid models, including 1) raw CMAQ-CALPUFF; 2) observation-fused CMAQ-CALPUFF; 3) raw CMAQ-LUR; and 4) observation-fused CMAQ-LUR. We conducted numerical simulations of the NO 2 concentrations during the winter season and compared the results with field data obtained from mobile measurements captured from December 2017 to February 2018. The results indicate that observation-fused hybrid models offered improved agreement with the mobile measurements: for the CMAQ-CALPUFF model, statistical bias and error were reduced to about 82% and 57%, respectively by using observation-fused CMAQ. We also found significant differences in the sub-grid variability of the NO 2 concentrations for the different hybrid models. The predictions obtained with CMAQ-CALPUFF showed concentrations that were more widely distributed (1.7 and 1.4 times for the 10–90th range, observation-fused case) when compared to the only-CMAQ and CMAQ-LUR predictions, respectively. Our study suggests that a properly evaluated hybrid model can increase the predictive accuracy of air pollutant concentration in complex urban areas to improve exposure assessments in health studies. Image 1 • Several hybrid modeling approaches to simulate NO 2 concentrations were compared. • Observation data fusing technique greatly improved CMAQ prediction. • Hybrid modeling approaches can enhance the ability to predict local details in NO 2 concentrations in a complex urban area. [ABSTRACT FROM AUTHOR]

Building occupancy, which reflects occupant presence, movements and activities within the building space, is a key factor to consider in building energy modelling and simulation. Characterising complex occupant behaviours and their determinants poses challenges from the sensing, modelling, interpretation and prediction perspectives. Past studies typically applied time-dependent models to predict regular occupancy patterns for commercial buildings. However, this prevalent reliance on purely time-of-day effects is typically not sufficient to accurately characterise the complex occupancy patterns as they may vary with building's surrounding conditions, i.e. the urban environment. Therefore, this paper proposes a conceptual framework to incorporate the interactions between urban systems and building occupancy. Under the framework, we propose a novel modelling methodology relying on competing risk hazard formulation to analyse the occupancy of a case study building in London, UK. The occupancy profiles were inferred from the Wi-Fi connection logs extracted from the existing Wi-Fi infrastructure. When compared with the conventional discrete-time Markov Chain Model (MCM), the hazard-based modelling approach was able to better capture the duration dependent nature of the transition probabilities as well as incorporate and quantify the influence of the local environment on occupancy transitions. The work has demonstrated that this approach enables a convenient and flexible incorporation of urban dependencies leading to accurate occupancy predictions whilst providing the ability to interpret the impacts of urban systems on building occupancy. •Model of interactions between occupancy behaviour and urban systems is proposed. •Competing risk hazard model is used to operationalise the model using Wi-Fi logs. •The hazard model flexibly captures dependence of transition probability on duration. •The model helps gain insights into exogenous effects on occupancy behaviour. •Compared to MCM, hazard model better predicts occupancy with flexible work agendas. [ABSTRACT FROM AUTHOR]

• Supplying temporary accommodation units is a frequent, yet problematic, implemented strategy after destructive earthquakes. • Estimating homeless is a key to the reliable development of temporary accommodation pre-disaster plans. • The prediction of damaged and destroyed lodgings allows the estimation of the homeless. • The tool to estimate temporary housing units performs these estimations and predictions to support pre-disaster plans. Earthquakes have been destructive events for the built environment, particularly for urban areas due to the concentration of people and constructions. Two of the important effects are damaged or destroyed houses and the homeless. In these scenarios, the provision of temporary accommodation solutions is one of the most important post-disaster actions to provide for minimum living conditions. However, the implemented solutions frequently end in undesirable outcomes for victims and cities. Pre-disaster planning has been considered the best way to minimize consequences and promote better emergency management. This way, the paper presents a tool to estimate temporary accommodation units needs (TETAN) aiming to forecast necessities in terms of space and resources to supply temporary units after hypothetical scenarios of damage and destruction caused by earthquakes and defined according to the modified Mercalli Scale. The tool is assessed in two cities with high seismic risk, analysing and discussing the results, as well as suggesting measures and strategies which can be considered in the urban planning of both cases, not only for pre-disaster planning of temporary accommodation but also for built environmental risk reduction. These strategies provide for the connection of pre-disaster planning and urban planning, increasing the resilience of cities and their inhabitants. [ABSTRACT FROM AUTHOR]

Area feeder long-term load forecast (LTLF) is one of the most critical forecasting tasks in electric distribution utility companies. Cost effective system upgrades can only be planned out based on accurate feeder LTLF results. However, the commonly used top-down and bottom-up LTLF methods fail to combine area and feeder information and cannot effectively deal with component-level LTLF. The previous research effort on hybrid approach that aims to combine top-down and bottom-up approaches is very limited. The recent work only focuses on the forecast of the next one-year and uses a one-fit-all model for all area feeders. In response, this paper proposes a novel selective sequence learning method that can convert a multi-year LTLF problem to a multi-timestep sequence prediction problem. The model learns how to predict sequence values as well as the best-performing sequential configuration for each feeder. In addition, unsupervised learning is introduced to automatically group feeders based on load compositions ahead of learning to further enhance the performance. The proposed method was tested on an urban distribution system in Canada and compared with many conventional methods and the existing hybrid forecasting method. It achieves the best forecasting accuracy measured by three metrics AMAPE, RMSE and R-squared. It also proves the feasibility of applying sequence learning to multi-year component-level load forecast. • Converts a multi-year LTLF problem to a multi-timestep sequence prediction problem. • Can incorporate area and feeder level information in multiple historical years. • Can be used to forecast multiple years in the future. • Best sequential configurations can be automatically learned for different feeders. • Unsupervised learning is adopted to further enhance forecasting accuracy. [ABSTRACT FROM AUTHOR]

• Transformation approach of excavation boundary in multi-layered clayey soils is established. • Semi-analytical method to predict ground movements in multi-layered clayey soils is proposed. • Semi-analytical method is verified through the comparisons with previous research. • Influence of the existence of interlayer soil on ground movements is analyzed. This paper develops a semi-analytical method to calculate the ground movements due to tunnelling in multi-layered clayey soils which are usually encountered in urban areas. The proposed method is based on the modified Loganathan-Poulos formula combined with the elastic equivalent theory. The key issue disposed in current study is the transformation of the boundary of excavation and the boundary after convergence from multi-layered soil system into single layer soil system. The proposed method is verified through the comparisons with previous associated studies associated with the field measurements from five well-documented cases. A parametric study based on the situation that the interlayer is arranged between the upper and lower soil layer is conducted to explore the effects of the mechanical properties and dimensional variables of the interlayer on ground settlements. The results indicate that the soil stratification has a significant impact on ground movements induced by tunnelling in multi-layered clayey soils. [ABSTRACT FROM AUTHOR]

In recent years, growing air pollution has become a significant issue due to its detrimental effects on the environment and different living organisms. Providing accurate and reliable forecasts of air quality over a long future horizon is an effective way to mitigate health risks. In this paper, the problem of urban PM2.5 forecasts for several days ahead is considered. An ensemble multi-step-ahead forecasting system is introduced for this problem, which combines different multi-step-ahead strategies (including single-output and multi-output approaches). The proposed hybrid framework consists of three parts. In the first part, the Ensemble Empirical Mode Decomposition (EEMD) technique is combined with a prediction tool and multi-step-ahead strategies. Boosting idea is considered in the second part of the algorithm. Finally, the stacked ensemble of boosted hybrid structures is developed to provide the final multi-step-ahead forecasts. Least Square Support Vector Regression (LSSVR), and Long Short-Term Memory neural network (LSTM) are employed as the prediction tools in the proposed hybrid framework. Through real PM2.5 data examples from Mashhad, Iran, the proposed ensemble model is investigated for 1-day-ahead to 10-days-ahead. The results reveal the effectiveness of the ensemble model in comparison with the multi-step-ahead strategies in all time-steps. The proposed model with LSSVR prediction tool shows the smallest mean RMSE, MAE, and MAPE values of 7.810, 5.562, and 18.104% over all time-steps, and RMSE improvement rates of more than 35% compared to simply combining different multi-step-ahead strategies with LSSVR approach. [ABSTRACT FROM AUTHOR]