Generating synthetic population with activity chains as agent-based model input using statistical raster census data

The prediction of trip generation is an essential problem for effective traffic engineering and urban management. Traditional methods are on the large spatial scale (e.g. Traffic analysis Zone, TAZ), based on the single source and fewer types data. It is difficult to carry out refined research on smaller spatial units, due to the high aggregation of personal trip survey data. In addition, the experience-based models cannot easily capture complex non-linear relationship, which leads to lower accuracy. Multi-sources data provides the possibility to improve the prediction accuracy of trip generation. Based on the point of interest data (POI), more disaggregate spatial unit are subdivided, and grid-scale spatial correlations are taken into consideration. This paper proposes a Convolutional Neural Network-Multidimensional Long-short term memory neural network (CNN-MDLSTM) model to analyze the spatial correlation between trip generation and land use features, capture prominent features in a spatial range through the convolution structure and describe the spatial interaction using the sequence transfer structure of Long-short term memory neural network (LSTM). The deformed Multi-Dimensional Long-Short Term Memory neural network (MDLSTM) is used to adapt to the two-dimensional spatial relationship. Through case analysis and comparative analysis between models, it is shown that CNN-MDLSTM characterizes the quantitative law of trip generation and land use features better than the other neural network models. In addition, this study also discusses the output prediction accuracy of different land use grid cells and the impact of different land use characteristics on the prediction accuracy.

show abstract

“…It has been proved by A.S.F. [16]that trip generation of rasterized area makes significant contributions to transportation planning.…”

Section: B Review Of Newly Developed Methodsmentioning

confidence: 99%

Trip Generation Prediction Based on the Convolutional Neural Network-Multidimensional Long-Short Term Memory Neural Network Model at Grid Cell Scale

Xiao

Sun

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These activity chains are typically generated through sampling from either: a set of conditional probabilities based on travellers' attributes such as occupation (He et al, 2020) or the demographic attributes (Balac and Hörl, 2021); based on econometrics and statistical models such as in CEMDAP (Bhat et al, 2004) or from randomly selecting the activity chains from existing data (Felbermair et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

An Activity-Based Model of Transport Demand for Greater Melbourne

Both¹,

Singh²,

Jafari³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we present an algorithm for creating a synthetic population for the Greater Melbourne area using a combination of machine learning, probabilistic, and gravity-based approaches. We combine these techniques in a hybrid model with three primary innovations: 1. when assigning activity patterns, we generate individual activity chains for every agent, tailored to their cohort; 2. when selecting destinations, we aim to strike a balance between the distance-decay of trip lengths and the activity-based attraction of destination locations; and 3. we take into account the number of trips remaining for an agent so as to ensure they do not select a destination that would be unreasonable to return home from. Our method is completely open and replicable, requiring only publicly available data to generate a synthetic population of agents compatible with commonly used agent-based modeling software such as MATSim. The synthetic population was found to be accurate in terms of distance distribution, mode choice, and destination choice for a variety of population sizes.

show abstract

Assessment of the activity scheduling optimization method using real travel data

Toaza,

Esztergár-Kiss

2024

Transportation

View full text Add to dashboard Cite

New mobility services are appearing with the support of technological developments. Part of them is related to activity scheduling of individuals and the optimization of their travel patterns. A novel method called Activity Chain Optimization (ACO) is an application of the Traveling Salesman Problem with Time Windows (TSP-TW) extended with additional assumptions about temporal and spatial flexibility of the activities, where the travelers can optimize the total travel time of their daily activity schedule. This paper aims to apply the ACO method and evaluate its performance using a real-world household survey dataset, where activity chains of up to 15 activities during a day are considered. The optimization is developed using the genetic algorithm (GA) metaheuristic with suitable parameters selected and the branch-and-bound exact algorithm. The findings demonstrate that the branch-and-bound solution exhibits superior performance for smaller activity chain sizes, while the GA outperforms computationally for activity chains with a size from nine. However, the GA found the solutions in only 2% of the time compared to the branch-and-bound method. By applying the ACO method, relevant time savings and emission reduction can be achieved for travelers, when realizing daily activities.

show abstract

Generating synthetic population with activity chains as agent-based model input using statistical raster census data

Cited by 7 publications

References 3 publications

Trip Generation Prediction Based on the Convolutional Neural Network-Multidimensional Long-Short Term Memory Neural Network Model at Grid Cell Scale

Trip Generation Prediction Based on the Convolutional Neural Network-Multidimensional Long-Short Term Memory Neural Network Model at Grid Cell Scale

An Activity-Based Model of Transport Demand for Greater Melbourne

Assessment of the activity scheduling optimization method using real travel data

Contact Info

Product

Resources

About