An Activity-Based Model of Transport Demand for Greater Melbourne

Abstract

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.

Smart Insertion Strategies for Sustainable Operation of Shared Autonomous Vehicles

“…This study uses an existing synthetic MATSim model of Melbourne's Metr Network [80]. The network file of the study area and the config file were taken f base scenario, and the config file was modified according to the requirements [81 5 shows the network of the Melbourne Metropolitan Area used as the case stud study.…”

Activity-based and agent-based Transport model of Melbourne (AToM): an open multi-modal transport simulation model for Greater Melbourne

“…For example, MB is the smallest geographical area defined by ABS and residential MBs have a dwelling count of approximately 30 to 60 in urban areas. 5 Both et al's algorithm also assigns a travel mode to each trip based on the starting region's probability to be used for the location assignment process (Both et al, 2021).…”

“…Hafezi et al (2021) used techniques from machine learning along with econometric techniques and proposed a hybrid framework for creating activities and travel diaries using a cohort-based synthetic pseudo panel engine to model. Similarly, a kmeans clustering algorithm was used byAllahviranloo et al (2017) to cluster activities based on trip attributes and to synthesize activity chains Both et al (2021). proposed an algorithm for creating the synthetic population for the Greater Melbourne area using a combination of machine learning, probabilistic and gravity-based approaches.…”

“…Figure 1: Selecting next region for a cycling trip from home (circle) to work (triangle) showing: region selection probability (Pr) for local and global distance distributions (a and b), region selection probability (Pr) for local and global destination attraction (cand d), number of trips (hop count) that would be reasonably required to reach home (e), and combined region likelihood (f) (source:(Both et al, 2021)). …”