Modeling and forecasting traffic flows with mobile phone big data in flooding risk areas to support a data-driven decision making

Abstract

Floods are one of the natural disasters which cause the worst human, social and economic impacts to the detriment of both public and private sectors. Today, public decision-makers can take advantage of the availability of data-driven systems that allow to monitor hydrogeological risk areas and that can be used for predictive purposes to deal with future emergency situations. Flooding risk exposure maps traditionally assume amount of presences constant over time, although crowding is a highly dynamic process in metropolitan areas. Real-time monitoring and forecasting of people’s presences and mobility is thus a relevant aspect for metropolitan areas subjected to flooding risk. In this respect, mobile phone network data have been used with the aim of obtaining dynamic measure for the exposure risk in areas with hydrogeological criticality. In this work, we use mobile phone origin-destination signals on traffic flows by Telecom Italia Mobile (TIM) users with the aim of forecasting the exposure risk and thus to help decision-makers in warning to who is transiting through that area. To model the complex seasonality of traffic flows data, we adopt a novel methodological strategy based on introducing in a Vector AutoRegressive with eXogenous variable (VARX) model a Dynamic Harmonic Regression (DHR) component. We apply the method to the case study of the “Mandolossa”, an urbanized area subject to flooding located on the western outskirt of Brescia, using hourly-basis data from September 2020 to August 2021. A cross validation based on the hit-rate and the mean absolute percentage error measures show a good forecasting accuracy.

Informing Urban Flood Risk Adaptation by Integrating Human Mobility Big Data During Heavy Precipitation

“…Second, although we have applied algorithms to attempt to remove trend effects such as short-term weekly fluctuations and long-term user increases, it is difficult to control all the confounding factors that affect the patterns of mobile phone signals, e.g., traffic accidents, construction projects, and other important public events. Unlike us, in the work of Metulini et al, 56 they decomposed mobile phone signaling data in days and focused on seasonal structure, which is also an amazing attempt. In the future, it will be worthwhile to compare the robustness of these two approaches.…”

Traffic flows time series in a flood-prone area: modeling and clustering on extreme values with a spatial constraint

“…Because we are interested in the flows from/to the area of the Mandolossa, our focus is directed towards two distinct groups of ACEs, that we treat separately: the four ACEs intersecting the flood risk map of the Mandolossa, indexed with an i, and specific neighboring ACEs, indexed with a j. 38 ACEs in the vicinity of the Mandolossa region were identified as neighbors, accounting for 84% of the total flows to and from the four aforementioned ACEs of interest (more details can be found in Metulini and Carpita (2023)).…”

“…With the aim to obtain uncorrelated estimated residuals that will subsequently be used for clustering purposes, we have made modifications to the original VARX DHR model introduced and applied by Metulini and Carpita (2023). In particular, we allow lags of order smaller than 24 to be utilized in our analysis.…”

“…This information is then used to construct statistical models capable of providing accurate predictions of human mobility. Metulini and Carpita (2023) proposed a model that combines vector autoregressive techniques with exogenous covariates and dynamic harmonic regression for this purpose. The application of this method was demonstrated in the case study of Mandolossa, an urbanized area prone to flooding situated on the western outskirts of Brescia (See Balistrocchi et al (2020) for more details about the area).…”

Review of Traffic Assignment and Future Challenges

“…Moreover, the mixed traffic digital twin can be designed to be proactive, not only highlighting problems, such as those proposed in ref. [182], but also proposing solutions to the decision-makers. To this end, the mixed traffic digital twin may be trained by using "classical traffic" assignment approaches.…”