A Survey on Deep Learning for Human Mobility

The study of human mobility is crucial due to its impact on several aspects of our society, such as disease spreading, urban planning, well-being, pollution, and more. The proliferation of digital mobility data, such as phone records, GPS traces, and social media posts, combined with the predictive power of artificial intelligence, triggered the application of deep learning to human mobility. Existing surveys focus on single tasks, data sources, mechanistic or traditional machine learning approaches, while a comprehensive description of deep learning solutions is missing. This survey provides a taxonomy of mobility tasks, a discussion on the challenges related to each task and how deep learning may overcome the limitations of traditional models, a description of the most relevant solutions to the mobility tasks described above, and the relevant challenges for the future. Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, trajectory generation, and flow generation. At the same time, it helps deep learning scientists and practitioners understand the fundamental concepts and the open challenges of the study of human mobility.

Assessing Large-Scale Power Relations among Locations from Mobility Data

The pervasiveness of smartphones has shaped our lives, social norms, and the structure that dictates human behavior. They now directly influence how individuals demand resources or interact with network services. From this scenario, identifying key locations in cities is fundamental for the investigation of human mobility and also for the understanding of social problems. In this context, we propose the first graph-based methodology in the literature to quantify the power of Point-of-Interests (POIs) over its vicinity by means of user mobility trajectories. Different from literature, we consider the flow of people in our analysis, instead of the number of neighbor POIs or their structural locations in the city. Thus, we modeled POI’s visits using the multiflow graph model where each POI is a node and the transitions of users among POIs are a weighted direct edge. Using this multiflow graph model, we compute the attract, support, and independence powers . The attract power and support power measure how many visits a POI gathers from and disseminate over its neighborhood, respectively. Moreover, the independence power captures the capacity of a POI to receive visitors independently from other POIs. We tested our methodology on well-known university campus mobility datasets and validated on Location-Based Social Networks (LBSNs) datasets from various cities around the world. Our findings show that in university campus: (i) buildings have low support power and attract power ; (ii) people tend to move over a few buildings and spend most of their time in the same building; and (iii) there is a slight dependence among buildings, even those with high independence power receive user visits from other buildings on campus. Globally, we reveal that (i) our metrics capture places that impact the number of visits in their neighborhood; (ii) cities in the same continent have similar independence patterns; and (iii) places with a high number of visitation and city central areas are the regions with the highest degree of independence.

COVID-GAN+: Estimating Human Mobility Responses to COVID-19 through Spatio-temporal Generative Adversarial Networks with Enhanced Features

Estimating human mobility responses to the large-scale spreading of the COVID-19 pandemic is crucial, since its significance guides policymakers to give Non-pharmaceutical Interventions, such as closure or reopening of businesses. It is challenging to model due to complex social contexts and limited training data. Recently, we proposed a conditional generative adversarial network (COVID-GAN) to estimate human mobility response under a set of social and policy conditions integrated from multiple data sources. Although COVID-GAN achieves a good average estimation accuracy under real-world conditions, it produces higher errors in certain regions due to the presence of spatial heterogeneity and outliers. To address these issues, in this article, we extend our prior work by introducing a new spatio-temporal deep generative model, namely, COVID-GAN+. COVID-GAN+ deals with the spatial heterogeneity issue by introducing a new spatial feature layer that utilizes the local Moran statistic to model the spatial heterogeneity strength in the data. In addition, we redesign the training objective to learn the estimated mobility changes from historical average levels to mitigate the effects of spatial outliers. We perform comprehensive evaluations using urban mobility data derived from cell phone records and census data. Results show that COVID-GAN+ can better approximate real-world human mobility responses than prior methods, including COVID-GAN.

Mobility Patterns and Mode Choice Preferences during the COVID-19 Situation

The empirical research on the COVID-19 epidemic’s consequences suggests a major drop in human mobility and a significant shift in travel patterns across all forms of transportation. We can observe a shift from public transport and an increase in car use, and in some cases also increase of cycling and (less often) walking. Furthermore, it seems that micromobility and, more generally, environmentally friendly and comanaged mobility (including shared services), are gaining ground. In previous research, much attention was paid to the mode choice preferences during lockdown, or early stages of the SARS-CoV-2 situation. The blind spot, and aim of this work, is how long observed changes in mode choice last and when or if we can expect the mode choice to shift back to the situation before the SARS-CoV-2 episodes. The research sample consisted of 636 cases; in total, 10 countries contributed to the sample examined in this study. The data were collected in two phases: the first in the spring of 2020 and the second in the fall of the same year. Results showed that respondents reduced mobility by car, local public transport and walking, but not bicycling during the lockdown, compared to the time before the pandemic started. When the easing came, respondents assessed their own use of the car and walking as almost back to normal. They also reported an increase in the use of public transport, but not reaching the level prior the pandemic by far. It seems that cycling was affected least by the pandemic; use of a bicycle hardly changed at all. As for the implication of our study, it is evident that special attention and actions will be needed to bring citizens back to public transport, as it seems that the impact of the pandemic on public transport use will last much longer than the pandemic itself.

Assessing the impact of human mobility to predict regional excess death in Ecuador

COVID-19 outbreaks have had high mortality in low- and middle-income countries such as Ecuador. Human mobility is an important factor influencing the spread of diseases possibly leading to a high burden of disease at the country level. Drastic control measures, such as complete lockdown, are effective epidemic controls, yet in practice one hopes that a partial shutdown would suffice. It is an open problem to determine how much mobility can be allowed while controlling an outbreak. In this paper, we use statistical models to relate human mobility to the excess death in Ecuador while controlling for demographic factors. The mobility index provided by GRANDATA, based on mobile phone users, represents the change of number of out-of-home events with respect to a benchmark date (March 2nd, 2020). The study confirms the global trend that more men are dying than expected compared to women, and that people under 30 show less deaths than expected, particularly individuals younger than 20 with a death rate reduction between 22 and 27%. The weekly median mobility time series shows a sharp decrease in human mobility immediately after a national lockdown was declared on March 17, 2020 and a progressive increase towards the pre-lockdown level within two months. Relating median mobility to excess deaths shows a lag in its effect: first, a decrease in mobility in the previous two to three weeks decreases excess death and, more novel, we found an increase of mobility variability four weeks prior increases the number of excess deaths.

Mobility in Unsupervised Word Embeddings for Knowledge Extraction—The Scholars’ Trajectories across Research Topics

In the knowledge discovery field of the Big Data domain the analysis of geographic positioning and mobility information plays a key role. At the same time, in the Natural Language Processing (NLP) domain pre-trained models such as BERT and word embedding algorithms such as Word2Vec enabled a rich encoding of words that allows mapping textual data into points of an arbitrary multi-dimensional space, in which the notion of proximity reflects an association among terms or topics. The main contribution of this paper is to show how analytical tools, traditionally adopted to deal with geographic data to measure the mobility of an agent in a time interval, can also be effectively applied to extract knowledge in a semantic realm, such as a semantic space of words and topics, looking for latent trajectories that can benefit the properties of neural network latent representations. As a case study, the Scopus database was queried about works of highly cited researchers in recent years. On this basis, we performed a dynamic analysis, for measuring the Radius of Gyration as an index of the mobility of researchers across scientific topics. The semantic space is built from the automatic analysis of the paper abstracts of each author. In particular, we evaluated two different methodologies to build the semantic space and we found that Word2Vec embeddings perform better than the BERT ones for this task. Finally, The scholars’ trajectories show some latent properties of this model, which also represent new scientific contributions of this work. These properties include (i) the correlation between the scientific mobility and the achievement of scientific results, measured through the H-index; (ii) differences in the behavior of researchers working in different countries and subjects; and (iii) some interesting similarities between mobility patterns in this semantic realm and those typically observed in the case of human mobility.

Analysis and Prediction of Human Mobility in the United States during the Early Stages of the COVID-19 Pandemic using Regularized Linear Models

Since the United States started grappling with the COVID-19 pandemic, with the highest number of confirmed cases and deaths in the world as of August 2020, most states have enforced travel restrictions resulting in drastic reductions in mobility and travel. However, the long-term implications of this crisis to mobility still remain uncertain. To this end, this study proposes an analytical framework that determines the most significant factors affecting human mobility in the United States during the early days of the pandemic. Particularly, the study uses least absolute shrinkage and selection operator (LASSO) regularization to identify the most significant variables influencing human mobility and uses linear regularization algorithms, including ridge, LASSO, and elastic net modeling techniques, to predict human mobility. State-level data were obtained from various sources from January 1, 2020 to June 13, 2020. The entire data set was divided into a training and a test data set, and the variables selected by LASSO were used to train models by the linear regularization algorithms, using the training data set. Finally, the prediction accuracy of the developed models was examined on the test data. The results indicate that several factors, including the number of new cases, social distancing, stay-at-home orders, domestic travel restrictions, mask-wearing policy, socioeconomic status, unemployment rate, transit mode share, percent of population working from home, and percent of older (60+ years) and African and Hispanic American populations, among others, significantly influence daily trips. Moreover, among all models, ridge regression provides the most superior performance with the least error, whereas both LASSO and elastic net performed better than the ordinary linear model.