Assessing internal displacement patterns in Ukraine during the beginning of the Russian invasion in 2022.

Given the worldwide increase of forcibly displaced populations, particularly internally displaced persons (IDPs), it's crucial to have an up-to-date and precise tracking framework for population movements. Here, we study how the spatial and temporal pattern of a large-scale internal population movement can be monitored using human mobility datasets by exploring the case of IDPs in Ukraine at the beginning of the Russian invasion of 2022. Specifically, this study examines the sizes and travel distances of internal displacements based on GPS human mobility data, using the combinations of mobility pattern estimation methods such as truncated power law fitting and visualizing the results for humanitarian operations. Our analysis reveals that, although the city of Kyiv started to lose its population around 5 weeks before the invasion, a significant drop happened in the second week of the invasion (4.3 times larger than the size of the population lost in 5 weeks before the invasion), and the population coming to the city increased again from the third week of the invasion, indicating that displaced people started to back to their homes. Meanwhile, adjacent southern areas of Kyiv and the areas close to the western borders experienced many migrants from the first week of the invasion and from the second to third weeks of the invasion, respectively. In addition, people from relatively higher-wealth areas tended to relocate their home locations far away from their original locations compared to those from other areas. For example, 19 % of people who originally lived in higher wealth areas in the North region, including the city of Kyiv, moved their home location more than 500 km, while only 9 % of those who originally lived in lower wealth areas in the North region moved their home location more than 500 km..

YJMob100K: City-scale and longitudinal dataset of anonymized human mobility trajectories.

Modeling and predicting human mobility trajectories in urban areas is an essential task for various applications including transportation modeling, disaster management, and urban planning. The recent availability of large-scale human movement data collected from mobile devices has enabled the development of complex human mobility prediction models. However, human mobility prediction methods are often trained and tested on different datasets, due to the lack of open-source large-scale human mobility datasets amid privacy concerns, posing a challenge towards conducting transparent performance comparisons between methods. To this end, we created an open-source, anonymized, metropolitan scale, and longitudinal (75 days) dataset of 100,000 individuals' human mobility trajectories, using mobile phone location data provided by Yahoo Japan Corporation (currently renamed to LY Corporation), named YJMob100K. The location pings are spatially and temporally discretized, and the metropolitan area is undisclosed to protect users' privacy. The 90-day period is composed of 75 days of business-as-usual and 15 days during an emergency, to test human mobility predictability during both normal and anomalous situations.

Geometric-based approach for linking various building measurement data to a 3D city model.

Currently, the Ministry of Land, Infrastructure, Transport, and Tourism (Japan) is in the process of developing an open 3D city model known as PLATEAU. Abundant measurement data related to buildings, including maps produced by private companies and mobile mapping system point clouds, have been collected to enhance the value of the 3D city model. To achieve this, it is necessary to identify the buildings for which measurement data is available. In this study, we propose and evaluate an efficient matching method for various building measurement data, primarily using geometric properties. In Numazu city, PLATEAU IDs were assigned to 88,525 Zenrin buildings as part of a private map. The results indicate that 90.6% of the polygons were matched. For aerial images, 93.6% of the extracted buildings matched the PLATEAU buildings, although only 70.9% of the PLATEAU data was extracted from the images. Using the level of detail 1 and 2 models, 46 textured building files were created from the mobile mapping system point cloud. In addition, the cover ratio for the laser profiling point cloud was mostly greater than 40%, which was higher than that of the mobile mapping system.

Real-time classification of longitudinal conveyor belt cracks with deep-learning approach.

Long tunnels are a necessary means of connectivity due to topological conditions across the world. In recent years, various technologies have been developed to support construction of tunnels and reduce the burden on construction workers. In continuation, mountain tunnel construction sites especially pose a major problem for continuous long conveyor belts to remove crushed rocks and rubbles out of tunnels during the process of mucking. Consequently, this process damages conveyor belts quite frequently, and a visual inspection is needed to analyze the damages. Towards this, the paper proposes a model to configure the damage and its size on conveyor belt in real-time. Further, the model also localizes the damage with respect to the length of conveyor belt by detecting the number markings at every 10 meters of the belt. The effectiveness of the proposed framework confirms superior real-time performance with optimized model detecting cracks and number markings with mAP of 0.850 and 0.99 respectively, while capturing 15 frames per second on edge device. The current study marks and validates the versatility of deep learning solutions for mountain tunnel construction sites.

Development of a Large-Scale Roadside Facility Detection Model Based on the Mapillary Dataset.

The detection of road facilities or roadside structures is essential for high-definition (HD) maps and intelligent transportation systems (ITSs). With the rapid development of deep-learning algorithms in recent years, deep-learning-based object detection techniques have provided more accurate and efficient performance, and have become an essential tool for HD map reconstruction and advanced driver-assistance systems (ADASs). Therefore, the performance evaluation and comparison of the latest deep-learning algorithms in this field is indispensable. However, most existing works in this area limit their focus to the detection of individual targets, such as vehicles or pedestrians and traffic signs, from driving view images. In this study, we present a systematic comparison of three recent algorithms for large-scale multi-class road facility detection, namely Mask R-CNN, YOLOx, and YOLOv7, on the Mapillary dataset. The experimental results are evaluated according to the recall, precision, mean F1-score and computational consumption. YOLOv7 outperforms the other two networks in road facility detection, with a precision and recall of 87.57% and 72.60%, respectively. Furthermore, we test the model performance on our custom dataset obtained from the Japanese road environment. The results demonstrate that models trained on the Mapillary dataset exhibit sufficient generalization ability. The comparison presented in this study aids in understanding the strengths and limitations of the latest networks in multiclass object detection on large-scale street-level datasets.

Do open data impact citizens' behavior? Assessing face mask panic buying behaviors during the Covid-19 pandemic.

Data are essential for digital solutions and supporting citizens' everyday behavior. Open data initiatives have expanded worldwide in the last decades, yet investigating the actual usage of open data and evaluating their impacts are insufficient. Thus, in this paper, we examine an exemplary use case of open data during the early stage of the Covid-19 pandemic and assess its impacts on citizens. Based on quasi-experimental methods, the study found that publishing local stores' real-time face mask stock levels as open data may have influenced people's purchase behaviors. Results indicate a reduced panic buying behavior as a consequence of the openly accessible information in the form of an online mask map. Furthermore, the results also suggested that such open-data-based countermeasures did not equally impact every citizen and rather varied among socioeconomic conditions, in particular the education level.

Early warning of COVID-19 hotspots using human mobility and web search query data.

COVID-19 has disrupted the global economy and well-being of people at an unprecedented scale and magnitude. To contain the disease, an effective early warning system that predicts the locations of outbreaks is of crucial importance. Studies have shown the effectiveness of using large-scale mobility data to monitor the impacts of non-pharmaceutical interventions (e.g., lockdowns) through population density analysis. However, predicting the locations of potential outbreak occurrence is difficult using mobility data alone. Meanwhile, web search queries have been shown to be good predictors of the disease spread. In this study, we utilize a unique dataset of human mobility trajectories (GPS traces) and web search queries with common user identifiers (> 450 K users), to predict COVID-19 hotspot locations beforehand. More specifically, web search query analysis is conducted to identify users with high risk of COVID-19 contraction, and social contact analysis was further performed on the mobility patterns of these users to quantify the risk of an outbreak. Our approach is empirically tested using data collected from users in Tokyo, Japan. We show that by integrating COVID-19 related web search query analytics with social contact networks, we are able to predict COVID-19 hotspot locations 1-2 weeks beforehand, compared to just using social contact indexes or web search data analysis. This study proposes a novel method that can be used in early warning systems for disease outbreak hotspots, which can assist government agencies to prepare effective strategies to prevent further disease spread. Human mobility data and web search query data linked with common IDs are used to predict COVID-19 outbreaks. High risk social contact index captures both the contact density and COVID-19 contraction risks of individuals. Real world data was collected from 200 K individual users in Tokyo during the COVID-19 pandemic. Experiments showed that the index can be used for microscopic outbreak early warning.

RDD2020: An annotated image dataset for automatic road damage detection using deep learning.

This data article provides details for the RDD2020 dataset comprising 26,336 road images from India, Japan, and the Czech Republic with more than 31,000 instances of road damage. The dataset captures four types of road damage: longitudinal cracks, transverse cracks, alligator cracks, and potholes; and is intended for developing deep learning-based methods to detect and classify road damage automatically. The images in RDD2020 were captured using vehicle-mounted smartphones, making it useful for municipalities and road agencies to develop methods for low-cost monitoring of road pavement surface conditions. Further, the machine learning researchers can use the datasets for benchmarking the performance of different algorithms for solving other problems of the same type (image classification, object detection, etc.). RDD2020 is freely available at [1]. The latest updates and the corresponding articles related to the dataset can be accessed at [2].

Sky Monitoring System for Flying Object Detection Using 4K Resolution Camera.

The use of drones and other unmanned aerial vehicles has expanded rapidly in recent years. These devices are expected to enter practical use in various fields, such as taking measurements through aerial photography and transporting small and lightweight objects. Simultaneously, concerns over these devices being misused for terrorism or other criminal activities have increased. In response, several sensor systems have been developed to monitor drone flights. In particular, with the recent progress of deep neural network technology, the monitoring of systems using image processing has been proposed. This study developed a monitoring system for flying objects using a 4K camera and a state-of-the-art convolutional neural network model to achieve real-time processing. We installed a monitoring system in a high-rise building in an urban area during this study and evaluated the precision with which it could detect flying objects at different distances under different weather conditions. The results obtained provide important information for determining the accuracy of monitoring systems with image processing in practice.

Non-compulsory measures sufficiently reduced human mobility in Tokyo during the COVID-19 epidemic.

While large scale mobility data has become a popular tool to monitor the mobility patterns during the COVID-19 pandemic, the impacts of non-compulsory measures in Tokyo, Japan on human mobility patterns has been under-studied. Here, we analyze the temporal changes in human mobility behavior, social contact rates, and their correlations with the transmissibility of COVID-19, using mobility data collected from more than 200K anonymized mobile phone users in Tokyo. The analysis concludes that by April 15th (1 week into state of emergency), human mobility behavior decreased by around 50%, resulting in a 70% reduction of social contacts in Tokyo, showing the strong relationships with non-compulsory measures. Furthermore, the reduction in data-driven human mobility metrics showed correlation with the decrease in estimated effective reproduction number of COVID-19 in Tokyo. Such empirical insights could inform policy makers on deciding sufficient levels of mobility reduction to contain the disease.

Crowd Counting with Semantic Scene Segmentation in Helicopter Footage.

Continually improving crowd counting neural networks have been developed in recent years. The accuracy of these networks has reached such high levels that further improvement is becoming very difficult. However, this high accuracy lacks deeper semantic information, such as social roles (e.g., student, company worker, or police officer) or location-based roles (e.g., pedestrian, tenant, or construction worker). Some of these can be learned from the same set of features as the human nature of an entity, whereas others require wider contextual information from the human surroundings. The primary end-goal of developing recognition software is to involve them in autonomous decision-making systems. Therefore, it must be foolproof, which is, it must have good semantic understanding of the input. In this study, we focus on counting pedestrians in helicopter footage and introduce a dataset created from helicopter videos for this purpose. We use semantic segmentation to extract the required additional contextual information from the surroundings of an entity. We demonstrate that it is possible to increase the pedestrian counting accuracy in this manner. Furthermore, we show that crowd counting and semantic segmentation can be simultaneously achieved, with comparable or even improved accuracy, by using the same crowd counting neural network for both tasks through hard parameter sharing. The presented method is generic and it can be applied to arbitrary crowd density estimation methods. A link to the dataset is available at the end of the paper.

Convcast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data.

Nowcasting of precipitation is a difficult spatiotemporal task because of the non-uniform characterization of meteorological structures over time. Recently, convolutional LSTM has been shown to be successful in solving various complex spatiotemporal based problems. In this research, we propose a novel precipitation nowcasting architecture 'Convcast' to predict various short-term precipitation events using satellite data. We train Convcast with ten consecutive NASA's IMERG precipitation data sets each at intervals of 30 minutes. We use the trained neural network model to predict the eleventh precipitation data of the corresponding ten precipitation sequence. Subsequently, the predicted precipitation data are used iteratively for precipitation nowcasting of up to 150 minutes lead time. Convcast achieves an overall accuracy of 0.93 with an RMSE of 0.805 mm/h for 30 minutes lead time, and an overall accuracy of 0.87 with an RMSE of 1.389 mm/h for 150 minutes lead time. Experiments on the test dataset demonstrate that Convcast consistently outperforms other state-of-the-art optical flow based nowcasting algorithms. Results from this research can be used for nowcasting of weather events from satellite data as well as for future on-board processing of precipitation data.

Understanding post-disaster population recovery patterns.

Despite the rising importance of enhancing community resilience to disasters, our understandings on when, how and why communities are able to recover from such extreme events are limited. Here, we study the macroscopic population recovery patterns in disaster affected regions, by observing human mobility trajectories of over 1.9 million mobile phone users across three countries before, during and after five major disasters. We find that, despite the diversity in socio-economic characteristics among the affected regions and the types of hazards, population recovery trends after significant displacement resemble similar patterns after all five disasters. Moreover, the heterogeneity in initial and long-term displacement rates across communities in the three countries were explained by a set of key common factors, including the community's median income level, population, housing damage rates and the connectedness to other cities. Such insights discovered from large-scale empirical data could assist policymaking in various disciplines for developing community resilience to disasters.

Cross-comparative analysis of evacuation behavior after earthquakes using mobile phone data.

Despite the importance of predicting evacuation mobility dynamics after large scale disasters for effective first response and disaster relief, our general understanding of evacuation behavior remains limited because of the lack of empirical evidence on the evacuation movement of individuals across multiple disaster instances. Here we investigate the GPS trajectories of a total of more than 1 million anonymized mobile phone users whose positions were tracked for a period of 2 months before and after four of the major earthquakes that occurred in Japan. Through a cross comparative analysis between the four disaster instances, we find that in contrast to the assumed complexity of evacuation decision making mechanisms in crisis situations, an individual's evacuation probability is strongly dependent on the seismic intensity that they experience. In fact, we show that the evacuation probabilities in all earthquakes collapse into a similar pattern, with a critical threshold at around seismic intensity 5.5. This indicates that despite the diversity in the earthquakes profiles and urban characteristics, evacuation behavior is similarly dependent on seismic intensity. Moreover, we found that probability density functions of the distances that individuals evacuate are not dependent on seismic intensities that individuals experience. These insights from empirical analysis on evacuation from multiple earthquake instances using large scale mobility data contributes to a deeper understanding of how people react to earthquakes, and can potentially assist decision makers to simulate and predict the number of evacuees in urban areas with little computational time and cost. This can be achieved by utilizing only the information on population density distribution and seismic intensity distribution, which can be observed instantaneously after the shock.

Weather effects on the patterns of people's everyday activities: a study using GPS traces of mobile phone users.

This study explores the effects that the weather has on people's everyday activity patterns. Temperature, rainfall, and wind speed were used as weather parameters. People's daily activity patterns were inferred, such as place visited, the time this took place, the duration of the visit, based on the GPS location traces of their mobile phones overlaid upon Yellow Pages information. Our analysis of 31,855 mobile phone users allowed us to infer that people were more likely to stay longer at eateries or food outlets, and (to a lesser degree) at retail or shopping areas when the weather is very cold or when conditions are calm (non-windy). When compared to people's regular activity patterns, certain weather conditions affected people's movements and activities noticeably at different times of the day. On cold days, people's activities were found to be more diverse especially after 10AM, showing greatest variations between 2PM and 6PM. A similar trend is observed between 10AM and midnight on rainy days, with people's activities found to be most diverse on days with heaviest rainfalls or on days when the wind speed was stronger than 4 km/h, especially between 10AM-1AM. Finally, we observed that different geographical areas of a large metropolis were impacted differently by the weather. Using data of urban infrastructure to characterize areas, we found strong correlations between weather conditions upon people's accessibility to trains. This study sheds new light on the influence of weather conditions on human behavior, in particular the choice of daily activities and how mobile phone data can be used to investigate the influence of environmental factors on urban dynamics.