Travel route planning method to avoid epidemic hot-spots in the post-epidemic era

The Chinese government adhered to the "dynamic clearance” epidemic prevention strategy from August 2021 to December 7, 2022, during the post-epidemic era (this study started in March 2022 and ended in September 2022). People are gradually resuming their daily routines, and demand for travel is rising again. Nonetheless, the epidemic occasionally breaks out on a smaller scale, causing social concern. As a social reaction, the essential issue is how to avoid COVID-19 hot-spots effectively by offering secure travel options for local residents who tend to travel privately. Two travel route planning models are proposed to avoid COVID-19 hot-spots based on the invalid road sections which are affected by epidemic. Specifically, the static model aims at generating the shortest travel distance after detours, with the constraint of avoiding COVID-19 hot-spots;the dynamic model takes real-time data into account, which includes epidemic risk levels, road grades, and real-time traffic information on road selection. Shenzhen, China, is illustrated as an example of the research area in this paper. To assess the effectiveness and efficiency of the suggested approaches, data regarding the road network, the prevalence of epidemics, and traffic congestion are collected. The experimental results demonstrate that 1) the proposed two route planning models can effectively bypass areas with high levels of epidemic risk. 2) The static route planning model increases the travel distance by 12.24% and 13.03%, while the dynamic route planning model increases the travel distance by 24.33% and 27.69% compared with the conventional shortest route, given the same origin and destination and the same impact radii of the COVID-19 hot-spots (300 and 500 m respectively). When taking detour routes to avoid COVID-19 hot-spots, the average increase in trip distance does not surpass 50%, which is acceptable psychologically for travelers. 3) The static travel route planning model is suitable for the severe epidemic situation for it can strictly avoid the epidemic hot-spots;The dynamic travel route planning model is applicable to the situation where the epidemic situation is relatively mild. Ultimately, the route planning models can be utilized to develop a framework to provide travelers with detour options, which would make a practical difference to ensure travelers' safety during traveling and contribute to preventing the spread of the epidemic. © 2023 The Author(s)

Automatic 3D Building Reconstruction from OpenStreetMap and LiDAR Using Convolutional Neural Networks.

This paper presents the implementation of an automatic method for the reconstruction of 3D building maps. The core innovation of the proposed method is the supplementation of OpenStreetMap data with LiDAR data to reconstruct 3D urban environments automatically. The only input of the method is the area that needs to be reconstructed, defined by the enclosing points in terms of the latitude and longitude. First, area data are requested in OpenStreetMap format. However, there are certain buildings and geometries that are not fully received in OpenStreetMap files, such as information on roof types or the heights of buildings. To complete the information that is missing in the OpenStreetMap data, LiDAR data are read directly and analyzed using a convolutional neural network. The proposed approach shows that a model can be obtained with only a few samples of roof images from an urban area in Spain, and is capable of inferring roofs in other urban areas of Spain as well as other countries that were not used to train the model. The results allow us to identify a mean of 75.57% for height data and a mean of 38.81% for roof data. The finally inferred data are added to the 3D urban model, resulting in detailed and accurate 3D building maps. This work shows that the neural network is able to detect buildings that are not present in OpenStreetMap for which in LiDAR data are available. In future work, it would be interesting to compare the results of the proposed method with other approaches for generating 3D models from OSM and LiDAR data, such as point cloud segmentation or voxel-based approaches. Another area for future research could be the use of data augmentation techniques to increase the size and robustness of the training dataset.

Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection.

Humans rely on clean water for their health, well-being, and various socio-economic activities. During the past few years, the COVID-19 pandemic has been a constant reminder of about the importance of hygiene and sanitation for public health. The most common approach to securing clean water supplies for this purpose is via wastewater treatment. To date, an effective method of detecting wastewater treatment plants (WWTP) accurately and automatically via remote sensing is unavailable. In this paper, we provide a solution to this task by proposing a novel joint deep learning (JDL) method that consists of a fine-tuned object detection network and a multi-task residual attention network (RAN). By leveraging OpenStreetMap (OSM) and multimodal remote sensing (RS) data, our JDL method is able to simultaneously tackle two different tasks: land use land cover (LULC) and WWTP classification. Moreover, JDL exploits the complementary effects between these tasks for a performance gain. We train JDL using 4,187 WWTP features and 4,200 LULC samples and validate the performance of the proposed method over a selected area around Stuttgart with 723 WWTP features and 1,200 LULC samples to generate an LULC classification map and a WWTP detection map. Extensive experiments conducted with different comparative methods demonstrate the effectiveness and efficiency of our JDL method in automatic WWTP detection in comparison with single-modality/single-task or traditional survey methods. Moreover, lessons learned pave the way for future works to simultaneously and effectively address multiple large-scale mapping tasks (e.g., both mapping LULC and detecting WWTP) from multimodal RS data via deep learning.

OSM Science—The Academic Study of the OpenStreetMap Project, Data, Contributors, Community, and Applications

This paper is an Editorial for the Special Issue titled “OpenStreetMap as a multidisciplinary nexus: perspectives, practices and procedures”. The Special Issue is largely based on the talks presented in the 2019 and 2020 editions of the Academic Track at the State of the Map conferences. As such, it represents the most pressing and relevant issues and topics considered by the academic community in relation to OpenStreetMap (OSM)—a global project and community aimed to create and maintain a free and editable database and map of the world. In this Editorial, we survey the papers included in the Special Issue, grouping them into three research perspectives: applications of OSM for studies within other disciplines, OSM data quality, and dynamics in OSM. This survey reveals that these perspectives, while being distinct, are also interrelated. This calls for the formalization of an ‘OSM science’ that will provide the conceptual grounds to advance the scientific study of OSM, not as a set of individualized efforts but as a unified approach.

GazPNE2: A general place name extractor for microblogs fusing gazetteers and pretrained transformer models

The concept of ‘human as sensors’defines a new sensing model, in which humans act as sensors by contributing their observations, perceptions, and sensations. This is crucial for the development of social Internet of Things, which is an integral part of Cyber-Physical-Social systems. Online social media platforms, as the most active places where users act as social sensors, are responsive to real-world events and are useful for gathering situational information in real-time. Unfortunately, posts rarely contain structured geographic information, thus hindering their usage for contributing to various challenges, such as emergency response. We address this limitation by introducing a general approach for extracting place names from tweets, named GazPNE2. It combines global gazetteers (i.e., OpenStreetMap and GeoNames), deep learning, and pretrained transformer models (i.e., BERT and BERTweet), which requires no manually annotated data. It can extract place names at both coarse (e.g., city) and fine-grained (e.g., street and POI) levels and place names with abbreviations. To fully evaluate GazPNE2 and compare it with 11 competing approaches, we use 19 public tweet datasets, containing 38,802 tweets and 22,197 places across the world. The results show GazPNE2 achieves much higher F1 (0.8) than the other approaches. Furthermore, we apply GazPNE2 to three large unannotated tweet datasets related to over 20 crisis events (e.g., COVID-19), containing 560,040 tweets. An F1 of 0.84 is achieved on 3,000 tweets, which are randomly selected from the three datasets and then manually annotated. Code and data are available on GitHub page: https://github.com/uhuohuy/GazPNE2. IEEE

Street masking: a network-based geographic mask for easily protecting geoprivacy.

BACKGROUND: Geographic masks are techniques used to protect individual privacy in published maps but are highly under-utilized in research. This leads to continual violations of individual privacy, as sensitive health records are put at risk in unmasked maps. New approaches to geographic masking are required that foster accessibility and ease of use, such that they become more widely adopted. This article describes a new geographic masking method, called street masking, that reduces the burden on users of finding supplemental population data by instead automatically retrieving OpenStreetMap data and using the road network as a basis for masking. We compare it to donut geomasking, both with and without population density taken into account, to evaluate its efficacy against geographic masks that require slightly less and slightly more supplemental data. Our analysis is performed on synthetic data in three different Canadian cities. RESULTS: Street masking performs similarly to population-based donut geomasking with regard to privacy protection, achieving comparable k-anonymity values at similar median displacement distances. As expected, distance-based donut geomasking performs worst at privacy protection. Street masking also performs very well regarding information loss, achieving far better cluster preservation and landcover agreement than population-based donut geomasking. Distance-based donut geomasking performs similarly to street masking, though at the cost of reduced privacy protection. CONCLUSION: Street masking competes with, if not out-performs population-based donut geomasking and does so without requiring any supplemental data from users. Moreover, unlike most other geographic masks, it significantly minimizes the risk of false attribution and inherently takes many geographic barriers into account. It is easily accessible for Python users and provides the foundation for interfaces to be built for non-coding users, such that privacy can be better protected in sensitive geospatial research.