Urban spatial risk prediction and optimization analysis of POI based on deep learning from the perspective of an epidemic

From an epidemiological perspective, previous research on COVID-19 has generally been based on classical statistical analyses. As a result, spatial information is often not used effectively. This paper uses image-based neural networks to explore the relationship between urban spatial risk and the distribution of infected populations, and the design of urban facilities. To achieve this objective, we use spatio-temporal data of people infected with new coronary pneumonia prior to 28 February 2020 in Wuhan. We then use kriging, which is a method of spatial interpolation, as well as core density estimation technology to establish the epidemic heat distribution on fine grid units. We further evaluate the influence of nine major spatial risk factors, including the distribution of agencies, hospitals, park squares, sports fields, banks and hotels, by testing them for significant positive correlation with the distribution of the epidemic. The weights of these spatial risk factors are used for training Generative Adversarial Network (GAN) models, which predict the distribution of cases in a given area. The input image for the machine learning model is a city plan converted by public infrastructures, and the output image is a map of urban spatial risk factors in the given area. The results of the trained model demonstrate that optimising the relevant point of interests (POI) in urban areas to effectively control potential risk factors can aid in managing the epidemic and preventing it from dispersing further.

Spatiotemporal patterns and spatial risk factors for visceral leishmaniasis from 2007 to 2017 in Western and Central China: A modelling analysis

Visceral leishmaniasis (VL) is a neglected disease caused by trypanosomatid protozoa in the genus Leishmania, which is transmitted by phlebotomine sandflies. Although this vector-borne disease has been eliminated in several regions of China during the last century, the reported human VL cases have rebounded in Western and Central China in recent decades. However, understanding of the spatial epidemiology of the disease remains vague, as the spatial risk factors driving the spatial heterogeneity of VL. In this study, we analyzed the spatiotemporal patterns of annual human VL cases in Western and Central China from 2007 to 2017. Based on the related spatial maps, the boosted regression tree (BRT) model was adopted to explore the relationships between VL and spatial correlates as well as predicting both the existing and potential infection risk zones of VL in Western and Central China. The mined links reveal that elevation, minimum temperature, relative humidity, and annual accumulated precipitation make great contributions to the spatial heterogeneity of VL. The maps show that Xinjiang Uygur Autonomous Region, Gansu, western Inner Mongolia Autonomous Region, and Sichuan are predicted to fall in the highest infection risk zones of VL. Approximately 61.60 million resident populations lived in the high-risk regions of VL in Western and Central China. Our results provide a better understanding of how spatial risk factors driving VL spread as well as identifying the potential endemic risk region of VL, thereby enhancing the biosurveillance capacity of public health authorities.

Forecasting homicide in the red stick: Risk terrain modeling and the spatial influence of urban blight on lethal violence in Baton Rouge, Louisiana

Incorporating features of the built environment, risk terrain modeling (RTM), is used to predict future criminal events in micro-units (i.e., city blocks). The current study examines the application of RTM to forecast homicide in the capital city of Baton Rouge, Louisiana while including a novel environmental risk factor, blighted properties. Based upon the extant literature and knowledge of the city, eighteen environmental risk factors are expected to spatially influence homicide. Results indicate that places most at risk of experiencing a homicide are located in areas where blighted properties are concentrated and in close proximity to convenience stores. RTM successfully identities and evaluates environmental risk factors that spatially influence lethal violence. Additionally, RTM is able to accurately forecast future acts of homicide. The results underscore how crime prevention through environmental design (CPTED) and blight remediation could be utilized as straightforward and prudent strategies to reduce lethal violence.

Spatial and risk factor analysis of bovine viral diarrhoea (BVD) virus after the first-year compulsory phase of BVD eradication programme in Northern Ireland

Bovine viral diarrhoea virus (BVDV) causes bovine viral diarrhoea (BVD), which is a contagious pathogen that can have a significant economic impact on cattle industries. In Northern Ireland (NI), the compulsory phase of a BVD eradication programme was implemented in 2016. The aim of this retrospective population based study was to utilize herd-level data after the first year of the compulsory phase (March 2016-March 2017) to determine the spatial distribution and variation of BVDV, to identify clusters of infection, and to quantify some risk factors associated with BVD in NI. Global spatial clustering (autocorrelation) and local spatial hot-spot analyses were used to specify the clustering areas (hot- and cold-spot). A suite of multivariable logistic analyses was performed to estimate the associations of spatial and non-spatial factors (relating to herd characteristics) with the risk of being a BVDV positive herd. Final models were compared by evaluating the model fit and the ability to account for spatial autocorrelation in the study area. There were 17,186 herds included in the analysis. The herd-level prevalence of BVDV was 11.31%. Significant spatial clustering of BVDV positive herds was presented in the central region of NI. A mixed effects logistic model, with a spatial random effect term, was considered the best model. The final model showed that a positive BVDV status during the voluntary phase prior to the compulsory phase started (OR = 2.25; CI 95% = 1.85-2.73), larger herd size (OR = 6.19; CI 95% = 5.22-7.34 for herd size > 100 animals) and a larger number of positive nearest neighbours within 4 km radius (OR = 1.24; CI 95% = 1.05-1.47 for 8-9 neighbours and OR = 1.41; CI 95% = 1.20-1.65 for 10-12 neighbours) were significantly related to the risk of a herd being tested positive for BVDV. The clear spatial pattern from the local spatial clustering analyses could be used for targeted surveillance and control measures by focusing on the central region of NI.

Relative associations of cattle movements, local spread, and biosecurity with bovine viral diarrhoea virus (BVDV) seropositivity in beef and dairy herds

The success of bovine viral diarrhoea virus (BVDV) eradication campaigns can be undermined by spread through local transmission pathways and poor farmer compliance with biosecurity recommendations. This work combines recent survey data with cattle movement data to explore the issues likely to impact on the success of BVDV control in Scotland. In this analysis, data from 249 beef suckler herds and 185 dairy herds in Scotland were studied retrospectively to determine the relative influence of cattle movements, local spread, and biosecurity on BVDV seropositivity. Multivariable logistic regression models revealed that cattle movement risk factors had approximately 3 times greater explanatory power than risk factors for local spread amongst beef suckler herds, but approximately the same explanatory power as risk factors for local spread amongst dairy herds. These findings are most likely related to differences in cattle husbandry practices and suggest that where financial prioritization is required, focusing on reducing movement-based risk is likely to be of greatest benefit when applied to beef suckler herds. The reported use of biosecurity measures such as purchasing cattle from BVDV accredited herds only, performing diagnostic screening at the time of sale, implementing isolation periods for purchased cattle, and installing double fencing on shared field boundaries had minimal impact on the risk of beef or dairy herds being seropositive for BVDV. Only 28% of beef farmers and 24% of dairy farmers with seropositive herds recognized that their cattle were affected by BVDV and those that did perceive a problem were no less likely to sell animals as replacement breeding stock and no more likely to implement biosecurity measures against local spread than farmers with no perceived problems. In relation to the current legislative framework for BVDV control in Scotland, these findings emphasize the importance of requiring infected herds take appropriate biosecurity measures to prevent further disease transmission and conducting adequate follow-up to ensure that biosecurity measures are being implemented correctly in the field.