Spatial prediction of sparse events using a discrete global grid system;a case study of hate crimes in the USA

Spatial prediction of any geographic phenomenon can be an intractable problem.Predicting sparse and uncertain spatial events related to many influencing factors necessitates the integration of multiple data sources.We present an innovative approach that combines data in a Discrete Global Grid System(DGGS)and uses machine learning for analysis.A DGGS provides a structured input for multiple types of spatial data,consistent over multiple scales.This data framework facilitates the training of an Artificial Neural Network(ANN)to map and predict a phenomenon.Spatial lag regression models(SLRM)are used to evaluate and rank the outputs of the ANN.In our case study,we predict hate crimes in the USA.Hate crimes get attention from mass media and the scientific community,but data on such events is sparse.We trained the ANN with data ingested in the DGGS based on a 50%sample of hate crimes as identified by the Southern Poverty Law Center(SPLC).Our spatial prediction is up to 78%accurate and verified at the state level against the independent FBI hate crime statistics with a fit of 80%.The derived risk maps are a guide to action for policy makers and law enforcement.

Monitoring the built-up environment of Shanghai on the street-block level using SAR and volunteered geographic information

In this geo-statistical analysis of change detection,we illustrate the evolution of the built-up environment in Shanghai at the street-block level.Based on two TerraSAR-X image stacks with 36 and 15 images,covering the city centre of Shanghai for the time period from 2008 to 2015,a set of coherence images was created using a small baseline approach.The road network from Open Street Map,a volunteered geographic information product,serves as the input dataset to create street-blocks.A street-block is surrounded by roads and resembles a ground parcel,a real estate property–a cadastral unit.The coherence information is aggregated to these street-blocks for each observation and the variation is analysed over time.An analysis of spatial autocorrelation reveals clusters of similar behaviours.The result is a detailed map of Shanghai highlighting areas of change.We argue that the aggregation and grouping of synthetic aperture radar coherence image information to real-world entities(street-blocks)is comprehensible and relevant to the urban planning process.Therefore,this research is a contribution to the community of urban planners,designers,and government agencies who want to monitor the development of the urban landscape.