Risk Terrain Modeling Research Articles

Applying Crime Pattern Theory and Risk Terrain Modeling to Examine Environmental Crime in Cambodia

The spatial-temporal analysis of crime has significantly evolved. One innovative technique recently developed is risk terrain modeling (RTM). RTM, however, has yet to be used for environmental crime. This research applies RTM and draws from crime pattern theory to examine illegal activities in two protected areas in Cambodia. Findings suggest that pathways, edges, areas with suitable targets, conservation posts, landcover, and prior incidents are related to fauna- and flora-related illegal activities, though this relationship varies by season, units of analysis, and study area (i.e., patrol-based compared with official designation). Implications for theory and policy are outlined.

Risk of robbery in a tourist destination: a monthly examination of Atlantic City, New Jersey

Purpose The purpose of this study is to identify potential changes in crime generators and attractors based on monthly models in a high-tourist destination. Design/methodology/approach A risk terrain modeling approach was used to assess spatial relationships between 27 crime generator and attractor types in Atlantic City, New Jersey with robbery occurrence for the 2015 calendar year. In total, 12 separate monthly models were run to identify changes in risk factors based on the month of the year. Findings Results indicated unique significant risk factors based on the month of the year. Over the warmer and summer months, there was a shift in environmental risk factors that falls in line with more of a change in routine activities for residents and tourists and related situational contexts for the crime. Practical implications The analytical approach used in the current study could be used by police departments and jurisdictions to understand types of crime generators and attractors influencing local crime occurrence. Subsequent analyses were used by Atlantic City Police Department to direct place-based policing efforts. Originality/value With growing crime and place research that accounts for temporal scales, the authors advance these endeavors by focusing on a tourist destination, Atlantic City, New Jersey.

Comparison of near-Repeat, Machine Learning and Risk Terrain Modeling for Making Spatiotemporal Predictions of Crime

The main objective of this study is to test and compare the prediction performance of three of the most common predictive policing methods. A near-repeat model, a supervised machine learning model, and a risk terrain model are tested and compared against each other using retrospective analysis of home burglary crime data from a Belgian city. Hotspot analysis is included as a baseline. Predictions are made for three different months (January, May and September 2017) to account for seasonal differences. Variations in spatial context (city center vs. suburbs) and the number of predicted risk locations are also tested. Prediction performance is measured using accuracy, near-hit rate, precision and F1-score. The results show that there are some notable differences in prediction performance between the model types across the tested variations. In general, the ensemble model tends to be the most consistent high performer across all tested variations. Also notable is that hotspot analysis is not clearly outperformed by the other methods. The different methods have their own strengths and weaknesses and optimal prediction performance crucially depends on the specific location context. More comparative analyses of predictive policing methods in different contexts are needed to gain a more complete picture. Future research could also focus on how combining methods can help improve crime prediction performance.

Pharmacies and features of the built environment associated with opioid overdose: A geospatial comparison of rural and urban regions in Alabama, USA

Elements of the physical environment have been shown to influence health behaviors including drug use and overdose mortality. Throughout the opioid epidemic in the United States, rural regions have been disproportionately affected by opioid overdose. Although the relationship between the urban built environment and opioid overdose has been established, little is known as to how trends may differ in rural areas. Risk terrain modeling was usedas a spatial analytical approachto assess environmental features thatsignificantly increasethe risk of opioid overdose in Jefferson County, Alabama. Spatial risk assessmentswere conducted for urban and rural regions as well as for the county as a whole. Criminogenic, opioid-related, and community variables were includedand compared across spatial risk models. The geographic context, rural or urban, influenced the relationship between environmental features and opioid overdose.In rural areas, community features such as bus stops and public schools were related to the occurrence of opioid overdose. In urban areas,inpatient treatment centers, transitional living facilities, express loan establishments, and liquor vendors were significantly related to the locations of opioid overdose. Risk terrain modeling can be used to locate high-risk areas for opioid overdosewhile identifying factors that are contributing to the risk of events occurring in communities. The patterns of overdose risk differ in rural and urban contexts and may be used to inform the placement of treatment and prevention resources.

Cholera deaths in Soho, London, 1854: Risk Terrain Modeling for epidemiological investigations.

Risk Terrain Modeling (RTM) is a spatial analysis technique used to diagnose environmental conditions that lead to hazardous outcomes. Originally developed for applications to violent crime analysis, RTM is utilized here to analyze Dr. John Snow’s data from the 1854 cholera outbreak in London to demonstrate its potential value to contemporary epidemiological investigations. Dr. Snow saved countless lives when he traced the source of the cholera outbreak to a specific water pump through inductive reasoning, which he communicated through maps and spatial evidence. His methods have since inspired several fields of scientific inquiry. Informed by the extant research on RTM, we speculated that it could have helped test Dr. Snow’s hypothesis about cholera and empirically identified the sole source of contaminated well water. We learned that it could and, although it was not available to Dr. Snow in the 1800s, we discuss RTM’s implications for present-day research and practice as it relates to the analysis, prevention and treatment of cholera and other public health threats around the world.

Exploring the geography of suicide threats and suicide attempts: An application of Risk Terrain Modeling.

The purpose of this research is twofold: first, the spatial distribution of 911 emergency calls for service to the police for suicides in progress and threats of suicide in the City of Detroit, Michigan will be explored to determine whether these events exhibit different patterns of spatial clustering. Second, this research will explore the utility of Risk Terrain Modeling (RTM) to assist in our understanding of the locations of calls for service to the police related to suicide threats and suicides in progress. The results suggest that these events are different social phenomenon, both with respect to the spatial clustering of these events as well as qualitative differences in the environmental factors that may contribute to their occurrence.

Can we Trust Crime Predictors and Crime Categories? Expansions on the Potential Problem of Generalization

City-driven open data initiatives have made spatially referenced crime and risk factor data more readily available online, allowing for significance tests to determine the relationship between environment and crime. This paper uses a variety of open source data to assess risk factors for specific violent crime types (assault, homicide, rape, robbery) in three different cities. The results contribute to our understanding of 1) variation in intra-city risk factors for each violent crime type, 2) the degree of spatial overlap for high-risk places for each violent crime type within a city, and 3) the generalizability of risk factors across crime types and cities. Risk Terrain Modeling (RTM) was used to determine the risk factors associated with each crime type at the micro-level and conjunctive analyses of case configurations (CACC) determined the unique behavior settings at the highest risk for each specific violent crime in each city. The findings indicate that intra-city risk factors vary greatly for each violent crime, highrisk places for different violent crimes tend to not overlap spatially within a city, and risk factors are not generalizable across crime types or across cities. Researchers and law enforcement need to examine local, crime-specific contexts when assessing crime problems and generating solutions.

Crime in an Affluent City: Applications of Risk Terrain Modeling for Residential and Vehicle Burglary in Coral Gables, Florida, 2004–2016

Risk Terrain Modeling (RTM) — an innovative geospatial approach to analyze the locations of high crime areas within cities— was used to analyze criminogenic spaces and identify the riskiest places contributing to vehicle and residential burglary in the city of Coral Gables, Florida from 2004 to 2016. Official crime incident data on residential and vehicle burglary were provided by the Coral Gables Police Department. We investigated the role of environmental predictors of crime by analyzing the effects of the designated riskiest places including alcohol vendors, car dealers, gas stations, bars, secondary/post-secondary schools, grocery stores, and restaurants. We identified risky places and their proximity to the occurrence of residential and vehicle burglary with a regression process using the RTM technique to determine the Relative Risk Values (i.e., weighted risk) that each risk factor had. We examined different temporal designations, including day and night, day of the week, and monthly intervals. Our results indicated that restaurants and grocery stores located in the downtown area and along the US 1 highway were higher risk locations for the occurrence of both types of crime throughout the city. The locations of risky places in the study area were spatially consistent with high crime areas, supporting our main hypothesis. The use of RTM with targeted community policing strategies could move policy from a reactionary approach to more proactive solutions to crime prevention. Concepts drawn from routine activity theory, as well as crime and place perspectives, both receive moderate empirical support for vehicle and residential burglary outcomes.

Risk Terrain Modeling: Seasonality and Predictive Validity

This study focuses on crimes involving firearms in Baltimore, Maryland to answer three research questions concerning the effect of seasonality: (1) Do changes in the seasons affect which spatial factors are significantly related to crime?; (2) Does risk terrain modeling have predictive validity on a short-term basis?; and (3) Are the same areas high-risk throughout the year? To accomplish this, the authors ran twelve monthly risk terrain models and one yearly risk terrain model. The study found that risk factors vary by month and that monthly and yearly spatial risk factors do not necessarily overlap. The study also found that risk terrain models retain their predictive validity on a short-term basis. The results are further discussed in relation to whether the same areas are high-risk throughout the course of the year.

Using risk terrain modeling to predict homeless related crime in Los Angeles, California

We apply Risk Terrain Modeling (RTM) to identify the factors that predict homeless related crime at micro grid cells in Los Angeles, CA. We find that place based factors predicting whether homeless individuals are victimized or the offender being homeless are largely consistent with one another. Out of 26 different crime attractors and generators, prior drug arrests, homeless shelters, and bus stops are the three biggest factors in predicting homeless related crime. We show how the RTM model can effectively forecast future homeless related crimes as well. This suggests that targeted spatial strategies can reduce both homeless offending and victimization risk. Given that the majority of homeless individuals are only intermittently homeless, place based strategies may be a more an effective way to limit risk than strategies that focus on individuals.

Using Vulnerability and Exposure to Improve Robbery Prediction and Target Area Selection

A large body of research has found that crime is much more likely to occur at certain places relative to others. Attempting to capitalize on this finding to maximize crime prevention, many police administrators have sought to narrow their department’s operational focus and allocate resources and attention to the most problematic locations. However, in the face of a growing number of technological advances in crime forecasting that have facilitated this trend, it is still unclear how to best identify the most appropriate set of places to which resources and attention should be directed. Our goal was to examine this issue by exploring the ways in which spatial vulnerabilities and exposures could be used to identify the best target areas for policing. Using the Theory of Risky Places as a guide, we employed kernel density estimation (KDE) to measure crime exposures and risk terrain modeling (RTM) to identify crime vulnerabilities with the expectation that crime would be predicted more accurately by integrating the outputs from these two methods. To test this hypothesis, our analysis utilized 1 year of data on street robbery in Brooklyn, New York. A common metric, the prediction accuracy index (PAI), was computed for KDE, RTM, and the integrated approach, over 1 month and 3 month intervals. We found that the integrated approach, on average and most frequently, produces the most accurate predictions. These results demonstrate that place-based policing and related policies can be improved via actionable intelligence produced from multiple crime analysis tools that are designed to measure unique aspects of the spatial dynamics of crime.

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.

Aggravating effects of alcohol outlet types on street robbery and aggravated assault in New York City

ABSTRACTThe present study uses Risk Terrain Modeling (RTM) to analyze how nine different alcohol outlet types differentially influence the likelihood of aggravated assault and street robbery at micro-level places in New York City. Separate models were conducted for each of New York’s five boroughs to account for the differing environmental characteristics across the city. Results suggest that spatial influence of crime risk differed across alcohol outlet types, with off-premise grocery stores having the largest influence on the likelihood of both aggravated assault and street robbery and on-premise bars/taverns having a strong influence only on the likelihood of street robbery. In addition, although certain alcohol outlets affected crime in each borough, the spatial influence of others was more volatile. It is clear not all alcohol outlet types are equally criminogenic across boroughs. Thus, crime reduction efforts should be unique and localized according to the risk associated with outlet types and place.

Risk terrain modeling for road safety: identifying crash-related environmental factors in the province of Cádiz, Spain

Environmental Criminology has developed a robust framework that provides the scientific support and necessary foundation for crime analysis through crime mapping. This theoretical approach focuses on the situational and temporal characteristics of criminal opportunity rather than on the offender’s behavior for crime prevention. In the scope of road safety and traffic crashes, few studies have adopted this approach. This study used risk terrain modeling (RTM), developed by the Rutgers Center on Public Security, to determine the relative importance of varying environmental risk factors on alcohol-related crashes and traffic accidents. The independent variables consisted of a set of potential environmental risk factors, while the dependent variable comprised all DWI crashes and traffic accidents in the province of Cadiz in 2012. According to the results of the current study, restaurant locations are spatially associated with the occurrence of drunk driving crashes, while proximity restaurants and recreational lodging centers correlate with the sites of traffic accidents.

Enhancing Data-Driven Law Enforcement Efforts: Exploring how Risk Terrain Modeling and Conjunctive Analysis Fit in a Crime and Traffic Safety Framework

Law enforcement’s examination of vehicle crashes is often nested in the Data-Driven Approaches to Crime and Traffic Safety (DDACTS) framework which highlights the importance of hot spot analysis. To assist law enforcement efforts, this study explores how two additional spatial techniques, namely risk terrain modeling (RTM) and conjunctive analysis of case configurations (CACC), could be incorporated within the DDACTS framework. RTM was utilized to identify how the built, physical environment contributed to the risk of traffic incidents. RTM identified 6 risk factors related to the occurrence of vehicle crashes, and high-risk places were compared to hot spots on predictive accuracy. CACC was used to explore configurations likely to result in traffic incidents for the priority places. Our findings support the Theory of Risky Places and fit within a vulnerability-exposure framework, providing law enforcement with guidance for identifying places where vehicle crashes are likely to occur in the future. In addition to providing insight for law enforcement, we discuss how law enforcement can develop working partnerships with stakeholders capable of preventing and/or reducing traffic incidents, which is in line with the general DDACTS framework.

Gang violence predictability: Using risk terrain modeling to study gang homicides and gang assaults in East Los Angeles

PurposeThe current study investigates the application of risk terrain modeling (RTM) to forecast gang violence. RTM is routinely utilized to predict future criminal events in micro-units (i.e., city blocks) based upon features of the physical environment. The particular focus of the current study is RTM's ability to separately predict future gang assaults and gang homicides in the Los Angeles Police Department's (LAPD) Hollenbeck Community Policing Area. MethodGuided by the existing gang literature and knowledge of the region, 22 environmental risk factors are anticipated to spatially influence gang assaults and gang homicides. An RTM is established for 2009 gang assaults and 2009–2011 gang homicides. The RTM is then used to predict 2012 gang assaults and 2012 gang homicides respectively. ResultsPlaces most at risk of experiencing a gang assault are in close proximity to where gang members are frequently observed loitering by police and Metro rail stops while also contending with residential concentrations of local gang members. Areas most at risk of experiencing a gang homicide cope with residential concentrations of local gang members and gang set space. The ability for RTM to successfully forecast future gang violence may be limited. ConclusionsRTM is able to successfully identify and evaluate meaningful environment risk factors that spatially influence gang assaults and gang violence. However, the ability for RTM to successfully forecast future gang violence may be limited.

Utilizing a Risk of Crime Measure for Recidivism Research: Moving Environmental Corrections Forward

The current study expands recidivism research by developing a risk of crime (ROC) measure rooted in environmental criminology, reflecting the risk of criminal opportunities, and lending itself to environmental corrections. Data were collected from a city in the Northeast region of the United States. The ROC measure was constructed through risk terrain modeling and reflected a parolee-specific neighborhood ROC. Conjunctive analysis of case configurations was utilized to explore how individual characteristics interacted with the ROC measure. Results indicated a relationship between parolees residing in an elevated ROC neighborhood and the likelihood of recidivism. The results were discussed in relation to how environmental criminology could be further integrated into environmental corrections, accounting for physical and social characteristics of the backcloth.

Predicting Property Crime Risk: an Application of Risk Terrain Modeling in Vancouver, Canada

Research on the spatial dimension of crime has developed significantly over the past few decades. An important aspect of this research is the visualization of this dimension and its underlying risk across space. However, most methods of such visualization, and subsequent analyses, only consider crime data or, perhaps, a population at risk in a crime rate. Risk terrain modeling (RTM) provides an alternative to such methods and can incorporate the entire environmental backcloth, data permitting. To date, the RTM literature has dominantly focused on violent crime in the United States. In this paper, we apply RTM to property crime victimization (residential burglary) in Vancouver, Canada. We are able to show that not only does RTM have applicability in a Canadian context but provides insight into nonviolent victimization.

Predicting Dynamical Crime Distribution From Environmental and Social Influences

Understanding how social and environmental factors contribute to the spatio-temporal distribution of criminal activities is a fundamental question in modern criminology. Thanks to the development of statistical techniques such as Risk Terrain Modeling (RTM), it is possible to evaluate precisely the criminogenic contribution of environmental features to a given location. However, the role of social information in shaping the distribution of criminal acts is largely understudied by the criminological research literature. In this paper we investigate the existence of spatio-temporal correlations between successive robbery events, after controlling for environmental influences as estimated by RTM. We begin by showing that a robbery event increases the likelihood of future robberies at and in the neighborhood of its location. This event-dependent influence decreases exponentially with time and as an inverse function of the distance to the original event. We then combine event-dependence and environmental influences in a simulation model to predict robbery patterns at the scale of a large city (Newark, NJ). We show that this model significantly improves upon the predictions of RTM alone and of a model taking into account event-dependence only when tested against real data that were not used to calibrate either model. We conclude that combining risk from exposure (past event) and vulnerability (environment) when modeling crime distribution can improve crime suppression and prevention efforts by providing more accurate forecasting of the most likely locations of criminal events.

Risk Terrain Modeling and Socio-Economic Stratification: Identifying Risky Places for Violent Crime Victimization in Bogotá, Colombia

This research focused on the effect of the built environment on Bogota’s violent crime by using the Risk Terrain Modeling (RTM) technique. The current study used 17 ecological variables, including micro-level data on the spatial distribution of socio-economic strata, and the location of an array of businesses and other features of the landscape. As suggested by the results of this study, the spatial distribution of violent crime in Bogota is highly correlated with the allocation of socio-economic strata throughout its geography. A statistically valid RTM analysis identified the micro-level risk factors associated with three types of violent crime incidents, namely homicide, assault, and theft incidents. These results suggest that future violent crime incidents are more likely to occur at a reduced number of high-risk micro-places. Moreover, while homicide and assault incidents were more likely to cluster within the poorest areas of the city, theft incidents presented a higher risk of victimization near the city center, where economic activity and suitable targets concentrate. This study offers a unique account regarding the effect of socio-economic segregation on violent crime victimization across Bogota’s geography and within different socio-economic strata classifications.