Scholarlink

<p>Wildlife criminal activity exhibits distinct spatial patterns influenced by environmental and anthropogenic drivers. This study applies Maximum Entropy (MaxEnt) modelling, a presence-only and robust machine learning technique originally designed for species distribution, to estimate the potential distribution of suitable sites based on recorded wildlife crime incidents, in Gonarezhou National Park (GNP), Zimbabwe. A total of 1,305 georeferenced crime incident locations were analysed alongside a suite of environmental predictors including elevation, slope, Normalised Difference Vegetation Index (NDVI), distance to roads, distance to settlements, distance to water bodies, and distance to park boundary. The model achieved an Area Under Curve (AUC) of 0.9, indicating excellent predictive performance. Among the predictors, elevation, distance to settlements and roads emerged as the most influential variables. The spatial distribution of crime suite ability revealed heightened crime risk near park boundaries and adjacent communities, reflecting the interplay between terrain, accessibility, and land-use gradients as key determinants for wildlife crime. These findings highlight the value of integrating ecological modelling techniques into conservation criminology and support the implementation of spatially targeted law enforcement strategies within protected areas. The resulting surface reflects spatial patterns of recorded incidents influenced by patrol detection effort rather than unbiased estimates of actual crime occurrence.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating environmental and anthropogenic drivers in MaxEnt models to understand the spatial patterns of wildlife crime

  • 期刊论文

  • 发表日期：

    2026年7月6日

查看全文
  • Cliff Jawe,
  • Mark Zvidzai,
  • Honour Chinoitezvi,
  • Patience Gandiwa,
  • Paul Dzikiti,
  • Ratidzo Blessing Mapfumo

摘要

Wildlife criminal activity exhibits distinct spatial patterns influenced by environmental and anthropogenic drivers. This study applies Maximum Entropy (MaxEnt) modelling, a presence-only and robust machine learning technique originally designed for species distribution, to estimate the potential distribution of suitable sites based on recorded wildlife crime incidents, in Gonarezhou National Park (GNP), Zimbabwe. A total of 1,305 georeferenced crime incident locations were analysed alongside a suite of environmental predictors including elevation, slope, Normalised Difference Vegetation Index (NDVI), distance to roads, distance to settlements, distance to water bodies, and distance to park boundary. The model achieved an Area Under Curve (AUC) of 0.9, indicating excellent predictive performance. Among the predictors, elevation, distance to settlements and roads emerged as the most influential variables. The spatial distribution of crime suite ability revealed heightened crime risk near park boundaries and adjacent communities, reflecting the interplay between terrain, accessibility, and land-use gradients as key determinants for wildlife crime. These findings highlight the value of integrating ecological modelling techniques into conservation criminology and support the implementation of spatially targeted law enforcement strategies within protected areas. The resulting surface reflects spatial patterns of recorded incidents influenced by patrol detection effort rather than unbiased estimates of actual crime occurrence.