Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Spatial Cluster Analysis and Random Forest-Based Study on the Influencing Factors of Wildlife-Vehicle Collisions Hotspots on General Highways

공간적 군집분석 및 랜덤포레스트를 이용한 국도 동물 찻길 사고 핫스팟 영향요인 연구

  • Hyunjin Seo (Ecological Restoration Team, National Institution of Ecology) ;
  • Sehee Kim (Ecological Restoration Team, National Institution of Ecology) ;
  • Euigeun Song (Ecological Restoration Team, National Institution of Ecology) ;
  • Chulhyun Choi (Ecosystem Services Team, National Institution of Ecology)
  • 서현진 (국립생태원 복원생태팀) ;
  • 김세희 (국립생태원 복원생태팀) ;
  • 송의근 (국립생태원 복원생태팀) ;
  • 최철현 (국립생태원 생태계서비스팀)
  • Received : 2024.12.05
  • Accepted : 2024.12.13
  • Published : 2024.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aimed to identify the spatial clustering patterns of wildlife-vehicle collisions (WVCs) on General Highways in South Korea and to determine the key environmental factors influencing hotspot occurrences. To achieve this, WVC occurrence data were collected nationwide, and spatial clustering analysis was conducted. Additionally, hotspot areas were identified, and the influence of various environmental factors on these hotspots was quantitatively analyzed using the Random Forest model. The analysis revealed that WVCs exhibited distinct changes in clustering patterns at approximately a 1 km distance. Among the key environmental factors influencing the hotspots, speed limits were identified as the most significant factor, followed by the number of lanes, mean elevation, population, and core area. By systematically analyzing the spatial distribution and influencing factors of wildlife-vehicle collisions, this study provides scientific evidence for mitigating WVCs. The findings are expected to be practically utilized in establishing tailored mitigation strategies for specific road sections, selecting locations for ecological corridors, managing road speed limits, and formulating effective wildlife protection policies.

본 연구는 남한의 일반국도를 대상으로 동물 찻길 사고의 공간적 군집 패턴을 파악하고 핫스팟 발생에 영향을 미치는 주요 환경 요인을 규명하고자 하였다. 이를 위해 전국을 대상으로 동물 찻길 사고 발생 데이터를 수집하여 공간적 군집성을 분석하였다. 또한 핫스팟 지역을 도출하고 이에 영향을 미치는 다양한 환경요인에 대해서 랜덤포레스트 모델을 활용하여 영향요인을 정량적으로 분석하였다. 분석 결과, 동물 찻길 사고는 약 1km 거리를 기준으로 뚜렷한 군집 패턴의 변화를 보였다. 핫스팟에 영향을 미치는 주요 환경 요인을 분석한 결과, 제한속도가 가장 큰 영향을 미치는 요인으로 확인되었으며, 다음으로 차선 수, 평균 고도, 인구수, 핵심 서식지 면적 순으로 분석되었다. 본 연구는 동물 찻길 사고의 공간적 분포와 영향 요인을 체계적으로 분석함으로써, 동물 찻길 사고 저감을 위한 과학적 근거를 제시하였다는 점에서 의의가 있다. 연구 결과는 향후 도로구간별 맞춤형 저감 대책 수립, 생태통로 설치 지점 선정, 도로 제한속도 관리 등 효과적인 야생동물 보호 정책 수립에 있어 실질적으로 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 환경부 및 국립생태원(NIE)의 지원으로 수행되었습니다.(NIE-B-2024-05)

References

  1. Apley, D.W., J. Zhu. 2020. Visualizing the effects of predictor variables in black box supervised learning models. J R Stat Soc: Series B (Statistical Methodology) 82(4):1059–1086. https://doi.org/10.1111/rssb.12377
  2. Barrientos, R., L. Bolonio. 2009. The presence of rabbits adjacent to roads increases polecat road mortality. Biodivers Conserv 18:405–418. https://doi.org/10.1007/s10531-008-9499-9
  3. Breiman, L. 2001. Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
  4. Cartes Yegros, J.L., M. Santacruz, D. Gómez, L. López, F. Díaz, D. Rodríguez, M. Figueroa, M. Santacruz. 2024. Analysis of patterns related to wildlife roadkill in the Humid Chaco of Paraguay. One Ecosyst 9:e13117.
  5. Clevenger, A.P., B. Chruszcz, K.E. Gunson. 2001. Drainage culverts as habitat linkages and factors affecting passage by mammals. J Appl Ecol 38(6):1340–1349. https://doi.org/10.1046/j.0021-8901.2001.00678.x
  6. Filius, J., Y. van der Hoek, P. Jarrín‐V, P. van Hooft. 2020. Wildlife roadkill patterns in a fragmented landscape of the Western Amazon. Ecol Evol 10(13):6623–6635. https://doi.org/10.1002/ece3.6394
  7. Finder, R.A., J.L. Roseberry, A. Woolf. 1999. Site and landscape conditions at white tailed deer/vehicle collision locations in Illinois. Landsc Urban Plan 44(2–3):77–85. https://doi.org/10.1016/S0169-2046(99)00006-7
  8. Fluss, R., D. Faraggi, B. Reiser. 2005. Estimation of the Youden Index and its associated cutoff point. Biom J 47:458–472. https://doi.org/10.1002/bimj.200410135
  9. Getis, A., J.K. Ord. 1992. The analysis of spatial association by use of distance statistics. Geogr Anal 24(3):189–206. https://doi.org/10.1111/j.1538-4632.1992.tb00261.x.
  10. Grilo, C., J.A. Bissonette, M. Santos-Reis. 2009. Spatial-temporal patterns in Mediterranean carnivore road casualties: Consequences for mitigation. Biol Conserv 142(2):301–313. https://doi.org/10.1016/j.biocon.2008.10.026
  11. Grilo, C., L. Borda-de-Agua, P. Beja. 2021. Conservation threats from roadkill in the global road network. Glob Ecol Biogeogr 00:1–11. https://doi.org/10.1111/geb.13375
  12. Hastie, T., R. Tibshirani, J. Friedman. 2009. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. New York: Springer.
  13. Heo, S., J. Kim. 2024. A study on machine learning-based estimation of roadkill incidents and exploration of influencing factors. J Environ Impact Assess 33(2): 74–83 (허소진, 김지영. 2024. 기계학습 기반의 로드킬 발생 예측과 영향 요인 탐색에 대한 연구. 환경영향평가 33(2): 74-83). https://doi.org/10.14249/EIA.2024.33.2.74
  14. Hong, S., H.B. Park, M. Kim, H.G. Kim. 2022. History and future challenges of roadkill research in South Korea. Sustainability 14(23):15564.
  15. Kang, W., E.S. Minor, C.R. Park, D. Lee. 2016. Forest mammal roadkills as related to habitat connectivity in protected areas. Biodivers Conserv 25(14):2673–2686. https://doi.org/10.1007/s10531-016-1194-7
  16. Kanda, L.L., T.K. Fuller, P.R. Sievert. 2006. Landscape associations of road-killed Virginia opossums (Didelphis virginiana) in central Massachusetts. Am Midl Nat 156(1):128–134. https://doi.org/10.1674/0003-0031(2006)156[128:LAORVO]2.0.CO;2
  17. Kim, M., H. Park, S. Lee. 2021. Analysis of roadkill on the Korean expressways from 2004 to 2019. Int J Environ Res Public Health 18(19):10252.
  18. Kim, M., S. Lee. 2023. Identification of emerging roadkill hotspots on Korean expressways using space–time cubes. Int J Environ Res Public Health 20(6):4896.
  19. Lee, J.H., Y.W. Mo. 2023. Prediction of water deer roadkill rate in Yeongnam region. J Daegu Gyeongbuk Stud 22(2): 167–187 (이지훈, 모용원. 2023. 영남지역 내 고라니 로드킬 발생률 예측. 대구경북연구 22(2):167-187). https://doi.org/10.23029/JDGS.2023.22.2.167
  20. Liu, Z., C. He, J. Wu. 2016. The relationship between habitat loss and fragmentation during urbanization: an empirical evaluation from 16 world cities. PLoS One 11(4): e0154613.
  21. Medrano-Vizcaino, P., C. Grilo, D. Brito Zapata, M. González-Suárez. 2023. Landscape and road features linked to wildlife mortality in the Amazon. Biodivers Conserv 32(13):4337–4352. https://doi.org/10.1007/s10531-023-02699-4
  22. Muller, M.P., G. Tomlinson, T.J. Marrie. 2005. Can routine laboratory tests discriminate between severe acute respiratory syndrome and other causes of community-acquired pneumonia? Clin Infect Dis 40(8):1079–1086. https://doi.org/10.1086/428577
  23. Ng, J.W., C. Nielson, C.C. St. Clair. 2008. Landscape and traffic factors influencing deer–vehicle collisions in an urban environment. Hum-Wildl Conflicts 2(1):34–47.
  24. Ramp, D., J. Caldwell, K.A. Edwards. 2005. Modelling of wildlife fatality hotspots along the Snowy Mountain Highway in New South Wales, Australia. Biol Conserv 126(4):474–490. https://doi.org/10.1016/j.biocon.2005.07.001
  25. Saint-Andrieux, C., C. Calenge, C. Bonenfant. 2020. Comparison of environmental, biological and anthropogenic causes of wildlife–vehicle collisions among three large herbivore species. Popul Ecol 62(1):64–79. https://doi.org/10.1002/1438-390X.12029
  26. Santos, E., M. Cordova, C. Rosa, D. Rodrigues. 2022. Hotspots and season related to wildlife roadkill in the Amazonia– Cerrado transition. Diversity 14(8):657. https://doi.org/10.3390/d14080657.
  27. Seiler, A., M. Bhardwaj. 2020. Wildlife and traffic: An inevitable but not unsolvable problem? In: Angelici, F., Rossi, L., eds. Problematic Wildlife II. Cham: Springer. https://doi.org/10.1007/978-3-030-42335-3_6.
  28. Seo, H.J., C.H. Choi, S.W. Lee, J.H. Kim. 2024. Analysis of ecological connectivity of forest habitats using spatial morphological characteristics and roadkill data. Korean J Ecol Environ 57(2):75–82 https://doi.org/10.11614/KSL.2024.57.2.075
  29. Song, E.G., H.J. Seo, K.M. Kim, D.G. Woo, T.J. Park, T.Y. Choi. 2019. Analysis of roadkill hotspot according to the spatial clustering methods. J Environ Impact Assess 28(6):580–591 (송의근, 서현진, 김경민, 우동걸, 박태진, 최태영. 2019. 공간 군집지역 탐색방법에 따른 로드킬 다발구간 분석. 한국환경영향평가 28(6):580-591).
  30. Szot, T., C. Specht, M. Specht, P.S. Dabrowski. 2019. Comparative analysis of positioning accuracy of Samsung Galaxy smartphones in stationary measurements. PLoS One 14(4).
  31. Vogt, P., K.H. Riitters, C. Estreguil, J. Kozak, T.G. Wade, J.D. Wickham. 2007. Mapping spatial patterns with morphological image processing. Landsc Ecol 22(2):171–177. https://doi.org/10.1007/s10980-006-9013-2.
  32. Yamada, I., P.A. Rogerson. 2003. An empirical comparison of edge effect correction methods applied to K-function analysis. Geogr Anal 35(2):97–109. https://doi.org/10.1111/j.1538-4632.2003.tb01103.x.