Proceedings of the National Institute of Ecology of the Republic of Korea

National Institute of Ecology (국립생태원)
권호 표지
DOI QR코드

DOI QR Code

Application of Statistical and Machine Learning Techniques for Habitat Potential Mapping of Siberian Roe Deer in South Korea

  • Lee, Saro (Geoscience Platform Division, Korea Institute of Geoscience and Mineral Resources (KIGAM)) ;
  • Rezaie, Fatemeh (Geoscience Platform Division, Korea Institute of Geoscience and Mineral Resources (KIGAM))
  • Received : 2020.12.28
  • Accepted : 2021.01.13
  • Published : 2021.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

The study has been carried out with an objective to prepare Siberian roe deer habitat potential maps in South Korea based on three geographic information system-based models including frequency ratio (FR) as a bivariate statistical approach as well as convolutional neural network (CNN) and long short-term memory (LSTM) as machine learning algorithms. According to field observations, 741 locations were reported as roe deer's habitat preferences. The dataset were divided with a proportion of 70:30 for constructing models and validation purposes. Through FR model, a total of 10 influential factors were opted for the modelling process, namely altitude, valley depth, slope height, topographic position index (TPI), topographic wetness index (TWI), normalized difference water index, drainage density, road density, radar intensity, and morphological feature. The results of variable importance analysis determined that TPI, TWI, altitude and valley depth have higher impact on predicting. Furthermore, the area under the receiver operating characteristic (ROC) curve was applied to assess the prediction accuracies of three models. The results showed that all the models almost have similar performances, but LSTM model had relatively higher prediction ability in comparison to FR and CNN models with the accuracy of 76% and 73% during the training and validation process. The obtained map of LSTM model was categorized into five classes of potentiality including very low, low, moderate, high and very high with proportions of 19.70%, 19.81%, 19.31%, 19.86%, and 21.31%, respectively. The resultant potential maps may be valuable to monitor and preserve the Siberian roe deer habitats.

Keywords

References

  1. Acevedo, P., Real, R., and Gortazar, C. (2011). [Favorabilidad ecogeografica para el corzo: distribucion y abundancia]. Pirineos, 166, 9-27. https://doi.org/10.3989/pirineos.2011.166001
  2. Aini, S., Sood, A.M., and Saaban, S. (2015). Analysing elephant habitat parameters using GIS, remote sensing and analytic hierarchy process in Peninsular Malaysia. Pertanika Journal of Science and Technology, 23, 37-50.
  3. Al-Abadi, A.M., Al-Temmeme, A.A., and Al-Ghanimy, M.A. (2016). A GIS-based combining of frequency ratio and index of entropy approaches for mapping groundwater availability zones at Badra-Al Al-Gharbi-Teeb areas, Iraq. Sustainable Water Resources Management, 2, 265-283. https://doi.org/10.1007/s40899-016-0056-5
  4. Al-Abadi, A.M., Pourghasemi, H.R., Shahid, S., and Ghalib, H.B. (2017). Spatial mapping of groundwater potential using entropy weighted linear aggregate novel approach and GIS. Arabian Journal for Science and Engineering, 42, 1185-1199. https://doi.org/10.1007/s13369-016-2374-1
  5. Altafi Dadgar, M., Zeaieanfirouzabadi, P., Dashti, M., and Porhemmat, R. (2017). Extracting of prospective groundwater potential zones using remote sensing data, GIS, and a probabilistic approach in Bojnourd basin, NE of Iran. Arabian Journal of Geosciences, 10, 114. https://doi.org/10.1007/s12517-017-2910-7
  6. Arabameri, A., Rezaei, K., Cerda, A., Lombardo, L., and RodrigoComino, J. (2019). GIS-based groundwater potential mapping in Shahroud plain, Iran. A comparison among statistical (bivariate and multivariate), data mining and MCDM approaches. Science of the Total Environment, 658, 160-177. https://doi.org/10.1016/j.scitotenv.2018.12.115
  7. Arya, S., Subramani, T., and Karunanidhi, D. (2020). Delineation of groundwater potential zones and recommendation of artificial recharge structures for augmentation of groundwater resources in Vattamalaikarai Basin, South India. Environmental Earth Sciences, 79, 102. https://doi.org/10.1007/s12665-020-8832-9
  8. Biswas, S., Mukhopadhyay, B.P., and Bera, A. (2020). Delineating groundwater potential zones of agriculture dominated landscapes using GIS based AHP techniques: a case study from Uttar Dinajpur district, West Bengal. Environmental Earth Sciences, 79, 302. https://doi.org/10.1007/s12665-020-09053-9
  9. Chen, W., Panahi, M., Khosravi, K., Pourghasemi, H.R., Rezaie, F., and Parvinnezhad, D. (2019). Spatial prediction of groundwater potentiality using ANFIS ensembled with teachinglearning-based and biogeography-based optimization. Journal of Hydrology, 572, 435-448. https://doi.org/10.1016/j.jhydrol.2019.03.013
  10. Choi, J.K., Oh, H.J., Koo, B.J., Ryu, J.H., and Lee, S. (2011a). Crustacean habitat potential mapping in a tidal flat using remote sensing and GIS. Ecological Modelling, 222, 1522-1533. https://doi.org/10.1016/j.ecolmodel.2010.12.008
  11. Choi, J.K., Oh, H.J., Koo, B.J., Ryu, J.H., and Lee, S. (2011b). Spatial polychaeta habitat potential mapping using probabilistic models. Estuarine, Coastal and Shelf Science, 93, 98-105. https://doi.org/10.1016/j.ecss.2011.03.006
  12. Cui, X., Liu, H., Fan, M., Ai, B., Ma, D., and Yang, F. (2021). Seafloor habitat mapping using multibeam bathymetric and backscatter intensity multi-features SVM classification framework. Applied Acoustics, 174, 107728. https://doi.org/10.1016/j.apacoust.2020.107728
  13. Danilkin, A., and Hewison, A.J.M. (1996). Behavioural Ecology of Siberian and European Roe Deer, London: Chapman and Hall.
  14. Dodangeh, E., Panahi, M., Rezaie, F., Lee, S., Bui, D.T., Lee, C.W., et al. (2020). Novel hybrid intelligence models for flood-susceptibility prediction: meta optimization of the GMDH and SVR models with the genetic algorithm and harmony search. Journal of Hydrology, 590, 125423. https://doi.org/10.1016/j.jhydrol.2020.125423
  15. Duarte, J., Farfan, M.A., and Vargas, J.M. (2010). [Seleccion primaveral de habitat del corzo andaluz (Capreolus capreolus) en un borde de su area de distribucion]. Ecologia, 23, 177-192.
  16. Evcin, O., Kucuk, O., and Akturk, E. (2019). Habitat suitability model with maximum entropy approach for European roe deer (Capreolus capreolus) in the Black Sea Region. Environmental Monitoring and Assessment, 191, 669. https://doi.org/10.1007/s10661-019-7853-x
  17. Farrell, A., Wang, G., Rush, S.A., Martin, J.A., Belant, J.L., Butler, A.B., et al. (2019). Machine learning of large-scale spatial distributions of wild turkeys with high-dimensional environmental data. Ecology and Evolution, 9, 5938-5949. https://doi.org/10.1002/ece3.5177
  18. Garzon, M.B., Blazek, R., Neteler, M., De Dios, R.S., Ollero, H.S., and Furlanello, C. (2006). Predicting habitat suitability with machine learning models: the potential area of Pinus sylvestris L. in the Iberian Peninsula. Ecological Modelling, 197, 383-393. https://doi.org/10.1016/j.ecolmodel.2006.03.015
  19. Imam, E., and Kushwaha, S.P.S. (2013). Habitat suitability modelling for Gaur (Bos gaurus) using multiple logistic regression, remote sensing and GIS. Journal of Applied Animal Research, 41, 189-199. https://doi.org/10.1080/09712119.2012.739089
  20. Imam, E., and Tesfamichael, G.Y. (2013). Use of remote sensing, GIS and analytical hierarchy process (AHP) in wildlife habitat suitability analysis. Journal of Materials and Environmental Science, 4, 460-467.
  21. Jaafari, A., Panahi, M., Pham, B.T., Shahabi, H., Bui, D.T., Rezaie, F., et al. (2019). Meta optimization of an adaptive neurofuzzy inference system with grey wolf optimizer and biogeography-based optimization algorithms for spatial prediction of landslide susceptibility. CATENA, 175, 430-445. https://doi.org/10.1016/j.catena.2018.12.033
  22. Jiang, G., Qi, J., Wang, G., Shi, Q., Darman, Y., Hebblewhite, M., et al. (2015). New hope for the survival of the Amur leopard in China. Scientific Reports, 5, 15475. https://doi.org/10.1038/srep15475
  23. Kadirhodjaev, A., Rezaie, F., Lee, M.J., and Lee, S. (2020). Landslide susceptibility assessment using an optimized group method of data handling model. ISPRS International Journal of Geo-Information, 9, 566. https://doi.org/10.3390/ijgi9100566
  24. Kamali Maskooni, E., Naghibi, S.A., Hashemi, H., and Berndtsson, R. (2020). Application of advanced machine learning algorithms to assess groundwater potential using remote sensing-derived data. Remote Sensing, 12, 2742. https://doi.org/10.3390/rs12172742
  25. Koh, H.S., and Randi, E. (2001). Genetic distinction of roe deer {Capreolus pygargus Pallas) sampled in Korea. Mammalian Biology, 66, 371-375.
  26. Korea Meteorological Administration (KMA). (2020). Article title. Retrieved December 11, 2020 from https://www.weather. go.kr/weather/main.jsp.
  27. Kosicki, J.Z. (2020). Generalised Additive Models and Random Forest approach as effective methods for predictive species density and functional species richness. Environmental and Ecological Statistics, 27, 273-292. https://doi.org/10.1007/s10651-020-00445-5
  28. Kumar, P., and Hati, A.S. (2020). Deep convolutional neural network based on adaptive gradient optimizer for fault detection in SCIM. ISA Transactions. doi:10.1016/2020.10.052.
  29. Leathwick, J.R., Rowe, D., Richardson, J., Elith, J., and Hastie, T. (2005). Using multivariate adaptive regression splines to predict the distributions of New Zealand's freshwater diadromous fish. Freshwater Biology, 50, 2034-2052. https://doi.org/10.1111/j.1365-2427.2005.01448.x
  30. Lee, S., and Talib, J.A. (2005). Probabilistic landslide susceptibility and factor effect analysis. Environmental Geology, 47, 982-990. https://doi.org/10.1007/s00254-005-1228-z
  31. Lee, S., Lee, S., Song, W., and Lee, M.J. (2017). Habitat potential mapping of marten (Martes flavigula) and leopard cat (Prionailurus bengalensis) in South Korea using artificial neural network machine learning. Applied Sciences, 7, 912. https://doi.org/10.3390/app7090912
  32. Lee, S., Park, I., Koo, B.J., Ryu, J.H., Choi, J.K., and Woo, H.J. (2013). Macrobenthos habitat potential mapping using GISbased artificial neural network models. Marine Pollution Bulletin, 67, 177-186. https://doi.org/10.1016/j.marpolbul.2012.10.023
  33. Lee, S., Syifa, M., Koo, B.J., Lee, C.W., and Oh, H.J. (2019). Spatial macrobenthos habitat on Ganghwa tidal flat, Korea: Part II- habitat potential mapping of Potamocorbula laevis using probability models. Journal of Coastal Research, 90(SI), 401-408. https://doi.org/10.2112/SI90-051.1
  34. Lee, Y.S., Markov, N., Argunov, A., Voloshina, I., Bayarlkhagva, D., Kim, B.J., et al. (2016). Genetic diversity and phylogeography of Siberian roe deer, Caproulus pygargus, in central and peripheral populations. Ecology and Evolution, 6, 7286-7297. https://doi.org/10.1002/ece3.2458
  35. Lee, Y.S., Markov, N., Voloshina, I., Argunov, A., Bayarlkhagva, D., Oh, J.G., et al. (2015). Genetic diversity and genetic structure of the Siberian roe deer (Capreolus pygargus) populations from Asia. BMC Genetics, 16, 100.
  36. Loro, M., Ortega, E., Arce, R.M., and Geneletti, D. (2016). Assessing landscape resistance to roe deer dispersal using fuzzy set theory and multicriteria analysis: a case study in Central Spain. Landscape and Ecological Engineering, 12, 41-60. https://doi.org/10.1007/s11355-015-0275-1
  37. Lovari, S., Masseti, M., and Lorenzini, R. (2016). Capreolus pygargus. Retrieved December 14, 2020 from https://dx.doi.org/10.2305/IUCN.UK.2016-1.RLTS.T42396A22161884.en.
  38. Lopez-Martin, J.M., Martinez-Martinez, D., and Such, A. (2009). Supervivencia, dispersion y seleccion de recursos de corzos Capreolus capreolus (Linnaeus, 1758) reintroducidos en un habitat mediterraneo. Galemys, 21, 143-164.
  39. Mesfin, Y., and Berhan, G. (2016). Geospatial approach for Grevy's zebra suitable habitat analysis, Allidegi wildlife reserve, Ethiopia. International Journal of Applied Remote Sensing and GIS, 3, 34-42.
  40. Ng, W.T., Candido de Oliveira Silva, A., Rima, P., Atzberger, C., and Immitzer, M. (2018). Ensemble approach for potential habitat mapping of invasive Prosopis spp. in Turkana, Kenya. Ecology and Evolution, 8, 11921-11931. https://doi.org/10.1002/ece3.4649
  41. Nguyen, P.T., Ha, D.H., Avand, M., Jaafari, A., Nguyen, H.D., AlAnsari, N., et al. (2020). Soft computing ensemble models based on logistic regression for groundwater potential mapping. Applied Sciences, 10, 2469. https://doi.org/10.3390/app10072469
  42. Oh, H.J., Syifa, M., Lee, C.W., and Lee, S. (2019). Ruditapes philippinarum habitat mapping potential using SVM and Naive Bayes. Journal of Coastal Research, 90(sp1), 41-48. https://doi.org/10.2112/SI90-006.1
  43. Panahi, M., Gayen, A., Pourghasemi, H.R., Rezaie, F., and Lee, S. (2020a). Spatial prediction of landslide susceptibility using hybrid support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) with various metaheuristic algorithms. Science of the Total Environment, 741, 139937. https://doi.org/10.1016/j.scitotenv.2020.139937
  44. Panahi, M., Sadhasivam, N., Pourghasemi, H.R., Rezaie, F., and Lee, S. (2020b). Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). Journal of Hydrology, 588, 125033. https://doi.org/10.1016/j.jhydrol.2020.125033
  45. Park, J., Kim, D.S., Song, K.H., Jeong, T.J., and Park, S.J. (2018). Mapping potential habitats for the management of exportable insects in South Korea. Journal of Asia-Pacific Biodiversity, 11, 11-20.
  46. Park, Y.S., Kim, B.J., Lee, W.S., Kim, J.T., Kim, T.W., and Oh, H.S. (2014). Molecular phylogenetic status of Siberian roe deer (Capreolus pygargus) based on mitochondrial cytochrome b from Jeju Island in Korea. Chinese Science Bulletin, 59, 4283-4288. https://doi.org/10.1007/s11434-014-0535-8
  47. Pays, O., Fortin, D., Gassani, J., and Duchesne, J. (2012). Group dynamics and landscape features constrain the exploration of herds in fusion-fission societies: the case of European roe deer. PloS One, 7, e34678. https://doi.org/10.1371/journal.pone.0034678
  48. Pereira, J.M.C., and Itami, R.M. (1991). GIs-based habitat modeling using logistic multiple regression: a study of the Mt. Graham red squirrel. Photogrammetric Engneering and Remote Sensing, 57, 1475-1486.
  49. Pradhan, A., Kim, Y.T., Shrestha, S., Huynh, T.C., and Nguyen, B.P. (2020). Application of deep neural network to capture groundwater potential zone in mountainous terrain, Nepal Himalaya. Environmental Science and Pollution Research International. doi:10.1007/11356-020-10646-x.
  50. Rahimian Boogar, A., Salehi, H., Pourghasemi, H.R., and Blaschke, T. (2019). Predicting habitat suitability and conserving Juniperus spp. habitat using SVM and maximum entropy machine learning techniques. Water, 11, 2049. https://doi.org/10.3390/w11102049
  51. Razavi Termeh, S.V., Kornejady, A., Pourghasemi, H.R., and Keesstra, S. (2018). Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. Science of the Total Environment, 615, 438-451. https://doi.org/10.1016/j.scitotenv.2017.09.262
  52. Reimoser, S., Partl, E., Reimoser, F., and Vospernik, S. (2009). Roe-deer habitat suitability and predisposition of forest to browsing damage in its dependence on forest growth- model sensitivity in an alpine forest region. Ecological Modelling, 220, 2231-2243. https://doi.org/10.1016/j.ecolmodel.2009.05.022
  53. Robert, K., Jones, D.O.B., Roberts, J.M., and Huvenne, V.A.I. (2016). Improving predictive mapping of deep-water habitats: considering multiple model outputs and ensemble techniques. Deep Sea Research Part I: Oceanographic Research Papers, 113, 80-89. https://doi.org/10.1016/j.dsr.2016.04.008
  54. Rosell, C., Carretero, M.A., Cahill, S., and Pasquina, A. (1996). Seguimiento de una reintroduccion de corzo (Capreolus capreolus) en ambiente mediterraneo. Dispersion y area de campeo. Donana Acta Vertebrata, 23, 109-122.
  55. Sanare, J.E., Ganawa, E.S., and Abdelrahim, A.M.S. (2015). Wildlife habitat suitability analysis at Serengeti National Park (SNP), Tanzania case study Loxodonta sp. Journal of Ecosystem and Ecography, 5, 164.
  56. Sanchez, P., Demestre, M., Recasens, L., Maynou, F., and Martin, P. (2008). Combining GIS and GAMs to identify potential habitats of squid Loligo vulgaris in the Northwestern Mediterranean. In V.D., Valavanis (Eds.), Essential Fish Habitat Mapping in the Mediterranean (pp. 91-98). Dordrecht: Springer.
  57. Schmiing, M., Afonso, P., Tempera, F., and Santos, R.S. (2013). Predictive habitat modelling of reef fishes with contrasting trophic ecologies. Marine Ecology Progress Series, 474, 201-216. https://doi.org/10.3354/meps10099
  58. Shi, Y., Song, X., and Song, G. (2021). Productivity prediction of a multilateral-well geothermal system based on a long short-term memory and multi-layer perceptron combinational neural network. Applied Energy, 282, 116046. https://doi.org/10.1016/j.apenergy.2020.116046
  59. Sokolov, V.E., Danilkin, A.A., and Dulamtseren, S. (1982). Contemporary distribution and populations of the forest ungulates in Mongolia. Zoological Studies in the People's Republic of Mongolia, 8, 37-56.
  60. Supreetha, B.S., Shenoy, N., and Nayak, P. (2020). Lion algorithm-optimized long short-term memory network for groundwater level forecasting in Udupi District, India. Applied Computational Intelligence and Soft Computing, 2020, 8685724.
  61. Tang, J., Su, Q., Su, B., Fong, S., Cao, W., and Gong, X. (2020). Parallel ensemble learning of convolutional neural networks and local binary patterns for face recognition. Computer Methods and Programs in Biomedicine, 197, 105622. https://doi.org/10.1016/j.cmpb.2020.105622
  62. Tekerek, A. (2021). A novel architecture for web-based attack detection using convolutional neural network. Computers and Security, 100, 102096. https://doi.org/10.1016/j.cose.2020.102096
  63. Tin, T.C., Chiew, K.L., Phang, S.C., Sze, S.N., and Tan, P.S. (2019). Incoming Work-In-Progress prediction in semiconductor fabrication foundry using long short-term memory. Computational Intelligence and Neuroscience, 2019, 8729367. https://doi.org/10.1155/2019/8729367
  64. Vu, M.T., Jardani, A., Massei, N., and Fournier, M. (2020). Reconstruction of missing groundwater level data by using Long Short-Term Memory (LSTM) deep neural network. Journal of Hydrology. doi:10.1016/2020.125776.
  65. Wei, C.C. (2020). Development of stacked long short-term memory neural networks with numerical solutions for wind velocity predictions. Advances in Meteorology, 2020, 5462040.
  66. Yang, H., Pan, Z., and Tao, Q. (2017). Robust and adaptive online time series prediction with long short-term memory. Computational Intelligence and Neuroscience, 2017, 9478952.
  67. Zare, S., and Ayati, M. (2020). Simultaneous fault diagnosis of wind turbine using multichannel convolutional neural networks. ISA transactions. doi:10.1016/2020.08.021.
  68. Zhang, G., Zhu, A.X., He, Y.C., Huang, Z.P., Ren, G.P., and Xiao, W. (2020a). Integrating multi-source data for wildlife habitat mapping: a case study of the black-and-white snub-nosed monkey (Rhinopithecus bieti) in Yunnan, China. Ecological Indicators, 118, 106735. https://doi.org/10.1016/j.ecolind.2020.106735
  69. Zhang, Q., Zhang, M., Chen, T., Sun, Z., Ma, Y., and Yu, B. (2019). Recent advances in convolutional neural network acceleration. Neurocomputing, 323, 37-51. https://doi.org/10.1016/j.neucom.2018.09.038
  70. Zhang, X., Wu, F., and Li, Z. (2020b). Application of convolutional neural network to traditional data. Expert Systems with Applications. doi:10.1016/2020.114185.