Mapping Potential Distribution of Wild Bird Using Convolutional Neural Network
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [18]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Remote sensing images play an important role in the development of species distribution model. However, low spatial resolution ecological niche derived from remote sensing data and lack of fine-scale presence data requires alternative approaches. With the application of various data acquisition devices, a large number of animal movement data can be considered as the presence data. In this study, we use DBSCAN method to cluster the movement data and each cluster represents a stopover. Then, we split the remote sensing image into 16×16 patches and divide them into positive and negative samples on the basis of clustering result. In addition, a multi-convolutional neural network model is proposed for the training and prediction of the potential distribution of wild geese surrounding Qinghai Lake. We evaluate the proposed system using a real GPS dataset collected on 29 birds over three years. The experiments show that the proposed method outperforms the GLCM method in terms of overall accuracy, F1 score, and AUC. The proposed method also can obtain a better result in a potential distribution prediction experiment.

    Reference
    [1] McKee JK, Sciulli PW, David Fooce C, et al. Forecasting global biodiversity threats associated with human population growth. Biological Conservation, 2004, 115(1):161-164.
    [2] Nielsen SE, Johnson CJ, Heard DC, et al. Can models of presence-absence be used to scale abundance? Two case studies considering extremes in life history. Ecography, 2005, 28(2):197-208.
    [3] Hu JH, Hu HJ, Jiang ZG. The impacts of climate change on the wintering distribution of an endangered migratory bird. Oecologia, 2010, 164(2):555-565.
    [4] 张颖, 李君, 林蔚, 等. 基于最大熵生态位元模型的入侵杂草春飞蓬在中国潜在分布区的预测. 应用生态学报, 2011, 22(11):2970-2976.
    [5] Bisrat SA, White MA, Beard KH, et al. Predicting the distribution potential of an invasive frog using remotely sensed data in Hawaii. Diversity and Distributions, 2012, 18(7):648-660.
    [6] Parviainen M, Zimmermann NE, Heikkinen RK, et al. Using unclassified continuous remote sensing data to improve distribution models of red-listed plant species. Biodiversity and Conservation, 2013, 22(8):1731-1754.
    [7] Phillips SJ, Dudík M, Schapire RE. A maximum entropy approach to species distribution modeling. Proceedings of the 21st International Conference on Machine Learning. Banff, Alberta, Canada. 2004, doi:10.1145/1015330.1015412.
    [8] Gibson L, Barrett B, Burbidge A. Dealing with uncertain absences in habitat modelling:A case study of a rare ground-dwelling parrot. Diversity and Distributions, 2007, 13(6):704-713.
    [9] 吴庆明, 王磊, 朱瑞萍, 等. 基于MAXENT模型的丹顶鹤营巢生境适宜性分析——以扎龙保护区为例. 生态学报, 2016, 36(12):3758-3764.
    [10] Franco AMA, Brito JC, Almeida J. Modelling habitat selection of Common Cranes Grus grus wintering in Portugal using multiple logistic regression. IBIS, 2000, 142(3):351-358, doi:10.1111/j.1474-919X.2000.tb04430.x.
    [11] Ball LC, Doherty Jr PF, McDonald MW. An occupancy modeling approach to evaluating a palm springs ground squirrel habitat model. The Journal of Wildlife Management, 2005, 69(3):894-904, doi:10.2193/0022-541X(2005)069[0894:AOMATE]2.0.CO;2.
    [12] Yoo JW, Lee YW, Lee CG, et al. Effective prediction of biodiversity in tidal flat habitats using an artificial neural network. Marine Environmental Research, 2013, 83:1-9.
    [13] Pittman SJ, Christensen JD, Caldow C, et al. Predictive mapping of fish species richness across shallow-water seascapes in the Caribbean. Ecological Modelling, 2007, 204(1-2):9-21.
    [14] Rodriguez-Galiano VF, Chica-Olmo M, Chica-Rivas M. Predictive modelling of gold potential with the integration of multisource information based on random forest:A case study on the Rodalquilar area, Southern Spain. International Journal of Geographical Information Science, 2014, 28(7):1336-1354.
    [15] Ester M, Kriegel HP, Sander J, et al. A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining. Portland, OR, USA. 1996. 226-231.
    [16] Ioffe S, Szegedy C. Batch normalization:Accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167, 2015.
    [17] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
    [18] Abadi M, Agarwal A, Barham P, et al. TensorFlow:Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467, 2016.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

苏锦河,朴英超,罗泽,阎保平.基于卷积神经网络的候鸟潜在分布预测.计算机系统应用,2018,27(10):248-254

Copy
Share
Article Metrics
  • Abstract:1935
  • PDF: 2826
  • HTML: 1703
  • Cited by: 0
History
  • Received:March 07,2018
  • Revised:March 22,2018
  • Online: September 29,2018
Article QR Code
You are the first990365Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063