Welcome to Francis Academic Press

Academic Journal of Environment & Earth Science, 2021, 3(1); doi: 10.25236/AJEE.2021.030110.

A study of species distribution prediction based on kernel density estimation

Author(s)

Beixin Fang, Yanling Jiang, Yimeng Cao

Corresponding Author:
Beixin Fang
Affiliation(s)

School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu 730000, China

Abstract

The occurrence of Vespa mandarine in the State of Washington is terrible news for the local Western bees, as Vespa mandarine is a very effective predictor. The Washington State government is taking the Vespa mandarine invasion seriously and hopes that people will report it when pests are found. This article processes the sighting reports provided, establishes a model, predicts the potential distribution of coriander, and can effectively provide the possibility of a new report being positive so as to quickly determine the most likely positive report and help the government allocate resources rationally. First, a species distribution prediction model based on kernel density estimation (KDE) was established. We took the Gaussian function as the kernel function, performed KDE on the given data, and controlled the search radius of the kernel function to be 30km from the center of the nest to obtain a probability density heat map reflecting the possibility of coriander spreading to a certain area, which shows that the scope of the spread and the possibility of each location are predictable. It is also essential to consider the circumstances under which the hives are cleared. Therefore, when a hive is removed, we will update the KDE model. If the distance is less than 30km, the point closest to the coordinates of the cleared hive will be deleted.

Keywords

Kernel Density Estimation, Computer Vision, Vespa mandarinia

Cite This Paper

Beixin Fang, Yanling Jiang, Yimeng Cao. A study of species distribution prediction based on kernel density estimation. Academic Journal of Environment & Earth Science (2021) Vol. 3 Issue 1: 47-51. https://doi.org/10.25236/AJEE.2021.030110.

References

[1] Asian Giant Hornet | National Invasive Species Information Center. (n.d.). National Invasive Species Information Center. Retrieved February 8, 2021, from https://www.invasivespeciesinfo.gov/terrestrial/ invertebrates/asian-giant-hornet

[2] Blonder, B., Lamanna, C., Violle, C., Enquist, B. J. (2017). Using n-dimensional hypervolumes for species distribution modelling: A response to Qiao et al.(). Global Ecology and Biogeography, 26(9), 1071-1075.

[3] Beazley, L., Kenchington, E., Lirette, C. (2017). Species distribution modelling and kernel density analysis of benthic ecologically and biologically significant areas (EBSAs) and other benthic fauna in the Maritimes Region. Ocean and Ecosystem Sciences Division, Maritimes Region, Fisheries and Oceans Canada, Bedford Institute of Oceanography.

[4] Xiangyun Liu, Hongqin Peng, Yun Bai Lueling Liao (2014). Tourism Flows Prediction based on an Improved Grey GM(1,1) Model. 138767-775.