Spatial and temporal trajectory analysis of the Crested Ibis (Nipponia
Nippon) by fusing multiple sources of data
Abstract
Aim: Crested Ibis is an endangered animal with extremely high
ecological, humanistic and scientific value. However, there is still a
survival predicament due to increasingly shrinking foraging grounds,
serious interference by human behavior, and increased habitat
requirements. The geographical environment is significant for Crested
Ibis behavior patterns analysis and habitat protection. The spatial and
temporal trajectory contains the habitat location and period
information, a vital record of the Crested Ibis’ habits, and the basis
of all research. Nevertheless, there are only a handful of studies on
the missing trajectory data and fusing multiple sources of environmental
data research methods. Location: Henan Province, Shaanxi Province, China
Methods: The LSTM model was adopted to supplement the missing trajectory
data, and cluster mining was performed. Using Spatial and temporal
trajectory and geographic data, we developed a Random Forest model to
predict the habitat of the Crested Ibis and assessed the habitat
suitability in Luoshan Country. Results: Based on trajectory, we
identified that the Crested Ibis distribution pattern is characterized
by high altitude and proximity to woodland and rivers. And the habitat
dependence on the village implicates human agricultural activities
positively impacting its reproduction. The Random Forest model with high
fitting accuracy (R2 = 84.9%)is superior, and the
influence factors were gained, finding that 68% of the area is suitable
in Luoshan County. Main conclusions: The trajectory complement model and
the habitat prediction model are developed to obtain the Crested Ibis’
behavioral patterns and habitat distribution. This paper provides a
complete method for analyzing Crested Ibis’ spatial and temporal
trajectory by fusing multi-source data, which is crucial for protecting
the survival and reproduction of Crested Ibis.