Book ChapterDOI
Species Environmental Niche Distribution Modeling for Panthera Tigris Tigris ‘Royal Bengal Tiger’ Using Machine Learning
Shaurya Bajaj,D. Geraldine Bessie Amali +1 more
- pp 251-263
TLDR
In this article, the authors predict and model the distribution of the species Panthera Tigris Tigris by combining various climatic, human influence, and environmental factors so as to predict alternate ecological niche for the already dwindling tiger habitats in India.Abstract:
Biodiversity loss due to habitat degradation, exploitation of natural deposits, rapid change of environment and climate, and various anthropogenic phenomenon throughout the last few decades in the quest of development have led to rise in safeguarding species ecological domain. With natural habitat of the endangered Panthera Tigris Tigris fast declining, coupled with factors such as loss in genetic diversity and disruption of ecological corridors, there is an urgent need to conserve and reintroduce it to newer geographic locations. The study aims to predict and model the distribution of the species Panthera Tigris Tigris by combining various climatic, human influence, and environmental factors so as to predict alternate ecological niche for the already dwindling tiger habitats in India. 19 Bioclimatic variables, Elevation level, 17 Land Cover classes, Population Density, and Human Footprint data were taken. MAXENT, SVM, Random Forest, and Artificial Neural Networks were used for modeling. Sampling bias on the species was removed through spatial thinning. These variables were tested for Pearson correlation and those having coefficient greater than 0.70 were removed. Kappa statistic and AUC were used to study the results of the methodology implemented. Testing data comprises 25% of the presence only points and test AUC value of MAXENT was found to be the highest at 0.963, followed by RF at 0.931, ANN at 0.906, and lastly SVM at 0.898. These indicated a high degree of accuracy for prediction. The most recent datasets were taken into consideration for the above variables increasing accuracy in both time and spatial domain.read more
Citations
More filters
Journal ArticleDOI
Factors affecting the occupancy of Chinese pangolins ( Manis pentadactyla ) suggest a highly specialized ecological niche
Bijaya Dhami,Bijay Neupane,Bishnu Prasad Devkota,T. K. Maraseni,Bipana Maiya Sadadev,Shreyashi Bista,Amit Kumar Adhikari,Narendra Bahadur Chhetri,Melina Panta,Alyssa B. Stewart +9 more
TL;DR: In this article , the authors identified the current burrow density status, distribution pattern, and important habitat parameters associated with Chinese pangolin distribution in Nepal through opportunistic field surveys.
Journal ArticleDOI
Habitat preference and distribution of Chinese pangolin and people’s attitude to its conservation in Gorkha District, Nepal
Melina Panta,Bijaya Dhami,Bikram Shrestha,Nirjala Raut,Yajna Prasad Timilsina,Bir Bahadur Khanal Chhetri,Sujan Khanal,Hari Adhikari,Soňa Vařachová,Pavel Kindlmann +9 more
TL;DR: In this paper , the authors used a logistic regression model to determine the most important factors affecting pangolin presence and found that habitat, soil, canopy cover, terrain, and distance to water were statistically significantly associated with the presence of Pangolin burrows.
Journal ArticleDOI
Predicting suitable habitat of swamp deer (Rucervus duvaucelii) across the Western Terai Arc Landscape of Nepal
TL;DR: In this article , the authors explored potential habitat for swamp deer across this landscape using species distribution modeling through the MaxEnt algorithm by using 173 field-verified presence points alongside six anthropogenic, four topographic, and four vegetation-related variables.
References
More filters
Journal ArticleDOI
Maximum entropy modeling of species geographic distributions
TL;DR: In this paper, the use of the maximum entropy method (Maxent) for modeling species geographic distributions with presence-only data was introduced, which is a general-purpose machine learning method with a simple and precise mathematical formulation.
Journal ArticleDOI
Novel methods improve prediction of species' distributions from occurrence data
Jane Elith,Catherine H. Graham,Robert P. Anderson,Miroslav Dudík,Simon Ferrier,Antoine Guisan,Robert J. Hijmans,Falk Huettmann,John R. Leathwick,Anthony Lehmann,Jin Li,Lúcia G. Lohmann,Bette A. Loiselle,Glenn Manion,Craig Moritz,Miguel Nakamura,Yoshinori Nakazawa,Jacob C. M. Mc Overton,A. Townsend Peterson,Steven J. Phillips,Karen Richardson,Ricardo Scachetti-Pereira,Robert E. Schapire,Jorge Soberón,Stephen E. Williams,Mary S. Wisz,Niklaus E. Zimmermann +26 more
TL;DR: This work compared 16 modelling methods over 226 species from 6 regions of the world, creating the most comprehensive set of model comparisons to date and found that presence-only data were effective for modelling species' distributions for many species and regions.
Journal ArticleDOI
The effect of sample size and species characteristics on performance of different species distribution modeling methods
TL;DR: Maxent was the most capable of the four modeling methods in producing useful results with sample sizes as small as 5, 10 and 25 occurrences, a result that should encourage conservationists to add distribution modeling to their toolbox.
Journal ArticleDOI
The Niche-Relationships of the California Thrasher
TL;DR: The seemingly impossible was made a practical certainty, for the keeper of a bantam found the body of a screech owl with the claws of one foot firlnly imbedded in theBody of the bantam.
Journal ArticleDOI
Global warming in the twenty-first century: An alternative scenario
TL;DR: Assessment of ongoing and future climate change requires composition-specific long-term global monitoring of aerosol properties, and a reduction of non-CO(2) GHGs could lead to a decline in the rate of global warming, reducing the danger of dramatic climate change.
Related Papers (5)
Modeling and mapping the current and future climatic-niche of endangered Himalayan musk deer
Kapil K. Khadka,Douglas A. James +1 more