When AI Meets Wildlife: Predicting Animal Migration from Habitat Cues DOI

Daksh Kuraichya

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: May 20, 2025

Abstract Elephant migration plays a critical role in maintaining biodiversity, yet predicting their movement remains complex challenge influenced by environmental, human, and ecological factors. This study develops machine learning model to forecast elephant between Bandipur National Park Wayanad Wildlife Sanctuary analyzing 34 months of historical data incorporating features like temperature, humidity, air quality index, vegetation water availability index. After extensive preprocessing, including outlier removal, feature selection, balancing using SMOTE, multiple algorithms were evaluated. Logistic Regression achieved the highest performance, with an accuracy 94%, outperforming Decision Trees, Random Forests, Support Vector Machines, Naive Bayes, Neural Networks. Exploratory analysis revealed key environmental triggers influencing migration, such as seasonal temperature variations. Hyperparameter tuning further optimized performance. The results demonstrate that predictive analytics can enhance conservation strategies, reduce human-elephant conflict, support policy-making for habitat protection. Future work aims incorporate real-time tracking additional factors improve robustness applicability dynamic environments.

Language: Английский

Understanding the patterns and predictors of human-elephant conflict in Tamil Nadu, India DOI
Thekke Thumbath Shameer,

Priyambada Routray,

A. Udhayan

et al.

European Journal of Wildlife Research, Journal Year: 2024, Volume and Issue: 70(5)

Published: Sept. 14, 2024

Language: Английский

Citations

4
Utilizing spatial modeling to evaluate habitat suitability and develop conservation corridors for effective conservation planning of Asian elephants (Elephas maximus) in Jeli, Kelantan, Malaysia DOI
Nur Hairunnisa Rafaai, Hazizi Husain,

Shukor Md Nor

et al.

Ecological Modelling, Journal Year: 2025, Volume and Issue: 502, P. 111043 - 111043

Published: Feb. 10, 2025

Language: Английский

Citations

0
Mapping the Paths of Giants: A GIS‐Based Habitat Connectivity Model for Forest Elephant Conservation in a West African Forest Block DOI Creative Commons

Adriana Owusu‐Sekyere,

George Ashiagbor

African Journal of Ecology, Journal Year: 2025, Volume and Issue: 63(2)

Published: Feb. 25, 2025

ABSTRACT The long‐term survival of African forest elephants ( Loxodonta cyclotis ) in the Bia Goaso Forest Block (BGFB) is threatened due to a lack spatially explicit data on their movement patterns and corridors guide conservation actions. aim this study model potential connectivity between core habitats BGFB. First, seven key variables influencing elephants’ choice were mapped as rasters ranked using analytical hierarchy process. Suitability indices then assigned based relative influence corridor choice. A total resistance raster was calculated weighted sum method. Finally, Linkage Mapper used map pairs protected areas. Nine identified, with Euclidean distances ranging from 3.89 13.50 km, cost‐weighted 13.20 34.75 km least‐cost path 4.10 16.23 km. Game Production–Krokosua Hills NP–Bia North corridors, centrality scores 19.16 Amps 13.14 Amps, respectively, identified most critical maintaining connectivity. Krokosua, Tano, Ayum, Bonkoni Bosam Bepo reserves, 36 69 areas for This result provides first comprehensive geospatial dataset habitat BGFB, which will inform efforts effective management restore population support elephant conservation.

Language: Английский

Citations

0
When AI Meets Wildlife: Predicting Animal Migration from Habitat Cues DOI

Daksh Kuraichya

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: May 13, 2025

Abstract Elephant migration is essential for preserving biodiversity, but accurately predicting their movement patterns challenging due to the influence of environmental, human, and ecological factors. This research introduces a machine learning-based approach predict elephant routes between Bandipur National Park Wayanad Wildlife Sanctuary. The study uses 34 months historical data, including variables such as temperature, humidity, air quality, vegetation health, water availability. dataset underwent thorough preprocessing, outlier handling, feature selection, data balancing using SMOTE. Several learning models were tested, with Logistic Regression yielding best results—achieving 94% accuracy—surpassing like Random Forests, Decision Trees, Naive Bayes, Support Vector Machines, Neural Networks. analysis identified important environmental factors, seasonal presence temperature changes, key triggers migration. Additionally, hyperparameter tuning helped refine further. findings show that predictive modeling can aid in wildlife conservation, minimize conflicts humans elephants, inform policy. Future developments will focus on integrating real-time tracking expanding range indicators improve model’s effectiveness changing conditions.

Language: Английский

Citations

0
When AI Meets Wildlife: Predicting Animal Migration from Habitat Cues DOI

Daksh Kuraichya

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: May 20, 2025

Abstract Elephant migration plays a critical role in maintaining biodiversity, yet predicting their movement remains complex challenge influenced by environmental, human, and ecological factors. This study develops machine learning model to forecast elephant between Bandipur National Park Wayanad Wildlife Sanctuary analyzing 34 months of historical data incorporating features like temperature, humidity, air quality index, vegetation water availability index. After extensive preprocessing, including outlier removal, feature selection, balancing using SMOTE, multiple algorithms were evaluated. Logistic Regression achieved the highest performance, with an accuracy 94%, outperforming Decision Trees, Random Forests, Support Vector Machines, Naive Bayes, Neural Networks. Exploratory analysis revealed key environmental triggers influencing migration, such as seasonal temperature variations. Hyperparameter tuning further optimized performance. The results demonstrate that predictive analytics can enhance conservation strategies, reduce human-elephant conflict, support policy-making for habitat protection. Future work aims incorporate real-time tracking additional factors improve robustness applicability dynamic environments.

Language: Английский

Citations

0