Tree inventory analysis using AI and GIS in Uzbekistan: A case study from Tashkent
This study explores the application of artificial intelligence (AI) and geographic information systems (GIS) for tree inventory analysis in Tashkent, Uzbekistan, providing a pioneering model for urban forestry management in Central Asia. Rapid urbanization in Tashkent has intensified the need for ef...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | BIO Web of Conferences |
| Online Access: | https://www.bio-conferences.org/articles/bioconf/pdf/2025/24/bioconf_afe2024_01043.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study explores the application of artificial intelligence (AI) and geographic information systems (GIS) for tree inventory analysis in Tashkent, Uzbekistan, providing a pioneering model for urban forestry management in Central Asia. Rapid urbanization in Tashkent has intensified the need for efficient and accurate methods to monitor and manage urban trees, which play a crucial role in mitigating environmental challenges. Using high-resolution satellite imagery, we employed a Convolutional Neural Network (CNN) for initial tree detection and classification, supplemented by a Random Forest algorithm to refine classification accuracy. Tree locations were mapped on a true-color satellite image, visualized through GIS, enabling detailed analysis of spatial distribution and density across the city’s districts. The results show substantial variation in tree density, with Yunusobod district demonstrating the highest tree count and detection accuracy, while Chilonzor and Yakkasaroy faced marginally lower accuracy rates. Overall, this AI-GIS approach achieved an accuracy rate of 88.8%, demonstrating the potential for scalable urban tree inventory management. This study offers a valuable framework for Tashkent and similar cities, contributing to sustainable urban planning and resilience against environmental stressors through data-driven urban forestry practices. |
|---|---|
| ISSN: | 2117-4458 |