Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abuhani, Diaa Addeen, Seccaroni, Marco, Mazzarello, Martina, Zualkernan, Imran, Duarte, Fabio, Ratti, Carlo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908499927105536
author Abuhani, Diaa Addeen
Seccaroni, Marco
Mazzarello, Martina
Zualkernan, Imran
Duarte, Fabio
Ratti, Carlo
author_facet Abuhani, Diaa Addeen
Seccaroni, Marco
Mazzarello, Martina
Zualkernan, Imran
Duarte, Fabio
Ratti, Carlo
contents Urban tree biodiversity is critical for climate resilience, ecological stability, and livability in cities, yet most municipalities lack detailed knowledge of their canopies. Field-based inventories provide reliable estimates of Shannon and Simpson diversity but are costly and time-consuming, while supervised AI methods require labeled data that often fail to generalize across regions. We introduce an unsupervised clustering framework that integrates visual embeddings from street-level imagery with spatial planting patterns to estimate biodiversity without labels. Applied to eight North American cities, the method recovers genus-level diversity patterns with high fidelity, achieving low Wasserstein distances to ground truth for Shannon and Simpson indices and preserving spatial autocorrelation. This scalable, fine-grained approach enables biodiversity mapping in cities lacking detailed inventories and offers a pathway for continuous, low-cost monitoring to support equitable access to greenery and adaptive management of urban ecosystems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering
Abuhani, Diaa Addeen
Seccaroni, Marco
Mazzarello, Martina
Zualkernan, Imran
Duarte, Fabio
Ratti, Carlo
Computer Vision and Pattern Recognition
Machine Learning
Urban tree biodiversity is critical for climate resilience, ecological stability, and livability in cities, yet most municipalities lack detailed knowledge of their canopies. Field-based inventories provide reliable estimates of Shannon and Simpson diversity but are costly and time-consuming, while supervised AI methods require labeled data that often fail to generalize across regions. We introduce an unsupervised clustering framework that integrates visual embeddings from street-level imagery with spatial planting patterns to estimate biodiversity without labels. Applied to eight North American cities, the method recovers genus-level diversity patterns with high fidelity, achieving low Wasserstein distances to ground truth for Shannon and Simpson indices and preserving spatial autocorrelation. This scalable, fine-grained approach enables biodiversity mapping in cities lacking detailed inventories and offers a pathway for continuous, low-cost monitoring to support equitable access to greenery and adaptive management of urban ecosystems.
title Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.13814