Atlas Urban Index: A VLM-Based Approach for Spatially and Temporally Calibrated Urban Development Monitoring
Mithul Chander, Sai Pragnya Ranga, Prathamesh Mayekar
TL;DR
The paper addresses the need for robust, scalable urban development monitoring by overcoming limitations of pixel-based indices like NDBI, which are sensitive to atmosphere, seasonality, and cloud cover. It introduces the Atlas Urban Index (AUI), a Vision-Language Model (VLM)-based framework that fuses a time series of Sentinel-2 imagery with cloud-filtered windows and a triplet of inputs—current image, a curated set of reference images with known AUI levels, and the immediate past image—to calibrate spatial and temporal scores. AUI scores range from $0$ to $10$, partitioned into discrete ranges (0, 1--2, 3--4, 5--6, 7--8, 9--10), and are demonstrated on Bangalore regions where AUI aligns with observed urbanization trends and outperforms the NDBI metric, defined as $NDBI = rac{SWIR - NIR}{SWIR + NIR}$. The approach is designed to generalize to other standardized spatial units and imagery sources, with practical implications for urban planning, real estate, and policy evaluation, and offers avenues for forecasting future development through data augmentation and supervised learning.
Abstract
We introduce the {\em Atlas Urban Index} (AUI), a metric for measuring urban development computed using Sentinel-2 \citep{spoto2012sentinel2} satellite imagery. Existing approaches, such as the {\em Normalized Difference Built-up Index} (NDBI), often struggle to accurately capture urban development due to factors like atmospheric noise, seasonal variation, and cloud cover. These limitations hinder large-scale monitoring of human development and urbanization. To address these challenges, we propose an approach that leverages {\em Vision-Language Models }(VLMs) to provide a development score for regions. Specifically, we collect a time series of Sentinel-2 images for each region. Then, we further process the images within fixed time windows to get an image with minimal cloud cover, which serves as the representative image for that time window. To ensure consistent scoring, we adopt two strategies: (i) providing the VLM with a curated set of reference images representing different levels of urbanization, and (ii) supplying the most recent past image to both anchor temporal consistency and mitigate cloud-related noise in the current image. Together, these components enable AUI to overcome the challenges of traditional urbanization indices and produce more reliable and stable development scores. Our qualitative experiments on Bangalore suggest that AUI outperforms standard indices such as NDBI.