Abstract
Industrial lands, as a key component of economic development, pose great environmental challenges, which underscores the need for close global monitoring to support sustainable urban development. Despite this importance, global city-level maps of industrial land use, especially over multiple years, have been lacking. Here, we present a 10-m resolution global dataset tracking industrial land use in 1,093 large cities (area 100 km² or more) from 2017 to 2023. Using multisource geospatial data and machine learning, the dataset achieves a high overall accuracy of 91.87% to 92.21% across the seven-year period, aligning well with official city maps. We further validated its reliability by computing industrial land area per capita for 1,093 cities, which correlated strongly with per capita CO2 emissions (r = 0.72). These maps offer a valuable tool for tracking industrial land use changes and assessing their impact on urban ecosystems. The dataset is a critical resource for studying the links between industrialization, urbanization, and environmental sustainability while providing insights to policymakers on balancing economic and environmental priorities.
| Original language | English |
|---|---|
| Article number | 278 |
| Journal | Scientific data |
| Volume | 12 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 16 Feb 2025 |
ASJC Scopus subject areas
- Statistics and Probability
- Information Systems
- Education
- Computer Science Applications
- Statistics, Probability and Uncertainty
- Library and Information Sciences