Urban forests are crucial for achieving sustainable development by improving biodiversity, equity, and sustainability in cities. High tree biodiversity and structure complexity can increase resilience and decrease temperature stress. However, urban forests are often inequitably distributed due to past discriminatory practices. Integrating remote sensing data (Sentinel2 and GEDI) and field observations, our machine learning models efficiently predict forest structure and diversity, identifying areas where conservation and restoration efforts can have a significant impact on people and nature. These results can guide efforts to improve the quality, distribution and access to urban forests and enhance human well-being in an equitable way.
