GeoAI at the forefront of climate action

Abstract

GeoAI, merging artificial intelligence with geospatial data, is transforming climate change mitigation and adaptation. This review synthesizes 2020–2025 advancements, focusing on deep learning models like convolutional neural networks (CNNs) and transformers, achieving 90–95% accuracy in flood prediction, carbon sequestration mapping, and urban heat mitigation. Key mitigation strategies include forest biomass estimation in the Amazon and renewable energy optimization in India, while adaptation efforts encompass real-time flood mapping in Bangladesh and coastal resilience modeling in the Pacific Islands. Despite successes, challenges persist, including data biases, computational costs, and ethical concerns like privacy in urban GeoAI applications. Public discourse on platforms like X highlights demand for equitable climate solutions, reflected in discussions on wildfires and Arctic rain. Future directions involve federated learning for privacy-preserving GeoAI and generative AI for climate scenario modeling. Aligning with Sustainable Development Goal 13, GeoAI offers transformative potential to enhance global climate resilience, necessitating investment in open-access tools and interdisciplinary collaboration to address research gaps and ensure inclusivity.