Heatwaves lead to catastrophic consequences on public health and the economy. Accurate and timely predictions of regional heatwaves can improve climate preparedness and foster decision‐making to alleviate the burdens due to climate change. In this paper, we propose a heatwave prediction algorithm based on a novel deep learning model, that is, Graph Neural Network (GNN). This new GNN framework can provide real time warnings of the sudden occurrence of regional heatwaves with high accuracy at lower costs of computation and data collection. In addition, its interpretable structure unravels the spatiotemporal patterns of regional heatwaves and helps to enrich our understanding of the general climate dynamics and the causal influences between locations. The proposed GNN framework can be applied for the detection and prediction of other extreme or compound climate events, which calls for future studies.

Global climate changes, especially the rise of global mean temperature due to the increased carbon dioxide (CO₂) concentration, can, in turn, result in higher anthropogenic and biogenic greenhouse gas emissions. This potentially leads to a positive loop of climate–carbon feedback in the Earth’s climate system, which calls for sustainable environmental strategies that can mitigate both heat and carbon emissions, such as urban greening. In this study, we investigate the impact of urban irrigation over green spaces on ambient temperatures and CO₂ exchange across major cities in the contiguous United States. Our modeling results indicate that the carbon release from urban ecosystem respiration is reduced by evaporative cooling in humid climate, but promoted in arid/semi-arid regions due to increased soil moisture. The irrigation-induced environmental co-benefit in heat and carbon mitigation is, in general, positively correlated with urban greening fraction and has the potential to help counteract climate–carbon feedback in the built environment.

Advances in data science and artificial intelligence (AI) offer unprecedented opportunities to provide actionable insights, drive innovative solutions, and create long-term strategies for sustainable development in response to the triple existential crises facing humanity: climate change, pollution, and biodiversity loss. The rapid development of AI models has been the subject of extensive debate and is high on the political agenda, but at present the vast potential for AI to contribute positively to informed decision making, improved environmental risk management, and the development of technological solutions to sustainability challenges remains underdeveloped. In this paper, we consider four inter-dependent areas in which data science and AI can make a substantial contribution to developing sustainable future interactions with the environment: (i) quantification and tracking progress towards the United Nations Sustainable Development Goals; (ii) embedding AI technologies to reduce emissions at source; (iii) developing systems to increase our resilience to natural hazards; (iv) Net Zero and the built environment. We also consider the wider challenges associated with the widespread use of AI, including data access and discoverability, trust and regulation, inference and decision making, and the sustainable use of AI.