The Rise of AI in Weather and Climate Information and Its Impact on Global Inequity

The rapid integration of Artificial Intelligence (AI) into Earth system science promises a transformative revolution in predictive speed and fidelity, yet this technological prowess rests on a fragile and unequal foundation. We argue that the current trajectory of AI development risks automating and amplifying the historical North-South divide in the global climate information system. The systemic inequalities are manifested and compounded across the three primary stages of the AI modeling pipeline: input, process, and output.

At the input level, we highlight the risks of relying on global datasets, such as ERA5, which inadvertently inherit and reinforce geographic biases and observational gaps in the Global South; most notably in the Amazon and Sub-Saharan Africa. At the process level, we detail a profound compute sovereignty gap, where the concentration of exascale High Performance Computing infrastructure in the Global North gatekeeps the development of foundation models. Finally, at the output level, we demonstrate that AI-powered forecasting improvements are unevenly distributed, with wealthy regions seeing significantly greater skill gains than the vulnerable populations most in need of accurate early warning systems. 

To steer this revolution toward just outcomes, we call for a move toward Climate Digital Public Infrastructure. By prioritizing data-centric AI, human-cost evaluation metrics, and knowledge co-production, we can ensure that the AI revolution fosters genuine systemic resilience rather than exacerbating global inequity.