The development of AI models is increasing at a rapid rate. However, when are they ready to be deployed in real-world operational settings? In this paper, we introduce a framework to support such assessments and apply it to Google’s recently released AI-based flood prediction system, which is claimed to achieve “reliability in predicting extreme riverine events” and provide “accurate and timely warnings” that are available “earlier and over larger and more impactful events in ungauged basins”. The system has been integrated into an operational early-warning platform producing open, real-time forecasts in more than 80 countries. While this development promises to usher in a new and exciting age in global flood forecasting, the supporting evidence relies heavily on several subjective choices, the implications of which have not been acknowledged or assessed. Here, we evaluate the consequences of these choices on claims of operational deployment readiness across four dimensions: predictive accuracy, forecast timeliness, the characterization of extreme events, and benchmarking against state-of-the-art models. Our assessment reveals that the system’s actual predictive accuracy is likely to be substantially lower than reported—particularly for extreme events—raising concerns about responsible practices across modelling and publicity in high-stakes applications. The deployment of the Google AI model therefore risks misinforming those who depend on its outputs for evacuation and preparedness decisions, particularly in less-developed countries such as those targeted by the enterprise, given its alarmingly high (>90%) rates of false positives and false negatives. Beyond the immediate operational consequences, if left unaddressed, these outcomes may erode public trust in AI within hydrological sciences. We conclude by calling for greater transparency, accountability, and methodological rigor in the integration of AI into flood forecasting.

Sustainable management of water resources is crucial for humanity. However, traditional methods for achieving this are becoming obsolete. This is because they are underpinned by the assumption that we have a good understanding of how water availability and demand will change in the future. However, based on our current experience with climate change, this is not the case. In fact, rather than having a good understanding of what the future might look like, it is, in fact, deeply uncertain. Consequently, a new paradigm for water resources management is needed; one that accounts for deep uncertainty by embracing scenario thinking. We categorize and summarize different causes of deep uncertainty in water resources management and provide examples of how an emerging paradigm rooted in scenario thinking can deal with these. We hope to stimulate discussion to enable this new paradigm to be developed further and embedded in standard practice.

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.