Toward a Learnable Climate Model in the Artificial Intelligence Era

Artificial intelligence(AI)models have significantly impacted various areas of the atmospheric sciences,reshaping our approach to climate-related challenges.Amid this AI-driven transformation,the foundational role of physics in climate science has occasionally been overlooked.Our perspective suggests that the future of climate modeling involves a synergistic partnership between AI and physics,rather than an“either/or”scenario.Scrutinizing controversies around current physical inconsistencies in large AI models,we stress the critical need for detailed dynamic diagnostics and physical constraints.Furthermore,we provide illustrative examples to guide future assessments and constraints for AI models.Regarding AI integration with numerical models,we argue that offline AI parameterization schemes may fall short of achieving global optimality,emphasizing the importance of constructing online schemes.Additionally,we highlight the significance of fostering a community culture and propose the OCR(Open,Comparable,Reproducible)principles.Through a better community culture and a deep integration of physics and AI,we contend that developing a learnable climate model,balancing AI and physics,is an achievable goal.

Unified deep learning model for El Niño/Southern Oscillation forecasts by incorporating seasonality in climate data

Although deep learning has achieved a milestone in forecasting the El Niño-Southern Oscillation(ENSO),the current models are insufficient to simulate diverse characteristics of the ENSO,which depends on the calendar season.Consequently,a model was generated for specific seasons which indicates these models did not consider physical constraints between different target seasons and forecast lead times,thereby leading to arbitrary fluctuations in the predicted time series.To overcome this problem and account for ENSO seasonality,we developed an all-season convolutional neural network(A_CNN)model.The correlation skill of the ENSO index was particularly improved for forecasts of the boreal spring,which is the most challenging season to predict.Moreover,activation map values indicated a clear time evolution with increasing forecast lead time.The study findings reveal the comprehensive role of various climate precursors of ENSO events that act differently over time,thus indicating the potential of the A_CNN model as a diagnostic tool.