The recent revolution of data-driven forecasting systems based on artificial intelligence (AI) has opened new research possibilities in weather forecasting, climate science, and various other areas. At the same time, many open questions remain–such as how to properly evaluate the model outputs in terms of generalizability under climate change, whether models extrapolate to unseen extremes, and to what extent they are consistent with physical principles. This session focuses on new scientific approaches emerging from this AI revolution, limitations of current models, and strategies to overcome them. We encourage submissions that explore a wide range of topics, including evaluations of outputs and comparisons to numerical models, technical advancements in initial condition optimization or model fine-tuning, novel techniques from explainable AI, and other relevant studies. Bringing together experts from AI, climate sciences, statistics, and applied math will foster interdisciplinary collaborations and guide scientific progress in this quickly evolving field of research.