The field of environmental forecasting and climate modeling is rapidly advancing, driven by innovations in machine learning, data analytics, and high-performance computing. Recent developments have focused on improving the accuracy and efficiency of forecasting models, particularly for complex phenomena such as weather patterns, sea surface temperature, and sea ice drift. Notable advancements include the use of deep learning techniques, such as convolutional neural networks and generative models, to predict climate variables and improve forecast skill. Additionally, researchers have explored the application of transfer learning and multi-task learning to adapt models to new domains and tasks, reducing the need for large amounts of labeled training data. These advancements have significant implications for climate modeling, weather forecasting, and decision-making in environmental and economic sectors. Noteworthy papers in this area include the Physics-Guided AI Cascaded Corrector Model, which significantly extends the skillful forecast range of the Madden-Julian Oscillation, and the Flow Matching-based generative AI model, which efficiently forecasts the spatiotemporal evolution of stratospheric circulation. The Radar DataTree framework also stands out for its ability to transform operational radar archives into FAIR-compliant, cloud-optimized datasets, enabling efficient and scalable analysis.