Google Research is driven by exploring the art of the possible and is making a tangible difference in tackling climate crises such as wildfires, floods, extreme weather, and cyclones. The company is advancing research and harnessing tech innovation to help build more resilience and deliver timely, reliable predictions of these threats. Google Research's groundbreaking global hydrological AI model enables accurate flood forecasting around the world up to seven days in advance, covering over 700 million people across more than 100 countries. The company is also working on improving the lead time and accuracy of cyclone forecasts, predicting existence, track, intensity, size, and structure up to 15 days in advance. Additionally, Google Research is applying AI to improve forecasts for everyday weather, generating hyper-local, short-term weather predictions with a 5km resolution, updated every 15 minutes, up to 12 hours ahead. The company is also leveraging AI to understand and mitigate the growing threat of wildfires, detecting fires as small as a 5x5 meter classroom with its FireSat satellite constellation. Furthermore, Google Research is pioneering new frontiers by enabling insights about the planet with Geospatial Reasoning, a framework that brings Earth models together with generative AI to accelerate geospatial problem solving. The company is also using AI to reduce transport-related emissions and improve air quality, paving the way for making air and ground transportation more sustainable. Overall, Google Research is confident that advancing AI and scientific research can play a key role in addressing the difficult problems of timely, reliable global predictions, working towards better climate resilience.