Foundation models bring a new way of predicting floods, wildfires and heat waves linked to climate change. IBM's Geospatial Studio is designed to simplify model customization. Fine-tuning required some expertise in curating data and training AI models. It can involve adapting the model’s architecture, cleaning and harmonizing data from different modalities, and incorporating data into the model without causing it to forget what it previously learned. With a geospatial foundation model, fine-tuning may require integrating satellite images with historical weather observations, street maps and climate projections. IBM Research developed the Geospatial Studio, a cloud-native toolkit, that guides you through data curation, fine-tuning and model deployment and visualization of results.