I will share how our team built an end-to-end system to transform raw satellite imagery into analysis-ready datasets for use cases like vegetation monitoring, deforestation detection, and identifying third-party activity. We streamlined the entire pipeline from automated acquisition and cloud storage to preprocessing that ensures spatial, spectral, and temporal consistency. By leveraging Prefect for orchestration, Anyscale Ray for scalable processing, and the open source STAC standard for metadata indexing, we reduced processing times from days to near real-time. We addressed challenges like inconsistent metadata and diverse sensor types, building a flexible system capable of supporting large-scale geospatial analytics and AI workloads.

On Survivor, it's all fun and games until someone fails and a challenge is lost. People scramble, they frantically search for hidden immunity idols (and sometimes even crazier things happen).

Within data teams, everything is fine until that one Slack alert comes in about a failed run. Chaos doesn't need to ensue between analytics and data engineers when triaging an error with the warehouse or upstream infrastructure. Order fulfillment? Orders are initiated by a user in a web app. Fraud detection? The logic is usually based on ML models that require training and testing. Workflows are connected, making disparate systems a necessity to connect.

The keys to success on Survivor, and on data teams: create links to find hidden immunity idols—I mean, the root cause of why a workflow failed.

Run double duty during this talk: learn about Survivor social science and how to bridge the gap between analytics and data engineering beyond the warehouse for a one-happy-family feeling.

Speaker: Sarah Krasnik Bedell, Growth Lead, Prefect

Register for Coalesce at https://coalesce.getdbt.com