California is one of the major rice-producing regions in the United States, with a significant concentration of production in the Sacramento Valley. Rice production depends heavily on environmental conditions, seasonal patterns, and water availability. This project was motivated by an interest in exploring how open geospatial datasets and satellite observations can be combined to build reproducible workflows for agricultural monitoring.

The focus of this presentation is not on developing a final prediction model, but on building a practical Python-based geospatial workflow using open-source tools and public datasets. The workflow explores how publicly available agricultural boundaries and geospatial data can be integrated with satellite-derived environmental indicators.

Topics covered include:

Accessing and filtering public agricultural polygon datasets
Integrating satellite observations into a Python workflow
Exploring indicators related to vegetation conditions, photosynthetic activity, and environmental changes
Building workflows using tools such as Google Earth Engine Python API, GeoPandas, and Jupyter/Colab
Data preprocessing and visualization techniques
Lessons learned while handling large-scale geospatial datasets

The workflow is intentionally designed to remain flexible regarding the choice of satellite datasets and derived indicators. Rather than focusing on a single metric, the goal is to create a reusable and reproducible framework that can be adapted to different agricultural and environmental applications.

Attendees will gain practical insights into designing Python-based geospatial workflows and integrating public GIS and satellite datasets into real-world analysis pipelines.