Coding with LLMs
Earners of this badge have completed a hands-on workshop in which they used prompt engineering and Google Gemini to write and debug Python code in Google Colab. Working with real U.S. Census and NASA satellite (HLS NDVI) data for the Baltimore region, participants built a geospatial analysis pipeline that integrates socioeconomic and remote sensing datasets to identify environmental justice hotspots. The workshop emphasized practical strategies for working with LLMs to accelerate analysis, lower coding barriers, and generate reproducible, data-driven insights — no prior Python experience required.
About this Credential
Learning Objectives:
- Apply prompt engineering strategies (context, expectations, iterative refinement, persona framing) to guide LLMs in generating working Python code.
- Navigate the Google Colab environment and manage a Python workspace including library installation, file access, and working directory setup.
- Load, inspect, and process geospatial vector and raster datasets (GeoJSON, GeoTIFF) using GeoPandas and rasterio.
- Construct a Social Vulnerability Index (SVI) by computing and normalizing socioeconomic metrics from U.S. Census data.
- Integrate satellite-derived NDVI data with census tract data using zonal statistics to calculate a Green Space Inequity Index.
- Apply data visualization techniques including choropleth maps, scatter plots, correlation heatmaps, and histograms to communicate environmental justice findings.
- Use KMeans clustering to identify spatially distinct environmental justice patterns and interpret cluster profiles.
- Identify and prioritize census tracts with the greatest environmental justice needs using a composite data-driven scoring approach.
- Copy the specific credential link for your earned record from your My Credentials page.
- In LinkedIn, choose Add profile section > Licenses & Certifications.
- Use this badge title as the certification name and “University of Maryland Center for Environmental Science (UMCES)” as the issuing organization.
- Paste your unique credential link into “Credential URL”.