Hands-on courses combining AI, geospatial science, and modern development. Built by a researcher, designed for builders.
Learn to build geospatial web applications using AI-assisted development workflows. From prompting to production, master the art of shipping geo tools fast.
Master Land Use / Land Cover analysis with Dynamic World in Google Earth Engine. From satellite imagery to classified maps using cloud-based geospatial AI.
Build a CNN and fine-tune ResNet50 on real Sentinel-2 satellite imagery from the EuroSAT dataset. Train, evaluate, and export land use classifiers entirely in the cloud.
Learn classic machine learning for land cover mapping. Train a Random Forest on Sentinel-2 patches, use PCA for dimensionality reduction, and interpret feature importance - no GPU needed.
Learn to prompt DeepSeek to generate GEE code - no API key, just smart prompting. Map flood extent using Sentinel-1 SAR, compute flooded area in hectares, and export results.
Detect deforestation across North Morocco using the Hansen Global Forest Change dataset. Generate GEE scripts with DeepSeek AI, compute annual loss by year, and map fire-driven deforestation with FIRMS.
Map urban heat islands in North Morocco using Landsat 8 imagery and Google Earth Engine. Utilize DeepSeek AI to analyze and interpret the results, providing insights into urban climate dynamics.
Monitor drought in North Morocco using MODIS NDVI data and Google Earth Engine. Learn to calculate NDVI time series and use DeepSeek for code generation.
Detect coastal erosion in North Morocco using Sentinel-2 imagery and DeepSeek. Analyze NDWI and time series data to identify areas at risk.
Analyze snow cover changes in North Morocco using MODIS data and Google Earth Engine. Learn to process satellite imagery and generate code with DeepSeek for efficient geospatial analysis.
Map cropland in North Morocco using Sentinel-2 and Dynamic World data in Google Earth Engine. A practical introduction to remote sensing for land cover classification.
Map wildfire risk in North Morocco using MODIS data and Google Earth Engine. Analyze fire detections, vegetation indices, and land surface temperature to identify vulnerable areas.
Monitor water quality using Sentinel-2 imagery and DeepSeek AI in Google Earth Engine. Analyze water bodies in North Morocco, estimate key parameters, and export your results.
Map solar energy potential in North Morocco using PVGIS principles and DeepSeek. Analyze ERA5-Land data and SRTM DEM in GEE to identify suitable locations for solar panel installations.
Map air quality using Sentinel-5P NO2 data in Google Earth Engine. Learn to filter, mask, and visualize NO2 concentrations and leverage DeepSeek for efficient code generation.
Detect mangrove loss using Hansen GFC data in Google Earth Engine. Learn to refine your analysis with DeepSeek AI for better accuracy in coastal forest monitoring.
Map glacier retreat in North Morocco using Landsat imagery and Google Earth Engine. Learn to calculate NDSI, classify glaciers, and visualize changes over time, enhanced with DeepSeek code generation.
Learn to estimate soil moisture using Sentinel-1 SAR data in Google Earth Engine. Use DeepSeek to generate code and analyze soil moisture trends in North Morocco.
Analyze urban green spaces in North Morocco using Landsat 8 imagery and NDVI. Learn to leverage Google Earth Engine and AI-powered tools for efficient geospatial analysis.
Detect dust storms in North Morocco using MODIS data and AI-generated code. Learn to process satellite imagery and leverage DeepSeek for rapid geospatial analysis.
Map land degradation in North Morocco using NDVI trends derived from Landsat 8 data in Google Earth Engine. Learn to calculate NDVI, perform time series analysis, and identify areas with significant degradation.
Map informal settlements in North Morocco using Sentinel-2 imagery and DeepSeek AI. This course teaches you to preprocess satellite data and leverage AI for urban feature extraction in Google Earth Engine.
Delinate river floodplains in North Morocco using SRTM DEM data and Google Earth Engine. Learn to calculate flow accumulation, apply thresholds, and refine results with NDWI using Sentinel-2 imagery, and automate the process with DeepSeek.
Detect crop stress in North Morocco using Sentinel-2 red edge bands and Google Earth Engine. Learn to calculate NDRE, identify stressed areas, and integrate DeepSeek for automated analysis, even with limited remote sensing experience.
Master global night light time-series analysis using VIIRS satellite imagery in Google Earth Engine. Learn to filter stray-light corrected composites, fit pixel-wise temporal trends, and execute machine learning workflows.
Master urban health surveillance workflows using Google Earth Engine. Combine Sentinel-5P air pollution data, MODIS thermal imagery, and GHSL infrastructure layers with spatial machine learning to evaluate global city exposures.
Learn to combine Google Trends web search volume metrics with Earth observation climate variables using Google Earth Engine. Build predictive machine learning models to map global syndromic health proxies while addressing spatial bias.
Learn to model dengue transmission risk across tropical Southeast Asia by integrating ERA5-Land climate reanalysis, CHIRPS precipitation, MODIS vegetation indices, and WorldPop demographics using Random Forest machine learning in Earth Engine.
Learn to model physical healthcare travel time and isolate underserved populations in Sub-Saharan Africa using WorldPop and global friction surface datasets inside Google Earth Engine.
Master advanced spatial health workflows by combining Landsat Land Surface Temperature, WorldPop demographic layers, and GeoAI machine learning algorithms to model urban heat vulnerability across global cities.
Quantify ambient NO2 air pollution exposure and evaluate respiratory health risk across global urban centers using Sentinel-5P, ERA5, GHSL, and machine learning models in Google Earth Engine.
Master advanced SAR remote sensing and demographic integration in Google Earth Engine to map flood extent and quantify public health risk exposure during severe inundation events.
Master climate-driven vector-borne disease risk modeling using multi-sensor satellite imagery and Random Forest classifiers in Google Earth Engine. Quantify tropical environmental suitability proxies for public health surveillance and climate adaptation planning.
Master advanced spatial epidemiology workflows by combining ERA5-Land climate data, MODIS vegetation indices, and WorldPop grids. Learn to model disease vector suitability and quantify exposed populations using GeoAI.
Learn to integrate WorldPop data, Sentinel-5P atmospheric metrics, and ERA5 thermal climate reanalysis in Google Earth Engine to construct spatial population vulnerability indices for public health management.
Learn how to quantify urban air pollution, surface heat islands, and population vulnerability across global cities using Sentinel-5P, MODIS, and GHSL datasets in Google Earth Engine.
IoT for Environmental Monitoring, Flood Prediction with ML, Spatial Epidemiology, and more.