💻 Software & Environment Setup
Agriculture & Food Technology
The computational toolchain and environment used throughout Space to Soil: Practical AI Applications in Satellite Imagery.
Space soil practical training course for researchersAgriculture workshopLearn space soil practicalWeather training for researchersSatellite workshopWeather workshop
# Recommended conda environmentconda create -n dstc_env python=3.11 -yconda activate dstc_envpip install rasterio geopandas scikit-learn xarrayGoogle Earth Engine
Remote-sensing crop analysis
Remote-sensing crop analysis
QGIS
Field mapping & spatial analysis
Field mapping & spatial analysis
R (agricolae)
Agronomic trial statistics
Agronomic trial statistics
scikit-learn
Yield & disease prediction models
Yield & disease prediction models
Supported OS: Linux (Ubuntu 22.04+), macOS, or Windows via WSL2.
Hardware: 16 GB RAM minimum; a CUDA GPU helps for deep-learning modules.
Earn government-registered certification in Space to Soil: Practical AI Applications in Satellite Imagery
e-Certificate and e-Marksheet issued on successful completion.
