Tutorials

Geospatial Data Science

Code, cloud, and automation — the future of working with spatial data.

Geospatial Data Science

Integrating programming, cloud analytics, statistical modelling and artificial intelligence for modern geospatial solutions.

Python

The language that powers modern geospatial work.

Python has become the world's leading programming language for Remote Sensing, GIS and Geospatial Data Science. It allows researchers and engineers to automate workflows, analyse spatial datasets, build machine learning models and develop powerful GIS applications.

Learning Track

Basics of Python Programming

Variables, loops, functions, modules, scripting and automation for GIS and Remote Sensing.

Geospatial Python Libraries

GeoPandas, Rasterio, Shapely, Fiona, PyProj and GDAL.

Spatial Analysis & Visualization

Spatial statistics, raster processing, mapping and automated GIS workflows.

Python Example

import geopandas as gpd

roads = gpd.read_file("roads.shp")

buffer = roads.buffer(500)

buffer.to_file("roads_buffer.gpkg")

R

Where spatial analysis meets statistical power.

R is widely used for advanced statistical analysis, spatial modelling, predictive analytics and scientific visualization. It is the preferred language for many researchers working in Remote Sensing, GIS and environmental science.

Learning Track

Introduction to R Programming

Learn syntax, vectors, data frames, scripting and spatial workflows using R.

Spatial Packages (sf, terra, raster & tmap)

Perform vector, raster, terrain analysis and create publication-quality maps.

Statistical Modelling & Visualization

Regression, interpolation, clustering, kriging, predictive modelling and reporting.

R Code Example

library(sf)
library(terra)
library(tmap)

roads <- st_read("roads.shp")

tm_shape(roads)+
tm_lines(col="blue")

tmap_save(
"road_network.png"
)

Google Earth Engine (GEE)

Planet-scale geospatial analysis directly from your browser.

Google Earth Engine combines decades of satellite imagery with Google's cloud computing platform, allowing researchers to analyse enormous spatial datasets without requiring powerful local computers. It has become one of the most important cloud platforms for Remote Sensing and environmental monitoring.

Learning Track

Cloud-Based Geospatial Processing

Learn image collections, feature collections, reducers, client-server concepts and cloud GIS workflows.

Satellite Image Processing

Process Sentinel, Landsat and MODIS imagery, calculate NDVI, NDWI, LST and create cloud-free composites.

Time-Series & Machine Learning

Perform land cover classification, change detection, temporal analysis and Random Forest modelling at planetary scale.

Google Earth Engine JavaScript Example

// Load Sentinel-2 Collection

var collection = ee.ImageCollection('COPERNICUS/S2_SR')
.filterBounds(study_area)
.filterDate('2025-01-01','2025-12-31')
.filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE',10));

// Median Composite

var image = collection.median();

Map.centerObject(study_area,10);

Map.addLayer(image,{
bands:['B4','B3','B2'],
min:0,
max:3000
},'Sentinel-2 RGB');

Additional Tools & Techniques

Build a complete geospatial technology ecosystem.

Modern geospatial professionals work with far more than programming languages. Desktop GIS, cloud platforms, spatial databases, automation tools and collaborative development environments all play an essential role in professional GIS, Remote Sensing and Geospatial Data Science projects.

Learning Track

Desktop GIS & Spatial Analysis

Master professional GIS software including QGIS, ArcGIS Pro and GRASS GIS for mapping, editing, spatial analysis, geoprocessing, cartography and terrain modelling.

Automation & Geospatial Development

Learn GDAL, OGR, PyQGIS, ArcPy, PostGIS, GeoServer and REST APIs to automate GIS workflows and build enterprise geospatial applications.

Cloud, AI & Collaborative Workflows

Work with GitHub, Docker, Jupyter Notebook, VS Code, AWS, Microsoft Planetary Computer, Machine Learning and AI-powered geospatial applications.

GDAL Command Example

# Convert GeoTIFF to COG

gdal_translate \
input.tif \
output_cog.tif \
-of COG

# Reproject Raster

gdalwarp \
-t_srs EPSG:4326 \
input.tif \
output_wgs84.tif

# Generate Tiles

gdal2tiles.py \
-z 0-18 \
output_wgs84.tif \
tiles/

Professional Skills You'll Develop

Spatial Database Design

PostgreSQL/PostGIS, Spatial SQL, indexing, optimization and enterprise geodatabase management.

WebGIS Deployment

Publish interactive GIS applications using GeoServer, Leaflet, OpenLayers, MapLibre GL and cloud hosting.

End-to-End Geospatial Workflow

Integrate satellite imagery, field surveys, GIS analysis, Machine Learning, visualization and web publishing into one professional workflow.