Nick Lempesis

Maps, GIS and geospatial web

Image classifications


I have carried out satellite imagery classification using a number of methods and software. For Coursera's GIS Specialisation, I classified Landsat 8 images of central Chile from 2014 using false-colour composites to find the extent of wildfires the country was fighting at the time.

This was an unsupervised classification in ArcMap. In my MSc course on remote sensing I calculated the seasonal shrinkage of Lake Chilwa in Malawi using ERDAS Imagine and European Space Agency's SNAP software. The classification used a Random Forest algorithm after a comparative literature review on classification options. I tested for accuracy and produced an error matrix for manual samples.

Cover Image for Infrastructure map

Infrastructure map

Country-wide infrastructure visualisation
Cover Image for Productivity GIS tools

Productivity GIS tools

Improving editorial efficiency
Cover Image for Line network processing

Line network processing

Data integration with smart suggestions
Cover Image for Structure from motion

Structure from motion

Drone photogrammetry and point-cloud
Cover Image for Land plot database

Land plot database

Custom geodatabase schema
Cover Image for Windfarm visual impact

Windfarm visual impact

Landscape change in animated 3D
Cover Image for Coordinate transformations

Coordinate transformations

Programming geomatics in Python
Cover Image for Windfarm siting algorithm

Windfarm siting algorithm

Automating a site-finding workflow