Detecting crop growth phases from Earth Observation data

KappaZeta Ltd
Based on the farmer user interviews of KappaZeta (run in 2020/21) detecting the crop growth phase is one of the most important questions a farmer and agronomist needs to know. Several agri-technical decisions rely on the crop growth phase as an input. It is possible to provide a list of services based on crop-growth phase information, including:
- recommendation for optimal timing of the fertilizer application;
- recommendation for optimal timing of pesticide/fungicide application;
- harvesting time recommendation, etc.
Optical and radar satellite imagery provide a rich set of input features that can be related with crop growth phase. The task is to develop growth-phase detection models for the most common crops in Northern European conditions, including: spring barley, winter wheat and winter rapeseed. As input features both aggregated parcel-based statistics (min, max, median, average and stddev) and raster images' time series should be considered.
It is an interdisciplinary topic to be solved in cooperation with Estonian University of Life Sciences.
Graduation Theses defence year
Kaupo Voormansik
Spoken language (s)
Estonian, English
Requirements for candidates
The candidates should have basic software development skills and know the fundamentals of machine learning and deep learning. Interest towards Earth Observation and satellite technology is required, but prior knowledge is not. KappaZeta can provide the basic training needed to get going.
Bachelor, Masters

Application of contact

Kaupo Voormansik
See more