This MSc topic is linked to the STARS (Spurring a Transformation for Agriculture through Remote Sensing) project. STARS explores ways to use remote sensing technology to improve agricultural practices of smallholder farmers in sub-Saharan Africa and South Asia with the hope of advancing the livelihoods of famers and their families in some of the world’s poorest countries.

To achieve this, STARS has collected a temporally dense set of RGB and multispectral images over agricultural lands dominated by smallholder farming activities. These images, acquired from unmanned aerial vehicles (UAVs) as well as from very high spatial resolution (VHR) satellite sensors, were used to recognize crop types and to monitor crop condition. This topic deals with the former task. More precisely, with the use of Google Earth Engine (a cloud-based storage and processing platform) to design a multi-classifier system to map crop types using the time series of images collected by the STARS project (e.g. UAV, Worldview-2 and -3, RapidEye, Landsat and, eventually, the Sentinels 1 and 2)

In this context, a multi-classifier system should be understood as a system that combines the outputs provided by various classifiers (e.g. support vector machines, random forest, etc). The combination of these classifiers will result in heterogeneous ensembles.  This provides the second challenge of this topic: how to smartly combine the outcome of individual classifiers to produce a better cropland map.

Besides the STARS team (for more information visit http://www.stars-project.org), one PhD student (Azar Zafari) and one post-doc (Emma Izquierdo-Verdiguier) are working on this topic. These researchers can advise and/or co-supervise the MSc candidate. Given the nature of the topic, an analytical mind and affinity with scripting are highly recommended for this MSc research topic.