A temporal stack of Sentinel-2 images of a small area in Slovenia, followed by a land cover prediction, obtained via methods presented in this post.
Diagram of a machine learning pipeline, showing that the ML code actually represents a relatively small part of the ML pipeline. Source: Sculley et al. Hidden Technical Debt in Machine Learning Systems, NIPS 2015
A visual representation of a temporal stack of Sentinel-2 images over a randomly selected area. The transparent pixels on the left imply missing data due to cloud coverage. The stack on the right represents the pixel values after temporal interpolation, taking cloud masks into account.
Temporal evolution of NDVI values for pixels of selected land cover types through the year.
Reference map for a small part of the AOI before (left) and after (right) the application of the negative buffer on the map.
Schematic of the decision trees in the LightGBM framework. Source: http://arogozhnikov.github.io/2016/06/24/gradient_boosting_explained.html
Two aspects of viewing the normalised confusion matrix of a trained model.
Frequency of pixels for each class in the training dataset. In general, the distribution is not uniform.
ROC curves of the classifier, represented as “one vs. rest” for each class in the dataset. Numbers in brackets are the area-under-curve (AUC) values.
A part of this AOI consisting of 3x3 EOPatches covered with snow.
Sentinel-2 image (left), ground truth (centre) and prediction (right) for a random EOPatch in the selected AOI. Some differences are visible, which is mostly due to the application of the negative buffer on the reference map, otherwise the agreement is satisfactory for this use case.
Screenshot of the land cover prediction for Slovenia 2017 using the approach shown in this blog post, available for detailed browsing in the CloudGIS Geopedia portal (https://www.geopedia.world/#T244).
Sentinel-2 image (left), ground truth (centre) and prediction (right) for the area around the small sports airfield Levec, near Celje, Slovenia. The classifier correctly recognises the landing strip as grassland, which is marked as artificial surface in the official land use data.
Sentinel-2 image (left), ground truth (centre) and prediction (right) for the area around the Ljubljana Jože Pučnik Airport, the largest airport in Slovenia. The classifier recognises the tarmac runway and the road network, while still correctly identifying grassland and cultivated land in the surrounding area.

Sentinel Hub Blog

Stories from the next generation satellite imagery platform

Thanks to Grega Milcinski, Miha Kadunc, Devis Peressutti, Anze Zupanc, and Matej Batič

Matic Lubej

Written by

Data Scientist from Slovenia with a Background in Particle Physics.

Sentinel Hub Blog

Stories from the next generation satellite imagery platform

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade