Analyzing the planet at scale with satellite imagery and machine learning is a dream that has been constantly hindered by the cost of difficult-to-access highly-representative high-resolution imagery. To remediate this, we introduce here the WorldStratified dataset. The largest and most varied such publicly available dataset, at Airbus SPOT 6/7 satellites' high resolution of up to 1.5 m/pixel, empowered by European Space Agency's Phi-Lab as part of the ESA-funded QueryPlanet project, we curate 10,000 sq km of unique locations to ensure stratified representation of all types of land-use across the world: from agriculture to ice caps, from forests to multiple urbanization densities. We also enrich those with locations typically under-represented in ML datasets: sites of humanitarian interest, illegal mining sites, and settlements of persons at risk. We temporally-match each high-resolution image with multiple low-resolution images from the freely accessible lower-resolution Sentinel-2 satellites at 10 m/pixel. We accompany this dataset with an open-source Python package to: rebuild or extend the WorldStrat dataset, train and infer baseline algorithms, and learn with abundant tutorials, all compatible with the popular EO-learn toolbox. We hereby hope to foster broad-spectrum applications of ML to satellite imagery, and possibly develop from free public low-resolution Sentinel2 imagery the same power of analysis allowed by costly private high-resolution imagery. We illustrate this specific point by training and releasing several highly compute-efficient baselines on the task of Multi-Frame Super-Resolution. License-wise, the high-resolution Airbus imagery is CC-BY-NC, while the labels, Sentinel2 imagery, and trained weights are under CC-BY, and the source code under BSD, to allow for the widest use and dissemination. The dataset is available at \url{https://zenodo.org/record/6810792} and the software package at \url{https://github.com/worldstrat/worldstrat}.

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the marginal likelihood. We show that this principled kind of regularisation yields comparable performance to dropout on MNIST classification. We then demonstrate how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems, and how this weight uncertainty can be used to drive the exploration-exploitation trade-off in reinforcement learning.

In this article, we present how we managed to build a low cost, homemade, up and running receiving station able to store almost a year of data from Meteosat Second Generation satellite. After a presentation of the context of the study, we will detail the hardware and software aspects of the station, followed by the educational stake, which links students and scientists working together. In the conclusion we will explain how this station led us to be involved in our first international project called AMMA (African Monsoon Multidisciplinary Analysis) and how we are going to realize an autonomous meteorological alert system which will forewarn of approaching thunderstorms and start recording ground images of this phenomenon.