The Rise of Deep Learning in Earth Observation

Deep learning is just a subset of machine learning. It's very costly to train in terms of computational cost, but also in terms of data needed to train them. And then when once the algorithm is trained, its application can also be more expensive than classical machine learning algorithms like Random Forest for instance. This is why most of operational applications of machine learning today are not yet using deep learning because the computational cost to train the algorithms and also the amount of data which is needed to training them.

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app