This distinction is based on paper 'Explainable Machine Learning for Scientific Insights and Discoveries' by Ribana Roscher et al.

Others make a different distinction: Interpretable for 'inherently interpretable' models and explainability for post-hoc methods. But I'm not a fan

Are you a researcher in the field of photogrammetry 📷 and remote sensing 🌍? Then, we cordially invite you to submit a paper to our Ph & RS Special Track GCPR 2024. The deadline for submissions is May 29!

Am 18. April referiert Prof. Dr.-Ing. Ribana Roscher (@fz_juelich Rheinische Friedrich-Wilhelms-Universität Bonn) im Rahmen des Geodätischen Kolloquiums der HafenCity Universität Hamburg (HCU) zum Thema „Explain it to me! On the use of explainable machine learning for the agricultural and environmental sciences“
#AllesImLot #myVDVdates

There appears to be a mismatch between publishing criteria in AI conferences and 'what actually works'. It is easy to publish new mathematical constructs (e.g. new models, new layers, new modules, new losses), but as Apple's MM1 paper concludes:

1. Encoder Lesson: Image…

New Research: Estimating daily semantic segmentation maps of classified ocean eddies using sea level anomaly data from along-track altimetry frontiersin.org/articles/10.33… #AI

⏰ We extended the deadline for the ICLR 2024 #ML4RS workshop!

The new deadline is Feb 9th! 🙌

Thanks to Hyperplan and European Space Agency, we also have limited funding to help students travel to the conference:

Please check the requirements on our website
ml-for-rs.github.io/iclr2024/#trav…

Systematic learning across earth observation problems spanning different spatial resolutions is now possible with a METEOR, a meta-learning methodology that uses only a handful of labeled data.
@marccoru et al.
devistuia sherwag Benjamin Kellenberger @ribanaroscher
nature.com/articles/s4324…

Thank you Ribana Roscher for giving a captivating and inspiring AI for Good 🇺🇳 #AIforGood talk about #ML for the agricultural & environmental sciences 🏞️🍀

Check out the links below if you missed the talk⬇️
Part 1: shorturl.at/btvLN
Part 2: shorturl.at/cxDK1

#AI 🌍🛰️| With just a handful of examples an AI programme can train neural networks to recognise new objects faster in satellite and drone images. An international team has developed a new application for this: METEOR! Want to know how it works?👉ap.lc/pTihB

🚨📢 New nature Communications Earth & Environment paper 😀

Meta-learning to address diverse Earth observation problems across resolutions.

nature.com/articles/s4324…

It's joint work between EPFL and Wageningen U&R
and collaborators Sherrie Wang (@MIT) Benjamin Kellenberger (@Yale) Ribana Roscher (@fz_juelich) devistuia

Don't miss the talk by Ribana Roscher about 'Explainable machine learning for agricultural and environmental sciences' on Jan 17 at 5 pm 👇

Join the next talk of our AI for Good 🇺🇳 #AIforGood lecture series “ #AI for Earth & #Sustainability Science” on Jan 17 at 5 PM 🫵🏻✨

Speaker: Ribana Roscher 🗣️
Moderator: Joachim Denzler (@CvJena)

Register here & find out more about the topic ➡️ shorturl.at/fmLT6

New arXiv paper! 📢📢

Data is at the center of ML-based solutions for effective Geospatial Remote Sensing applications!

Happy New Year 2024!

We just amended our newsletter 16 with the upcoming Climate Change AI ICLR workshop and The Alan Turing Institute's Climate Informatics 2024 conference in London.

Stay up-to-date with upcoming venues and deadlines in our newsletter:
iapr-tc7.github.io/newsletter/