Dr. Nils C. Prieur

Dr. Nils C. Prieur

ML Engineer / Earth & Planetary Scientist

First manuscript accepted! Moving back to Norway after two years in the US

2 minute read

Published:

Let’s go!!! 🎉 After nearly two years of hard work, my first article for the BOULDERING project has been accepted in the Journal of Geophysical Research: Planets! You can check it out here. This has been a long road, but also an incredibly rewarding one. Over 33,000 boulders were collected across more than 750 tiles/images from three planetary bodies: Earth, Mars, and the Moon.

The dataset, including images, labeled boulder data, the model setup for the best-performing Mask R-CNN model, and its trained weights, is now publicly available on Zenodo:

While the model achieved human-like detection rates—average precision: 72%, recall: 64%—I’m still not completely satisfied with its generalization. Over the next few months, I plan to improve the machine learning code base, and I’m considering switching to YOLO. Early tests have shown that YOLO delivers superior results using the same dataset, so let’s see where this exploration takes me!

On the personal front, things have been busy with baby Finn’s arrival at the end of August, two weeks earlier than expected! Luckily, we had everything ready to go (phew!). Adjusting to parenthood has been a whirlwind, especially with sleepless nights, but it’s been such a joy.

Norway’s parental leave system is fantastic, giving us much-needed time to bond with Finn. I’ll be on paternity leave from April through August, and I’ve taken some extra holiday leave too. Work has understandably taken a back seat lately as we settle into life as new parents.

The move back to Norway from the US was quite the challenge, especially with Siri being heavily pregnant. We had to sell all our furniture, pack up our lives into countless suitcases (and a few precious framed paintings—2 out of 3 survived the journey!), and navigate international travel. Despite the chaos, the experience of living in the US was extraordinary. I’m so grateful to the Marie Skłodowska-Curie Fellowship program for making it possible.

I’ll miss the amazing colleagues, the sunny California weather, and the breathtaking nature. But at the same time, it feels good to be back in Europe—because, well, you can’t have it all! I’m keeping in touch with my Stanford colleagues, especially Mathieu. Fun fact: Brian, one of the undergraduates who worked on the project, is now publishing his own article comparing our boulder detection algorithm with rock abundance data from the DIVINER instrument onboard the Lunar Reconnaissance Orbiter. (Google it—super interesting stuff!)

Gotta run—Finn’s crying, and it’s my turn! Take care, everyone! 😊

Group at stanford Caption: Nice atmosphere with colleagues during group meeting at Stanford. Miss you already guys!

Goodbye lunch Caption: Goodbye party/lunch at the private restaurant at the campus! Thanks Mathieu.

You May Also Enjoy

Transition to YOLOv8, always improving the algorithm, collecting more labels…

3 minute read

Published:

Bonjour, everyone! Time feels like it’s slipping away faster than ever these days. With paternity leave in full swing, finding work hours here and there has been a challenge (and honestly, it’s hard not to get distracted by Baby Finn’s cuteness). Despite the chaos, I’ve managed to make a major leap forward in the project: transitioning from Detectron2 Mask R-CNN to YOLOv8. Let me tell you—it’s been a game-changer.

Wifey at Stanford now! Baby Boss incoming in September

1 minute read

Published:

Big life updates, everyone! Siri is now at Stanford! Thanks to a fantastic program from the Norwegian Research Council (NRC), postdocs already involved in NRC projects can apply for a research stay abroad for up to a year. The NRC covers the salary, and with a high success rate for these grants, it’s a great way to build international collaborations. After some searching, Siri found a group at Stanford doing work closely related to her research at NMBU in Ås. A few weeks of visa wrangling later, she’s here!

One Step Forth, Two Steps Back.

3 minute read

Published:

Hey everyone! The past few months have felt like a game of two steps forward, one step back, but progress is happening—slowly but surely. Most of my time has been spent processing and fine-tuning the orthoimages collected during fieldwork and improving the prediction workflow for the Mask R-CNN model.