Each week, we will introduce an interview with an early-career researcher working on the MAMBO project. Meet the scientists who bring innovation to the way we monitor biodiversity across Europe.

---

Can you introduce yourself and your research in a couple of sentences?

I'm an early-career researcher (I finished my PhD 3 months ago at the University of Montpellier) working at the intersection of biodiversity modelling and artificial intelligence. During my PhD, I developed tools like Pl@ntBERT (a large language model that treats plants as words and species assemblages as sentences) and contributed to GeoPl@ntNet (an interactive web application designed to make Essential Biodiversity Variables accessible and understandable to everyone through dynamic maps and fact sheets), which both use deep learning to better understand and map plant biodiversity across Europe.

What knowledge gap is your PhD thesis focused on?

My PhD addressed the lack of scalable methods to understand plant communities from large and heterogeneous datasets. In particular, it explored how AI can capture the "syntax" of species co-occurrence and improve biodiversity monitoring beyond traditional approaches, through Pl@ntBERT, the first language model trying to decode the language of nature.

How has MAMBO directly shaped or enabled your thesis research? Were there datasets, fieldwork opportunities, or collaborations that changed your direction?

The MAMBO project provided a strong framework for integrating AI into biodiversity monitoring, which directly aligned with my work. It enabled access to large-scale datasets and collaborations that helped connect methodological developments like Pl@ntBERT with real-world monitoring challenges, especially in the context of automated and scalable biodiversity assessment.

Do your scientific results contribute to solving national or European problems, and can they be used to inform policies? If so, to which policies would they be relevant?

Yes, my work contributes to improving large-scale biodiversity monitoring, which is a key limitation in Europe today. These methods can support policies such as the EU Biodiversity Strategy for 2030 and the Habitats Directives by providing more consistent, scalable, and data-driven indicators of species and habitat status.

As MAMBO wraps up, how do you see its research to continue?

I see MAMBO's legacy in the integration of AI, remote sensing, and ecological data into unified monitoring systems. The tools and datasets developed will likely continue to evolve into operational platforms for biodiversity assessment at the European scale, especially through initiatives like GeoPl@ntNet, which already maps all the plants of Europe at a very high resolution, hence providing very important biodiversity indicators, such as invasive or specialist species, everywhere.

What's next for you professionally?

I'm continuing as a postdoctoral researcher at École Normale Supérieure (Paris, France), developing next-generation eco-evolutionary models while building on my PhD work. I aim to further bridge AI and ecology to better predict biodiversity dynamics and support conservation decisions.

---

Follow the early-career researchers campaign also on social media - LinkedIn, Bluesky and X.