Netherlands
I'm an AI researcher using machine learning to help monitor and protect biodiversity. I started out in physics (Radboud University) and computational neuroscience (Sorbonne & Oxford univ.), before redirecting my ML expertise to ecological and environmental sciences (Peak District National Park, Alan Turing Institute, Wageningen univ). These days I'm at Wageningen University, leading a small research engineering team building explainable and multimodal AI for biodiversity monitoring. Career highlights include mapping the entire Peak District National Park at 12.5 cm resolution — the first updated land cover map in 40 years, building a probabilistic model of the entire zebrafish brain (100k neurons), and adapting techniques from neuroscience and representation learning to interpret geospatial embeddings. I care a lot about clean code, reproducible science, and seeing research through to deployment. My big vision: an AI system that combines multimodal biodiversity data to transparently monitor the condition of habitats at scale. I think it's one of the most exciting ML and scientific challenges out there right now. If that sounds interesting, check out my 2025 position paper (https://doi.org/10.1002/2688-8319.70040), website (https://vdplasthijs.github.io/), or let's talk!
Working with various ML (e.g., deep learning, LLMs, VLMs, Bayesian inference) to integrate multimodal ecological data (EO, time series, fieldwork etc.) to develop systems for ecosystem-level monitoring and scenario planning.
Development of new machine learning methods for biodiversity monitoring, by integrating remote sensing data with field observations of wildlife. Research on computer vision, geospatial foundation models, multimodal AI, ML for remote sensing, ML for biodiversity, geospatial data engineering, analysis and visualisation.
Designed and implemented a convolutional neural network-based model to classify land cover from very-high-resolution aerial photography, mapping 1,439 km2 at 12.5 cm resolution. Oversaw the entire ML lifecycle and successfully introduced ML analysis to a conservation organisation. Read more about this project and its impact at https://www.turing.ac.uk/about-us/impact/mapping-habitats-peak-district-national-park
Developed statistical and machine learning analyses for neurobiology lab. Specialised in making sense out of large and noisy data sets, and design the statistical tests to validate findings. My contributions led to the discovery of a new neural signal propagation mechanism, published in Nature Neuroscience (joint 1st author), and a artificial RNN model of working memory encoding, published in Proceedings of ML Research (1st author). Passed viva with no corrections.
Demonstrator for the following 3 DPhil courses: - Introduction in Programming (2020, 2021) - Modelling & Scientific Computing (2022) - Statistics and Data Management (2022)
TA for the following 3 BSc courses: - Introduction to Machine Learning (2018) - Nonlinear Dynamics, Chaos & Applications (2017) - Introductory Statistics (2017)