PhD Position in Multimodal AI for Forest Biodiversity Mapping

This PhD position at NIBIO in Norway focuses on advancing multimodal artificial intelligence to enhance forest biodiversity mapping and monitoring. The candidate will explore how diverse data—including remote sensing, inventory data, environmental variables, and AI-derived representations—can be integrated to characterize forests and address critical biodiversity challenges. The project emphasizes developing scalable AI models for predicting old-growth forests and key habitats at regional and national scales. The successful applicant will collaborate with researchers from NIBIO and NMBU, contributing to both fundamental AI research and real-world environmental applications. The position offers a unique opportunity to work at the intersection of AI and sustainability, with access to extensive national forest datasets and interdisciplinary research environments.

• Develop multimodal deep learning methods to integrate heterogeneous forest and environmental datasets (remote sensing, inventory data, maps, climate variables, AI representations).
• Investigate approaches for combining information across spatial resolutions, temporal scales, and modalities, including handling incomplete data sources.
• Explore foundation models and self-supervised learning for extracting transferable representations from large-scale forest and Earth observation datasets.
• Design AI models to predict and map old-growth forests, key biodiversity habitats, and other ecologically relevant forest characteristics.
• Incorporate ecological knowledge and biodiversity observations into model development and validation processes.
• Evaluate model generalization and transferability across forest types, environmental gradients, and geographical regions.
• Produce regional and national biodiversity-related forest maps and assess their accuracy and ecological relevance.
• Publish research findings in high-impact international journals and conferences, and collaborate with national/international partners.