Junior Data Scientist​/Scientific assistant – Tree species detection using deep-learning

Organisation/Company ETH Zürich Research Field Agricultural sciences » Forest sciences Computer science » Programming Computer science » Other Environmental science » Earth science Environmental science » Other Researcher Profile First Stage Researcher (R1) Country Switzerland Final date to receive applications 17 Mar 2026 - 22:59 (UTC) Type of Contract Temporary Job Status Full-time Is the job funded through the EU Research Framework Programme?

Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Junior Data Scientist / Scientific assistant – Tree species detection using deep-learning

Are you an ambitious data scientist with strong analytical and numerical skills, and expertise in geomatics, remote sensing, and data processing? We invite you to join our team and help shape the future of Earth observation in forest management.

Project background

You will join FORM (the Professorship of Forest Resources Management) and the team that focuses (1) on the acquisition, processing, and interpretation of satellite and drone data, as well as (2) on the development of operational applications for emerging intelligent earth observation technologies.

Our researchers develop cutting-edge algorithms and AI-based solutions for data processing and validation and provide scientific expertise for the implementation of future remote sensing missions. The team’s work bridges earth observation with applied forest monitoring, including tree species identification, forest structural changes, and forest resilience assessments, with a growing focus on spectral and functional trait analysis to support biodiversity and genetic monitoring in forestry.

The TreeAI Global Initiative focuses on extending the current database and mapping individual trees, which are essential tasks that support forest management. Using aerial RGB imagery, we aim to create a cost-effective, automated system for detecting and identifying tree species, with broad applications in forest monitoring.

You will support the TreeAI global initiative by developing data driven methods to enhance large scale tree monitoring. The role focuses on managing and expanding the TreeAI database and advancing deep learning workflows for tree species mapping. The position contributes to building a scalable system for forest monitoring by refining model performance and ensuring high quality geospatial data integration.

Key Responsibilities:

• Acquire and harmonize new spatial and aerial datasets for the TreeAI database.
• Support the development of the TreeAI database by integrating various datasets, such as tree species annotations, climate, and topography, into deep learning algorithms.
• Test deep learning models (Transformers and CNNs) for optimal accuracy using large datasets that include over 110,000 tree species annotations, along with climatic, topographic, and lidar data.
• Test the best algorithms developed for the identification of tree species over large areas.

Profile

• MSc in Remote sensing, Geoinformatics, Data Science, Forestry, Environmental Sciences, or a related field, from an internationally recognized university.
• Strong background in geoinformatics and remote sensing is required.
• Experience in working with multimodal data fusion and high-resolution remotely sensed data is required.
• Proficiency in programming, particularly in Python, is essential.
• Knowledge of deep learning approaches and experience in using semantic segmentation or instance segmentation is desired.
• Knowledge of or interest in forestry is desired.
• Fluency in English (written and spoken)
• Strong collaboration and communication skills

We offer

• Opportunities to engage in cutting-edge research with the potential for high impact in the fields of forestry and deep learning.
• Opportunities for professional development.
• Opportunities to engage with different communities bridging data science, remote sensing and forest research, leading to high-impact publications.
• You will be part of a highly motivated, diverse, friendly and collaborative team.

The position is initially for one year, renewable for up to six years. The desired starting date is 15 February,…