Profile picture

Devis Tuia

devis.tuia@epfl.ch +41 21 693 00 11

EPFL Valais Wallis
EPFL ENAC IIE ECEO
Route des Ronquos 86
1951 Sion

EPFL ENAC SSIE-GE
GR B0 421 (Bâtiment GR)
Station 2
1015 Lausanne

Expertise

- Earth Observation, remote sensing: from drones to satellites
- Machine learning, deep learning
- Image processing

Current work

- Making remote sensing accessible to everyone! Developing algorithms for human machine interaction
- Open the black box: interpretable deep learning and uncertainties in environmental modeling
- Digital wildlife conservation: using imaging to automatize censuses and conservation efforts
I come from Ticino and studied in Lausanne, between UNIL and EPFL. After my PhD at UNIL in remote sensing, I was postdoc in Valencia (Spain), Boulder (CO) and EPFL, working on model adaptation and prior knowledge integration in machine learning. In 2014 I became Research Assistant Professor at University of Zurich, then Associate and Full professor at Wageningen University in the Netherlands. Since 2020 I lead the ECEO laboratory of EPFL, where we study Earth from above with machine learning, computer vision and remote sensing.

Awards

ISPRS president citation award

Recognition of outstanding services in the International Society for Photogrammetry and Remote Sensing (ISPRS)

2022

Fellow of the IEEE

IEEE

2024

Selected publications

Perspectives in machine learning for wildlife conservation

D. Tuia, B. Kellenberger, S. Beery, B. Costelloe, S. Zuffi, B. Risse, A. Mathis, M. W. Mathis et al.
Published in Nature Communications in

Deep learning for the Earth Sciences: A comprehensive approach to remote sensing, climate science and geosciences.

G. Camps-Valls, D. Tuia, X. X. Zhu, M. Reichstein
Published in Wiley in

Towards a collective agenda on AI for earth science data analysis

D. Tuia, R. Roscher, J. D. Wegner, N. Jacobs, X. X. Zhu, G. Camps-Valls
Published in IEEE Geoscience and Remote Sensing Magazine in

Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning

B, Kellenberger, D., Marcos, D., Tuia
Published in Remote Sensing of Environment in

RSVQA: visual question answering for remote sensing data

S. Lobry, D., Marcos, J., Murray, D., Tuia
Published in IEEE Transactions on Geoscience and Remote Sensing in

Teaching & PhD

Current Phd

Nina Marion Aurélia Van Tiel, Gianfranco Basile, Robin Zbinden, Giacomo Günter May, Valentin Alexandre Guy Gabeff, Chang Xu, Manon Béchaz, Hugo Laurent Pascal Porta, Li Mi, Jan Pisl, Valérie Zermatten, Jonathan Sauder, Filip Dorm

Past Phd As Director

Thiên-Anh Nguyen, Christel Tartini-Chappuis

Past Phd As Codirector

Timothée Produit, Matthew Josef Parkan

Courses

Frontiers of Deep Learning for Engineers

CIVIL-611

The seminar aims at discussing recent research papers in the field of deep learning, implementing the transferability/adaptability of the proposed approaches to applications in the field of research of the Ph.D. student.

Fundamentals of geomatics

ENV-140

Fundamental of geomatics for civil and environmental engineers. Introduction to acquisition, management and visualization of geodata. Learning and doing practical experiments: geodata acquisition and land imaging.

Image processing for Earth observation

ENV-540

This course covers optical remote sensing from satellites and airborne platforms. The different systems are presented. The students will acquire skills in image processing and machine/deep learning to extract end-products from the images such as land cover or risk maps.

Sensing and spatial modeling for earth observation

ENV-408

Students get acquainted with the process of mapping from images (orthophoto and DEM), as well as with methods for monitoring the Earth surface using remotely sensed data. Methods will span from machine learning to geostatistics and model the spatiotemporal variability of processes.