David Rolnick

Biography

David Rolnick is an assistant professor at McGill University’s School of Computer Science, a core academic member of Mila – Quebec Artificial Intelligence Institute and holds a Canada CIFAR AI Chair. Rolnick’s work focuses on applications of machine learning to help address climate change. He is the co-founder and chair of Climate Change AI, and scientific co-director of Sustainability in the Digital Age. After completing his PhD in applied mathematics at the Massachusetts Institute of Technology (MIT), he was a NSF Mathematical Sciences Postdoctoral Research Fellow, an NSF Graduate Research Fellow and a Fulbright Scholar. He was named to MIT Technology Review’s “35 Innovators Under 35” in 2021.

Current Students

Aditya Aditya

Collaborating researcher

Collaborating Alumni - McGill University

Collaborating researcher - Cambridge University

Postdoctorate - McGill University

Michael Bunsen

Collaborating researcher - McGill University

Shahana Chatterjee

Collaborating researcher - N/A

Yuyan Chen

PhD - McGill University

Eya Cherif

Collaborating researcher - Leipzig University

Othmane Echchabi

Master's Research - McGill University

Collaborating researcher

Mohamed Elabbas

Collaborating researcher

Jannik Endres

Collaborating researcher

Jacopo Ghirri

Independent visiting researcher - Politecnico di Milano

Paula Harder

Independent visiting researcher

Collaborating researcher - Johannes Kepler University

Christina Isaicu Isaicu

Collaborating researcher - University of Amsterdam

Gaurav Iyer

Master's Research - McGill University

Julia Kaltenborn

PhD - McGill University

Devin Kwok

PhD - McGill University

Independent visiting researcher - Université de Montréal

Pierre-Louis Lemaire

Collaborating researcher - Polytechnique Montréal Montréal

Principal supervisor :

Alex Hernandez-Garcia

Joshi Manoj

Collaborating researcher - University of East Anglia

David Mickisch

Collaborating researcher

Juan Nathaniel Nathaniel

Collaborating researcher - Columbia university

Postdoctorate - McGill University

Co-supervisor :

Lena Podina

Collaborating researcher - University of Waterloo

Venkatesh Ramesh

Collaborating Alumni - Université de Montréal

Marlena Reil

Master's Research - McGill University

Carla Roesch

Collaborating researcher - Columbia university

Rasha Saha

Master's Research - McGill University

Luca Marie Schmidt

Collaborating researcher - University of Tübingen

Independent visiting researcher

Ilija Trajković

Collaborating researcher - Karlsruhe Institute of Technology

Gabriel Tseng

PhD - McGill University

Donna Vakalis

Collaborating Alumni - Université de Montréal

Collaborating researcher

Catherine Villeneuve

PhD - McGill University

Shan Zhao

Collaborating researcher - Technical University of Munich

Democratizing Access to Satellite Data with AI

Blog Posts

diagram illustrating how the AI foundation model for Earth observation, Galileo, works

October 21, 2025

Gabriel Tseng

David Rolnick

Read the article

Publications

Galileo: Learning Global&Local Features of Many Remote Sensing Modalities

Gabriel Tseng

Anthony Fuller

Marlena Reil

Henry Herzog

Patrick Beukema

Favyen Bastani

James R Green

Evan Shelhamer

Hannah Kerner

We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, … (see more)elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.

2025-02-12

ArXiv (preprint)

proceedings.mlr.press

Using Image-based Al for insect monitoring and conservation - InsectAI COST Action

Tom August

Mario V Balzan

Paul Bodesheim

Gunnar Brehm

Lisette Cantú-Salazar

Sílvia Castro

Joseph Chipperfield

Guillaume Ghisbain

Alba Gomez-Segura

Jérémie Goulnik

Quentin Groom

Laurens Hogeweg

Chantal Huijbers

Andreas Kamilaris

Karolis Kazlauskis

Wouter Koch

Dimitri Korsch

João Loureiro

Youri Martin

Angeliki F Martinou … (see 27 more)

Kent McFarland

Xavier Mestdagh

Denis Michez

Charlie Outhwaite

Luca Pegoraro

Nadja Pernat

Lars B. Pettersson

Pavel Pipek

Cristina Preda

Tobias Roth

David B Roy

Helen Roy

Veljo Runnel

Martina Sasic

Dmitry Schigel

Julie Koch Sheard

Cecilie Svenningsen

Heliana Teixeira

Nicolas Titeux

Thomas Tscheulin

Elli Tzirkalli

Marijn van der Velde

Roel van Klink

Nicolas J Vereecken

Sarah Vray

Toke Thomas Høye

The InsectAI COST action will support insect monitoring and conservation at the national and continental scale in order to understand and co… (see more)unteract widespread insect declines. The Action will bring together a critical mass of researchers and stakeholders in image-based insect AI technologies to direct and drive the research agenda, build research capacity across Europe and support innovation and application. There is mounting evidence that populations of insects around the world are in sharp decline. Understanding trends in species and their drivers is key to knowing the size of the challenge, its causes and how to address it. To identify solutions that lead to sustainable biodiversity alongside economic prosperity, insect monitoring should be efficient and provide standardised and frequently updated status indicators to guide conservation actions. The EU Biodiversity Strategy 2030 identifies the critical challenge of delivering standardised information about the state of nature and image-based insect AI can contribute to this. Specifically, the EU Nature Restoration Law will likely set binding targets for the high resolution data that cameras can provide. Thus, outputs of the Action will contribute directly to EU policies implementation, where biodiversity monitoring is considered a key component. The InsectAI COST Action will organise workshops, conferences, short-term scientific missions, hackathons, design-sprints and much more, across four Working Groups. These groups will address how image-based insect AI technologies can best address Societal Needs, support innovation in Image Collection hardware, create standardised approaches for Image Processing and develop novel Data Analysis and Integration methods for turning data into actionable insights.

2025-02-09

Research Ideas and Outcomes (published)

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

Devin Kwok

Gül Sena Altıntaş

Colin Raffel

Neural network training is inherently sensitive to initialization and the randomness induced by stochastic gradient descent. However, it is … (see more)unclear to what extent such effects lead to meaningfully different networks, either in terms of the models' weights or the underlying functions that were learned. In this work, we show that during the initial "chaotic" phase of training, even extremely small perturbations reliably causes otherwise identical training trajectories to diverge-an effect that diminishes rapidly over training time. We quantify this divergence through (i)

2024-12-31

ICML (published)

proceedings.mlr.press

Tree semantic segmentation from aerial image time series

Venkatesh Ramesh

Arthur Ouaknine

Earth's forests play an important role in the fight against climate change, and are in turn negatively affected by it. Effective monitoring … (see more)of different tree species is essential to understanding and improving the health and biodiversity of forests. In this work, we address the challenge of tree species identification by performing semantic segmentation of trees using an aerial image dataset spanning over a year. We compare models trained on single images versus those trained on time series to assess the impact of tree phenology on segmentation performances. We also introduce a simple convolutional block for extracting spatio-temporal features from image time series, enabling the use of popular pretrained backbones and methods. We leverage the hierarchical structure of tree species taxonomy by incorporating a custom loss function that refines predictions at three levels: species, genus, and higher-level taxa. Our findings demonstrate the superiority of our methodology in exploiting the time series modality and confirm that enriching labels using taxonomic information improves the semantic segmentation performance.

2024-12-31

Environmental Data Science (published)

Insect Identification in the Wild: The AMI Dataset

Aditya Jain

F. Cunha

M. J. Bunsen

Juan Sebastián Cañas

L. Pasi

N. Pinoy

Flemming Helsing

JoAnne Russo

Marc Botham

Michael Sabourin

Jonathan Fréchette

Alexandre Anctil

Yacksecari Lopez

Eduardo Navarro

Filonila Perez Pimentel

Ana Cecilia Zamora

José Alejandro Ramirez Silva

Jonathan Gagnon

Tom August

K. Bjerge … (see 8 more)

Alba Gomez Segura

Marc Bélisle

Yves Basset

K. P. McFarland

David Roy

Toke Thomas Høye

Maxim Larrivée

Insects represent half of all global biodiversity, yet many of the world's insects are disappearing, with severe implications for ecosystems… (see more) and agriculture. Despite this crisis, data on insect diversity and abundance remain woefully inadequate, due to the scarcity of human experts and the lack of scalable tools for monitoring. Ecologists have started to adopt camera traps to record and study insects, and have proposed computer vision algorithms as an answer for scalable data processing. However, insect monitoring in the wild poses unique challenges that have not yet been addressed within computer vision, including the combination of long-tailed data, extremely similar classes, and significant distribution shifts. We provide the first large-scale machine learning benchmarks for fine-grained insect recognition, designed to match real-world tasks faced by ecologists. Our contributions include a curated dataset of images from citizen science platforms and museums, and an expert-annotated dataset drawn from automated camera traps across multiple continents, designed to test out-of-distribution generalization under field conditions. We train and evaluate a variety of baseline algorithms and introduce a combination of data augmentation techniques that enhance generalization across geographies and hardware setups.

2024-12-01

Lecture Notes in Computer Science (published)

Causal Representation Learning in Temporal Data via Single-Parent Decoding

Yaniv Gurwicz

Peer Nowack

Jakob Runge

Scientific research often seeks to understand the causal structure underlying high-level variables in a system. For example, climate scienti… (see more)sts study how phenomena, such as El Niño, affect other climate processes at remote locations across the globe. However, scientists typically collect low-level measurements, such as geographically distributed temperature readings. From these, one needs to learn both a mapping to causally-relevant latent variables, such as a high-level representation of the El Niño phenomenon and other processes, as well as the causal model over them. The challenge is that this task, called causal representation learning, is highly underdetermined from observational data alone, requiring other constraints during learning to resolve the indeterminacies. In this work, we consider a temporal model with a sparsity assumption, namely single-parent decoding: each observed low-level variable is only affected by a single latent variable. Such an assumption is reasonable in many scientific applications that require finding groups of low-level variables, such as extracting regions from geographically gridded measurement data in climate research or capturing brain regions from neural activity data. We demonstrate the identifiability of the resulting model and propose a differentiable method, Causal Discovery with Single-parent Decoding (CDSD), that simultaneously learns the underlying latents and a causal graph over them. We assess the validity of our theoretical results using simulated data and showcase the practical validity of our method in an application to real-world data from the climate science field.

2024-10-08

ArXiv (preprint)

openreview.net

Pushing the frontiers in climate modelling and analysis with machine learning

Veronika Eyring

William D. Collins

Pierre Gentine

Elizabeth A. Barnes

Marcelo Barreiro

Tom Beucler

Marc Bocquet

Christopher S. Bretherton

Hannah M. Christensen

Katherine Dagon

David John Gagne

David Hall

Dorit Hammerling

Stephan Hoyer

Fernando Iglesias-Suarez

Ignacio Lopez-Gomez

Marie C. McGraw

Gerald A. Meehl

Maria J. Molina

Claire Monteleoni … (see 9 more)

Juliane Mueller

Michael S. Pritchard

Jakob Runge

Philip Stier

Oliver Watt-Meyer

Katja Weigel

Rose Yu

Laure Zanna

2024-08-22

Nature Climate Change (published)

Evaluating the transferability potential of deep learning models for climate downscaling

Ayush Prasad

Paula Harder

Qidong Yang

Prasanna Sattegeri

D. Szwarcman

Campbell Watson

Climate downscaling, the process of generating high-resolution climate data from low-resolution simulations, is essential for understanding … (see more)and adapting to climate change at regional and local scales. Deep learning approaches have proven useful in tackling this problem. However, existing studies usually focus on training models for one specific task, location and variable, which are therefore limited in their generalizability and transferability. In this paper, we evaluate the efficacy of training deep learning downscaling models on multiple diverse climate datasets to learn more robust and transferable representations. We evaluate the effectiveness of architectures zero-shot transferability using CNNs, Fourier Neural Operators (FNOs), and vision Transformers (ViTs). We assess the spatial, variable, and product transferability of downscaling models experimentally, to understand the generalizability of these different architecture types.

2024-07-16

ArXiv (preprint)

Stealing part of a production language model

Nicholas Carlini

Daniel Paleka

Krishnamurthy Dj Dvijotham

Thomas Steinke

Jonathan Hayase

A. Feder Cooper

Katherine Lee

Matthew Jagielski

Milad Nasr

Arthur Conmy

Eric Wallace

Florian Tramèr

We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like … (see more)OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \\

2024-07-07

Proceedings of the 41st International Conference on Machine Learning (published)

proceedings.mlr.press

Improving Molecular Modeling with Geometric GNNs: an Empirical Study

Fragkiskos D. Malliaros

Alexandre AGM Duval

2024-06-16

ICML.cc/2024/Workshop/ML4LMS (poster)

openreview.net

The Butterfly Effect: Tiny Perturbations Cause Neural Network Training to Diverge

Gül Sena Altıntaş

Devin Kwok

Neural network training begins with a chaotic phase in which the network is sensitive to small perturbations, such as those caused by stocha… (see more)stic gradient descent (SGD). This sensitivity can cause identically initialized networks to diverge both in parameter space and functional similarity. However, the exact degree to which networks are sensitive to perturbation, and the sensitivity of networks as they transition out of the chaotic phase, is unclear. To address this uncertainty, we apply a controlled perturbation at a single point in training time and measure its effect on otherwise identical training trajectories. We find that both the

2024-06-15

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

A machine learning pipeline for automated insect monitoring

Aditya Jain

F. Cunha

M. J. Bunsen

L. Pasi

Anna Viklund

Maxim Larrivée

Climate change and other anthropogenic factors have led to a catastrophic decline in insects, endangering both biodiversity and the ecosyste… (see more)m services on which human society depends. Data on insect abundance, however, remains woefully inadequate. Camera traps, conventionally used for monitoring terrestrial vertebrates, are now being modified for insects, especially moths. We describe a complete, open-source machine learning-based software pipeline for automated monitoring of moths via camera traps, including object detection, moth/non-moth classification, fine-grained identification of moth species, and tracking individuals. We believe that our tools, which are already in use across three continents, represent the future of massively scalable data collection in entomology.

2024-05-31

arXiv (published)