Portrait de David Rolnick

David Rolnick

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur adjoint, McGill University, École d'informatique
Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Théorie de l'apprentissage automatique

Biographie

David Rolnick est professeur adjoint et titulaire d’une chaire en IA Canada-CIFAR à l'École d'informatique de l'Université McGill et membre académique principal de Mila – Institut québécois d’intelligence artificielle. Ses travaux portent sur les applications de l'apprentissage automatique dans la lutte contre le changement climatique. Il est cofondateur et président de Climate Change AI et codirecteur scientifique de Sustainability in the Digital Age. David Rolnick a obtenu un doctorat en mathématiques appliquées du Massachusetts Institute of Technology (MIT). Il a été chercheur postdoctoral en sciences mathématiques à la National Science Foundation (NSF), chercheur diplômé à la NSF et boursier Fulbright. Il a figuré sur la liste des « 35 innovateurs de moins de 35 ans » de la MIT Technology Review en 2021.

Étudiants actuels

Collaborateur·rice alumni - McGill
Collaborateur·rice alumni - UdeM
Collaborateur·rice de recherche - Cambridge University
Co-superviseur⋅e :
Postdoctorat - McGill
Collaborateur·rice de recherche - McGill
Collaborateur·rice de recherche
Collaborateur·rice de recherche - N/A
Co-superviseur⋅e :
Maîtrise recherche - McGill
Collaborateur·rice de recherche - Leipzig University
Collaborateur·rice de recherche
Collaborateur·rice de recherche
Visiteur de recherche indépendant
Collaborateur·rice de recherche - UdeM
Collaborateur·rice de recherche - Johannes Kepler University
Collaborateur·rice de recherche - University of Amsterdam
Maîtrise recherche - McGill
Collaborateur·rice de recherche
Visiteur de recherche indépendant - Université de Montréal
Collaborateur·rice de recherche
Stagiaire de recherche - UdeM
Collaborateur·rice de recherche - Columbia university
Postdoctorat - McGill
Co-superviseur⋅e :
Doctorat - University of Waterloo
Co-superviseur⋅e :
Collaborateur·rice alumni - UdeM
Maîtrise recherche - McGill
Collaborateur·rice de recherche - Columbia university
Collaborateur·rice de recherche - University of Tübingen
Collaborateur·rice de recherche - Karlsruhe Institute of Technology
Doctorat - McGill
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche
Doctorat - McGill
Collaborateur·rice alumni - McGill

Publications

Causal Climate Emulation with Bayesian Filtering
Sebastian H. M. Hickman
Ilija Trajkovic
Julia Kaltenborn
Francis Pelletier
Alex Archibald
Yaniv Gurwicz
Peer Nowack
Julien Boussard
Traditional models of climate change use complex systems of coupled equations to simulate physical processes across the Earth system. These … (voir plus)simulations are highly computationally expensive, limiting our predictions of climate change and analyses of its causes and effects. Machine learning has the potential to quickly emulate data from climate models, but current approaches are not able to incorporate physics-informed causal relationships. Here, we develop an interpretable climate model emulator based on causal representation learning. We derive a physics-informed approach including a Bayesian filter for stable long-term autoregressive emulation. We demonstrate that our emulator learns accurate climate dynamics, and we show the importance of each one of its components on a realistic synthetic dataset and data from two widely deployed climate models.
Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery
Mélisande Teng
Arthur Ouaknine
Etienne Lalibert'e
Information on trees at the individual level is crucial for monitoring forest ecosystems and planning forest management. Current monitoring … (voir plus)methods involve ground measurements, requiring extensive cost, time and labor. Advances in drone remote sensing and computer vision offer great potential for mapping individual trees from aerial imagery at broad-scale. Large pre-trained vision models, such as the Segment Anything Model (SAM), represent a particularly compelling choice given limited labeled data. In this work, we compare methods leveraging SAM for the task of automatic tree crown instance segmentation in high resolution drone imagery in three use cases: 1) boreal plantations, 2) temperate forests and 3) tropical forests. We also study the integration of elevation data into models, in the form of Digital Surface Model (DSM) information, which can readily be obtained at no additional cost from RGB drone imagery. We present BalSAM, a model leveraging SAM and DSM information, which shows potential over other methods, particularly in the context of plantations. We find that methods using SAM out-of-the-box do not outperform a custom Mask R-CNN, even with well-designed prompts. However, efficiently tuning SAM end-to-end and integrating DSM information are both promising avenues for tree crown instance segmentation models.
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, … (voir plus)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.
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 … (voir plus)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)
FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring
Nikolaos Ioannis Bountos
Arthur Ouaknine
Ioannis Papoutsis
Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery
Mélisande Teng
Arthur Ouaknine
Etienne Lalibert'e
Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery
Mélisande Teng
Arthur Ouaknine
Etienne Lalibert'e
A Joint Space-Time Encoder for Geographic Time-Series Data
David Mickisch
Konstantin Klemmer
Mélisande Teng
Many real-world processes are characterized by complex spatio-temporal dependencies, from climate dynamics to disease spread. Here, we intro… (voir plus)duce a new neural network architecture to model such dynamics at scale: the \emph{Space-Time Encoder}. Building on recent advances in \emph{location encoders}, models that take as inputs geographic coordinates, we develop a method that takes in geographic and temporal information simultaneously and learns smooth, continuous functions in both space and time. The inputs are first transformed using positional encoding functions and then fed into neural networks that allow the learning of complex functions. We implement a prototype of the \emph{Space-Time Encoder}, discuss the design choices of the novel temporal encoding, and demonstrate its utility in climate model emulation. We discuss the potential of the method across use cases, as well as promising avenues for further methodological innovation.
OpenForest: a data catalog for machine learning in forest monitoring
Arthur Ouaknine
Teja Kattenborn
Etienne Lalibert'e
Harnessing artificial intelligence to fill global shortfalls in biodiversity knowledge
Justin Kitzes
Sara Beery
Kaitlyn M. Gaynor
Marta A. Jarzyna
Oisin Mac Aodha
Bernd Meyer
Graham W. Taylor
Devis Tuia
Tanya Berger-Wolf
Galileo: Learning Global and Local Features in Pretrained Remote Sensing Models
Gabriel Tseng
Anthony Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R Green
Evan Shelhamer
Hannah Kerner
From crop mapping to flood detection, machine learning in remote sensing has a wide range of societally beneficial applications. The commona… (voir plus)lities between remote sensing data in these applications present an opportunity for pretrained machine learning models tailored to remote sensing to reduce the labeled data and effort required to solve individual tasks. However, such models must be: (i) flexible enough to ingest input data of varying sensor modalities and shapes (i.e., of varying spatial and temporal dimensions), and (ii) able to model Earth surface phenomena of varying scales and types. To solve this gap, we present Galileo, a family of pretrained remote sensing models designed to flexibly process multimodal remote sensing data. We also introduce a novel and highly effective self-supervised learning approach to learn both large- and small-scale features, a challenge not addressed by previous models. Our Galileo models obtain state-of-the-art results across diverse remote sensing tasks.
Galileo: Learning Global and Local Features in Pretrained Remote Sensing Models
Gabriel Tseng
A. Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R. Green
Evan Shelhamer
Hannah Kerner
From crop mapping to flood detection, machine learning in remote sensing has a wide range of societally beneficial applications. The commona… (voir plus)lities between remote sensing data in these applications present an opportunity for pretrained machine learning models tailored to remote sensing to reduce the labeled data and effort required to solve individual tasks. However, such models must be: (i) flexible enough to ingest input data of varying sensor modalities and shapes (i.e., of varying spatial and temporal dimensions), and (ii) able to model Earth surface phenomena of varying scales and types. To solve this gap, we present Galileo, a family of pretrained remote sensing models designed to flexibly process multimodal remote sensing data. We also introduce a novel and highly effective self-supervised learning approach to learn both large- and small-scale features, a challenge not addressed by previous models. Our Galileo models obtain state-of-the-art results across diverse remote sensing tasks.