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

Benjamin Akera Binen

Collaborating Alumni - McGill University

Collaborating researcher - Cambridge University

Co-supervisor :

julien.boussard@mila.quebec

berkes.anais@mila.quebec

Postdoctorate - McGill University

Michael Bunsen

Collaborating researcher - McGill University

michael.bunsen@mila.quebec

Shahana Chatterjee

Collaborating researcher - N/A

Co-supervisor :

shahana.chatterjee@mila.quebec

Yuyan Chen

PhD - McGill University

yuyan.chen@mila.quebec

Graham Clyne

Postdoctorate - McGill University

graham.clyne@mila.quebec

Ruth Crasto

PhD - McGill University

ruth.crasto@mila.quebec

othmane.echchabi@mila.quebec

Othmane Echchabi

Master's Research - McGill University

Collaborating researcher

amna.elmustafa@mila.quebec

mohamed.elabbas@mila.quebec

Mohamed Elabbas

Collaborating researcher

jannik.endres@mila.quebec

Jannik Endres

Collaborating researcher

jacopo.ghirri@mila.quebec

Jacopo Ghirri

Independent visiting researcher - Politecnico di Milano

Independent visiting researcher

paula.harder@mila.quebec

Collaborating researcher - Johannes Kepler University

christina.humer@mila.quebec

Gaurav Iyer

Master's Research - McGill University

gaurav.iyer@mila.quebec

julia.kaltenborn@mila.quebec

Julia Kaltenborn

PhD - McGill University

vincent.lefalher@mila.quebec

Devin Kwok

PhD - McGill University

devin.kwok@mila.quebec

Independent visiting researcher - Université de Montréal

Pierre-Louis Lemaire

Collaborating researcher - Polytechnique Montréal Montréal

Principal supervisor :

Alex Hernández-García

pierre-louis.lemaire@mila.quebec

david.mickisch@mila.quebec

David Mickisch

Collaborating researcher

Postdoctorate - McGill University

Co-supervisor :

Étienne Laliberté

arthur.ouaknine@mila.quebec

Lena Podina

Collaborating researcher - University of Waterloo

Co-supervisor :

elena.podina@mila.quebec

Marlena Reil

Master's Research - McGill University

marlena.reil@mila.quebec

Rasha Saha

Master's Research - McGill University

sulagna.saha@mila.quebec

luca.schmidt@uni-tuebingen.de

Luca Marie Schmidt

Collaborating researcher - University of Tübingen

Independent visiting researcher - Karlsruhe Institute of Technology

hossein.shirali@mila.quebec

Wietze Suijker

Independent visiting researcher

wietze.suijker@gmail.com

ilija.trajkovic@mila.quebec

Ilija Trajković

Collaborating researcher - Karlsruhe Institute of Technology

gabriel.tseng@mila.quebec

Gabriel Tseng

PhD - McGill University

Donna Vakalis

Collaborating Alumni - Université de Montréal

Principal supervisor :

donna.vakalis@mila.quebec

Collaborating researcher

anna.viklund@mila.quebec

catherine.villeneuve@mila.quebec

Catherine Villeneuve

PhD - McGill University

mohamed.yebari@mila.quebec

Mohamed Yebari

Collaborating researcher - Ecole Polytechnique Montréal Fédérale de Lausanne (EPFL)

Co-supervisor :

Loubna Benabbou

Shan Zhao

Collaborating researcher - Technical University of Munich

zhaoshanuestc@gmail.com

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

Bayesian Decision-Time Inference for In-Context Reinforcement Learning from Suboptimal Data

Anaïs Berkes

In-context reinforcement learning (ICRL) promises rapid adaptation without parameter updates, but standard supervised objectives often fail … (see more)when pretraining data is generated by suboptimal behaviour policies. In these regimes, logged actions are unreliable labels while rewards still provide value-relevant information. To address this, we introduce SPICE, a Bayesian decision-time inference method that shifts online ICRL from action-logit prediction to approximate posterior inference over action values, requiring neither expert action labels nor algorithmic learning traces. SPICE learns a task-conditioned value prior with a transformer value ensemble and, at test time with parameters frozen, fuses this prior with kernel-weighted context evidence via a closed-form Gaussian fusion update. The resulting estimates drive a posterior-UCB controller, enabling principled online exploration and adaptation without gradient updates. A stochastic-bandit analysis shows logarithmic regret growth for the fixed-prior controller under scheduled exploration, while quantifying the additional early cost caused by inaccurate prior estimates. Across bandits, Darkroom, image-based MiniWorld, and continuous building control, SPICE adapts more effectively from suboptimal data than supervised ICRL baselines.

2026-06-15

ContinualRL @ Reinforcement Learning Conference (published)

Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study

Lena Podina

Alex Hernández-García

Efficient and inexpensive energy storage is essential for accelerating the adoption of renewable energy and ensuring a stable supply, despit… (see more)e fluctuations in sources such as wind and solar. Electrocatalysts play a key role in hydrogen energy storage (HES), allowing the energy to be stored as hydrogen. However, the development of affordable and high-performance catalysts for this process remains a significant challenge. We introduce Catalyst GFlowNet, a generative model that leverages machine learning-based predictors of formation and adsorption energy to design crystal surfaces that act as efficient catalysts. We demonstrate the performance of the model through a proof-of-concept application to the hydrogen evolution reaction, a key reaction in HES, for which we successfully identified platinum as the most efficient known catalyst. In future work, we aim to extend this approach to the oxygen evolution reaction, where current optimal catalysts are expensive metal oxides, and open the search space to discover new materials. This generative modeling framework offers a promising pathway for accelerating the search for novel and efficient catalysts.

2026-04-23

OpenReview (published)

Identifying birdsong syllables without labelled data

Mélisande Teng

Julien Boussard

Hugo Larochelle

Identifying sequences of syllables within birdsongs is key to tackling a wide array of challenges, including bird individual identification … (see more)and better understanding of animal communication and sensory-motor learning. Recently, machine learning approaches have demonstrated great potential to alleviate the need for experts to label long audio recordings by hand. However, they still typically rely on the availability of labelled data for model training, restricting applicability to a few species and datasets. In this work, we build the first fully unsupervised algorithm to decompose birdsong recordings into sequences of syllables. We first detect syllable events, then cluster them to extract templates -- syllable representations -- before performing matching pursuit to decompose the recording as a sequence of syllables. We evaluate our automatic annotations against human labels on a dataset of Bengalese finch songs and find that our unsupervised method achieves high performance. We also demonstrate that our approach can distinguish individual birds within a species through their unique vocal signatures, for both Bengalese finches and another species, the great tit.

2026-04-20

IEEE International Conference on Acoustics, Speech and Signal Processing (published)

Estimating Individual Tree Height and Species from UAV Imagery

J. Endres

Étienne Laliberté

Arthur Ouaknine

Accurate estimation of forest biomass, a major carbon sink, relies heavily on tree-level traits such as height and species. Unoccupied Aeria… (see more)l Vehicles (UAVs) capturing high-resolution imagery from a single RGB camera offer a cost-effective and scalable approach for mapping and measuring individual trees. We introduce BIRCH-Trees, the first benchmark for individual tree height and species estimation from tree-centered UAV images, spanning three datasets: temperate forests, tropical forests, and boreal plantations. We also present DINOvTree, a unified approach using a Vision Foundation Model (VFM) backbone with task-specific heads for simultaneous height and species prediction. Through extensive evaluations on BIRCH-Trees, we compare DINOvTree against commonly used vision methods, including VFMs, as well as biological allometric equations. We find that DINOvTree achieves top overall results with accurate height predictions and competitive classification accuracy while using only 54% to 58% of the parameters of the second-best approach.

2026-03-23

arXiv (preprint)

BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models

Catherine Villeneuve

Benjamin Akera

Mélisande Teng

Species distribution models (SDMs), which aim to predict species occurrence based on environmental variables, are widely used to monitor and… (see more) respond to biodiversity change. Recent deep learning advances for SDMs have been shown to perform well on complex and heterogeneous datasets, but their effectiveness remains limited by spatial biases in the data. In this paper, we revisit deep SDMs from a Bayesian perspective and introduce BATIS, a novel and practical framework wherein prior predictions are updated iteratively using limited observational data. Models must appropriately capture both aleatoric and epistemic uncertainty to effectively combine fine-grained local insights with broader ecological patterns. We benchmark an extensive set of uncertainty quantification approaches on a novel dataset including citizen science observations from the eBird platform. Our empirical study shows how Bayesian deep learning approaches can greatly improve the reliability of SDMs in data-scarce locations, which can contribute to ecological understanding and conservation efforts.

2026-03-13

AAAI Conference on Artificial Intelligence (published)

Learning a Spatial Partitioning and its Causal Relations from Temporal Data

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 the task of partitioning observed variables into disentangled factors, 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, from temporal data, 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.

2026-03-09

Conference on Causal Learning and Reasoning (poster)

proceedings.mlr.press

Understanding Representation Gaps across Scales in Tropical Tree Species Classification from Drone Imagery

Sulagna Saha

Arthur Ouaknine

Étienne Laliberté

Carol Altimas

Evan M. Gora

Adriane Esquivel Muelbert

Ian R. McGregor

César Gutiérrez

Vanessa E. Rubio

Accurate classification of tropical tree species from unoccupied aerial vehicle (UAV) imagery remains challenging due to high species divers… (see more)ity and strong visual similarity among species at typical image resolutions (centimeters per pixel). In contrast, models trained on close-up citizen science photographs captured with smartphones achieve strong plant species classification performance. Recent advances in UAV data acquisition now enable the collection of close-up images that are spatially registered with top-view aerial imagery and approach the level of visual detail found in smartphone photographs, with the trade-off that such high-resolution photos cannot be acquired for many trees. In this work, we evaluate the performance of existing methods using paired top-view and close-up UAV imagery collected in a species-rich tropical forest. Through fine-tuning experiments, we quantify the performance gap between vision foundation models and in-domain generalist plant recognition models across both image types (high-resolution close-up versus coarser-resolution top-view imagery). We show that classification performance is consistently higher on close-up images than on top-view aerial imagery, and that this performance gap widens for rare species. Finally, we propose that self-supervised representation alignment across these two spatial scales offers a promising approach for integrating fine-grained visual information into canopy-level species classification models based on top-view UAV imagery. Leveraging high-resolution close-up UAV imagery to enhance canopy-level species classification could substantially improve large-scale monitoring of tropical forest biodiversity.

2026-02-28

ML4RS @ International Conference on Learning Representations (published)

Localized, High-resolution Geographic Representations with Slepian Functions

Arjun Rao

Ruth Crasto

Tessa Ooms

Konstantin Klemmer

Marc Rußwurm

Geographic data is fundamentally local. Disease outbreaks cluster in population centers, ecological patterns emerge along coastlines, and ec… (see more)onomic activity concentrates within country borders. Machine learning models that encode geographic location, however, distribute representational capacity uniformly across the globe, struggling at the fine-grained resolutions that localized applications require. We propose a geographic location encoder built from spherical Slepian functions that concentrate representational capacity inside a region-of-interest and scale to high resolutions without extensive computational demands. For settings requiring global context, we present a hybrid Slepian-Spherical Harmonic encoder that efficiently bridges the tradeoff between local-global performance, while retaining desirable properties such as pole-safety and spherical-surface-distance preservation. Across five tasks spanning classification, regression, and image-augmented prediction, Slepian encodings outperform baselines and retain performance advantages across a wide range of neural network architectures.

2026-01-29

arXiv (preprint)

Benchmarking the geographic generalization of deep learning models for precipitation downscaling

Paula Harder

Luca Schmidt

Francis Pelletier

Nicole Ludwig

Matthew Chantry

Christian Lessig

Alex Hernández-García

Earth System Models (ESM) are our main tool for projecting the impacts of climate change. However, running these models at sufficient resolu… (see more)tion for local-scale risk-assessments is not computationally feasible. Deep learning-based super-resolution models offer a promising solution to downscale ESM outputs to higher resolutions by learning from data. Yet, due to regional variations in climatic processes, these models typically require retraining for each geographical area–demanding high-resolution observational data, which is unevenly available across the globe. This highlights the need to assess how well these models generalize across geographic regions. To address this, we introduce RainShift, a dataset and benchmark for evaluating downscaling under geographic distribution shifts. We evaluate state-of-the-art downscaling approaches including GANs and diffusion models in generalizing across data gaps between the Global North and Global South. Our findings reveal substantial performance drops in out-of-distribution regions, depending on model and geographic area. While expanding the training domain generally improves generalization, it is insufficient to overcome shifts between geographically distinct regions. We show that addressing these shifts through, for example, domain adaptation can improve spatial generalization. Our work advances the global applicability of downscaling methods and represents a step toward reducing inequities in access to high-resolution climate information.

2026-01-26

Scientific Reports (published)

In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior

Anaïs Berkes

In-context reinforcement learning (ICRL) promises fast adaptation to unseen environments without parameter updates, but current methods eith… (see more)er cannot improve beyond the training distribution or require near-optimal data, limiting practical adoption. We introduce SPICE, a Bayesian ICRL method that learns a prior over Q-values via deep ensemble and updates this prior at test-time using in-context information through Bayesian updates. To recover from poor priors resulting from training on sub-optimal data, our online inference follows an Upper-Confidence Bound rule that favours exploration and adaptation. We prove that SPICE achieves regret-optimal behaviour in both stochastic bandits and finite-horizon MDPs, even when pretrained only on suboptimal trajectories. We validate these findings empirically across bandit and control benchmarks. SPICE achieves near-optimal decisions on unseen tasks, substantially reduces regret compared to prior ICRL and meta-RL approaches while rapidly adapting to unseen tasks and remaining robust under distribution shift.

2025-12-31

arXiv (preprint)

Adsorption energies are necessary but not sufficient to identify good catalysts

Alexander Davis

Alexandre AGM Duval

Oleksandr Voznyy

Alex Hern'andez-Garcia

Félix Therrien

2025-12-04

ArXiv (preprint)

Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery

Mélisande Teng

Information on trees at the individual level is crucial for monitoring forest ecosystems and planning forest management. Current monitoring … (see more)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.

2025-12-02

Advances in Neural Information Processing Systems (Accept (poster))