Publications (44)
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
Michael McCabe, Payel Mukhopadhyay, Tanya Marwah +22
Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unst…
FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
Chirag Modi, Francois Lanusse, Uros Seljak
We present FlowPM, a Particle-Mesh (PM) cosmological N-body code implemented in Mesh-TensorFlow for GPU-accelerated, distributed, and differentiable simulations. We implement and v…
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data
The Multimodal Universe Collaboration, Jeroen Audenaert, Micah Bowles +26
We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MU…
Teaching dark matter simulations to speak the halo language
Shivam Pandey, Francois Lanusse, Chirag Modi +1
We develop a transformer-based conditional generative model for discrete point objects and their properties. We use it to build a model for populating cosmological simulations with…
Modeling halo and central galaxy orientations on the SO(3) manifold with score-based generative models
Yesukhei Jagvaral, Rachel Mandelbaum, Francois Lanusse
Upcoming cosmological weak lensing surveys are expected to constrain cosmological parameters with unprecedented precision. In preparation for these surveys, large simulations with…
Probabilistic Mapping of Dark Matter by Neural Score Matching
Benjamin Remy, Francois Lanusse, Zaccharie Ramzi +3
The Dark Matter present in the Large-Scale Structure of the Universe is invisible, but its presence can be inferred through the small gravitational lensing effect it has on the ima…
Rubin-Euclid Derived Data Products: Initial Recommendations
Leanne P. Guy, Jean-Charles Cuillandre, Etienne Bachelet +117
This report is the result of a joint discussion between the Rubin and Euclid scientific communities. The work presented in this report was focused on designing and recommending an…
Deep Generative Models for Galaxy Image Simulations
Francois Lanusse, Rachel Mandelbaum, Siamak Ravanbakhsh +3
Image simulations are essential tools for preparing and validating the analysis of current and future wide-field optical surveys. However, the galaxy models used as the basis for t…
Detecting Tidal Features using Self-Supervised Representation Learning
Alice Desmons, Sarah Brough, Francois Lanusse
Low surface brightness substructures around galaxies, known as tidal features, are a valuable tool in the detection of past or ongoing galaxy mergers. Their properties can answer q…
Galaxies on graph neural networks: towards robust synthetic galaxy catalogs with deep generative models
Yesukhei Jagvaral, Francois Lanusse, Sukhdeep Singh +3
The future astronomical imaging surveys are set to provide precise constraints on cosmological parameters, such as dark energy. However, production of synthetic data for these surv…
An Empirical Model For Intrinsic Alignments: Insights From Cosmological Simulations
Nicholas Van Alfen, Duncan Campbell, Jonathan Blazek +5
We extend current models of the halo occupation distribution (HOD) to include a flexible, empirical framework for the forward modeling of the intrinsic alignment (IA) of galaxies.…
Core Cosmology Library: Precision Cosmological Predictions for LSST
Nora Elisa Chisari, David Alonso, Elisabeth Krause +27
The Core Cosmology Library (CCL) provides routines to compute basic cosmological observables to a high degree of accuracy, which have been verified with an extensive suite of valid…
The relationship between fine galaxy stellar morphology and star formation activity in cosmological simulations: a deep learning view
Lorenzo Zanisi, Marc Huertas-Company, Francois Lanusse +10
Hydrodynamical simulations of galaxy formation and evolution attempt to fully model the physics that shapes galaxies. The agreement between the morphology of simulated and real gal…
Anomaly Detection in Astronomical Images with Generative Adversarial Networks
Kate Storey-Fisher, Marc Huertas-Company, Nesar Ramachandra +4
We present an anomaly detection method using Wasserstein generative adversarial networks (WGANs) on optical galaxy images from the wide-field survey conducted with the Hyper Suprim…
AION-1: Omnimodal Foundation Model for Astronomical Sciences
Liam Parker, Francois Lanusse, Jeff Shen +24
While foundation models have shown promise across a variety of fields, astronomy still lacks a unified framework for joint modeling across its highly diverse data modalities. In th…
Denoising Score-Matching for Uncertainty Quantification in Inverse Problems
Zaccharie Ramzi, Benjamin Remy, Francois Lanusse +2
Deep neural networks have proven extremely efficient at solving a wide rangeof inverse problems, but most often the uncertainty on the solution they provideis hard to quantify. In…
Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems
Francois Lanusse, Peter Melchior, Fred Moolekamp
We present a Bayesian machine learning architecture that combines a physically motivated parametrization and an analytic error model for the likelihood with a deep generative model…
Probabilistic Mass Mapping with Neural Score Estimation
Benjamin Remy, Francois Lanusse, Niall Jeffrey +4
Weak lensing mass-mapping is a useful tool to access the full distribution of dark matter on the sky, but because of intrinsic galaxy ellipticies and finite fields/missing data, th…
Enabling Dark Energy Science with Deep Generative Models of Galaxy Images
Siamak Ravanbakhsh, Francois Lanusse, Rachel Mandelbaum +2
Understanding the nature of dark energy, the mysterious force driving the accelerated expansion of the Universe, is a major challenge of modern cosmology. The next generation of co…
High Resolution Weak Lensing Mass-Mapping Combining Shear and Flexion
Francois Lanusse, Jean-Luc Starck, Adrienne Leonard +1
We propose a new mass-mapping algorithm, specifically designed to recover small-scale information from a combination of gravitational shear and flexion. Including flexion allows us…
MIMIC: A Generative Multimodal Foundation Model for Biomolecules
Siavash Golkar, Jake Kovalic, Irina Espejo Morales +28
Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained with…
Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
Payel Mukhopadhyay, Stefan S. Nixon, Romain Watteaux +20
Whether physics foundation models can be usefully deployed on laboratory experiments remains an open question for scientific machine learning (ML). We test this question on the Ray…
Geometric deep learning for galaxy-halo connection: a case study for galaxy intrinsic alignments
Yesukhei Jagvaral, Francois Lanusse, Rachel Mandelbaum
Forthcoming cosmological imaging surveys, such as the Rubin Observatory LSST, require large-scale simulations encompassing realistic galaxy populations for a variety of scientific…
Adaptive wavelet distillation from neural networks through interpretations
Wooseok Ha, Chandan Singh, Francois Lanusse +2
Recent deep-learning models have achieved impressive prediction performance, but often sacrifice interpretability and computational efficiency. Interpretability is crucial in many…
Semantic search for 100M+ galaxy images using AI-generated captions
Nolan Koblischke, Liam Parker, Francois Lanusse +3
Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes. In…
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning
Jeff Shen, Francois Lanusse, Liam Holden Parker +24
Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Ast…
AstroCLIP: A Cross-Modal Foundation Model for Galaxies
Liam Parker, Francois Lanusse, Siavash Golkar +12
We present AstroCLIP, a single, versatile model that can embed both galaxy images and spectra into a shared, physically meaningful latent space. These embeddings can then be used -…
Measuring the intracluster light fraction with machine learning
Louisa Canepa, Sarah Brough, Francois Lanusse +2
The intracluster light (ICL) is an important tracer of a galaxy cluster's history and past interactions. However, only small samples have been studied to date due to its very low s…
xVal: A Continuous Numerical Tokenization for Scientific Language Models
Siavash Golkar, Mariel Pettee, Michael Eickenberg +11
Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific…
Real-Time Likelihood-Free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation
Keming Zhang, Joshua S. Bloom, B. Scott Gaudi +3
Fast and automated inference of binary-lens, single-source (2L1S) microlensing events with sampling-based Bayesian algorithms (e.g., Markov Chain Monte Carlo; MCMC) is challenged o…
Multiple Physics Pretraining for Physical Surrogate Models
Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker +11
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers. I…
The Role of Machine Learning in the Next Decade of Cosmology
Michelle Ntampaka, Camille Avestruz, Steven Boada +27
In recent years, machine learning (ML) methods have remarkably improved how cosmologists can interpret data. The next decade will bring new opportunities for data-driven cosmologic…
CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
Francois Lanusse, Quanbin Ma, Nan Li +5
Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints,…
Detecting Galaxy Tidal Features Using Self-Supervised Representation Learning
Alice Desmons, Sarah Brough, Francois Lanusse
Low surface brightness substructures around galaxies, known as tidal features, are a valuable tool in the detection of past or ongoing galaxy mergers, and their properties can answ…
Towards solving model bias in cosmic shear forward modeling
Benjamin Remy, Francois Lanusse, Jean-Luc Starck
As the volume and quality of modern galaxy surveys increase, so does the difficulty of measuring the cosmological signal imprinted in galaxy shapes. Weak gravitational lensing sour…
Bridging Simulators with Conditional Optimal Transport
Justine Zeghal, Benjamin Remy, Yashar Hezaveh +2
We propose a new field-level emulator that bridges two simulators using unpaired simulation datasets. Our method leverages a flow-based approach to learn the likelihood transport f…
Transformation Importance with Applications to Cosmology
Chandan Singh, Wooseok Ha, Francois Lanusse +3
Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence. Its potential benefits to these fields requires…
Unified framework for diffusion generative models in SO(3): applications in computer vision and astrophysics
Yesukhei Jagvaral, Francois Lanusse, Rachel Mandelbaum
Diffusion-based generative models represent the current state-of-the-art for image generation. However, standard diffusion models are based on Euclidean geometry and do not transla…
Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
Kate Storey-Fisher, Marc Huertas-Company, Nesar Ramachandra +5
The problem of anomaly detection in astronomical surveys is becoming increasingly important as data sets grow in size. We present the results of an unsupervised anomaly detection m…
Differentiable Stochastic Halo Occupation Distribution
Benjamin Horowitz, ChangHoon Hahn, Francois Lanusse +2
In this work, we demonstrate how differentiable stochastic sampling techniques developed in the context of deep Reinforcement Learning can be used to perform efficient parameter in…
Cosmological constraints with weak lensing peak counts and second-order statistics in a large-field survey
Austin Peel, Chieh-An Lin, Francois Lanusse +3
Peak statistics in weak lensing maps access the non-Gaussian information contained in the large-scale distribution of matter in the Universe. They are therefore a promising complem…
The clustering of galaxies: Predictions from the BLUETIDES simulation
Aklant Kumar Bhowmick, Tiziana Di Matteo, Yu Feng +1
We study the clustering of the highest-z galaxies (from ~ to a few tens Mpc scales) using the BLUETIDES simulation and compare it to current observational constraints from Hu…
Weak lensing reconstructions in 2D & 3D: implications for cluster studies
Adrienne Leonard, Francois Lanusse, Jean-Luc Starck
We compare the efficiency with which 2D and 3D weak lensing mass mapping techniques are able to detect clusters of galaxies using two state-of-the-art mass reconstruction technique…
Automating Inference of Binary Microlensing Events with Neural Density Estimation
Keming Zhang, Joshua S. Bloom, B. Scott Gaudi +3
Automated inference of binary microlensing events with traditional sampling-based algorithms such as MCMC has been hampered by the slowness of the physical forward model and the pa…