
Machine Learning for Science (ML4SCI)
Machine Learning for Science (ML4SCI) is an umbrella organization for machine learning-related projects in science. ML4SCI brings together researchers from universities and scientific laboratories with motivated students to join existing scientific collaborations and contribute to cutting edge science projects across a wide variety of disciplines. Students work on existing problems to develop new machine learning-based approaches and produce open source code that directly contributes to solving these scientific challenges. ML4SCI currently includes projects from a variety of fields. For example, some of them explore the uses of machine learning for particle reconstruction and classification in high-energy physics, deep learning-based searches for dark matter in astrophysics, applications of machine learning techniques to data returned from planetary science missions, applications of quantum machine learning to science, and others. Machine learning ideas and approaches can be broadly applicable and transferable across the scientific domains. The goals of ML4SCI projects are to grow the open-source community in machine learning for science by addressing important scientific challenges and transferring the knowledge and tools of machine learning across the disciplines. We look forward to your applications!
GSoC Participation History
Technologies
Topics
Past Projects
Agentic AI for Autonomous Gravitational Lensing Simulation Workflows
DeepLenseSim (built on lenstronomy) requires substantial manual intervention for configuring parameters, managing outputs, and iterating on failures...
Radiomics Feature Extraction and Calcium Phenotype Discovery
A preliminary pipeline on 30 COCA patients achieves Spearman rho = 0.986 between extracted calcium volume and Agatston score, with 11/15 features...
Exoplanet Atmosphere Characterization
Exoplanet Atmosphere Characterisation plays a vital role in understanding chemical compositions, weather patterns and habitability of the exoplanet....
[DeepLense] Foundation Model for Gravitational Lensing - WaveLens-JEPA
Strong gravitational lensing is a powerful probe of dark matter structure and cosmology, yet no foundation model exists that is purpose-built for...
Quantum Resource Analysis and Benchmarking
Frameworks like PennyLane and Qiskit handle circuit construction and simulation well but provide almost no tools for measuring the quantum resources...
Event Classification With Masked Transformer Autoencoders
The proposal titled "Event Classification With Masked Transformer Autoencoders" aims to enhance particle jet tagging by developing a...
Using Next-Gen Transformers to Seed Generative Models for Symbolic Regression
Symbolic regression (SR) aims to discover human-interpretable mathematical expressions from numerical data. While recent transformer models achieve...
DeepLense: Lens Finding for LSST Images
In GSoC 2025, I prepared a novel physics-informed Swin Transformer to classify between lens models in simulated gravitational lensing images. The...
Physics-Informed Neural Network Shape Optimization
Vanilla MLP PINNs suffer from spectral bias and slow convergence, which directly limits the quality of shapes produced by PINN-based shape...
Brain-to-Brain Decoder: Leakage-Aware Validation and Interpretable CEBRA Mapping for Dyadic EEG
This proposal is for the ML4SCI GSoC 2026 project “Brain-to-Brain Decoder – Validating Neural Synchrony Patterns in Human Conversation.” The project...
Hybrid Quantum-Classical Representation Learning for Dark Matter Substructure Classification
This proposal presents a plan to develop hybrid quantum-classical models for classifying dark matter substructure from strong gravitational lensing...
Quantum Sinusoidal Kolmogorov Arnold Networks for High Energy Physics
The High Luminosity LHC program requires novel computational approaches to process massive datasets and identify rare signals. This project...
Agentic Lagrangian Extraction from the Literature ML4SCI – HEPSIM5
Hundreds of BSM Lagrangians have been proposed in the literature, but translating them into validated FeynRules .fr model files is still a manual,...
Linear attention vision transformers for end to end mass regression and classification
This project addresses a key challenge in High Energy Physics: efficient and accurate end-to-end reconstruction of particle properties from detector...
EXXA - Denoising Astronomical Observations of Protoplanetary Disks
Astronomical observations of protoplanetary disks often contain noise that obscures important structures such as rings and gaps that may indicate...
Machine Learning for Gravitational Lens Finding
Strong gravitational lenses are rare and scientifically valuable, but finding them in large imaging surveys requires automated methods. Furthermore,...
Quantum Latent Diffusion Models for High-Resolution Simulation
Accurate simulation of particle interactions within detectors is one of the most computationally expensive tasks in High Energy Physics (HEP). While...
Linear Attention Vision Transformers for CMS End-to-End Jet Classification and Mass Regression
This project develops linear-scale attention vision transformers for CMS End-to-End jet classification and proxy mass regression on 8-channel 99.1%...
Neural Operators for Fast Simulation of Strong Gravitational Lensing
Strong gravitational lensing is a key observational probe for dark matter and cosmology, but traditional ray-tracing simulations are computationally...
Unsupervised Super-Resolution and Analysis of Real Lensing Images
Strong gravitational lensing is among the most powerful observational probes of dark matter substructure. High-resolution lensing images encode the...
Hybrid 3D CNN with Deformable Attention and FNO for CAC Segmentation
This project develops a high-precision, clinically viable pipeline for segmenting Coronary Artery Calcium (CAC) from non contrast cardiac CT scans...
Physics-Aware Super-Resolution of CMS Jet Images Using Transformer - Diffusion Architectures
At the CMS detector, jet images are stored at reduced resolution, discarding ~75% of total deposited energy. Standard super-resolution fails here...
Physics-Informed Models for Squared Amplitude Calculation
This project aims to advance the SYMBA framework for calculating squared scattering amplitudes in high-energy physics by incorporating...
Graph Representation Learning for Fast Detector Simulation
This project addresses the challenge of fast and accurate particle detector simulation in high-energy physics. Traditional Monte Carlo methods are...
Data Augmentation Using Physics-Informed Plaque Growth Simulation
This project addresses the challenge of limited and imbalanced datasets in coronary artery calcium (CAC) analysis, particularly for rare high-risk...
Physics Informed Neural Network Diffusion Equation (PINNDE)
Generating simulations of calorimeter showers of interacting particles are a crucial step in analyzing the results of large scale experiments at LHC....
Building and Comparing Segmentation Strategies for Coronary Artery Calcium CAC
CAC segmentation is harder than it looks. Calcium deposits are tiny, sparse, and look identical to nearby bone a small miss doesn't just drop your...
Foundation models for End-to-End event reconstruction
This project aims to develop a multi-modal foundation model training pipeline for end-to-end particle reconstruction in the CMS experiment. Building...
Physics Guided Machine Learning on Real Gravitational Lensing Images
Strong gravitational lensing is a powerful tool for studying dark matter, but machine learning models trained on simulated data often fail to...
Foundation Models for Exoplanet Characterization
This project aims to build a multimodal foundation model for exoplanet characterization by addressing the challenge of heterogeneous astronomical...
Physics-Informed Neural Network Diffusion Equation (PINNDE)
Building on the PINNDE proof-of-concept from GSoC 2025, I propose two directions: (1) systematic improvements to the PINN architecture and training —...
Quantum Circuit Design with LLMs
Variational quantum circuits are essential for near term quantum algorithms but designing them involves complex manual trial and error. This project...
Deep Graph Anomaly Detection with Contrastive Learning for New Physics Searches
This project proposed to develop a graph-based unsupervised Anomaly Detection model for identifying new physics at the LHC, combining contrastive...
Frequently Asked Questions
Machine Learning for Science (ML4SCI) | GSoC Org Profile & Stats - Learn about Machine Learning for Science (ML4SCI)'s involvement in Google Summer of Code (GSoC), their technologies, detailed reports.
Participation
Projects
Top Programming Languages
Project Difficulty Distribution
No difficulty data available