Projects per cycle
Machine Learning for Science (ML4SCI), 2016 to 2026
View as table
| Projects | |
|---|---|
| 2016 | 0 |
| 2017 | 0 |
| 2018 | 0 |
| 2019 | 0 |
| 2020 | 0 |
| 2021 | 19 |
| 2022 | 20 |
| 2023 | 23 |
| 2024 | 26 |
| 2025 | 31 |
| 2026 | 33 |
PROJECTS
Machine Learning for Science (ML4SCI) GSoC projects
152 accepted projects across 6 cycles, 2021 to 2026. Each one links to its contributor, mentors and code.
Projects listed
152
Across 6 cycles
In GSoC 2026
33
31 in 2025
Busiest cycle
2026
33 projects
Mentors named
94
Across all listed projects
First cycle
2021
Latest 2026
Agentic AI for Autonomous Gravitational Lensing Simulation Workflows
Aatmaj28
DeepLenseSim (built on lenstronomy) requires substantial manual intervention for configuring parameters, managing outputs, and iterating on failures...
Radiomics Feature Extraction and Calcium Phenotype Discovery
AdityaParashar
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
Anushree Upasham
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
Arnesh2212
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
ashutoshm1771
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
Avishikta Bhattacharjee.
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
Dhruv1108
Symbolic regression (SR) aims to discover human-interpretable mathematical expressions from numerical data. While recent transformer models achieve...
DeepLense: Lens Finding for LSST Images
DhruvSrivastava
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
George Liao
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
Hubert Huang
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
Jen-Yu Chang
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
Jorge Toral
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
kenwu
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
Krish Malik
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
Krishan Yadav
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
MichaelJiao
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
Miguel Pámanes
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
Naresh Meena
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
PARAS BALANI
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
Prajwal Uday
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
Rajat Nandkumar Shedshyal
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
rajveer43
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
Ria Khatoniar
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
Rushil Singha
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
Shriyam Baloni
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)
Sijil
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
Soham Jadhav
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
Suryansh Mishra
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
Susmit
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
Tanmay Singhal
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)
Tina Shen
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
Tomoya Hatanaka
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
Yeyang
This project proposed to develop a graph-based unsupervised Anomaly Detection model for identifying new physics at the LHC, combining contrastive...
Foundation models for End-to-End event reconstruction
Aaditya PorwalMentored by Diptarko Choudhury, Ruchi Chudasama
Current deep learning models for CMS particle reconstruction are often task-specific. This project aims to develop versatile foundation models by...
Super-Resolution and Analysis of Gravitational Lensing Images
Aleksandr DuplinskiiMentored by Pranath Reddy, Brendan Ames, Mike Toomey
This project develops an open-source, unsupervised super-resolution (SR) pipeline for enhancing the resolution of gravitational lensing images,...
Quantum Particle transformer for High Energy Physics Analysis at the LHC
Alessandro TesiMentored by Eyup, KC Kong, Isabel Pedraza
This proposal aims to build upon and expand the progress made in recent years on Quantum Vision Transformers (QViTs) for High Energy Physics (HEP)...
Discovering Hidden Symmetries in CMS Calorimetric Data via Semi-Supervised Learning
Alexandra MurariuMentored by ML4SCI, Diptarko Choudhury, Konstantin Matchev +1
This project tackles the challenge of learning hidden symmetries in complex, high-dimensional physics data using modern machine learning techniques....
Unsupervised super-resolution and analysis of observed lensing images
Anirudh ShankarMentored by Pranath Reddy, Anna Parul
Machine learning based analyses are proving to be very potent in understanding complex physical systems. This project aims to develop a reinforcement...
Q-MAML for Variational Quantum Algorithms for High Energy Physics Analysis at the LHC
arnavsinghal09Mentored by KC Kong, Jeihee, Junyong Lee
This project focuses on developing a new machine learning approach called Quantum Model-Agnostic Meta-Learning (Q-MAML) specifically for high-energy...
Physics Guided Machine Learning on Real Lensing Images
Ashutosh OjhaMentored by ML4SCI, Pranath Reddy, Mike Toomey
The project aims to develop a physics-informed neural network framework to infer the properties and distribution of dark matter in the lensing galaxy...
Discovery of hidden symmetries and conservation laws
Avishikta_BhattacharjeeMentored by Diptarko Choudhury, Konstantin Matchev, Alexander Roman
Because of its cylindrical shape, the Compact Muon Solenoid (CMS) detector has intrinsic rotational symmetries. Data analysis can be greatly improved...
Physics-Informed Performer for Symbolic Squared Amplitudes in HEP
Ayush Mishra AMentored by Eric Reinhardt, Dinesh PR
In high-energy physics (HEP), automating the symbolic computation of squared amplitudes is essential for predicting cross-sections and validating...
A Diffusion-Based Deep Learning Framework for Denoising Protoplanetary Disk Observations
Chukwunwogor FaithfulMentored by ML4SCI, Jason Terry
This project proposes ProtoDiff, a diffusion-based deep learning model designed to denoise astronomical observations of protoplanetary disks from...
Continual learning for data quality monitoring
Daksh MorMentored by Eric Reinhardt, Resham, Dale Julson
Continuous learning serves as a powerful approach for maintaining reliable data quality monitoring in high-energy physics experiments facing evolving...
DeepLense: Gravitational Lens Finding Project
DhruvSrivastavaMentored by Anna Parul, Brendan Ames
This project aims to develop and optimize deep learning algorithms for identifying strong gravitational lenses within wide-field surveys such as the...
Exoplanet Atmosphere Characterization
Gaurav ShuklaMentored by Katia Matcheva, Emilie Panek
This project intends to develop cutting-edge machine-learning tools for spectral analysis to characterize the atmospheres of exoplanets. The project...
Discovery of hidden symmetries and conservation laws
Green KediaMentored by Diptarko Choudhury, Konstantin Matchev, Alexander Roman
This project aims to uncover fundamental symmetries and conserved laws hidden within complex high-energy physics data (specifically CMS datasets). It...
Diffusion Models for Gravitational Lensing Simulation
hamees-sayedMentored by Pranath Reddy, Mike Toomey
My project focuses on developing diffusion models for gravitational lensing simulations. I will implement and evaluate various diffusion-based...
Foundation Model for Gravitational Lensing
J RishiMentored by Pranath Reddy, Mike Toomey
This project aims to develop a vision foundation model for strong gravitational lensing by comparing various self-supervised learning techniques,...
Latent Neural Signatures in Clinical vs. Neurotypical Dyads: A CEBRA Pipeline
jeffreyhuang1009Mentored by Brendan Ames, Evie Malaia
This project aims to develop a cutting-edge computational pipeline—"Latent Neural Signatures in Clinical vs. Neurotypical Dyads: A CEBRA Pipeline"—to...
Data Processing Pipeline for the LSST
Kartik MandarMentored by Anna Parul, Brendan Ames
The project, "Data Processing Pipeline for the LSST," is designed to bridge the gap between the LSST data ecosystem and DeepLense's deep learning...
Foundation models for symbolic regression tasks
Krish MalikMentored by ML4SCI, Eric Reinhardt, Dinesh PR
Problem: Symbolic regression is crucial for discovering underlying physical laws from data, but traditional methods are often computationally...
Neural Harmony – Decoding Social Interactions with CEBRA-based framework for analysing EEG data
Maria GlushaninaMentored by Brendan Ames, Evie Malaia
This project aims to decode the neural dynamics of social interactions by adapting the CEBRA framework to analyze dyadic EEG data. Focusing on...
Quantum Diffusion Model for HEP
MashaMentored by ML4SCI, Isabel Pedraza
Diffusion models have experienced rapid growth in usability, availability, and research. The classical algorithm consists of two main parts: a...
Implementation of Quantum Generative Adversarial Networks to Perform HEP Analysis at the LHC
Maya MaMentored by ML4SCI, Amey Bhatuse, ToMago
This project aims to implement a Quantum Generative Adversarial Network (QGAN) using the Pennylane framework to explore the advantages of quantum...
State-space models for squared amplitude calculation in high-energy physics
Prasanth NaiduMentored by Eric Reinhardt, Dinesh PR
One of the most important physical quantities in particle physics is the cross section, or a probability that a particular process takes place in the...
Building a Foundational Model for Symbolic Regression in High Energy Physics
MicheMentored by ML4SCI, Eric Reinhardt
This project proposes the development of a foundational model for symbolic regression tailored to high energy physics (HEP). Symbolic regression can...
Quantum Kolmogorov-Arnold Networks for High Energy Physics Analysis at the LHC
Ria KhatoniarMentored by Marco Knipfer, Eric Reinhardt, Roy T. Forestano +1
This project explores Quantum Kolmogorov–Arnold Networks (QKANs) as a novel and interpretable architecture for analyzing collider data from the...
Graph Representation Learning for Fast Detector Simulation
Rushil SinghaMentored by ToMago, Diptarko Choudhury, Dinesh PR
High-fidelity detector simulations are critical for accurate analysis in particle physics, but traditional Monte Carlo-based methods are...
Next-Generation Transformer Models for Symbolic Calculations of Squared Amplitudes in HEP
Ritesh BhaleraoMentored by ML4SCI, Eric Reinhardt, Dinesh PR
In particle physics, a cross section is a measure of the likelihood that particles will interact or scatter with one another when they collide. It is...
Physics informed neural network diffusion equation
SijilMentored by Diptarko Choudhury, Harrison Prosper, Alexander Roman
This project aims at incorporating Physics informed neural network (PINN) based ODE solvers into the Diffusion probabilistic models(DPM) , to build a...
Quantum Machine Learning For Exoplanet Characterization
Sourish PhateMentored by Marco Knipfer, Konstantin Matchev, Katia Matcheva +2
This project aims to develop quantum machine learning models for exoplanet atmosphere characterization by leveraging the power of quantum neural...
Foundation Models for Exoplanet Characterization
Tanmay SinghalMentored by ML4SCI, Jason Terry, Konstantin Matchev +1
The project aims at building foundational models suitable for characterizing the vast astronomical data and emphasizing their use case for various...
A Self-Supervised, Physics-Informed Hybrid Transformer Framework for Multi-Tasks in HEP
Thanh P NguyenMentored by Diptarko Choudhury
Accurately classifying particle collisions—whether distinguishing quark- from gluon-initiated jets or isolating Higgs events from complex...
Learning quantum representations of classical high energy physics data with contrastive learning
Sanya NandaMentored by ToMago, Gopal Ramesh Dahale, KC Kong +1
This project investigates the fusion of classical data encoding onto quantum models using contrastive learning techniques. The objective is to...
Non-local GNNs for Jet Classification
Tanmay BakshiMentored by ToMago, Colin Crovella, Roy T. Forestano +1
The quest for new physics has encompassed and intrigued physicists for decades. At CERN LHC, high-energy proton-proton collisions can create new,...
Quantum transformer for High Energy Physics Analysis at the LHC
Alessandro TesiMentored by ML4SCI, ToMago, Gopal Ramesh Dahale +1
This proposal sets out to implement several kinds of Quantum Vision Transformers (QViT) for High Energy Physics (HEP) analysis at the Large Hadron...
Superresolution for Strong Gravitational Lensing
AtalMentored by Pranath Reddy, Geo Jolly, PG Guan +1
The "Superresolution for Strong Gravitational Lensing" project aims to enhance the resolution of astronomical images through advanced deep learning...
Graph Neural Networks for Particle Momentum Estimation in the CMS Trigger System
Vishak K BhatMentored by Colin Crovella, Ruchi Chudasama, Resham +1
This project aims to apply Deep Learning algorithms specifically Graph Neural Networks (GNN) for momentum regression in the trigger system....
Learning Representation Through Self-Supervised Learning on Real Gravitational Lensing Images
yaashwardhanMentored by Pranath Reddy, Kartik Sachdev, Anna Parul +1
Deep learning has transformed the analysis of supervised lensing data, utilizing feature spaces to uncover latent variables related to dark matter....
Masked Auto-Encoders for Efficient E2E Particle Reconstruction & Compression for CMS Experiment
Lokesh BadisaMentored by Emanuele Usai, Bhim Bam, Eric Reinhardt +1
The goal of this project is to develop Masked Vision Transformer for reconstruction and compression of CMS data. It is much easy to procure...
Equivariant quantum neural networks for High Energy Physics Analysis at the LHC
Lazaro Raul Diaz LievanoMentored by ML4SCI, KC Kong, Konstantin Matchev +1
The investigation of symmetries has long been a cornerstone in analyzing physical systems. As formalized by Noether’s theorem, conserved quantities...
Resilient Physics-Informed Anomaly Detection and Inference of Lensing Images on Sparse Datasets
Anirudh ShankarMentored by ML4SCI, Kartik Sachdev, PG Guan +1
Inferences using machine learning methods are becoming increasingly necessary in probing dynamical systems with complex and imperfect datasets. This...
Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
Jogi Suda NetoMentored by Roy T. Forestano, Konstantin Matchev, Katia Matcheva +1
Discovering new phenomena, like the Higgs boson, involves the identification of rare signals that could shed light into unanswered questions about...
QMLHEP3: Learning quantum representations of classical HEP data with contrastive learning
duydlMentored by Abhay Kamble, ToMago, Roy T. Forestano +1
QMLHEP3, or "Learning quantum representations of classical high energy physics data with contrastive learning," aims to study an intersection of...
Equivariant Vision Networks for Predicting Planetary Systems' Architectures
Alexandra MurariuMentored by ML4SCI, Jason Terry, Yurii Halychanskyi
Understanding the architecture of planetary systems is crucial for insights into their formation and evolution. This project aims to leverage the...
Physics-Guided Machine Learning
Ashutosh OjhaMentored by Pranath Reddy, Anna Parul, PG Guan +1
The project aims to develop a physics-informed neural network framework in order to do the inference for the properties and distribution of dark...
Evolutionary and Transformer Models for Symbolic Regression
Aryamaan ThakurMentored by Eric Reinhardt, Resham, Francois Charton
Symbolic Regression refers to discovering a function that accurately fits a given dataset. Evolutionary/genetic algorithms have been dominating this...
Quantum Generative Adversarial Networks for Monte Carlo Simulations
Rey GuadarramaMentored by Abhay Kamble, ToMago, Gopal Ramesh Dahale +2
This project aims to improve the efficiency and accuracy of Monte Carlo simulations by leveraging Quantum Generative Adversarial Networks (QGANs)....
Diffusion Models for Gravitational Lensing Simulation
J RishiMentored by Pranath Reddy, Anna Parul, PG Guan
My project focuses on utilizing Diffusion Models for Gravitational Lensing Simulation, encompassing two primary tasks. The first task involves...
Learning quantum representations of classical high energy physics data with contrastive learning
Amey BhatuseMentored by ToMago, Rui Zhang
In this project, we introduce quantum contrastive learning, a quantum machine learning technique to enhance performance of models involving high...
Implementation of Quantum Generative Adversarial Networks to Perform HEP Analysis at LHC
Adithya PenagondaMentored by Abhay Kamble, ToMago, Gopal Ramesh Dahale +1
The project aims to implement different GAN architectures ranging from classical models to fully quantum models, including hybrid models as well. And...
Exoplanet Atmosphere Characterization
Gaurav ShuklaMentored by Jason Terry, Konstantin Matchev, Katia Matcheva
This project intends to develop cutting-edge machine-learning tools for spectral analysis to characterize the atmospheres of exoplanets. The project...
Quantum Diffusion Model for High Energy Physics
MashaMentored by ML4SCI, ToMago, Gopal Ramesh Dahale +1
Classical diffusion models (DMs) have experienced rapid growth in usability, availability, and research. The classical DM algorithm consists of two...
Learning Representation Through Self-Supervised Learning on Real Gravitational Lensing Images
Sreehari IyerMentored by Kartik Sachdev, Anna Parul, Geo Jolly
Strong gravitational lensing provides a means to probe dark matter substructure. In recent years, machine learning techniques, particularly...
Masked Auto-Encoders for End-to-End Particle Reconstruction and Compression for the CMS Experiment
Shashank Shekhar ShuklaMentored by ML4SCI, Eric Reinhardt
Proposal Summary: The project aims to achieve two primary objectives: efficient and precise particle identification and the development of effective...
Self-Supervised Learning for End-to-End Particle Reconstruction for the CMS Experiment
3podiMentored by Diptarko Choudhury, Ruchi Chudasama, Abhipsa Acharya
The End-to-End Deep Learning project within the CMS experiment at the Large Hadron Collider plays a critical role in identifying and reconstructing...
Evolutionary and Transformer Models for Symbolic Regression
Samyak JhaMentored by Eric Reinhardt, VBaules, Nobuchika Okada +1
Symbolic Regression serves as a powerful tool for uncovering symbolic expressions that encapsulate data patterns, such as physical laws. This project...
Transformer Models for Symbolic Calculations of Squared Amplitudes in HEP
Ritesh BhaleraoMentored by Eric Reinhardt, VBaules, Nobuchika Okada
In particle physics, a cross section is a measure of the likelihood that particles will interact or scatter with one another when they collide. It is...
Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
Haemanth VMentored by Abhay Kamble, Roy T. Forestano, KC Kong +1
The Large Hadron Collider (LHC) built by CERN is the world’s largest and the most powerful particle accelerator, which generates about 1 billion...
Quantum Transformers for HEP Analysis at the LHC
Marçal Comajoan CaraMentored by Emanuele Usai, Amey Bhatuse, Purva Chaudhari
This project aims to develop quantum transformer architectures for high energy physics (HEP) analysis at the Large Hadron Collider (LHC). The focus...
Deriving planetary surface composition from orbiting observations from spacecraft
Sandeepan DhoundiyalMentored by ppeplowski
Multiple robotic spacecraft have been sent by NASA to collect orbital remote sensing data, which is used to analyze surface composition. Gamma-ray...
Prediction of High Energy Particle Kinematics via Masked Autoencoding
Eric ReinhardtMentored by Abdulhakim Alnuqaydan, Marco Knipfer, Colin Crovella
In high energy physics, much research revolves around the study of particles produced by colliding protons at near the speed of light. The Higgs...
Identifying the Physical Process of Planet Formation (EXXA)
Jason TerryMentored by Emanuele Usai, Shravan25
Planets form in complex, dynamic environments. The physics behind the process is not well-understood, and the limited high-quality observational data...
Quantum Graph Neural Networks for High Energy Physics Analysis at the LHC
Gopal Ramesh DahaleMentored by Shravan25, Ruchi Chudasama, KC Kong +1
The LHC at CERN contains large detectors which are made up of numerous small detectors that capture the hundreds of particles produced during...
Diffusion Models for Fast Detector Simulation
Akshit ChoudhariMentored by ML4SCI, Abdulhakim Alnuqaydan, Michelle Kuchera +1
Particle colliders such as the Large Hadron Collider (LHC) play a crucial role in advancing our understanding of fundamental particles and their...
FASEROH : Building seq2seq model for mapping histograms to empirical symbolic representations
Pushpdeep SinghMentored by Abdulhakim Alnuqaydan, Harrison Prosper
The problem involves creating a seq2seq model for mapping histograms to empirical function sequences. I propose to tackle this in two steps. Step 1...
Exploring the underlying symmetries in particle physics with equivariant neural networks
Diptarko ChoudhuryMentored by ML4SCI, Bhim Bam, Colin Crovella +1
Symmetry is one of the most beautiful and interesting phenomena in physics. Particle Physics is dominated by Lorentz symmetry. It is seen that...
Self-Supervised Learning for Strong Gravitational Lensing
yaashwardhanMentored by Yurii Halychanskyi, Anna Parul
Problem Statement: An unprecedented amount of lensing data is available, however manually labeling it is unsustainable. Hence an approach must be...
SYMBA - Symbolic empirical representation of squared amplitudes in high-energy physics
VBaulesMentored by Abdulhakim Alnuqaydan, Marco Knipfer, Harrison Prosper
The interaction cross-section is an important quantity in high-energy physics, serving as a bridge between abstract theory and experiment. Is is also...
Updating the DeepLense Pipeline
Saranga Kingkor MahantaMentored by Yurii Halychanskyi, Michael Toomey, Anna Parul +1
Studying the substructures of dark matter holds promise in solving the longstanding problem of determining the true nature of dark matter. By using...
Quantum transformer for High Energy Physics Analysis at the LHC
EyupMentored by Emanuele Usai, Amey Bhatuse, Purva Chaudhari +2
Transformer-based models are gaining more and more traction in many fields, including physics. However, they are particularly known to require...
Invariant and Equivariant Quantum Graph Attention Transformers for HEP Analysis at the LHC
Roy T. ForestanoMentored by Amey Bhatuse, KC Kong, Alkaid Cheng +1
Machine learning algorithms are heavily relied on to understand the data generated at the European Council for Nuclear Research's (CERN) Large Hadron...
Super-Resolution for Strong Gravitational Lensing
Pranath ReddyMentored by Yurii Halychanskyi, Michael Toomey, Brendan Ames +1
Strong gravitational lensing is a promising probe of the substructure of dark matter to better understand its underlying nature. Deep learning...
Quantum Generative Adversarial Networks for HEP event generation the LHC
ToMagoMentored by ML4SCI, Alkaid Cheng, Rui Zhang
An important part of the analysis pipeline of high energy physics experiments is the generation of expected data from first principles. For decades,...
Equivariant Quantum Neural Networks for Continuous Symmetry in High Energy Physics
Cosmos DongMentored by Konstantin Matchev, Katia Matcheva, Rui Zhang
This project aims to explore the development and application of equivariant quantum neural networks (EQNNs) for continuous symmetry in high-energy...
Finding Exoplanets with Astronomical Observations
Mihir TripathiMentored by Emanuele Usai, Shravan25
Protoplanetary disks are birthplaces of planetary systems. Newly forming planets inside a protoplanetary disk interact with gas and dust in the disks...
Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
Anthony SongMentored by ML4SCI, Bhim Bam, Colin Crovella +1
This project focuses on developing and evaluating end-to-end Graph Neural Network (GNN) models for low-momentum tau identification in the context of...
Lensiformer: A Physics-Informed Vision Transformer Architecture for Dark Matter Morphology
Lucas JoséMentored by Purva Chaudhari, Michael Toomey, Anna Parul +1
We introduce Lensiformer, a state-of-the-art transformer architecture that incorporates the principles of relativistic physics for the classification...
Self-Supervised Learning for Strong Gravitational Lensing
Kartik SachdevMentored by Yurii Halychanskyi, Michael Toomey, PG Guan
Supervised learning might be challenging in cases where there are extremely few known instances in a given category. This is a common occurrence in...
Symbolic empirical representation of squared amplitudes in high-energy physics
Neeraj AnandMentored by Abdulhakim Alnuqaydan, Marco Knipfer, Harrison Prosper
In particle physics, a cross section is a measure of the likelihood that particles will interact or scatter with one another when they collide. It is...
Equivariant Neural Networks for Dark Matter Morphology with Strong Gravitational Lensing
Geo JollyMentored by Emanuele Usai, Michael Toomey, Anna Parul +1
Strong gravitational lensing is a promising probe of the substructure of dark matter to better understand its underlying nature. Deep learning...
Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment
Ka Wa HoMentored by ML4SCI, Purva Chaudhari, Ruchi Chudasama +2
The goal of the project is to apply and develop “end-to-end” vision transformer (ViT)-based networks for jet-flavor identification with the CMS open...
Finding Exoplanets with Astronomical Observations
Jack McnishMentored by ML4SCI, Emanuele Usai, Ali Hariri +1
Finding Exoplanets with Astronomical Observations. The aim of this of this project would be to apply machine learning / deep learning methods on...
Implementation of QGANs to Perform High Energy Physics Analysis at the LHC
Abhay KambleMentored by ML4SCI, Emanuele Usai, Abdulhakim Alnuqaydan +1
One of the challenges in High-Energy Physics(HEP) is fast simulation of particle transport, and hence various deep neural network methods have been...
Anomalies Detection
Amal SaifMentored by Ali Hariri, Vishal Thengane, Michelle Kuchera +1
Anomaly detection is the process of identifying data points, events, and observations that differ from a dataset's expected behavior, called...
Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment
Diptarko ChoudhuryMentored by Shravan25, NickP, Colin Crovella +1
The project aims to use Vision Transformer-based architectures to classify high-energy particles. The data consists of multi-channel simulated images...
Quantum Generative Adversarial Neural Networks for High Energy Physics Analysis at the LHC
Amey BhatuseMentored by Ali Hariri, Colin Crovella
One of the problems in High Energy Physics experiments is that particle collisions give rise to novel subatomic particles which need to be detected...
Gravitational Lens Finding for Dark Matter Substructure Pipeline
Mriganka NathMentored by SR, Michael Toomey, Anna Parul +1
Machine learning techniques are regarded to have the potential to help researchers better comprehend dark matter. Convolutional Neural Networks...
Finding Exoplanets with Astronomical Observations
Mahdi BoulilaMentored by Emanuele Usai, Prateek Kumar Agnihotri
The purpose of this project is to use publicly available data from astronomical observations intended to identify exoplanets in order to determine...
Updating the DeepLense Pipeline
Saranga Kingkor MahantaMentored by Emanuele Usai, Pranath Reddy, Michael Toomey +1
The study of dark matter substructures has shown promise in addressing the open-ended and long-standing challenge of identifying the true nature of...
Finding Exoplanets with Astronomical Observations
Jason TerryMentored by ML4SCI, Emanuele Usai, Ali Hariri
The ultimate purpose of this project is to train image-based deep learning models to detect planets embedded in protoplanetary disks. This will be...
Symbolic empirical representation of squared amplitudes in high-energy physics
Marco KnipferMentored by ML4SCI, Abdulhakim Alnuqaydan
Calculating squared amplitudes and cross sections of a Feynman Diagram in high-energy physics is a tedious task. While software like MARTY (A Modern...
Quantum Variational Autoencoders for HEP Analysis at the LHC
ToMagoMentored by ML4SCI, Emanuele Usai, Abdulhakim Alnuqaydan +1
In the search for physics beyond the standard model physics, the growing amount of data and the evasive of the signals that are being searched for,...
Transformers for Dark Matter Morphology with Strong Gravitational Lensing
Kartik SachdevMentored by Pranath Reddy, Michael Toomey, Anna Parul
Strong gravitational lensing is a phenomenon where the light of distant galaxies is bent and distorted by the gravity of massive galaxy clusters,...
End-to-End Deep Learning Reconstruction for CMS Experiment
Purva ChaudhariMentored by ML4SCI, Emanuele Usai, Ana Maria Slivar +1
One of the important aspects of searches for new physics at the Large Hadron Collider (LHC) involves the identification and reconstruction of single...
Transformers for Dark Matter Morphology with Strong Gravitational Lensing
Archil SrivastavaMentored by ML4SCI, Pranath Reddy, SR +1
Since Dark Matter was discovered, physicists have been trying to understand its composition. In practice, the best method to detect substructure is...
Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
Jai BardhanMentored by Ana Maria Slivar, Bhim Bam, Colin Crovella
Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment: The goal of the project would be to develop, train, test, and...
Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
Xin YiMentored by Shravan25, Bhim Bam, Emre Kurtoglu +1
In recent years, the convolutional neural network has been successfully applied in particle physics identification tasks. Despite its great success,...
Quantum Convolutional Neural Networks for High Energy Physics Analysis at the LHC
Gopal Ramesh DahaleMentored by Emanuele Usai, Colin Crovella
This study aims to show the capabilities of QML especially QCNN for classifying the HEP image datasets. QCNN can be completely quantum or can be a...
Fast Accurate Symbolic Empirical Representation of Histograms
Aaron MayerMentored by ML4SCI, Abdulhakim Alnuqaydan
This proposal regards mapping histogram data to its underlying function; both of which can be represented as sequences and hence a transformer can...
Deep Regression Exploration
Zhongchao GuanMentored by Brendan Ames, Sanaz Hami Hassan Kiyadeh
Using Deep Regression techniques to decode Dark Matter with Strong Gravitational Lensing. Try to use the SOTA deep model (such as transformers) to do...
Equivariant Transformers for Decoding Dark Matter with Strong Gravitational Lensing
Yurii HalychanskyiMentored by SR, Brendan Ames, Sanaz Hami Hassan Kiyadeh
Convolutional Neural Networks require large receptive fields in order to track long-range dependencies within an image, which in practice involves...
Machine Learning Model for the Planetary Albedo
Sofia StrukovaMentored by Jason Terry, Sergei Gleyzer
The goal of the project is to use ML techniques to identify relationships between planetary mapped datasets, with the goal of providing deeper...
Equivariant Neural Networks for Dark Matter Morphology with Strong Gravitational Lensing
Apoorva Vikram SinghMentored by K Pranath Reddy, Michael Toomey, Jeremy Quijano +1
The study of substructures in the dark matter has shown signs of promise to deliver on the open-ended and long-standing problem of the identity of...
Graph Neural Networks for Particle Momentum Estimation in the CMS Trigger System
Emre KurtogluMentored by Prateek Kumar Agnihotri, Emanuele Usai, Davide Di Croce +1
The Compact Muon Solenoid (CMS) is a detector at the Large Hadron Collider (LHC) located near Geneva, Switzerland. The CMS experiment detects the...
On the potential of graph-based models in High Energy Physics
Ali A. HaririMentored by Harrison Prosper, Michelle Kuchera, Sergei Gleyzer
The Large Hadron Collider (LHC) at CERN is the world's highest energy particle accelerator, delivering the highest energy proton-proton collisions...
Machine Learning Model for the Albedo of Mercury
Georgios PipilisMentored by Jason Terry, Patrick Peplowski, Sergei Gleyzer
Using Deep Learning techniques in order to model the relationship between the planetary albedo and chemical composition of Mercury.
Direct Objective Function for Anomaly Detection
Yurii HalychanskyiMentored by Brendan Ames, Michael Toomey, Sergei Gleyzer +2
Currently, DeepLense supports the following models for unsupervised dark matter classification: - Adversarial Autoencoder - Convolutional...
Background Estimation with Neural AutoRegressive Flows
Muhammad Ehsan ul HaqMentored by Meenakshi Narain, Emanuele Usai, dannysli +3
Neural AutoRegressive Flows are one of the most recent addition to the family of autoregressive flows. By using NAFs, probability density estimation...
End-to-End Deep Learning Reconstruction for CMS Experiment
Purva ChaudhariMentored by bjornburkle, Emanuele Usai, Davide Di Croce +2
One of the important aspects of searches for new physics at the Large Hadron Collider (LHC) involves the identification and reconstruction of single...
Graph Neural Networks for End-to-End Particle Identification with the CMS Experiment
Shravan ChaudhariMentored by Emanuele Usai, Davide Di Croce, Sergei Gleyzer
This project focuses on the study and implementation of Graph Neural Networks (GNNs) for low-momentum Tau Particle Identification using the CMS Open...
Normalizing Flows for Fast Detector Simulation
Aditya AhujaMentored by John Blue, Harrison Prosper, Michelle Kuchera +2
DeepFalcon is an ultra-fast non-parametric detector simulation package. This project aims to extend DeepFalcon by adding functionality for Graph...
Quple - Quantum GAN
Chi Lung ChengMentored by Wen Guan, CHEN ZHOU, Rui Zhang +2
The proposed project "Quple - Quantum GAN" serves as an extension to the 2020 GSoC project "Quple" with a major focus on the implementation of...
Dimensionality Reduction for Studying Diffuse Circumgalactic Medium
Jakub RybakMentored by Sergei Gleyzer, Varsha Kulkarni, Jeremy Quijano +2
This project will seek to identify dimensionality-reduction methods that achieve a reduction in the number of features while maintaining predictive...
Quantum Convolutional Neural Networks for High-Energy Physics Analysis at the LHC
Eraraya Ricardo MutenMentored by Raphael Koh, Emanuele Usai, Sergei Gleyzer
One of the challenges in High-Energy Physics (HEP) is events classification, which is to predict whether an image of particle jets belongs to events...
Background Estimation with Neural Autoregressive Flows Proposal
Sinan GençoğluMentored by dannysli, Uli, Meenakshi Narain +2
Data-driven background estimation is crucial for many scientific searches, including searches for new phenomena in experimental datasets. Neural...
Machine Learning for Turbulent Fluid Dynamics
Amey VarhadeMentored by Brad Marston, Steven Tobias, Chenyu Zhang
Our understanding of Turbulence is still not very clear, studying fluid transitions to turbulence still poses challenging problems. The Navier-Stokes...
End-to-End Deep Learning Regression for Measurements with the CMS Experiment
Anis IsmailMentored by Emanuele Usai, Sergei Gleyzer, Davide Di Croce +3
Experiments conducted at the Large Hadron Collider (LHC) are the source of the most important discoveries in new physics. One of the most prominent...
Uncovering the Enigma of Type-Ia Supernovae: Thermonuclear Supernova Classification via their Nuclear Signatures
Sophia HeMentored by James Mastandrea, Patrick Peplowski, Richard S. Miller +1
Fundamental questions about Thermonuclear Supernovae (Type-Ia or SNeIa), the beacons visible across the universe, remain unanswered. Using the...
Decoding quantum states through Nuclear Magnetic Resonance
Anantha RaoMentored by Brad Marston, Chandrasekhar Ramanathan, Charles Snider +2
At low temperatures, many materials transition into an electronic phase which cannot be classified as a simple metal or insulator, and quantum phases...
Domain Adaptation for Decoding Dark Matter with Strong Gravitational Lensing
Marcos TidballMentored by K Pranath Reddy, Michael Toomey, Sourav Raha +2
Dark matter is one of the biggest questions in current cosmology, and many different theories were created to try to explain it. One of the...
Data: Google Summer of Code public archive. Official GSoC archive