Machine Learning in Physical Sciences
Data-Driven Physics
Scientific Machine Learning
Physics-Informed Machine Learning
Theory-Guided Machine Learning
Physics-Guided Artificial Intelligence
Mechanistic Machine Learning
Hybrid Physics–Machine Learning Models
First-Principles and Data-Driven Modeling
Empirical Models versus Physics-Based Models
Supervised Learning for Physics
Unsupervised Learning for Physics
Semi-Supervised Learning for Physics
Self-Supervised Learning for Physics
Reinforcement Learning for Physics
Transfer Learning in Physics
Multi-Task Learning in Physics
Active Learning for Physical Experiments
Continual Learning for Scientific Data
Few-Shot Learning for Physics
Linear Algebra for Machine Learning
Probability Theory for Physical Data
Bayesian Statistics in Physics
Statistical Inference in Physics
Maximum-Likelihood Estimation
Bayesian Parameter Estimation
Hypothesis Testing with Machine Learning
Regression Analysis in Physics
Classification Methods in Physics
Clustering of Physical Data
Dimensionality Reduction
Principal Component Analysis
Independent Component Analysis
Manifold Learning
Information Theory in Machine Learning
Entropy-Based Learning Methods
Optimization Methods for Physics
Convex and Nonconvex Optimization
Gradient-Based Optimization
Automatic Differentiation
Linear Regression for Physical Systems
Polynomial Regression
Logistic Regression
Decision Trees
Random Forests
Gradient-Boosted Trees
Support Vector Machines
k-Nearest Neighbors
Gaussian-Process Regression
Kernel Methods
Expectation–Maximization Algorithms
k-Means Clustering
Hierarchical Clustering
Density-Based Clustering
Anomaly-Detection Algorithms
Ensemble Learning
Symbolic Regression
Genetic Algorithms
Evolutionary Computation
Sparse Regression
Artificial Neural Networks
Deep Neural Networks
Multilayer Perceptrons
Convolutional Neural Networks
Recurrent Neural Networks
Long Short-Term Memory Networks
Gated Recurrent Units
Transformer Models for Physics
Vision Transformers for Scientific Images
Graph Neural Networks
Geometric Deep Learning
Equivariant Neural Networks
Symmetry-Preserving Neural Networks
Rotation-Equivariant Neural Networks
Lorentz-Equivariant Neural Networks
Hamiltonian Neural Networks
Lagrangian Neural Networks
Symplectic Neural Networks
Neural Ordinary Differential Equations
Neural Partial Differential Equations
Autoencoders for Physical Data
Variational Autoencoders
Generative Adversarial Networks
Diffusion Models for Physics
Normalizing Flows
Autoregressive Generative Models
Energy-Based Models
Generative Models for Event Simulation
Generative Models for Detector Simulation
Synthetic Scientific Data Generation
Generative Models for Materials Design
Generative Models for Molecular Systems
Inverse Design with Generative Models
Conditional Generative Models
Simulation-Based Generative Modeling
Physics-Informed Neural Networks
Differential-Equation-Constrained Learning
Boundary-Condition-Constrained Neural Networks
Initial-Condition-Constrained Learning
Conservation-Law-Constrained Learning
Energy-Conserving Neural Networks
Momentum-Conserving Neural Networks
Gauge-Invariant Neural Networks
Causality-Constrained Machine Learning
Thermodynamics-Informed Neural Networks
Maxwell-Equation-Informed Neural Networks
Schrödinger-Equation-Informed Neural Networks
Navier–Stokes-Informed Neural Networks
General-Relativity-Informed Neural Networks
Fractional Differential-Equation Learning
Stochastic Differential-Equation Learning
Multi-Fidelity Physics-Informed Learning
Weak-Form Physics-Informed Neural Networks
Domain-Decomposed Physics-Informed Networks
Adaptive Physics-Informed Neural Networks
Machine Learning for Ordinary Differential Equations
Machine Learning for Partial Differential Equations
Learning Differential Operators
Neural Operators
Fourier Neural Operators
Deep Operator Networks
Graph-Based PDE Solvers
Data-Driven Discovery of Differential Equations
Sparse Identification of Nonlinear Dynamics
Learning Governing Equations from Data
Dynamical-System Identification
Reduced-Order Modeling
Surrogate Modeling of Dynamical Systems
Chaotic-System Prediction
Nonlinear Time-Series Modeling
Bifurcation Detection with Machine Learning
Koopman-Operator Learning
State-Space Modeling
Latent-Space Dynamics
Equation-Free Modeling
Machine-Learning-Accelerated Simulation
Surrogate Models for Numerical Simulation
Emulation of Computationally Expensive Models
Machine Learning for Monte Carlo Simulation
Neural Monte Carlo Methods
Importance Sampling with Machine Learning
Adaptive Sampling
Markov Chain Monte Carlo with Machine Learning
Learned Proposal Distributions
Differentiable Simulation
Data-Driven Finite-Element Methods
Machine Learning for Finite-Difference Methods
Machine Learning for Spectral Methods
Mesh-Based Machine Learning
Mesh-Free Neural Solvers
Adaptive Mesh Refinement with Machine Learning
Error Correction for Numerical Solvers
Simulation Calibration
Simulation-to-Real Transfer
Digital Twins of Physical Systems
Machine Learning for Inverse Problems
Inverse Modeling in Physics
Parameter Reconstruction
Source Reconstruction
Image Reconstruction
Signal Reconstruction
Tomographic Reconstruction
Deconvolution with Machine Learning
Phase Retrieval
Spectral Inversion
Bayesian Inverse Problems
Neural Inverse Operators
Regularization with Machine Learning
Ill-Posed Problem Solving
System Identification
Latent-Parameter Estimation
Differentiable Inverse Modeling
Simulation-Based Inference
Likelihood-Free Inference
Approximate Bayesian Computation
Machine Learning for Experimental Design
Active Learning for Laboratory Experiments
Autonomous Laboratories
Self-Driving Scientific Laboratories
Real-Time Experimental Control
Reinforcement Learning for Instrument Control
Adaptive Measurement Strategies
Optimal Sensor Placement
Detector Calibration with Machine Learning
Detector Alignment
Trigger Systems Using Machine Learning
Real-Time Event Selection
Noise Reduction in Experimental Data
Signal Extraction from Background
Sensor-Fusion Methods
Fault Detection in Scientific Instruments
Predictive Maintenance of Experimental Facilities
Automated Data Acquisition
Robotic Experimentation
Closed-Loop Scientific Discovery
Machine Learning for Signal Processing
Scientific Image Classification
Scientific Image Segmentation
Object Detection in Physics Images
Feature Extraction from Detector Images
Denoising Scientific Images
Super-Resolution for Physical Measurements
Image Reconstruction from Sparse Data
Pattern Recognition in Physical Data
Spectral Analysis with Machine Learning
Waveform Classification
Pulse-Shape Discrimination
Transient Detection
Change-Point Detection
Time-Series Forecasting
Multivariate Time-Series Analysis
Spatiotemporal Machine Learning
Missing-Data Reconstruction
Data Compression with Neural Networks
Learned Scientific Data Representations
Machine Learning in High-Energy Physics
Particle Classification
Particle Identification
Jet Classification
Jet Tagging
Quark–Gluon Discrimination
Heavy-Flavour Tagging
Higgs-Boson Event Classification
Beyond-Standard-Model Searches
New-Particle Discovery with Machine Learning
Collider Event Reconstruction
Track Reconstruction
Vertex Reconstruction
Calorimeter Reconstruction
Particle-Flow Reconstruction
Trigger Optimization at Particle Colliders
Fast Detector Simulation
Event Generation with Neural Networks
Matrix-Element Surrogates
Unfolding Detector Effects
Background Estimation
Anomaly Detection at Colliders
Effective Field Theory Inference
Parton Distribution Function Learning
Lattice Gauge Theory with Machine Learning
Machine Learning for Neutrino Detection
Neutrino-Event Classification
Neutrino-Flavour Identification
Neutrino-Energy Reconstruction
Neutrino-Direction Reconstruction
Neutrino-Interaction Classification
Atmospheric-Neutrino Analysis
Solar-Neutrino Analysis
Reactor-Neutrino Analysis
Accelerator-Neutrino Analysis
Astrophysical-Neutrino Classification
High-Energy Neutrino Astronomy
Neutrino-Oscillation Parameter Estimation
Mass-Hierarchy Determination
Neutrino-Tomography Inference
Background Rejection in Neutrino Detectors
Cherenkov-Photon Pattern Recognition
Radio-Neutrino Signal Classification
Air-Shower Reconstruction from Tau Neutrinos
Machine Learning for Neutrino-Telescope Optimization
Machine Learning in Nuclear Physics
Nuclear-Reaction Modeling
Nuclear-Structure Prediction
Nuclear-Mass Prediction
Nuclear-Decay Prediction
Fission-Fragment Prediction
Nuclear Cross-Section Estimation
Nuclear-Level Classification
Equation-of-State Inference
Heavy-Ion Collision Analysis
Quark–Gluon Plasma Classification
Nuclear-Detector Signal Processing
Radiation-Type Identification
Gamma-Ray Spectroscopy with Machine Learning
Neutron Spectroscopy
Reactor Monitoring with Machine Learning
Reactor-Physics Surrogate Models
Nuclear-Fuel Optimization
Radiation Transport Acceleration
Nuclear-Safety Anomaly Detection
Machine Learning in Astrophysics
Machine Learning in Cosmology
Astronomical Object Classification
Star–Galaxy Classification
Galaxy Morphology Classification
Exoplanet Detection
Gravitational-Lens Detection
Supernova Classification
Transient Astronomy
Variable-Star Classification
Pulsar Detection
Fast Radio Burst Detection
Gamma-Ray Burst Classification
Black-Hole Parameter Estimation
Neutron-Star Modeling
Gravitational-Wave Detection
Gravitational-Wave Parameter Inference
Multi-Messenger Astronomy with Machine Learning
Photometric Redshift Estimation
Spectroscopic Redshift Estimation
Cosmic Microwave Background Analysis
Large-Scale Structure Reconstruction
Dark-Matter Distribution Mapping
Dark-Energy Parameter Estimation
Cosmological Simulation Emulation
Machine Learning in Plasma Physics
Plasma-State Classification
Plasma-Turbulence Modeling
Magnetic-Reconnection Prediction
Tokamak Plasma Control
Plasma-Instability Detection
Fusion-Disruption Prediction
Fusion-Reactor Optimization
Inertial-Confinement Fusion Modeling
Solar-Flare Prediction
Coronal-Mass-Ejection Prediction
Solar-Wind Forecasting
Magnetospheric Modeling
Ionospheric Modeling
Space-Weather Forecasting
Radiation-Belt Prediction
Auroral Classification
Satellite-Anomaly Prediction
Spacecraft-Trajectory Optimization
Autonomous Spacecraft Control
Machine Learning in Condensed-Matter Physics
Phase Classification
Phase-Transition Detection
Quantum Phase Recognition
Topological-Phase Classification
Many-Body State Classification
Spin-System Modeling
Ising-Model Learning
Hubbard-Model Learning
Electronic-Structure Prediction
Band-Structure Prediction
Density-of-States Prediction
Superconductivity Prediction
Strongly Correlated Material Modeling
Defect Detection in Solids
Crystal-Structure Classification
Microstructure Analysis
Domain-Wall Detection
Magnetic-Material Modeling
Transport-Property Prediction
Machine Learning for Materials Discovery
Materials Informatics
Materials-Property Prediction
Crystal-Structure Prediction
Crystal Graph Neural Networks
Interatomic-Potential Learning
Neural-Network Potentials
Force-Field Development
Molecular-Dynamics Acceleration
High-Throughput Materials Screening
Inverse Materials Design
Alloy Design with Machine Learning
Battery-Material Discovery
Photovoltaic-Material Prediction
Thermoelectric-Material Optimization
Catalytic-Material Discovery
Two-Dimensional Material Prediction
Metamaterial Design
Mechanical-Property Prediction
Materials-Failure Prediction
Machine Learning in Quantum Physics
Quantum Machine Learning
Classical Machine Learning for Quantum Systems
Neural Quantum States
Quantum-State Reconstruction
Quantum-State Tomography
Quantum-Process Tomography
Quantum-Control Optimization
Quantum-Error Correction with Machine Learning
Quantum-Error Mitigation
Quantum-Circuit Optimization
Variational Quantum Algorithms
Quantum Kernel Methods
Quantum Neural Networks
Quantum Reinforcement Learning
Quantum Many-Body Learning
Quantum-Phase Classification
Wavefunction Approximation
Density-Matrix Learning
Hamiltonian Learning
Quantum Measurement Optimization
Quantum Sensor Data Analysis
Quantum-Chemistry Machine Learning
Quantum Simulation with Neural Networks
Machine Learning for Quantum Hardware Calibration
Machine Learning in Atomic Physics
Machine Learning in Molecular Physics
Machine Learning in Optical Physics
Atomic-Spectra Classification
Molecular-Spectra Prediction
Spectral-Line Identification
Molecular-Potential Energy Surfaces
Molecular-Dynamics Learning
Chemical-Reaction Prediction
Laser-Pulse Optimization
Adaptive Optics with Machine Learning
Computational Imaging
Phase-Space Reconstruction
Optical-System Design
Photonic-Device Optimization
Photonic Neural Networks
Ultrafast-Physics Data Analysis
Cold-Atom Experiment Control
Bose–Einstein Condensate Modeling
Trapped-Ion Control
Machine Learning in Fluid Dynamics
Data-Driven Computational Fluid Dynamics
Turbulence Modeling
Turbulence Closure Models
Flow-Field Reconstruction
Fluid-Flow Prediction
Vortex Detection
Coherent-Structure Identification
Reduced-Order Fluid Models
Neural Navier–Stokes Solvers
Aerodynamic-Shape Optimization
Drag Prediction
Lift Prediction
Boundary-Layer Modeling
Multiphase-Flow Modeling
Combustion Modeling
Shock-Wave Detection
Supersonic-Flow Prediction
Weather-Flow Simulation
Ocean-Circulation Modeling
Machine Learning in Geophysics
Seismic-Event Detection
Earthquake Detection and Classification
Earthquake Early Warning
Seismic Tomography
Subsurface-Structure Reconstruction
Oil and Gas Reservoir Characterization
Mineral Exploration
Geomagnetic-Field Modeling
Gravity-Field Reconstruction
Volcanic-Eruption Forecasting
Landslide Prediction
Tsunami Detection
Soil-Property Prediction
Hydrological Modeling
Groundwater Prediction
Atmospheric-Physics Modeling
Climate Modeling with Machine Learning
Weather Forecasting
Extreme-Weather Detection
Cloud Classification
Aerosol-Property Retrieval
Air-Quality Prediction
Ocean-Temperature Prediction
Remote-Sensing Data Analysis
Machine Learning in Biophysics
Protein-Structure Prediction
Biomolecular-Dynamics Modeling
Single-Molecule Data Analysis
Cellular-Mechanics Modeling
Neural-Signal Analysis
Medical-Image Reconstruction
Computed-Tomography Reconstruction
Magnetic-Resonance Image Reconstruction
Positron-Emission Tomography Analysis
Radiation-Therapy Planning
Radiation-Dose Prediction
Particle-Therapy Optimization
Medical-Detector Calibration
Biomedical Signal Classification
Symmetry-Aware Machine Learning
Translational Invariance
Rotational Invariance
Permutation Invariance
Lorentz Invariance
Gauge Invariance
Scale Invariance
Equivariance in Neural Networks
Conservation-Law Enforcement
Dimensional Consistency in Machine Learning
Unit-Aware Neural Networks
Coordinate-Independent Learning
Causal Structure in Physical Models
Geometric Constraints
Topological Constraints
Uncertainty Quantification
Aleatoric Uncertainty
Epistemic Uncertainty
Bayesian Neural Networks
Gaussian Processes for Uncertainty Estimation
Deep Ensembles
Calibration of Machine-Learning Predictions
Confidence-Interval Estimation
Out-of-Distribution Detection
Domain-Shift Detection
Robust Machine Learning for Physics
Adversarial Robustness in Scientific Models
Sensitivity Analysis
Error Propagation
Model Validation against Physical Laws
Cross-Validation for Scientific Data
Benchmarking Machine-Learning Models
Reproducibility in Scientific Machine Learning
Interpretability of Scientific Models
Explainable Artificial Intelligence for Physics
Scientific Data Preprocessing
Physical-Data Normalization
Feature Engineering for Physics
Dimensional Analysis as Feature Engineering
Detector-Data Cleaning
Noise Filtering
Outlier Detection
Missing-Value Handling
Data Augmentation for Physics
Simulation-Based Data Augmentation
Class-Imbalance Correction
Large-Scale Scientific Databases
Distributed Machine Learning
Parallel Machine Learning
GPU-Accelerated Machine Learning
High-Performance Computing for Machine Learning
Edge Machine Learning for Detectors
Real-Time Machine-Learning Pipelines
Scientific Data Provenance
FAIR Data for Machine Learning
Reinforcement Learning for Physical Systems
Model-Based Reinforcement Learning
Model-Free Reinforcement Learning
Deep Reinforcement Learning
Safe Reinforcement Learning
Physics-Constrained Reinforcement Learning
Experimental Control with Reinforcement Learning
Accelerator Control
Plasma Control
Laser-System Control
Quantum-System Control
Robotic Laboratory Control
Adaptive Optics Control
Energy-System Optimization
Autonomous Navigation in Physical Environments
Automated Scientific Discovery
Machine-Assisted Hypothesis Generation
Discovery of Physical Laws from Data
Symbolic Discovery of Equations
Automated Theorem Discovery in Physics
Causal Discovery in Physical Systems
Discovery of Hidden Variables
Discovery of Conservation Laws
Identification of Emergent Phenomena
Detection of New Phases of Matter
Anomaly-Based Discovery
Literature-Based Scientific Discovery
Knowledge Graphs for Physics
Large Language Models for Physics Research
AI Agents for Experimental Physics
Dataset Bias in Physical Sciences
Model Bias in Scientific Inference
Data Leakage in Physics Analysis
Statistical Significance and Machine Learning
Look-Elsewhere Effects in Machine-Learning Searches
Reproducible Machine-Learning Workflows
Open-Source Scientific Machine Learning
Ethical Use of Artificial Intelligence in Physics
Responsible Automation of Experiments
Human-in-the-Loop Scientific Machine Learning
Verification and Validation of AI Models
Physical Plausibility Testing
Benchmark Datasets for Physics
Standardized Evaluation Metrics
Documentation of Scientific AI Models
Python for Machine Learning in Physics
NumPy for Physical Data
SciPy for Scientific Machine Learning
Pandas for Experimental Data
Matplotlib for Physics Visualization
Scikit-Learn for Physics
TensorFlow for Physics
PyTorch for Physics
JAX for Differentiable Physics
Keras for Scientific Neural Networks
XGBoost for Physical Data
PyTorch Geometric for Graph Physics
Deep Graph Library for Physical Systems
TensorFlow Probability
Pyro for Probabilistic Physics Models
Stan for Bayesian Physics
Julia for Scientific Machine Learning
DifferentialEquations.jl
Physics-Informed Neural-Network Libraries
Distributed Training for Scientific Models
Foundation Models for Physics
Multimodal Models for Scientific Data
Large Physics Models
Scientific Large Language Models
Generative AI for Physical Sciences
Neuro-Symbolic Physics
Differentiable Programming for Physics
Machine Learning with Conservation Guarantees
Foundation Models for Weather and Climate
Foundation Models for Materials Science
Foundation Models for Particle Physics
Autonomous Physics Research Agents
Machine Learning for Real-Time Discovery
Federated Learning for Scientific Collaborations
Privacy-Preserving Scientific Machine Learning
Neuromorphic Computing for Physics
Analog Machine Learning for Physical Systems
Optical Machine Learning
Quantum-Enhanced Scientific Machine Learning
Machine Learning for Digital-Twin Experiments
These topics can be organized under five broad branches: data analysis, physical modeling, simulation acceleration, experimental control, and automated scientific discovery.