Explore Machine Learning With AIP Publishing

Discover our extensive collection of journals, conference proceedings, and books that span machine learning and its intersections with other disciplines.

As your partner in publishing, whether you’re just beginning your journey or have years of experience, we’re here to provide you with the best home for your work and the tools and resources you need to elevate and amplify your research.

Featured Journals

Journals dedicated to research in machine learning:

APL Machine Learning

Machine Learning for Applied Physics
Applied Physics for Machine Learning

Journal Impact Factor: 4.1*
Cited Half-Life: 2.0 Years*
CiteScore™: 6.5^†
Avg. Views/Article Per Year (2024-2025): 850+
Days to 1st Decision (Avg.): 36^‡
Days to Acceptance (Avg): 92^‡
Days to Publish (Avg.): 116^‡
Topics covered: Machine learning, artificial intelligence, neural network dynamics, data mining, signal processing, robotics
Article types: Articles, Reviews, Perspectives, Tutorials
Access type: Gold open access

Browse Open Special Topics

Interdisciplinary Journals

Journals at the intersection of machine learning and related disciplines:

MechanoEngineering

Publishing open research at the intersection of mechanics and emerging technologies in the digital-AI era

First Issue Now Online

APL Computational Physics

Showcasing the transformative impact of computation across all physical science

Browse Open Special Topics

Journal of Applied Physics

Significant results in cutting-edge applied physics

Browse Open Special Topics

Applied Physics Letters

Shaping the future of applied physics for over 60 years

Browse Open Special Topics

The Journal of Chemical Physics

The most cited in chemical physics

Browse Open Special Topics

AIP Advances

A peer-reviewed, open access journal covering all areas of the physical sciences

Browse Open Special Topics

APL Quantum

Bridging fundamental quantum research with technological applications

Browse Open Special Topics

Applied Physics Reviews

High-impact research and authoritative reviews in applied physics

Browse Open Special Topics

Chaos

An Interdisciplinary Journal of Nonlinear Science

Browse Open Special Topics

More Journals to Explore

Browse all AIP Publishing and partner titles

AIP Conference Proceedings

AIP Conference Proceedings has been a trusted publishing partner for more than 40 years, delivering fast, affordable, and versatile publishing for maximum exposure of your meeting’s key research.

Browse all AIP Conference Proceedings

Highlighted Research

Brain-inspired learning in artificial neural networks: A review

Artificial neural networks have become central to machine learning and have succeeded in applications ranging from media generation and games to robotics. Despite these achievements, their operating mechanisms—particularly how they learn—differ fundamentally from those of biological brains.

Accelerating defect predictions in semiconductors using graph neural networks

First-principles methods can accurately estimate the energetics of point defects in semiconductors, but large supercells and advanced theories make the calculations expensive. Machine-learning models trained on computational data can accelerate these predictions when they adequately represent the local environments surrounding defects.

Training self-learning circuits for power-efficient solutions

As artificial-intelligence and machine-learning models become larger and more widespread, the energy and financial costs of training and operating them are becoming increasingly unsustainable. Prototype self-learning electronic circuits suggest that analog hardware could use physical processes to learn desired functions from examples with much lower energy consumption.

A highly ductile carbon material made of triangle rings: A study of machine learning

Carbon materials display a broad range of mechanical behavior, from rigid diamond to soft graphite. Highly ductile carbon materials are uncommon because carbon atoms are connected by strong covalent bonds.

Understanding the importance of four-phonon scattering in low-symmetry monolayer 1T′-ReS₂ using machine learning potential

Higher-order anharmonic effects have been shown to influence heat transport significantly in highly symmetric two-dimensional materials with large acoustic–optical phonon gaps. Their role in phonon scattering and thermal transport within low-symmetry structures remains unclear.

Molecular dynamics simulations of heat transport using machine-learned potentials: A mini-review and tutorial on GPUMD with neuroevolution potentials

Molecular-dynamics simulations are important for understanding and engineering heat transport in complex materials. Reliable predictions require interatomic potentials that are both accurate and computationally efficient.

Dissimilar thermal transport properties in κ-Ga₂O₃ and β-Ga₂O₃ revealed by homogeneous nonequilibrium molecular dynamics simulations using machine-learned potentials

The lattice thermal conductivity of Ga₂O₃ is especially important because managing heat in high-power devices is difficult. The researchers develop machine-learned neuroevolution potentials for single-crystal β-Ga₂O₃ and κ-Ga₂O₃ and demonstrate their accuracy for modeling thermal transport.

Perspective: Atomistic simulations of water and aqueous systems with machine learning potentials

Water has been a central subject of computational research since the beginning of computer simulation because of its importance as a solvent. Early studies relied on simplified interaction models, whereas first-principles molecular-dynamics methods later enabled more predictive simulations of aqueous systems.

Comparing machine learning potentials for water: Kernel-based regression and Behler–Parrinello neural networks

The study compares how effectively different machine-learning potentials predict important thermodynamic properties of water using RPBE+D3 reference calculations. It evaluates kernel-based regression and high-dimensional neural networks trained on a highly accurate dataset of about 1,500 structures and a second dataset roughly half that size generated through on-the-fly learning.

Inverse design of bio-inspired staggered composites via machine learning and genetic algorithms for tailored mechanical properties

Bio-inspired staggered composites have exceptional mechanical properties and strong potential for aerospace and rail-transport applications. This creates a need to solve the inverse-design problem of identifying the optimal microstructure for a desired large-scale mechanical performance.

Machine learning for mechanical design of composite materials and composite structures

Artificial intelligence has become closely integrated with composite-materials science and engineering, supporting both material discovery and performance optimization. The article first reviews how machine-learning algorithms, databases, and specialist knowledge are being combined across the design, fabrication, characterization, and service-performance evaluation of composite materials and structures.

Upcoming Conferences

You’ll find AIP Publishing’s editors and journal managers at these upcoming conferences and events. We hope to see you there!

Author Resources

Publishing Academy
Find resources to help you navigate key topics related to publishing and peer review, openness and reproducibility of science, and gaining visibility for your research.

Special Topics for Open Submissions
Browse our Special Topics now accepting papers that capture new insights into emerging fields and disciplines across the physical sciences.

*Data from the 2025 Journal Citation Reports® Science Edition (Clarivate, 2026).
^†CiteScore™ 2025 for AIP Publishing Journals Calculated by Scopus.
^‡Publication speeds vary depending on article type.