Advancing the science of
material intelligence

Ainuric conducts applied research at the intersection of materials science, machine learning, and computational modelling — publishing openly to accelerate progress across the field.

Research Focus

Where we focus our research

Our research is grounded in real engineering problems — always aimed at outcomes that can be deployed in practice.

Machine Learning for Materials

Developing and benchmarking ML models for predicting mechanical, thermal, and corrosion properties from composition and processing data — with rigorous uncertainty quantification.

Material Data Infrastructure

Building open standards and tools for structuring, sharing, and querying material data at scale — enabling reproducible research and interoperability between platforms.

Alloy Design & Optimisation

Applying generative AI and optimisation algorithms to accelerate the discovery of new alloy compositions with targeted property profiles — reducing the search space by orders of magnitude.

Publications

Publications & white papers

Methods notes, white papers, and peer-reviewed publications from Ainuric research.

2026

Graph-Based Material Similarity for Engineering Shortlisting

White paper · Ainuric · Find Similarity capability for MaterialPoint and MCP

An explainable method for ranking related materials from structured evidence graphs, designed for early engineering shortlist discovery and review.

Download PDF
2026

Runtime-Safe Synthesis of Engineering Stress-Strain Curves

White paper · Ainuric · Curve Synthesizer capability for MaterialPoint and MCP

A staged method for generating plausible engineering stress-strain curves from runtime-safe material metadata, helper-property inference, and constrained empirical reconstruction.

Download PDF
Academic Partnerships

Collaborate with us on materials research

We actively collaborate with universities, research institutes, and national labs. If you are working on material data, AI for materials, or related computational problems, we would love to explore joint projects, shared datasets, or co-authored publications.

We particularly welcome partnerships focused on open science and reproducible research.

Get in touch