Blog
Original, educational and honest writing on materials informatics, AI for materials discovery, critical raw materials and scientific data quality. When fixing a bug lowers a model’s score, the lower number gets published.
- Critical materials
Lithium has two chokepoints, and they sit in different countries
Chile ships 79% of the world's traded lithium carbonate. China ships 74% of the hydroxide. Which chokepoint you face depends on your battery chemistry.
- AI and machine learning
Claude Skills for materials science: what actually exists right now
What Claude Skills are, how they differ from MCP, and how to install three real materials science skills available today.
- Critical materials
Two governments, one shipment, two different numbers
Across 976 critical mineral trade flows, importer and exporter accounts differ by a median of 23 percent. Chile and China differ by 2.3x on lithium.
- Critical materials
Denmark's wind turbines will not be a rare earth mine
Denmark's wind fleet holds 124 tonnes of neodymium, and half of it sits in turbines I first assumed contained none. A material flow model.
- Materials data and quality
Do materials databases agree with each other? I measured it
I compared 344 structure-matched materials across the Materials Project and OQMD. Only 26 percent of formation energies agree within the conventional threshold.
- AI and machine learning
MCP and the Materials Project: a doorway for AI to materials data
What the Model Context Protocol is, why it matters for materials science, the Materials Project MCP servers that already exist, and how to build one yourself.
- Materials data and quality
Materials Project API: common mp-api errors and fixes
Fixes for the Materials Project mp-api errors people hit: get_dos_by_material_id returning CompleteDos, 403 Forbidden, API keys, and legacy vs new client.
- AI and machine learning
Materials informatics: a practical guide
What materials informatics is, how it turns data into material property predictions, the tools and databases behind it, and where it quietly breaks.
- AI and machine learning
AI for materials: how it actually works
AI for materials discovery, explained: property prediction, generative design, and machine-learning potentials, plus the honest limits of each.
- Materials data and quality
Materials data engineering, explained
Why materials data is messy, and how data engineering (pipelines, dbt, testing, orchestration) turns scattered scientific data into something you can model.
- Materials data and quality
Scientific data quality: why it decides your model
Scientific data is less trustworthy than the models built on it assume. Why quality, leakage, and provenance decide your result, and how to check them.
- AI and machine learning
Graph neural networks for materials, explained
Composition-based models cannot tell polymorphs apart. A graph neural network that reads crystal structure finally can. How GNNs work for materials.
- AI and machine learning
Physics-informed neural networks, explained
A network recovered a full cooling curve from six noisy points, refused to predict the impossible, and read a physical constant from the data. How PINNs work.
- AI and machine learning
Six ways to put physics into machine learning
Ordinary machine learning learns only from data. Scientific ML also respects physics. Here are the six places to inject it, one use case each.
- AI and machine learning
ML on the Materials Project, part 7: knowing what you don't know
A Gaussian Process predicts a value and an honest error bar. We audited whether the bars can be trusted, and found the model measured its own noise floor.
- AI and machine learning
ML on the Materials Project, part 8: opening the box
The series finale: which features does the model actually use, and did it learn real chemistry? Yes, worn as a proxy nobody expected.
- AI and machine learning
ML on the Materials Project, part 5: the map of chemical space
Unsupervised learning turns 26,566 materials into a 2D map with no labels, finds groups nobody defined, and shows why data's folds rarely match your question.
- AI and machine learning
ML on the Materials Project, part 6: the statistical auditor
An Isolation Forest given zero rules flags the dataset's strangest entries on geometry alone, including a formation energy twenty times past any sane threshold.
- AI and machine learning
ML on the Materials Project, part 3: is it even a metal?
Same features, a different question. Classification exposes the accuracy trap live, and asks why metallicity is hard to predict from composition.
- AI and machine learning
ML on the Materials Project, part 4: were we lying to ourselves?
Grouped cross-validation measures how much a model's score was flattered by polymorph twins leaking between train and test. The answer: thirty percent.
- AI and machine learning
ML on the Materials Project, part 2: trees, and overfitting caught
Same data, one change of model, and R2 jumps from 0.095 to 0.637. Plus the train-versus-test gap that shows memorization as a number.
- AI and machine learning
ML on the Materials Project, part 1: the honest floor
Fetching 26,568 real oxides, turning formulas into numbers a model can learn from, and why a first score of R2 = 0.095 is a good start.
- Materials data and quality
Materials Project API tutorial: mp-api, keys, Python
A beginner Materials Project API tutorial: get your API key, install mp-api, run your first Python request, and dodge the Cloudflare 403 gotcha.
- Materials data and quality
How to audit a materials database entry: a six-check list
A practical checklist for deciding whether a value from the Materials Project deserves your trust, with the reasoning behind each check.
- Materials data and quality
Properties belong to structures, not formulas
Diamond and graphite share a formula and agree on almost nothing else. Why polymorphism breaks naive materials data, and how to handle it.
- Materials data and quality
Automatic tests for scientific data: a dbt primer
How to attach rules to a materials dataset, no negative band gaps, one entry per polymorph, that run on every refresh and fail loudly.
- Materials data and quality
The data engineering stack, translated for materials science
What ETL, SQL, dbt, Airflow, Kafka and Spark actually do, each explained with a concrete materials use case, and the two worth learning first.
- AI and machine learning
Why AI-predicted materials rarely get made
Models have predicted millions of new materials, yet only hundreds exist. Understanding the gap between a predicted structure and a real one.
Also on Materials Decoded
Importing from China
Practical guides for UK businesses buying from Chinese suppliers: which shipping terms to use, how to run an inspection before you pay, and when to order around Chinese New Year.
All 3 importing guides · China sourcing and UK import support