Home

Reading the Moon

An interactive exhibit where you explore and identify the Moon's four major rock-forming minerals under a polarizing microscope, label your own datasets, contribute to a growing dataset for a foundation model of the Moon, and observe how an AI agent working in real time.

Intro

Lunar rocks are simple.

The Moon has no liquid water and no plate tectonics, so its minerals never weathered into clays or micas. As a result, a lunar thin section is a simple mosaic of just a handful of primary minerals, formed billions of years ago and have remained largely unchanged ever since. Two major rock types dominate the lunar surface. The bright highlands are composed mainly of anorthosite, which is almost pure plagioclase feldspar; the dark maria are basalts, containing mostly pyroxene, plagioclase, olivine, and titanium-rich ilmenite. Learn these four, and you can read most of the lunar surface.

A 30-micron-thick slice of rock is placed between two crossed polarizing filters. Each mineral splits light in its own way, glowing in interference colors. Rotate the stage and grains brighten, shift, and snap to black at extinction. The pattern of relief, cleavage, fracture, twinning, and color is a fingerprint.

Your path through the exhibit

01 · Mineral Lab

Meet the four minerals.

02 · Dataset

Examine unknown specimens, record what you observe, and assign a label. You are building a training set.

03 · ML

Turn your labels into a k-nearest-neighbor classifier, score it on fresh slides, then let a language-model petrographer identify a live unknown.

04 · Annotator

Label minerals using SLIC.

05 · Extractor

Extract lunar olivine oxide data from Apollo-era PDFs.

06 · Agent

Build a lunar sample Agent.

Station 01 — Optical mineralogy

The four major lunar minerals

Pick a mineral, and watch how each behaves under crossed polars — that behavior is the diagnostic.

Crossed polars (XPL) · stage rotation 0–360° · grains darken to extinction every 90°

Station 02 — Build the training set

Label the unknowns

Each slide is an unlabeled specimen. Observe it, record its optical properties, and assign the mineral you think it is. Your judgements become the data the AI learns from — so be honest about what you can actually see.

Record your observations

 

Labeled dataset · 0 rows

idreliefbirefcleavagefracturetwinningopacitylabel

Aim for at least 2–3 examples of each mineral before moving on. More variety = a better classifier.

Station 03 — From labels to KNN Classifier

Train, evaluate, deploy

1 · Train the classifier

Your labeled rows become the memory of a k-nearest-neighbor classifier. To classify an unknown, it finds the most similar slides you labeled and lets them vote. Transparent, no black box.

neighbors (k)

No model yet — build a dataset in Station 02 first.

2 · Evaluate

The classifier is scored on 40 held-out slides it has never been trained or taught on. The same 40 are reused all session, so you can measure it now, teach it in step 3, then evaluate again — any change in accuracy is real learning, not a different test.

3 · Deploy

Verdict

Train your classifier, then classify the unknown on the left.

Second opinion — language-model petrographer

Your k-NN agent reasons from numbers. This one reasons from words: describe a thin section and Claude will identify it and explain why. Try the live unknown's description, or write your own.

Awaiting a description…

Station 04 — Label minerals using SLIC

Station 05: Knowledge Base

Station 06: Lunar Sample Agent