~/aixsci
weekly updates

learn/model families

Dimensionality reduction

Dimensionality reduction is a way of describing data with fewer numbers than it arrived with, choosing new coordinates that keep the patterns scientists care about and discard the rest.

What it is

Scientific measurements often come as long lists of numbers. One material might be described by a few hundred numbers, one protein by thousands. Each number is a dimension, and data with many dimensions is hard to plot, hard to compare and hard to learn from. Dimensionality reduction replaces those many numbers with a handful of new ones. The new numbers are not the original measurements but combinations of them, worked out so that items which were close together in the long description stay close together in the short one, and items which were far apart stay far apart.

Methods differ in what they try to preserve. Some keep the broad spread of the whole dataset. Others, often called manifold methods, assume the data lies on a curved surface inside the larger space and try to keep each point's local neighbourhood intact. Some are built mainly for drawing a two-dimensional picture to look at. Others produce a compact description meant to be fed into a later model. The number of new dimensions is a choice, and it is usually settled by testing how well the shortened version supports whatever comes next.

Why scientists use it

Fewer dimensions make work possible that otherwise is not. Models trained on very long descriptions need far more examples before they can tell signal from coincidence, because there are so many ways to fit the data by accident. Shortening the description eases that. It also cuts computing time, and it removes the repetition that comes when several measurements say nearly the same thing.

The other reason is simply to see. Humans cannot picture a hundred dimensions, but they can look at a scatter plot. Reducing data to two or three dimensions lets researchers notice that samples fall into families, that one batch sits apart from the others, or that a property varies smoothly across the picture. This is why reduction and clustering are often used together: reduction changes the coordinates, clustering then decides which points belong in the same group.

In the record

Limits

Something is always thrown away, and there is no guarantee it was the unimportant part: a difference that matters for one question can vanish in coordinates chosen for another. Pictures from neighbourhood-preserving methods are especially easy to over-read, because the size of the gaps between groups, and sometimes the groups themselves, can be artefacts of the settings rather than features of the data. The new coordinates usually have no physical meaning, so they cannot be interpreted as a measured quantity, and results can shift when the method is rerun or retuned.

Written by AIxSci: the background from general knowledge, the examples from checked records.

By field

Every article

15articles
4structural-biology
4materials-chemistry
7astronomy
0climate-weather

aix-00276

Machine learning sorts a simulated polymer into ordered and disordered beads

classification

materials-chemistry · ai-result · arXiv · 2023

aix-00204

Neural networks stand in for a slow model of interstellar gas clouds

simulation surrogateanomaly detection

astronomy · ai-result · Astronomy and Astrophysics · 2023

aix-00181

Protein language model embeddings used to predict succinylation sites in proteins

classification

structural-biology · ai-result · Scientific Reports · 2022

aix-00186

Language model trained on protein sequences predicts shape and behaviour of disordered proteins

property predictionsimulation surrogate

structural-biology · ai-result · The Journal of Physical Chemistry B · 2024

aix-00125

Classifying stars by type from a single wide-band telescope image

classificationstructure determination

astronomy · ai-result · Astronomy and Astrophysics · 2025

aix-00100

Astronomers test pre-trained image models for sifting telescope alerts

classificationanomaly detection

astronomy · ai-result · arXiv · 2025

aix-00088

Neural network retrained to predict how crystals absorb light, from few examples

property predictionsimulation surrogate

materials-chemistry · ai-result · Nature Communications · 2025

aix-00082

Neural networks turn simulated dark matter maps into mock X-ray and microwave cluster images

simulation surrogate

astronomy · ai-result · RAS Techniques and Instruments · 2025

aix-00081

Language models trained on protein sequences used to predict sugar-attachment sites

classification

structural-biology · ai-result · Bioinformatics Advances · 2024

aix-00066

Machine learning sifts 25,000 known materials for quantum-technology host candidates

classification

materials-chemistry · ai-result · npj Computational Materials · 2022

aix-00060

Neural networks stand in for slow cosmology code in parameter fitting

simulation surrogate

astronomy · ai-result · arXiv · 2024

aix-00049

Eight machine learning methods sorted supernova gravitational wave signals by nuclear physics model

classification

astronomy · ai-result · Machine Learning Science and Technology · 2024

aix-00042

Two unsupervised methods compress fast radio burst spectra into a handful of numbers

denoisinganomaly detection

astronomy · ai-result

aix-00040

Statistical model of 5,441 perovskite solar cells predicts efficiency and suggests recipes

property predictioncandidate generationexperimental design

materials-chemistry · ai-result · Journal of Chemical Information and Modeling · 2026

aix-00001

Researchers measure folding stability for hundreds of thousands of protein variants

structure determinationcandidate generationproperty predictionclassification

structural-biology · ai-supporting · Nature · 2023