Where is your field going? A Machine Learning approach to study the relative motion of the domains of Physics

TL;DR

This paper introduces a machine learning-based method to quantitatively analyze the evolution and interconnectedness of physics domains over 25 years, revealing trends, predicting new field couplings, and highlighting influential scientific milestones.

Contribution

It presents a novel machine learning approach to represent and analyze the relative motion of physics domains using PACS codes in a multi-dimensional space.

Findings

Unveiled 25 years of scientific trends.

Predicted innovative couplings of physics fields.

Showed how Nobel Prize papers influence future research convergence.

Abstract

We propose an original approach to describe the scientific progress in a quantitative way. Using innovative Machine Learning techniques we create a vector representation for the PACS codes and we use them to represent the relative movements of the various domains of Physics in a multi-dimensional space. This methodology unveils about 25 years of scientific trends, enables us to predict innovative couplings of fields, and illustrates how Nobel Prize papers and APS milestones drive the future convergence of previously unrelated fields.