ElectroLens: Understanding Atomistic Simulations Through Spatially-resolved Visualization of High-dimensional Features

TL;DR

ElectroLens is a visualization tool that helps researchers interpret high-dimensional features in atomistic simulations by linking abstract data to actual chemical structures through interactive 3D and 2D visualizations.

Contribution

It introduces a scalable visualization platform that connects high-dimensional features to chemical systems, aiding understanding and diagnosis in machine learning applications.

Findings

Enables spatially-resolved visualization of high-dimensional features

Facilitates interpretation of machine learning features in chemical systems

Supports interactive exploration of atomistic data

Abstract

In recent years, machine learning (ML) has gained significant popularity in the field of chemical informatics and electronic structure theory. These techniques often require researchers to engineer abstract "features" that encode chemical concepts into a mathematical form compatible with the input to machine-learning models. However, there is no existing tool to connect these abstract features back to the actual chemical system, making it difficult to diagnose failures and to build intuition about the meaning of the features. We present ElectroLens, a new visualization tool for high-dimensional spatially-resolved features to tackle this problem. The tool visualizes high-dimensional data sets for atomistic and electron environment features by a series of linked 3D views and 2D plots. The tool is able to connect different derived features and their corresponding regions in 3D via interactive selection. It is built to be scalable, and integrate with existing infrastructure.