Exploring the Limitations of kNN Noisy Feature Detection and Recovery for Self-Driving Labs

TL;DR

This paper presents a model-agnostic workflow for detecting and recovering noisy features in self-driving laboratories, improving data quality for materials discovery through systematic analysis of noise effects and kNN imputation performance.

Contribution

It introduces a novel automated framework for identifying and correcting noisy features in SDL datasets, with comprehensive analysis of factors affecting recoverability and a benchmark of kNN imputation.

Findings

High noise and large datasets improve detection and correction.

Low noise can be mitigated with more clean data.

Feature distribution impacts recoverability.

Abstract

Self-driving laboratories (SDLs) have shown promise to accelerate materials discovery by integrating machine learning with automated experimental platforms. However, errors in the capture of input parameters may corrupt the features used to model system performance, compromising current and future campaigns. This study develops an automated workflow to systematically detect noisy features, determine sample-feature pairings that can be corrected, and finally recover the correct feature values. A systematic study is then performed to examine how dataset size, noise intensity, noise type, and feature value distribution affect both the detectability and recoverability of noisy features on both Density Functional Theory (DFT) and SDL datasets. In general, high-intensity noise and large training datasets are conducive to the detection and correction of noisy features. Low-intensity noise reduces detection and recovery but can be compensated for by larger clean training data sets. Detection and correction results vary between features, with continuous and dispersed feature distributions showing greater recoverability compared to features with discrete or narrow distributions. This systematic study not only demonstrates a model agnostic framework for rational data recovery in the presence of noise, limited data, and differing feature distributions but also provides a tangible benchmark of kNN imputation in materials datasets. Ultimately, it aims to enhance data quality and experimental precision in automated materials discovery.