# Optimizing Molecular Descriptors for Reliable Adsorption Energy Prediction on Transition Metal Nanoclusters

## TL;DR

This paper explores machine learning methods to predict how molecules stick to metal nanoclusters, aiming to speed up catalyst design.

## Contribution

The study introduces a new electronic feature to improve the generalizability of adsorption energy predictions for nanoclusters.

## Key findings

- Both Coulomb matrix and many-body tensor descriptors achieved 0.05 eV mean absolute error on test data.
- Adding unpaired electrons as a feature improved generalizability on new examples despite higher errors.
- Performance dropped significantly on external data with unprecedented examples.

## Abstract

Efficient catalytic processes are crucial for converting
pollutant
molecules into valuable products. Transition-metal nanoclusters show
promise as a result of their tunable properties, but identifying active
catalysts requires costly studies of the adsorption energetics. Machine
learning offers a faster alternative, predicting adsorption energies
when trained on suitable descriptors and relatively large density
functional theory (DFT) data sets. This study evaluates the predictive
power and transferability of two structural descriptors, the Coulomb
matrix and the many-body tensor representation, on a diverse nanocluster-adsorbate
data set using the random forest regression algorithm. Both descriptors
achieved a mean absolute error of 0.05 eV in test data, but performance
dropped significantly on an external generated set with unprecedented
examples. Adding a simple electronic feature, the number of unpaired
electrons of the adsorbate improved generalizability, even though
with higher mean absolute errors compared to the original data set,
highlighting the dependence on the training data.