Predictive Machine Learning Models Trained on Experimental Datasets for Electrochemical Nitrogen Reduction

Obtaining useful insights from machine learning models trained on experimental datasets collected across different groups to improve the sustainability of chemical processes can be challenging due to the small size and heterogeneity of the dataset. Here we show that shallow learning models such as decision trees and random forest algorithms can be an effective tool for guiding experimental research in the sustainable chemistry field. This study trained three different machine learning algorithms (decision tree, random forest, and multilayer perceptron) using 254 unique reaction conditions for the nitrogen reduction reaction (NRR) on heterogeneous electrocatalysts. Using the catalyst properties and experimental conditions as the features, we determined the ability of each model to regress the ammonia rate and the faradaic efficiency. We observed that the shallow learning decision tree and random forest models performed equal to or better than the deep learning multilayer perceptron models. Analysis of the models showed that the complex interaction between the applied potential and catalysts on the effective rate for the NRR. In addition, our model uncovered some underexplored catalysts-electrolyte combinations that give guidance to experimental researchers looking to improve both the rate and efficiency of the NRR reaction.