Exploiting machine learning for controlled synthesis of carbon dots-based corrosion inhibitors

Benefitting from their prominent corrosion inhibition properties, excellent water solubility and benign environmental friendliness, carbon dots (CDs) have functioned as an ideal candidate for next-generation green corrosion inhibitors. However, the extensive adoption of the trial-and-error route driven by artificial experience in the preparation of CDs-based corrosion inhibitors leads to resource waste and environmental implications, detrimental to their sustainable development. It is still a considerable challenge to controllably prepare CDs-based corrosion inhibitors with the predictable inhibition efficiency. Herein, firstly exploiting a data-driven machine learning (ML) approach, this study aims to precisely predict the inhibition efficiency of CDs and optimize their synthesis route, resulting in the controlled synthesis of CDs-based corrosion inhibitors. Specifically, the dataset is constructed by combining 102 data points on CDs synthesis and inhibition efficiency from numerous published studies and our own experiments. After training and evaluation of different ML models, the Random Forest (RF) ML regression model is chosen with the lowest root-mean-square error and mean absolute error as well as the highest coefficient of determination. The results show that this RF model can comprehensively reveal the relationship between various hydrothermal synthesis parameters and the inhibition efficiency. Guided by the RF model, the inhibition efficiencies of CDs-based corrosion inhibitors are accurately predicted with an error less than 10%, and based on the genetic algorithm, their synthesis route is intelligently optimized. This work demonstrates the feasibility of ML techniques in guiding the optimization of synthesis conditions for CDs-based corrosion inhibitors. This optimization process results in reduced development time and cost, contributing to the sustainability and cleaner production of inhibitors.