An explainable machine-learning approach for revealing the complex synthesis path–property relationships of nanomaterials

Abstract

Machine-learning (ML) models have recently shown important advantages in predicting nanomaterial properties, which avoids many trial-and-error explorations. However, complex variables that control the formation of nanomaterials exhibiting desired properties still...

A Study on Prediction of Size and Morphology of Ag Nanoparticles Using Machine Learning Models for Biomedical Applications

“…where Ω (f ) = γT + 1 2 λω 2 The difference between the target y i and the predicted value ŷi is measured by the differentiable convex loss function, denoted by l in this case. The model's complexity is penalized by the second term, Ω.…”

“…The model's complexity is penalized by the second term, Ω. In order to prevent over-fitting, the extra regularization term smoothens the final learned weights [1,36]. This algorithm, which uses the gradientboosting method, is the creation of a decision-tree-based model with boosting.…”

“…This is an expensive, time-consuming, and low-efficiency procedure. With the growing demand for nanomaterials for various applications, it is critical to quickly and precisely predict the characteristics based on synthesis factors [1].…”

“…The gathering and preparation of the dataset is a crucial step before developing a machine learning model [3]. The trial-and-error approach used to collect experimental data for optimizing the synthetic procedure for nanoparticle synthesis is time-consuming and not economical [1]. Therefore, with the physics-informed ML models, it is possible to optimize and predict the feasible synthetic procedures for producing nanoparticles.…”

“…Typically, two datasets with an 8:2 or 7:3 ratio are created from the data for training and testing the ML models. The superior performance of the machine learning approach cannot be simply assessed using the training set alone [1][2][3][4]. Any computational technique that helps narrow down the design space by forecasting desired process variables prior to synthesis would be beneficial to reduce the number of steps involved to produce nanoparticles by chemical routes.…”