Machine Learning Based Identification of Solvents from Post-Desiccation Patterns

TL;DR

This paper presents a neural network-based method to identify solvents from desiccation crack patterns in starch suspensions, achieving high accuracy even after complete evaporation, with potential applications in science and engineering.

Contribution

Introduces an optimized image analysis and neural network protocol for solvent identification from crack patterns, including feature selection for improved accuracy.

Findings

Average accuracy of 96% in solvent identification

Crack area distribution features yield highest accuracy

Method effective even after solvent evaporation

Abstract

We introduce an optimized protocol of fracture pattern classification using an artificial neural network to identify the solvent involved in the desiccation cracking process of starch-liquid slurries, even after it has been completely evaporated. For this purpose, image analysis techniques were used to characterize patterns obtained from drying suspensions using single solvents (water, ethanol, acetone) and two-component solvents (water-ethanol mixtures at different concentrations). Frequency histograms were generated based on nine morphological features, taking into account their size, shape, geometry and orientational ordering. Subsequently, we used these histograms as input data into artificial neural network variants to determine the set of features that lead to the higher accuracy in solvent identification. We obtained an average accuracy of $96(\pm 1)\%$ considering all solvents in the analysis. The highest accuracy was obtained with sets of features that include the crack area distribution. The proposed protocol can help to determine the combination of features that optimize pattern recognition in other fields of science and engineering.