Abstract
Many scientific and industrial applications depend on the precise measurement of chemical concentrations. The current study demonstrates how an inventive method of combining photographic images with a machine learning (ML) model successfully estimates the concentration of potassium dichromate (K2Cr2O7) in solution. A predictive model is created by taking photographs of K2Cr2O7 solutions and evaluating the color intensities of those photographs using a ridge regression model. The pre-diction accuracy of the model was evaluated using MAE, MSE, and RMSE, and a high correlation between the actual and predicted concentrations of K2Cr2O7 was obtained with MAE, MSE, and RMSE values of 0.4%, 0.003%, and 0.5%, respectively. The ridge regression model is also extended to predict the concentration of KMnO4 and highlights the potential of integrating machine learning techniques with image analysis to accurately quantify the concentration of any chemical species in the solution state. As this model solely depends on the color intensity of the sample without any molecular interactions, it surpasses the limitations of the Beer-Lambert law. The created machine learning model also minimizes the requirement of substantial expertise and training, hence bridging the gap between the experienced and novice analysts.
Supplementary materials
Title
Application of an Electronic Eye to Address the Limitations of Beer-Lambert Law
Description
1. Variation in K2Cr2O7 concentration (Table S1)
2. Variation in K2Cr2O7 concentration with images (Table S2.)
3. Variation in KMnO4 concentration (Table S3)
4. Experimental setup with parameters (Figure S1)
5. Conversion of a 3000 x 3000 pixel image into 20 x 20 pixel image (Figure S2)
6. 20 x 20 pixel images of KMnO4 with various concentrations (Figure S3)
Actions