Chemometric Approach Based on Explainable AI for Rapid Assessment of Macronutrients in Different Organic Fertilizers Using Fusion Spectra

Abstract

Wet chemical methods are usually employed in the analysis of macronutrients such as Potassium (K) and Phosphorus (P) and followed by traditional sensor techniques, including inductively coupled plasma optical emission spectrometry (ICP OES), flame atomic absorption spectrometry (FAAS), graphite furnace atomic absorption spectrometry (GF AAS), and inductively coupled plasma mass spectrometry (ICP-MS). Although these procedures have been established for many years, they are costly, time-consuming, and challenging to follow. This study studied the combination of laser-induced breakdown spectroscopy (LIBS) and visible and near-infrared spectroscopy (Vis-NIR) for the quick detection of PK in different varieties of organic fertilizers. Explainable AI (XAI) through Shapley additive explanation values computation (Shap values) was used to extract the valuable features of both sensors. The characteristic variables from different spectroscopic devices were combined to form the spectra fusion. Then, PK was determined using Support Vector Regression (SVR), Partial Least Squares Regression (PLSR), and Extremely Randomized Trees (Extratrees) models. The computation of the coefficient of determination (R2), root mean squared error (RMSE), and residual prediction deviation (RPD) showed that FUSION was more efficient in detecting P (R2p = 0.9946, RMSEp = 0.0649% and RPD = 13.26) and K (R2p = 0.9976, RMSEp = 0.0508% and RPD = 20.28) than single-sensor detection. The outcomes indicated that the features extracted by XAI and the data fusion of LIBS and Vis-NIR could improve the prediction of PK in different varieties of organic fertilizers.