Spectral sensor fusion for prediction of Li and Zr in rocks: Neural network and PLS methods

Integrating information from multiple sensors, known as sensor fusion, is particularly challenging for small datasets where selecting from the plethora of available methods poses a significant challenge in chemometric analysis. This study compares several sensor fusion methods (spanning data-level, feature-level, and decision-level fusion) based on partial least squares (PLS) and convolutional neural network (CNN) models. This study is the first to compare simple sensor fusion methods to the latest multiblock PLS models and parallel-input CNNs, to the best of our knowledge. We demonstrate sensor fusion using a small dataset of 177 rock samples on two prediction tasks: predicting lithium (Li) concentrations and zirconium (Zr) concentrations using three types of spectra, namely X-ray fluorescence (XRF), visible to short-wave infrared (Vis-NIR-SWIR), and laser-induced breakdown spectroscopy (LIBS). The best-performing Li model was PLS using XRF (mean RMSEP: 0.078%) and the best sensor fusion model was ROSA (mean RMSEP: 0.087%). The best Zr model was a high-level fusion of PLS models (mean RMSEP: 0.042%). •Tested neural network and PLS methods for small-dataset spectral sensor fusion.•Sensor fusion improved predictions on one of two prediction tasks.•ROSA and high-level fusion of PLS yielded the best sensor fusion results.•Demonstrated a parallel-input convolutional neural network for sensor fusion.