Computational study based on supervised neural architectures for fluorescence detection of fungicides

Abstract

Benzimidazole fungicides (BFs) are a type of pesticide of high environmental interest characterized by a heavy spectral overlap which complicates its detection in mixtures. In this paper we present a computational study based on supervised neural networks for a multi-label classification problem. Specifically, backpropagation (BPN) with data fusion and ensemble schemes is used for the simultaneous resolution of difficult multi-fungicide mixtures. We designed, optimized and compared simple BPNs, BPNs with data fusion and BPN ensembles. The information environment used is made up of synchronous and conventional BF fluorescence spectra. The mixture spectra are not used in the training stage. This study allows the use of supervised neural architectures to be compared to unsupervised ones, which have been developed in previous works, for the identification of BFs in complex multi-fungicide mixtures. The study was carried out using a new software tool, MULLPY, which was developed in Python.