Actividad Investigadora
Comprehensive Raman spectroscopy analysis for differentiating toxic cyanobacteria through multichannel 1D-CNNs and SHAP-based explainability.
Fecha de publicación:
Fecha Ahead of Print:
Autores de IDIVAL
Autores ajenos al IDIVAL
- Álvarez SD
- Monteoliva AP
Unidades
Abstract
Cyanobacterial blooms pose significant environmental and public health risks due to the production of toxins that contaminate water sources and disrupt aquatic ecosystems. Rapid and accurate identification of cyanobacterial species is crucial for effective monitoring and management strategies. In this study, we combined Raman spectroscopy with deep learning techniques to classify four toxic cyanobacterial species: Dolichospermum crassum, Aphanizomenon sp., Planktothrix agardhii and Microcystis aeruginosa. Spectral data were acquired using a confocal Raman microscope with a 532 nm excitation wavelength and subjected to preprocessing and filtering to enhance signal quality. We evaluated a multichannel one-dimensional convolutional neural network (1D-CNN) approach that incorporates raw spectra, baseline estimations, and preprocessed spectra. This multichannel approach improved overall classification accuracy, achieving 86% compared to 74% with a traditional single-channel 1D-CNN using only preprocessed spectra while maintaining low overfitting. Shapley Additive exPlanations (SHAP) were applied to identify critical spectral regions for classification to enhance interpretability. These findings highlight the potential of combining Raman spectroscopy with explainable deep learning methods as a powerful tool for water quality monitoring and the early detection of Harmful Algal Blooms (HABs).
Copyright © 2025 Elsevier B.V. All rights reserved.
Datos de la publicación
- ISSN/ISSNe:
- 0039-9140, 1873-3573
- Tipo:
- Article
- Páginas:
- 127845-127845
- PubMed:
- 40081250
TALANTA ELSEVIER
Citas Recibidas en Web of Science: 5
Documentos
- No hay documentos
Filiaciones
Keywords
- Cyanobacteria detection; Harmful Algal Blooms; One-dimensional convolutional neural networks; Raman spectroscopy; Shapley Additive Explanations; Water quality monitoring
Campos de Estudio
Proyectos asociados
CB21/13/00068 Fariñas Álvarez, María Del Carmen
Investigador Principal: María del Carmen Fariñas Álvarez
CB21/13/00068 . INSTITUTO DE SALUD CARLOS III. . 2022
eStructuras En Chip paRa la idEntificación de paTógenOs (SECRETO)
Investigador Principal: Luis Rodríguez Cobo
INNVAL23/10 . FUNDACION INSTITUTO DE INVESTIGACION MARQUES DE VALDECILLA . 2023
Contrato Predoctoral Maria Gabriela Fernández Manteca
Investigador Principal: Adolfo Cobo García
PREVAL23/05 . FUNDACION INSTITUTO DE INVESTIGACION MARQUES DE VALDECILLA . 2023
Detección temprana de Cándida y sus variantes resistentes mediante espectroscopia SERS (DETECTARS)
Investigador Principal: José Francisco Algorri Genaro
INNVAL24/28 . FUNDACION INSTITUTO DE INVESTIGACION MARQUES DE VALDECILLA . 2024
Cita
Fernández MG, García BG, Álvarez SD, Gómez C, Pérez A, Algorri JF, Monteoliva AP, López JM, Rodríguez L, Ocampo AA, Cobo A. Comprehensive Raman spectroscopy analysis for differentiating toxic cyanobacteria through multichannel 1D-CNNs and SHAP-based explainability. Talanta. 2025. 292. p. 127845-127845. IF:6,100. (1).
