RT Journal Article
T1 LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data
A1 Fournier, Claudia
A1 Fernández Fernández, Raúl
A1 Cirés, Samuel
A1 López Orozco, José Antonio
A1 Besada Portas, Eva
A1 Quesada, Antonio
AB Cyanobacteria are the most frequent dominant species of algal blooms in inland waters, threatening ecosystem function and water quality, especially when toxin-producing strains predominate. Enhanced by anthropogenic activities and global warming, cyanobacterial blooms are expected to increase in frequency and global distribution. Early warning systems (EWS) for cyanobacterial blooms development allow timely implementation of management measures, reducing the risks associated to these blooms. In this paper, we propose an effective EWS for cyanobacterial bloom forecasting, which uses 6 years of incomplete high-frequency spatio-temporal data from multiparametric probes, including phycocyanin (PC) fluorescence as a proxy for cyanobacteria. A probe agnostic and replicable method is proposed to pre-process the data and to generate time series specific for cyanobacterial bloom forecasting. Using these pre-processed data, six different non-site/species-specific predictive models were compared including the autoregressive and multivariate versions of Linear Regression, Random Forest, and Long-Term Short-Term (LSTM) neural networks. Results were analyzed for seven forecasting time horizons ranging from 4 to 28 days evaluated with a hybrid system that combined regression metrics (MSE, R2, MAPE) for PC values, classification metrics (Accuracy, F1, Kappa) for a proposed alarm level of 10 ug PC/L, and a forecasting-specific metric to measure prediction improvement over the displaced signal (skill). The multivariate version of LSTM showed the best and most consistent results across all forecasting horizons and metrics, achieving accuracies of up to 90% in predicting the proposed PC alarm level. Additionally, positive skill values indicated its outstanding effectiveness to forecast cyanobacterial blooms from 16 to 28 days in advance.
PB Elsevier
SN 0043-1354
YR 2024
FD 2024-09-30
LK https://hdl.handle.net/20.500.14352/108966
UL https://hdl.handle.net/20.500.14352/108966
LA eng
NO Fournier, C., Fernandez-Fernandez, R., Cirés, S., López-Orozco, J.A., Besada-Portas, E., Quesada, A., 2024. LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data. Water Research 267, 122553. https://doi.org/10.1016/j.watres.2024.122553
NO European Comission
NO Ministerio de Ciencia e Innovación (España)
NO Agencia Estatal de Investigación (España)
NO Comunidad de Madrid
DS Docta Complutense
RD 11 abr 2025