Flood early warning systems using machine learning techniques: the case of the Tomebamba catchment at the southern Andes of Ecuador

Bendix, JorMuñoz Pauta, Paúl AndrésOrellana Alvear, Johanna MarleneCélleri Alvear, Rolando EnriqueFeyen, Jan2022-02-102022-02-1020212306-5338http://dspace.ucuenca.edu.ec/handle/123456789/38023https://www.scopus.com/record/display.uri?eid=2-s2.0-85121787363&origin=resultslist&sort=plf-f&src=s&st1=Flood+early+warning+systems+using+machine+learning+techniques%3a+The+case+of+the+tomebamba+catchment+at+the+southern+Andes+of+Ecuador&sid=4065c7feb5a5555ffd1b4907acff3682&sot=b&sdt=b&sl=146&s=TITLE-ABS-KEY%28Flood+early+warning+systems+using+machine+learning+techniques%3a+The+case+of+the+tomebamba+catchment+at+the+southern+Andes+of+Ecuador%29&relpos=0&citeCnt=0&searchTerm=Worldwide, machine learning (ML) is increasingly being used for developing flood early warning systems (FEWSs). However, previous studies have not focused on establishing a methodology for determining the most efficient ML technique. We assessed FEWSs with three river states, No-alert, Pre-alert and Alert for flooding, for lead times between 1 to 12 h using the most common ML techniques, such as multi-layer perceptron (MLP), logistic regression (LR), K-nearest neighbors (KNN), naive Bayes (NB), and random forest (RF). The Tomebamba catchment in the tropical Andes of Ecuador was selected as a case study. For all lead times, MLP models achieve the highest performance followed by LR, with f1-macro (log-loss) scores of 0.82 (0.09) and 0.46 (0.20) for the 1 h and 12 h cases, respectively. The ranking was highly variable for the remaining ML techniques. According to the g-mean, LR models correctly forecast and show more stability at all states, while the MLP models perform better in the Pre-alert and Alert states. The proposed methodology for selecting the optimal ML technique for a FEWS can be extrapolated to other case studies. Future efforts are recommended to enhance the input data representation and develop communication applications to boost the awareness of society of floods.es-ESHydrological extremesFlood early warningForecastingMachine learningAndesFlood early warning systems using machine learning techniques: the case of the Tomebamba catchment at the southern Andes of EcuadorARTÍCULO10.3390/hydrology8040183