Next Article in Journal
Spatial Variability of Groundwater Quality for Freshwater Production in a Semi-Arid Area
Previous Article in Journal
Comparison of Desalination Technologies Using Renewable Energy Sources with Life Cycle, PESTLE, and Multi-Criteria Decision Analyses
 
 
Article

Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models

1
Departamento de Ingeniería Civil y Ambiental, Escuela Politécnica Nacional, Ladrón de Guevara E11·253, Quito 170525, Ecuador
2
Instituto Nacional de Meteorología e Hidrología, INAMHI, Iñaquito N36-14 y Corea, Quito 170507, Ecuador
3
Institut des Géosciences de l’Environnement (IGE), Université Grenoble Alpes, CNRS, IRD, Grenoble INP, IGE, 38000 Grenoble, France
4
Facultad de Ciencia y Tecnología, Instituto de Estudios de Régimen Seccional del Ecuador (IERSE), Universidad del Azuay, Cuenca 010204, Ecuador
5
Centro de Investigación y Control Ambiental, Departamento de Ingeniería Civil y Ambiental, Escuela Politécnica Nacional, Ladrón de Guevara E11-253, Quito 170525, Ecuador
*
Author to whom correspondence should be addressed.
Academic Editors: Zheng Duan and Babak Mohammadi
Water 2021, 13(21), 3022; https://doi.org/10.3390/w13213022
Received: 1 July 2021 / Revised: 12 October 2021 / Accepted: 12 October 2021 / Published: 28 October 2021
The precipitation phase (PP) affects the hydrologic cycle which in turn affects the climate system. A lower ratio of snow to rain due to climate change affects timing and duration of the stream flow. Thus, more knowledge about the PP occurrence and drivers is necessary and especially important in cities dependent on water coming from glaciers, such as Quito, the capital of Ecuador (2.5 million inhabitants), depending in part on the Antisana glacier. The logistic models (LM) of PP rely only on air temperature and relative humidity to predict PP. However, the processes related to PP are far more complex. The aims of this study were threefold: (i) to compare the performance of random forest (RF) and artificial neural networks (ANN) to derive PP in relation to LM; (ii) to identify the main drivers of PP occurrence using RF; and (iii) to develop LM using meteorological drivers derived from RF. The results show that RF and ANN outperformed LM in predicting PP in 8 out of 10 metrics. RF indicated that temperature, dew point temperature, and specific humidity are more important than wind or radiation for PP occurrence. With these predictors, parsimonious and efficient models were developed showing that data mining may help in understanding complex processes and complements expert knowledge. View Full-Text
Keywords: precipitation phase; Andes precipitation; random forest; logistic models; automatic discovery precipitation phase; Andes precipitation; random forest; logistic models; automatic discovery
Show Figures

Figure 1

MDPI and ACS Style

Campozano, L.; Robaina, L.; Gualco, L.F.; Maisincho, L.; Villacís, M.; Condom, T.; Ballari, D.; Páez, C. Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models. Water 2021, 13, 3022. https://doi.org/10.3390/w13213022

AMA Style

Campozano L, Robaina L, Gualco LF, Maisincho L, Villacís M, Condom T, Ballari D, Páez C. Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models. Water. 2021; 13(21):3022. https://doi.org/10.3390/w13213022

Chicago/Turabian Style

Campozano, Lenin, Leandro Robaina, Luis Felipe Gualco, Luis Maisincho, Marcos Villacís, Thomas Condom, Daniela Ballari, and Carlos Páez. 2021. "Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models" Water 13, no. 21: 3022. https://doi.org/10.3390/w13213022

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop