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

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 ci...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lenin Campozano, Leandro Robaina, Luis Felipe Gualco, Luis Maisincho, Marcos Villacís, Thomas Condom, Daniela Ballari, Carlos Páez
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	precipitation phase Andes precipitation random forest logistic models automatic discovery Hydraulic engineering TC1-978 Water supply for domestic and industrial purposes TD201-500
Acceso en línea:	https://doaj.org/article/77c87c05d30c48fbb321f6d3132007bd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:77c87c05d30c48fbb321f6d3132007bd
record_format	dspace
spelling	oai:doaj.org-article:77c87c05d30c48fbb321f6d3132007bd2021-11-11T19:54:55ZParsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models10.3390/w132130222073-4441https://doaj.org/article/77c87c05d30c48fbb321f6d3132007bd2021-10-01T00:00:00Zhttps://www.mdpi.com/2073-4441/13/21/3022https://doaj.org/toc/2073-4441The 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.Lenin CampozanoLeandro RobainaLuis Felipe GualcoLuis MaisinchoMarcos VillacísThomas CondomDaniela BallariCarlos PáezMDPI AGarticleprecipitation phaseAndes precipitationrandom forestlogistic modelsautomatic discoveryHydraulic engineeringTC1-978Water supply for domestic and industrial purposesTD201-500ENWater, Vol 13, Iss 3022, p 3022 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	precipitation phase Andes precipitation random forest logistic models automatic discovery Hydraulic engineering TC1-978 Water supply for domestic and industrial purposes TD201-500
spellingShingle	precipitation phase Andes precipitation random forest logistic models automatic discovery Hydraulic engineering TC1-978 Water supply for domestic and industrial purposes TD201-500 Lenin Campozano Leandro Robaina Luis Felipe Gualco Luis Maisincho Marcos Villacís Thomas Condom Daniela Ballari Carlos Páez Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
description	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.
format	article
author	Lenin Campozano Leandro Robaina Luis Felipe Gualco Luis Maisincho Marcos Villacís Thomas Condom Daniela Ballari Carlos Páez
author_facet	Lenin Campozano Leandro Robaina Luis Felipe Gualco Luis Maisincho Marcos Villacís Thomas Condom Daniela Ballari Carlos Páez
author_sort	Lenin Campozano
title	Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
title_short	Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
title_full	Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
title_fullStr	Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
title_full_unstemmed	Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models
title_sort	parsimonious models of precipitation phase derived from random forest knowledge: intercomparing logistic models, neural networks, and random forest models
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/77c87c05d30c48fbb321f6d3132007bd
work_keys_str_mv	AT lenincampozano parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT leandrorobaina parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT luisfelipegualco parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT luismaisincho parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT marcosvillacis parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT thomascondom parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT danielaballari parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels AT carlospaez parsimoniousmodelsofprecipitationphasederivedfromrandomforestknowledgeintercomparinglogisticmodelsneuralnetworksandrandomforestmodels
_version_	1718431357775904768

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

Ejemplares similares