Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment

Stalin Jimenez; Alex Aviles; Luciano Galán; Andrés Flores; Carlos Matovelle; Cristian Vintimilla

doi:10.1007/978-3-030-35740-5_13

Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment

Stalin Jimenez
, Alex Aviles
, Luciano Galán
, Andrés Flores
, Carlos Matovelle
, Cristian Vintimilla

Universidad de Cuenca
Universidad Católica de Cuenca

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

The techniques for downscaling climatic variables are essential to support tools for water resources planning and management in a climate change context in the entire world. Support vector machines (SVM) through regression approach (SVR), constitute an artificial intelligence method to downscaling climatic variables. Since that statistical downscaling based on regression methodologies is susceptible to the predictor variables, the aim of this study was exploring a big database of predictor variables to achieve the best performance of a statistical downscaling model using SVR to predict precipitation and temperature future projections. Data from regional climate models of Ecuador and information of three meteorological stations was used to apply this approach in the Tomebamba river sub-basin, located in southern Ecuadorian Andean region. The results show that the downscaling model has a better performance with the climatic averages. The precipitation extremes do not estimate in a good manner, but the model achieves an effective behavior with the temperature extremes values. These results could serve to improve water balance projections in the future for formulating suitable measures for climate change decision-making.

Original language	English
Title of host publication	Information and Communication Technologies of Ecuador, TIC.EC 2019
Editors	Efraín Fonseca C, Germania Rodríguez Morales, Marcos Orellana Cordero, Miguel Botto-Tobar, Esteban Crespo Martínez, Andrés Patiño León
Publisher	Springer
Pages	182-193
Number of pages	12
ISBN (Print)	9783030357399
DOIs	https://doi.org/10.1007/978-3-030-35740-5_13
State	Published - 2020
Event	6th Conference on Information and Communication Technologies, TIC.EC 2019 - Cuenca, Ecuador Duration: 27 Nov 2019 → 29 Nov 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1099
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	6th Conference on Information and Communication Technologies, TIC.EC 2019
Country/Territory	Ecuador
City	Cuenca
Period	27/11/19 → 29/11/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 6 Clean Water and Sanitation
SDG 13 Climate Action

Keywords

Andean basin
Artificial intelligence
Climate big data
Climate change
SVR
Statistical downscaling

Access to Document

10.1007/978-3-030-35740-5_13

Cite this

Jimenez, S., Aviles, A., Galán, L., Flores, A., Matovelle, C., & Vintimilla, C. (2020). Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment. In E. Fonseca C, G. Rodríguez Morales, M. Orellana Cordero, M. Botto-Tobar, E. Crespo Martínez, & A. Patiño León (Eds.), Information and Communication Technologies of Ecuador, TIC.EC 2019 (pp. 182-193). (Advances in Intelligent Systems and Computing; Vol. 1099). Springer. https://doi.org/10.1007/978-3-030-35740-5_13

Jimenez, Stalin ; Aviles, Alex ; Galán, Luciano et al. / Support Vector Regression to Downscaling Climate Big Data : An Application for Precipitation and Temperature Future Projection Assessment. Information and Communication Technologies of Ecuador, TIC.EC 2019. editor / Efraín Fonseca C ; Germania Rodríguez Morales ; Marcos Orellana Cordero ; Miguel Botto-Tobar ; Esteban Crespo Martínez ; Andrés Patiño León. Springer, 2020. pp. 182-193 (Advances in Intelligent Systems and Computing).

@inproceedings{7703f00cf4214731b510fdcab3dce5dd,

title = "Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment",

abstract = "The techniques for downscaling climatic variables are essential to support tools for water resources planning and management in a climate change context in the entire world. Support vector machines (SVM) through regression approach (SVR), constitute an artificial intelligence method to downscaling climatic variables. Since that statistical downscaling based on regression methodologies is susceptible to the predictor variables, the aim of this study was exploring a big database of predictor variables to achieve the best performance of a statistical downscaling model using SVR to predict precipitation and temperature future projections. Data from regional climate models of Ecuador and information of three meteorological stations was used to apply this approach in the Tomebamba river sub-basin, located in southern Ecuadorian Andean region. The results show that the downscaling model has a better performance with the climatic averages. The precipitation extremes do not estimate in a good manner, but the model achieves an effective behavior with the temperature extremes values. These results could serve to improve water balance projections in the future for formulating suitable measures for climate change decision-making.",

keywords = "Andean basin, Artificial intelligence, Climate big data, Climate change, SVR, Statistical downscaling",

author = "Stalin Jimenez and Alex Aviles and Luciano Gal{\'a}n and Andr{\'e}s Flores and Carlos Matovelle and Cristian Vintimilla",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 6th Conference on Information and Communication Technologies, TIC.EC 2019 ; Conference date: 27-11-2019 Through 29-11-2019",

year = "2020",

doi = "10.1007/978-3-030-35740-5\_13",

language = "Ingl{\'e}s",

isbn = "9783030357399",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "182--193",

editor = "\{Fonseca C\}, Efra{\'i}n and \{Rodr{\'i}guez Morales\}, Germania and \{Orellana Cordero\}, Marcos and Miguel Botto-Tobar and \{Crespo Mart{\'i}nez\}, Esteban and \{Pati{\~n}o Le{\'o}n\}, Andr{\'e}s",

booktitle = "Information and Communication Technologies of Ecuador, TIC.EC 2019",

}

Jimenez, S, Aviles, A, Galán, L, Flores, A, Matovelle, C & Vintimilla, C 2020, Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment. in E Fonseca C, G Rodríguez Morales, M Orellana Cordero, M Botto-Tobar, E Crespo Martínez & A Patiño León (eds), Information and Communication Technologies of Ecuador, TIC.EC 2019. Advances in Intelligent Systems and Computing, vol. 1099, Springer, pp. 182-193, 6th Conference on Information and Communication Technologies, TIC.EC 2019, Cuenca, Ecuador, 27/11/19. https://doi.org/10.1007/978-3-030-35740-5_13

Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment. / Jimenez, Stalin; Aviles, Alex; Galán, Luciano et al.
Information and Communication Technologies of Ecuador, TIC.EC 2019. ed. / Efraín Fonseca C; Germania Rodríguez Morales; Marcos Orellana Cordero; Miguel Botto-Tobar; Esteban Crespo Martínez; Andrés Patiño León. Springer, 2020. p. 182-193 (Advances in Intelligent Systems and Computing; Vol. 1099).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Support Vector Regression to Downscaling Climate Big Data

T2 - 6th Conference on Information and Communication Technologies, TIC.EC 2019

AU - Jimenez, Stalin

AU - Aviles, Alex

AU - Galán, Luciano

AU - Flores, Andrés

AU - Matovelle, Carlos

AU - Vintimilla, Cristian

PY - 2020

Y1 - 2020

N2 - The techniques for downscaling climatic variables are essential to support tools for water resources planning and management in a climate change context in the entire world. Support vector machines (SVM) through regression approach (SVR), constitute an artificial intelligence method to downscaling climatic variables. Since that statistical downscaling based on regression methodologies is susceptible to the predictor variables, the aim of this study was exploring a big database of predictor variables to achieve the best performance of a statistical downscaling model using SVR to predict precipitation and temperature future projections. Data from regional climate models of Ecuador and information of three meteorological stations was used to apply this approach in the Tomebamba river sub-basin, located in southern Ecuadorian Andean region. The results show that the downscaling model has a better performance with the climatic averages. The precipitation extremes do not estimate in a good manner, but the model achieves an effective behavior with the temperature extremes values. These results could serve to improve water balance projections in the future for formulating suitable measures for climate change decision-making.

AB - The techniques for downscaling climatic variables are essential to support tools for water resources planning and management in a climate change context in the entire world. Support vector machines (SVM) through regression approach (SVR), constitute an artificial intelligence method to downscaling climatic variables. Since that statistical downscaling based on regression methodologies is susceptible to the predictor variables, the aim of this study was exploring a big database of predictor variables to achieve the best performance of a statistical downscaling model using SVR to predict precipitation and temperature future projections. Data from regional climate models of Ecuador and information of three meteorological stations was used to apply this approach in the Tomebamba river sub-basin, located in southern Ecuadorian Andean region. The results show that the downscaling model has a better performance with the climatic averages. The precipitation extremes do not estimate in a good manner, but the model achieves an effective behavior with the temperature extremes values. These results could serve to improve water balance projections in the future for formulating suitable measures for climate change decision-making.

KW - Andean basin

KW - Artificial intelligence

KW - Climate big data

KW - Climate change

KW - SVR

KW - Statistical downscaling

UR - https://www.scopus.com/pages/publications/85076524642

U2 - 10.1007/978-3-030-35740-5_13

DO - 10.1007/978-3-030-35740-5_13

M3 - Contribución a la conferencia

AN - SCOPUS:85076524642

SN - 9783030357399

T3 - Advances in Intelligent Systems and Computing

SP - 182

EP - 193

BT - Information and Communication Technologies of Ecuador, TIC.EC 2019

A2 - Fonseca C, Efraín

A2 - Rodríguez Morales, Germania

A2 - Orellana Cordero, Marcos

A2 - Botto-Tobar, Miguel

A2 - Crespo Martínez, Esteban

A2 - Patiño León, Andrés

PB - Springer

Y2 - 27 November 2019 through 29 November 2019

ER -

Jimenez S, Aviles A, Galán L, Flores A, Matovelle C, Vintimilla C. Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment. In Fonseca C E, Rodríguez Morales G, Orellana Cordero M, Botto-Tobar M, Crespo Martínez E, Patiño León A, editors, Information and Communication Technologies of Ecuador, TIC.EC 2019. Springer. 2020. p. 182-193. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-35740-5_13

Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this