Quantile regression ensemble for summer temperatures time series and its impact on built environment studies

Manuel Herrera, Matthew Eames, Alfonso Ramallo Gonzalez, Chunde Liu, David Coley

Research output: Contribution to conferencePaper

23 Downloads (Pure)

Abstract

The occurrence of heat waves, heavy rainfall, or drought periods have an increasing trend nowadays as consequence of Earth's global warming. This seriously affects natural habitats and directly impacts on the human environment. Architects and engineers use different approaches to model reference and future weather conditions to achieve building designs that resilient and energy efficient. However, modelling extreme weather events within those future conditions is a relative few explored field. This paper introduces the analysis of regression models for summer temperature time series that facilitate the representation of those extreme events; this is based on upper and lower quantiles, instead of the ordinary regression which is conditioned by the mean. The advantage of this proposal is to focus on finding patterns for both higher temperatures during the day and warmer temperatures during the night. These two temperatures are key in the study of overheating and therefore thermal related morbidity as the night time temperature will show the possibility of night purging. Advances on quantile regression models coming from both resampling and ensemble approaches are further investigated and compared with the state of the art. The results are sound in terms of statistical robustness and knowledge of inputs that specifically affect to temperature extremes. The new method has been tested with real data of temperatures in London for a period of 50
years. The quantile regression technique provides more meaningful information for use in building simulation than standard methods.
Original languageEnglish
Publication statusPublished - Jul 2016
EventInternational Congress on Environmental Modelling and Software - École nationale supérieure d'électronique, d'électrotechnique, d'informatique, d'hydraulique et des télécommunications, Toulouse, France
Duration: 10 Jul 201614 Jul 2016
Conference number: 8
http://www.iemss.org/sites/iemss2016/index.php

Conference

ConferenceInternational Congress on Environmental Modelling and Software
Abbreviated titleiEMSs
CountryFrance
CityToulouse
Period10/07/1614/07/16
Internet address

Fingerprint

time series
summer
temperature
architectural design
extreme event
morbidity
built environment
global warming
drought
weather
rainfall
habitat
modeling
simulation
energy
method

Cite this

Herrera, M., Eames, M., Ramallo Gonzalez, A., Liu, C., & Coley, D. (2016). Quantile regression ensemble for summer temperatures time series and its impact on built environment studies. Paper presented at International Congress on Environmental Modelling and Software, Toulouse, France.

Quantile regression ensemble for summer temperatures time series and its impact on built environment studies. / Herrera, Manuel; Eames, Matthew; Ramallo Gonzalez, Alfonso; Liu, Chunde; Coley, David.

2016. Paper presented at International Congress on Environmental Modelling and Software, Toulouse, France.

Research output: Contribution to conferencePaper

Herrera, M, Eames, M, Ramallo Gonzalez, A, Liu, C & Coley, D 2016, 'Quantile regression ensemble for summer temperatures time series and its impact on built environment studies' Paper presented at International Congress on Environmental Modelling and Software, Toulouse, France, 10/07/16 - 14/07/16, .
Herrera M, Eames M, Ramallo Gonzalez A, Liu C, Coley D. Quantile regression ensemble for summer temperatures time series and its impact on built environment studies. 2016. Paper presented at International Congress on Environmental Modelling and Software, Toulouse, France.
Herrera, Manuel ; Eames, Matthew ; Ramallo Gonzalez, Alfonso ; Liu, Chunde ; Coley, David. / Quantile regression ensemble for summer temperatures time series and its impact on built environment studies. Paper presented at International Congress on Environmental Modelling and Software, Toulouse, France.
@conference{7a10df9d7ab94dbdb935838f78e457c7,
title = "Quantile regression ensemble for summer temperatures time series and its impact on built environment studies",
abstract = "The occurrence of heat waves, heavy rainfall, or drought periods have an increasing trend nowadays as consequence of Earth's global warming. This seriously affects natural habitats and directly impacts on the human environment. Architects and engineers use different approaches to model reference and future weather conditions to achieve building designs that resilient and energy efficient. However, modelling extreme weather events within those future conditions is a relative few explored field. This paper introduces the analysis of regression models for summer temperature time series that facilitate the representation of those extreme events; this is based on upper and lower quantiles, instead of the ordinary regression which is conditioned by the mean. The advantage of this proposal is to focus on finding patterns for both higher temperatures during the day and warmer temperatures during the night. These two temperatures are key in the study of overheating and therefore thermal related morbidity as the night time temperature will show the possibility of night purging. Advances on quantile regression models coming from both resampling and ensemble approaches are further investigated and compared with the state of the art. The results are sound in terms of statistical robustness and knowledge of inputs that specifically affect to temperature extremes. The new method has been tested with real data of temperatures in London for a period of 50years. The quantile regression technique provides more meaningful information for use in building simulation than standard methods.",
author = "Manuel Herrera and Matthew Eames and {Ramallo Gonzalez}, Alfonso and Chunde Liu and David Coley",
year = "2016",
month = "7",
language = "English",
note = "International Congress on Environmental Modelling and Software, iEMSs ; Conference date: 10-07-2016 Through 14-07-2016",
url = "http://www.iemss.org/sites/iemss2016/index.php",

}

TY - CONF

T1 - Quantile regression ensemble for summer temperatures time series and its impact on built environment studies

AU - Herrera, Manuel

AU - Eames, Matthew

AU - Ramallo Gonzalez, Alfonso

AU - Liu, Chunde

AU - Coley, David

PY - 2016/7

Y1 - 2016/7

N2 - The occurrence of heat waves, heavy rainfall, or drought periods have an increasing trend nowadays as consequence of Earth's global warming. This seriously affects natural habitats and directly impacts on the human environment. Architects and engineers use different approaches to model reference and future weather conditions to achieve building designs that resilient and energy efficient. However, modelling extreme weather events within those future conditions is a relative few explored field. This paper introduces the analysis of regression models for summer temperature time series that facilitate the representation of those extreme events; this is based on upper and lower quantiles, instead of the ordinary regression which is conditioned by the mean. The advantage of this proposal is to focus on finding patterns for both higher temperatures during the day and warmer temperatures during the night. These two temperatures are key in the study of overheating and therefore thermal related morbidity as the night time temperature will show the possibility of night purging. Advances on quantile regression models coming from both resampling and ensemble approaches are further investigated and compared with the state of the art. The results are sound in terms of statistical robustness and knowledge of inputs that specifically affect to temperature extremes. The new method has been tested with real data of temperatures in London for a period of 50years. The quantile regression technique provides more meaningful information for use in building simulation than standard methods.

AB - The occurrence of heat waves, heavy rainfall, or drought periods have an increasing trend nowadays as consequence of Earth's global warming. This seriously affects natural habitats and directly impacts on the human environment. Architects and engineers use different approaches to model reference and future weather conditions to achieve building designs that resilient and energy efficient. However, modelling extreme weather events within those future conditions is a relative few explored field. This paper introduces the analysis of regression models for summer temperature time series that facilitate the representation of those extreme events; this is based on upper and lower quantiles, instead of the ordinary regression which is conditioned by the mean. The advantage of this proposal is to focus on finding patterns for both higher temperatures during the day and warmer temperatures during the night. These two temperatures are key in the study of overheating and therefore thermal related morbidity as the night time temperature will show the possibility of night purging. Advances on quantile regression models coming from both resampling and ensemble approaches are further investigated and compared with the state of the art. The results are sound in terms of statistical robustness and knowledge of inputs that specifically affect to temperature extremes. The new method has been tested with real data of temperatures in London for a period of 50years. The quantile regression technique provides more meaningful information for use in building simulation than standard methods.

M3 - Paper

ER -