Building climate zoning in China using supervised classification-based machine learning

Abstract The planning, design and construction of buildings are all influenced by climate. Building climate zoning is significant for the formulation of building energy efficiency strategies in various regions. However, there is overlapping among the variables used for building climate zoning (Temp1 and Temp7 in zones I and VI, and Temp1 in zones II and VII) in the existing building climate zoning system in China. In addition, the climate conditions at some stations were not included in either zones due to the thresholds were low for some variables. In this study, based on data acquired by 701 national surface meteorological stations between 1984 and 2013 in China, a supervised classification algorithm was developed for building climate zoning and the Mahalanobis distance was used to assess the climate similarities between two regions. Three main variables from 172 stations were selected as the training samples for the supervised classification algorithm and the accuracy of the training results was 93.6%. The results obtained for 76 stations (10.8% of the total) using the interval judgment method could be considered controversial but only five stations (0.7% of the total) with the supervised classification algorithm. Compared with the interval judgment method, the supervised classification algorithm is advantageous and the classification results are suitable for indicating the climatic characteristics of different zones.

[1]  T. McMahon,et al.  Updated world map of the Köppen-Geiger climate classification , 2007 .

[2]  Chris C.S. Lau,et al.  Climate classification and passive solar design implications in China , 2007 .

[3]  D Daniel Cóstola,et al.  Performance-based validation of climatic zoning for building energy efficiency applications , 2018 .

[4]  Ali Malkawi,et al.  Investigating natural ventilation potentials across the globe: Regional and climatic variations , 2017 .

[5]  Xianliang Zhang,et al.  Temporal change of climate zones in China in the context of climate warming , 2013, Theoretical and Applied Climatology.

[6]  Alexandros Iosifidis,et al.  Semi-supervised Classification of Human Actions Based on Neural Networks , 2014, 2014 22nd International Conference on Pattern Recognition.

[7]  R. Knutti,et al.  Regional climate change patterns identified by cluster analysis , 2010 .

[8]  Meng Cai,et al.  Classification of Local Climate Zones Using ASTER and Landsat Data for High-Density Cities , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Shengli Wu,et al.  Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes , 2014, Sensors.

[10]  Daisuke Sumiyoshi,et al.  Optimization of passive design measures for residential buildings in different Chinese areas , 2012 .

[11]  Manuel Carpio,et al.  Climatic zoning for building construction in a temperate climate of Chile , 2018, Sustainable Cities and Society.

[12]  D Daniel Cóstola,et al.  Comparison of three climatic zoning methodologies for building energy efficiency applications , 2017 .

[13]  Dan Wang,et al.  An integrated local climatic evaluation system for green sustainable eco-city construction: A case study in Shenzhen, China , 2017 .

[14]  Liu Yang,et al.  Climate classifications and building energy use implications in China , 2010 .

[15]  Liu Yang,et al.  Changes in bioclimates in different climates around the world and implications for the built environment , 2012 .

[16]  R. Shankar,et al.  Thermal comfort design zone delineation for India using GIS , 2015 .

[17]  Servando Álvarez Domínguez,et al.  Climatic zoning and its application to Spanish building energy performance regulations , 2008 .

[18]  Peijun Shi,et al.  Climate change regionalization in China (1961–2010) , 2014, Science China Earth Sciences.

[19]  B. Rudolf,et al.  World Map of the Köppen-Geiger climate classification updated , 2006 .

[20]  Franz Rubel,et al.  Observed and projected climate shifts 1901-2100 depicted by world maps of the Köppen-Geiger climate classification , 2010 .

[21]  A. Strahler,et al.  Application of the MODIS global supervised classification model to vegetation and land cover mapping of Central America , 2000 .

[22]  Alex J. Cannon,et al.  A closer look at novel climates: new methods and insights at continental to landscape scales , 2017, Global change biology.

[23]  D Daniel Cóstola,et al.  Review of methods for climatic zoning for building energy efficiency programs , 2017 .

[24]  Manuel Carpio,et al.  Assessing the applicability of various climatic zoning methods for building construction: Case study from the extreme southern part of Chile , 2019, Building and Environment.

[25]  W. Köppen,et al.  Versuch einer Klassifikation der Klimate : vorzugsweise nach ihren Beziehungen zur Pflanzenwelt , 1900 .

[26]  Jianxi Huang,et al.  Forest Cover Classification from Multi-temporal MODIS Images in Southeast Asia Using Decision Tree , 2011, CCTA.

[27]  Danny H.W. Li,et al.  Impact of climate change on energy use in the built environment in different climate zones – A review , 2012 .

[28]  Wen-Shing Lee,et al.  Using climate classification to evaluate building energy performance , 2011 .

[29]  Jing Liu,et al.  Changes in climate regionalization indices in China during 1961–2010 , 2014, Advances in Atmospheric Sciences.

[30]  Xiao Zheng,et al.  A new climatic classification of afforestation in Three-North regions of China with multi-source remote sensing data , 2015, Theoretical and Applied Climatology.

[31]  M. Zhao,et al.  Parameters influencing the energy performance of residential buildings in different Chinese climate zones , 2015 .

[32]  Deliang Chen,et al.  Using the Köppen classification to quantify climate variation and change: An example for 1901–2010 , 2013 .

[33]  F. Moral,et al.  Climatic zoning for the calculation of the thermal demand of buildings in Extremadura (Spain) , 2017, Theoretical and Applied Climatology.

[34]  Khambadkone Naveen Kishore,et al.  A bioclimatic approach to develop spatial zoning maps for comfort, passive heating and cooling strategies within a composite zone of India , 2018 .

[35]  Baizhan Li,et al.  A hierarchical climatic zoning method for energy efficient building design applied in the region with diverse climate characteristics , 2019, Energy and Buildings.

[36]  R. Knight,et al.  Supervised classification of human microbiota. , 2011, FEMS microbiology reviews.

[37]  Shusheng Wang,et al.  Definition of new thermal climate zones for building energy efficiency response to the climate change during the past decades in China , 2019, Energy.

[38]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[39]  F. Garde,et al.  Development of climatic zones and passive solar design in Madagascar , 2009 .

[40]  P. Block,et al.  Optimal Cluster Analysis for Objective Regionalization of Seasonal Precipitation in Regions of High Spatial–Temporal Variability: Application to Western Ethiopia , 2016 .

[41]  Zhaolin Gu,et al.  Local climate zone classification with different source data in Xi’an, China , 2018, Indoor and Built Environment.