{"references": ["D. J. Rowlands et al. Broad range of 2050 warming from an\nobservationally constrained large climate model ensemble. Nature\nGeoscience, 5:256\u2013260, 03/2012 2012.", "S. Hajat, S. Vardoulakis, C. Heaviside, and B. Eggen. Climate change\neffects on human health: projections of temperature-related mortality for\nthe uk during the 2020s, 2050s and 2080s. Journal of Epidemiology and\nCommunity Health, 2014.", "World Health Organisation. Ambient (outdoor) air pollution in cities\ndatabase 2014.", "A. Mavrogianni, P. Wilkinson, M. Davies, P. Biddulph, and\nE. Oikonomou. Building characteristics as determinants of propensity\nto high indoor summer temperatures in London dwellings. Building and\nEnvironment, (55):117\u201330, 2012.", "J. Taylor, A. Mavrogianni, M. Davies, P. Das, C. Shrubsole, and\nP. Biddulph. Understanding and mitigating overheating and indoor\nPM2.5 risks using coupled temperature and indoor air quality\nmodels. Building Services Engineering Research and Technology,\n(0143624414566474), 2015.", "A. Mavrogianni, M. Davies, J. Taylor, Z. Chalabi, P. Biddulph, and\nE. Oikonomou. The impact of occupancy patterns, occupant-controlled\nventilation and shading on indoor overheating risk in domestic\nenvironments. Building and Environment, (78):183198, 2013.", "S. Porritt and P. Cropper. Heat wave adaptations for UK dwellings and\nintroducing a retrofit toolkit. International Journal of Disaster Resilience\nin the Built Environment, (4:3):269\u2013286, 2010.", "R. Gupta and M. Gregg. Preventing the overheating of English suburban\nhomes in a warming climate. Building Research & Information,\n(41):281\u2013300, 2013.", "J. Taylor, M. Davies, A. Mavrogianni, Z. Chalabi, P. Biddulph, and\nE. Oikonomou. The relative importance of input weather data for indoor\noverheating risk assessment in dwellings. Building and Environment,\n(76):81\u201391, 2014.\n[10] E. Oikonomou, M. Davies, A. Mavrogianni, P. Biddulph, P. Wilkinson,\nand M. Kolokotroni. Modelling the relative importance of the urban heat\nisland and the thermal quality of dwellings for overheating in London.\nBuilding and Environment, (57):223\u201338, 2012.\n[11] US-DoE. EnergyPlus V8. 2013.\n[12] L. Van Gelder, P. Das, H. Janssen, and S. Roels. Comparative study of\nmetamodelling techniques in building energy simulation: Guidelines for\npractitioners. Simulation Modelling Practice and Theory, (49):245\u201357,\n2014.\n[13] R. E. Edwards. Predicting future hourly residential electrical\nconsumption: A machine learning case study. Energy Buildings, 2012.\n[14] B. Eisenhower, Z. ONeill, S. Narayanan, V. A. Fonoberov, and I. Mezi.\nA methodology for meta-model based optimization in building energy\nmodels. Energy and Buildings, (47):292\u2013301, 2012.\n[15] B. Tang. Orthogonal Array-Based Latin Hypercubes. Journal of the\nAmerican Statistical Association, 2012.\n[16] Indian Society of Heating Refrigerating and Air Conditioning Engineers.\nNew delhi weather file.\n[17] A. J. McMichael et al. International study of temperature, heat and urban\nmortality: the 'isothurm' project. International Journal of Epidemiology,\n37(5):1121\u20131131, 2008.\n[18] W. S. McCulloch and W. Pitts. Neurocomputing: Foundations of\nresearch. chapter A Logical Calculus of the Ideas Immanent in Nervous\nActivity, pages 15\u201327. MIT Press, Cambridge, MA, USA, 1988.\n[19] T. Schaul et al. PyBrain. Journal of Machine Learning Research, 2010.\n[20] D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Neurocomputing:\nFoundations of research. chapter Learning Representations by\nBack-propagating Errors, pages 696\u2013699. MIT Press, Cambridge, MA,\nUSA, 1988.\n[21] C. Igel and M. H\u00a8usken. Empirical evaluation of the improved rprop\nlearning algorithms. Neurocomputing, 50:105\u2013123, 2003.\n[22] D. S. Broomhead and D. Lowe. Multivariable Functional Interpolation\nand Adaptive Networks. Complex Systems 2, pages 321\u2013355, 1988.\n[23] F. Pedregosa et al. Scikit-learn: Machine learning in Python. Journal\nof Machine Learning Research, 12:2825\u20132830, 2011.\n[24] M. C. Peel, B. L. Finlayson, and T. A. McMahon. Updated world map\nof the kppen-geiger climate classification. Hydrology and Earth System\nSciences, 11(5):1633\u20131644, 2007."]}

Average temperatures worldwide are expected to continue to rise. At the same time, major cities in developing countries are becoming increasingly populated and polluted. Governments are tasked with the problem of overheating and air quality in residential buildings. This paper presents the development of a model, which is able to estimate the occupant exposure to extreme temperatures and high air pollution within domestic buildings. Building physics simulations were performed using the EnergyPlus building physics software. An accurate metamodel is then formed by randomly sampling building input parameters and training on the outputs of EnergyPlus simulations. Metamodels are used to vastly reduce the amount of computation time required when performing optimisation and sensitivity analyses. Neural Networks (NNs) have been compared to a Radial Basis Function (RBF) algorithm when forming a metamodel. These techniques were implemented using the PyBrain and scikit-learn python libraries, respectively. NNs are shown to perform around 15% better than RBFs when estimating overheating and air pollution metrics modelled by EnergyPlus.