BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Talks.cam//talks.cam.ac.uk// X-WR-CALNAME:Talks.cam BEGIN:VEVENT SUMMARY:Computational Building Performance Analysis - Sam Wilkinson\, PhD Candidate\, University College London DTSTART:20121129T133000Z DTEND:20121129T153000Z UID:TALK39237@talks.cam.ac.uk CONTACT:Aaron Gillich DESCRIPTION:Research from the UCL Bartlett School of Graduate Studies and Energy Institute.\n\n\n1) Tia Kansara (UCL Energy Institute)\nThe Energy C ode in Abu Dhabi - \n'In 2011 the Department of Municipal Affairs\, Abu Dh abi\, developed the Energy Code in line with the ICC - International Code Council. This year it will be launched and there is a considerable debate around the topics that the Code discusses. Energy is a growing area of con cern as the Emirates continue to increase the built environment attracting more people to live in an energy-intensive environment. What will happen? What are the forecasts for energy supply and demand? This talk will outli ne the discussion around the Energy Sector in Abu Dhabi.'\n\n2) Greig Pate rson (UCL Bartlett School of Graduate Studies\, Complex Built Environment Systems Group)\nUtilising Monitored Data to Gain Environmental Feedback in Real-time as Early Design and Briefing Decisions are Made\nBuilding simul ation is often rejected by architects at the early design stages. Furtherm ore\, studies have shown that the predicted energy performance of building s is often lower than the actual performance once built. In view of this\, this research explores machine learning techniques\, utilising monitored and simulated data\, to form a platform for performance prediction. Using school design as a test case\, the aim is to develop a design tool which a llows environmental performance indicators to be communicated to the user in real-time as early design parameters are altered interactively - allowi ng the architect to sketch performance as well as form.\n\n\n3) Samuel Wil kinson (UCL Bartlett School of Graduate Studies\, Complex Built Environmen t Systems Group)\nTowards Machine Learning for Environmental Performance P rediction in Generative Design: Estimating Tall Building Surface Pressure. \nThe trend towards creating ever taller buildings continues\, with drama tic technological improvements in materials\, structures\, and modelling. However\, as height increases so too do gravitational\, wind and seismic f orces. Wind forces on tall buildings must be mitigated to avoid occupant discomfort from swaying\, reduce risk of facade damage\, and improve struc ture efficiency. Although these problems can generally be avoided through early decision form-finding\, current fluid simulations are costly and d o not provide rapid performance feedback necessary for such exploratory or optimization studies. Here an approach is described that uses machine lea rning to make predictions of the wind loads by recognizing shape features\ , through the use of procedural geometry generation and regression analysi s. Results will be shown whereby wind loads can be immediately predicted a nd visualized on models of arbitrary complexity.\n\n\n4) Kinda Al-Sayed (U CL Bartlett School of Graduate Studies\, Space Group): Natural Growth Proc esses in Urban Form - \n"Cities appear to exhibit autonomous growth behavi our\; they appear to imitate natural growth in response to large-scale hum an interventions. In Barcelona\, the uniform grid subdivides in response t o the increase in global accessibility of street network. In Manhattan\, l ocalized processes lead to the splitting and multiplication of elongated p atches reinforcing regular patterns similar to those in reaction-diffusion models. The generic mechanisms that are extracted from historical transfo rmations indicate that urban form has some inherent natural processes that build its complexity from the micro scale to the macro scale. Understandi ng the dynamics of this self-organised complexity will have significant im plications on urban design." LOCATION:CRASSH\, 7 West Road\, Cambridge\, CB3 9DP END:VEVENT END:VCALENDAR