{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/650884ac30ce950011b5fba6/69adea110722bbb60ba35ac1?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Physics and Machine Learning in Building Temperature Control with Jan Drgona ","description":"<p>Please click below to fill out the survey for this episode:</p><p><a href=\"https://docs.google.com/forms/d/1Muh6Ep6JLTMepAy6Fe6pkqUlkUxWP99Z-4RrMxDxC60/viewform?edit_requested=true\" rel=\"noopener noreferrer\" target=\"_blank\">Science Fare Podcast Feedback Form</a></p><p><br></p><p><a href=\"https://lucybethpohl.wixsite.com/sciencefare-podcast\" rel=\"noopener noreferrer\" target=\"_blank\">Science Fare Podcast website</a>&nbsp;</p><p><br></p><p>Our guest today is Jan Drgona, who joins us today from Johns Hopkins University.&nbsp;</p><p>Jan is an associate professor in the department of civil and systems engineering, and is also at the Ralph S O’Connor Sustainable Energy Institute.&nbsp;</p><p><br></p><p>Jan’s research focuses on energy management in buildings and he’s working on developing scientific machine learning methods to model energy management which turns out is very complex. In this mini episode, I ask Jan about what makes a building complicated to heat and cool, and describes the various factors that make temperature control a challenge, and hints at how physics and machine learning can help. Tune in next week for the full-length interview when Jan talks about making energy use in buildings sustainable and how scientific machine learning and problem solving with an engineering approach and mindset can help. </p><p><br></p>","author_name":"Susan Keatley"}