Marta Gonzalezr, Associate Professor, UC Berkeley, presented Urban Computing for Planning Energy Efficient and Healthier Cities at the NASA Berkeley Aviation Data Science Seminar February 12, 2020.
Abstract: My work uses data science to characterize how humans interact with the built and natural environments, seeking to plan for more sustainable and livable cities. Given the increasing ubiquity of plug-in electric vehicles (PEVs) in the Bay Area, I present a study that aims to assist in planning decisions by providing timing recommendations and assigning monetary values to modulations of PEV start and end charging times. According to the US Energy Information Administration, the number of PEVs in the United States doubled between 2013 and 2015 and are expected to reach 20 million by 2020. In the second part, I present DeepAir, a convolutional neural network platform that combines satellite imagery and urban maps with weather and air monitoring stations datasets. The goal is to enable science-informed policy by understanding various interdependencies in the quality of the air we breathe. These methodologies are aimed to be fully scalable and open source. The presented methods can be extended to other domains that involve human and environmental interactions.
Marta Gonzalez, is an Associate Professor with appointments both in Civil and Environmental Engineering and in City and Regional Planning at the University of California, Berkeley. She is also a Research Scientist in the Energy Analysis and Environmental Impacts Division of Lawrence Berkeley National Lab. Her research analyzes and combines spatial data on various complex systems, with applications to transportation networks, energy efficiency planning, and detection of urban lifestyles. Prior to joining Berkeley, she was an Associate Professor of Civil and Environmental Engineering at MIT.
The NASA Berkeley Aviation Data Science Seminar Series was launched in spring 2020 and is held weekly on Wednesdays in Stanley 106, at 11:00 AM - 12:00 PM, from January 22 through May 6. Presenters include experts in government, industry, and academia, who focus on how big data collection and machine learning are transforming aircraft, airspace, and airport operations, with topics ranging from feedback control, IoT, and IoV to autonomy, AI, and data security. All seminars are livecast and interactive across both campuses. The series is also being offered as a 1-credit course: the Berkeley course numbers are CEE198/CEE298 (class #: 33393) and CP298 (class #: 13328). This seminar series is hosted by NASA and UC Berkeley, sponsored by the Universities Space Research Association (USRA) and NASA Academic Mission Services; and presented by UC Berkeley's Urban Air Mobility Research Center (UAM@Berkeley), the Berkeley Institute of Transportation Studies, and BIDS.