A136
Urban Climate Informatics -- from sourcing to (deep) learning

Session ID#: 81563

Session Description:
In the era of big data and artificial intelligence, Urban Climate Informatics (UCI) is a newly evolving research field. It emerges from the synthesis of two established domains: Urban Climate (concerned with interactions between a city and the overlying atmosphere), and Climate Informatics (a combination of climate science with approaches from statistics, machine learning, and data mining). UCI seeks to explore and understand complex urban climate systems using novel sensing approaches, big data sources, and artificial intelligence.

As part of the cluster of Urban Geosciences, we welcome submissions that advance the field of urban climate through UCI methods. We are especially interested in studies that use novel data sources, such as crowdsourced data from wearables, mobile sensors, IoT, and Google Street View applications. We also seek big data-driven urban computing and analytics submissions that employ advanced data processing techniques such as machine learning and deep learning.

Co-Organized:
  • NG - Nonlinear Geophysics
Index Terms:

0430 Computational methods and data processing [BIOGEOSCIENCES]
0493 Urban systems [BIOGEOSCIENCES]
1942 Machine learning [INFORMATICS]
1952 Modeling [INFORMATICS]

Primary Convener:  Ariane Christine Middel, Arizona State University, Tempe, AZ, United States
Conveners:  Daniel J M Schertzer, U. Paris-Est, Marne La Vallee Cx 2, France, Matthias Demuzere, Ruhr-University Bochum, Bochum, Germany and Florian Arwed Schneider, Arizona State University, School of Sustainability, Tempe, United States
Primary Liaison:  Ariane Christine Middel, Arizona State University, Tempe, AZ, United States
 
A Hybrid Method for Retrieving All-weather Land Surface Temperature by Integrated Use Of MODIS Thermal Infrared, AMSR2 Passive Microwave Observations and Reanalysis Data (492041)
Kangning Li, Beijing, Beijing, China and Yunhao Chen, Beijing Normal University, Faculty of Geographical Science, Beijing, China
 
A new approach to develop the street-scale high-resolution on-road emission inventories based on dynamic traffic big data (494385)
Luolin Wu1, Ming Chang2, Xuemei Wang2, Jian Hang3 and Jinpu Zhang4, (1)Sun Yat-sen University, Guangzhou, Guangdong, China, (2)Jinan University, Institute for Environmental and Climate Research, Guangzhou, China, (3)Sun Yat-sen university, Guangzhou, China, (4)Guangzhou Environmental Monitoring Center, Guangzhou, China
 
Classification of heavy rainfall in Seoul using a machine learning (514592)
Nahyun Lee, Seoul, South Korea and Sujong Jeong, Seoul National University, Seoul, Korea, Republic of (South)
 
Machine Learning on satellite data to predict particulate matter in Seoul, South Korea (514786)
Ahreum Lee and Sujong Jeong, Seoul National University, Seoul, Korea, Republic of (South)
 
A Non-Stationary Surrogate Model for Meso-scale Surface Temperature with Extracted Diurnal Spatial Patterns (572771)
Byeongseong Choi1, Matteo Pozzi1, Mario Berges1 and Elie Bou-Zeid2, (1)Carnegie Mellon University, Civil and Environmental Engineering, Pittsburgh, PA, United States, (2)Princeton University, Civil and Environmental Engineering, Princeton, NJ, United States
See more of: Atmospheric Sciences
<< Previous Session Proposal | Next Session Proposal >>