A055
Deep Learning for improving short-term atmospheric modeling and prediction

Session ID#: 81500

Session Description:
Deep learning is one of the most popular emerging tools for mining high-level features and predicting future trends, and has been proven in many computer vision tasks. In atmospheric domain, deep learning has been successfully used in urban air quality monitoring, cloud detection, precipitation nowcasting, etc. With the rapid development of sensor technology, the atmosphere observation datasets have accumulated to a very large amount which meets the deep learning’s data requirements. This session will discuss the utilization of deep learning in improving the atmospheric monitoring and prediction. It will cover a wide spectrum of topics in the monitoring and forecasting of air quality (PM2.5, PM10, etc), air pollutant, CO2, ozone, clouds, nitrogen, smog, urban heat air, air density, atmospheric thickness, greenhouse effect, etc.
Index Terms:

0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1610 Atmosphere [GLOBAL CHANGE]
1942 Machine learning [INFORMATICS]
3360 Remote sensing [ATMOSPHERIC PROCESSES]

Primary Convener:  Ziheng Sun, George Mason University Fairfax, Center for Spatial Information Science and Systems, Fairfax, VA, United States
Convener:  Daniel Tong, George Mason University Foundation Inc., Columbia, MD, United States
Primary Liaison:  Ziheng Sun, George Mason University Fairfax, Center for Spatial Information Science and Systems, Fairfax, VA, United States
 
Exploiting Deep Learning Algorithms in Forecasting the Occurrence of Intense Lightning Activities (507342)
Chien Wang1, Evelyne Richard1 and Stephane Pedeboy2, (1)Laboratoire d'Aerologie, CNRS/UPS, Toulouse, France, (2)Météorage, Pau, France
 
PM10 Estimation using Applying Time Variation and recurrent neural network (530366)
Wonhee Cho1, Seung Hee Kim1, Mijin Kim2, Yun Gon Lee3, Kwang Nyun Kim3 and Menas Kafatos1, (1)Chapman University, Center of Excellence in Earth Systems Modeling & Observations, Orange, CA, United States, (2)Chapman University, Center of Excellence in Earth Systems Modeling & Observations, Orange, United States, (3)Chungnam National University, Department of Atmospheric Sciences, Daejeon, South Korea
 
Investigating Severe Weather Forecasting Using Machine Learning Techniques. (564278)
Elliot Shiben1, William Smith2, Qi Zhang3, James M Russell III4 and John M.C. McNabb1, (1)Hampton University, APS, Hampton, VA, United States, (2)University of Wisconsin Madison, Madison, WI, United States, (3)Nanjing University, Nanjing, China, (4)Hampton University, Department of Atmospheric and Planetary Sciences, Hampton, VA, United States
 
Development of PM2.5 prediction model using recurrent neural network in Seoul, South Korea (572539)
Ingyu Park, Chang-Hoi Ho and Sun-Kyong Hur, Seoul National University, School of Earth and Environmental Sciences, Seoul, South Korea
 
The Potential Application of Deep Machine Learning Technique for the Space Lidar Retrievals (584979)
SHAN Zeng1, Ali H Omar2, Mark Vaughan3, Charles R Trepte3, Yongxiang Hu3, David M Winker3 and Patricia Lucker4, (1)Science Systems and Applications, Inc., Lanham, MD, United States, (2)NASA/Langley Research Ctr, Hampton, VA, United States, (3)NASA Langley Research Center, Hampton, VA, United States, (4)Science Systems and Applications, Inc. Hampton, Hampton, VA, United States
 
A Deep Learning Based Methodology for Precipitation Nowcasting with Radar. (587062)
Lei Chen1, Yuan Cao2, Leiming Ma1 and Junping Zhang3, (1)Shanghai Meteorological Bureau, Shanghai, China, (2)School of Computer Science, Fudan University, Shanghai, Shanghai, China, (3)School of Computer Science, Fudan University, Shanghai, China
 
Indian Summer Monsoon Prediction by Deep Long Short-Term Memory Neural Network using Time Series Based Approach (590426)
Yajnaseni Dash, Indian Institute of Technology Delhi, New Delhi, India, Saroj K. Mishra, Centre for Atmospheric Sciences, Indian Institute of Technology Delhi, New Delhi, India and B. K. Panigrahi, Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India
 
Deep-season a Modelling and Prediction Approach for Cyclic Nature of Seasons with Deep Neural Networks (595846)
Namit Khanduja, Gurukul Kangri Vishvavidyalaya, Haridwar, Computer Science and Engineering, Haridwar, India and Ananjay Kumar Singh, Indian Institute of Technology Roorkee, Computer Science and Engineering, Roorkee, India
 
Deep learning based Tropical cyclone intensity estimation method using Communication, Ocean and Meteorological Satellite (COMS) (630089)
Junghee Lee1, Juhyun Lee1, Jungho Im2, Dong-Hyun Cha1 and Haemi Park3, (1)Ulsan National Institute of Science and Technology, Ulsan, Korea, Republic of (South), (2)Ulsan National Institute of Science and Technology, Ulsan, South Korea, (3)The University of Tokyo, Tokyo, Japan
 
Numerical Temperature Prediction Correction Model Based on Memory Network in Shanghai (631713)
Leiming Ma, Shanghai, Shanghai, China and Hong Lin, Bouge, Belgium
 
Estimating Instantaneous Gross Primary Productivity under all sky conditions (631963)
Jaese Lee1, Junghee Lee1 and Jungho Im2, (1)Ulsan National Institute of Science and Technology, Ulsan, Korea, Republic of (South), (2)Ulsan National Institute of Science and Technology, Ulsan, South Korea
 
Community-level Air Quality Estimation based on Embedding and Transfer Learning of Drive-by Sensing Data (633781)
Yawen Zhang1, Duanfeng Gao1, Qin Lv1, Robert Dick2 and Michael Hannigan3, (1)University of Colorado Boulder, Boulder, CO, United States, (2)Madison, AL, United States, (3)University of Colorado at Boulder, Boulder, CO, United States
 
CAMQ-AI: A computationally efficient deep learning model to improve CMAQ performance over the United States (Invited) (635444)
Yunsoo Choi, Ebrahim Eslami, Alqamah Sayeed and Yannic Lops, University of Houston, Houston, TX, United States
See more of: Atmospheric Sciences
<< Previous Session Proposal | Next Session Proposal >>