State-of-the-Art on Discovering Actionable Information about Climate and Agriculture II

Type: Virtual Paper
Theme: Geographies of Access: Inclusion and Pathways
Sponsor Groups: Remote Sensing Specialty Group
Poster #:
Day: 4/9/2021
Start / End Time: 11:10 AM / 12:25 PM (PST)
Room: Virtual 56
Organizers: Ziheng Sun
Chairs: Ziheng Sun

Call for Submissions

There are many complicated processes in the climate-agriculture-human cycle, which poses big challenges for scientists to monitor and predict the impacts of climate change and disruptive disasters on human societies, environments, agriculture, economy, businesses, industries, etc. Addressing these challenges involves a lot of the latest technologies. In recent years, new research technologies such as regression-based modeling and machine learning has been recognized as a broadly powerful tool for tackling many challenging big-data-related problems across the spectrum of science. Although these techniques are neither silver bullets nor one-size-for-all solutions, they have been proven to be able to overcome many hard research problems that are beyond the reach of conservative modeling or approaches. To better circulate the latest research progress on advocating new technologies to address problems in climate-agriculture geography, we want to invite the community to come forward and discuss theoretical thinking, methodology innovation, and technique development, and best practices. This session calls for work from the domains including but not limited to:
• Climate monitoring and prediction
• Agricultural geography
• Climate-dependent farming
• Climate/agriculture-oriented remote sensing
• Climate/agriculture-related economy
• Climate/agriculture-related social science
• Tooling and services for processing big climate/agro datasets
• Cyberinfrastructure for climate/agriculture
If you are interested in presenting in this session, please send your abstract and the Personal Identification Number (PIN) for AAG 2020 to Ziheng Sun (George Mason University; zsun@gmu.edu) and Liping Di (George Mason University; ldi@gmu.edu).

References
Sun, Ziheng, Liping Di, and Hui Fang. "Using long short-term memory recurrent neural network in land cover classification on Landsat and Cropland data layer time series." International journal of remote sensing 40, no. 2 (2019): 593-614
Sun, Ziheng, Liping Di, Annie Burgess, Jason A. Tullis, and Andrew B. Magill. "Geoweaver: Advanced Cyberinfrastructure for Managing Hybrid Geoscientific AI Workflows." ISPRS International Journal of Geo-Information 9, no. 2 (2020): 119.
Sun, Ziheng, Liping Di, Hui Fang, and Annie Burgess. "Deep Learning Classification for Crop Types in North Dakota." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2020).


Description

With the development of sensors and numeric models, petabytes of data about climate and agriculture have been observed, recorded, transmitted, and archived. However, the workflow of digging insights from the big data and delivering actionable information to worldwide stakeholders is far from being mature in many domains. While the traditional technology struggles to follow the pace, technical evolution has called out new technologies such as numeric modeling and machine learning to tackle those grand climate/agriculture challenges, such as forecasting extreme climate events, increasing farm productivity and sustainability, remote sensing emissions, precision agriculture, peatland monitoring, understanding aerosols, modeling agriculture-human interaction, informing policy, and designing markets. There are many ways in which AI/ML can contribute to climate and agriculture. Climate modeling prediction and precision agriculture can do general good for entire human societies and AI/ML can support many key components. For example, intelligent irrigation systems can use the climate and soil moisture datasets to save large amounts of drinkable water while reducing pesticide use because of the reduction in excessive soil moisture which could thrive pests. ML can predict crop yield based on historical records to help farmers predict market demand and price at the beginning of the growing season. With AI/ML, it will be no longer out of our reach that the actionable information is automatically extracted from the tremendous amount of data and precisely delivered to stakeholders in time to assist smart decisions on behalf of humankind, the environment, the economy, and the future generation.


Agenda

Type Details Minutes Start Time
Presenter Faisal Islam*, University of Tennessee, Madhuri Sharma, Associate Professor, University of Tennessee, Knoxville, A Bayesian Multilevel Regression Analysis of Gendered Livelihood Decision-Making Processes in in the Context of Climate Change 15 11:10 AM
Presenter Madison Wilson*, University of Oklahoma, Sophie Plassin, University of Oklahoma, Jennifer Koch, University of Oklahoma, Jack Friedman, University of Oklahoma, Stephanie Paladino, University of Oklahoma, Kevin Neal, University of Oklahoma, Integrated analysis of drivers of fallow/idle cropland dynamics in the Rio Grande Basin 15 11:25 AM
Presenter Ziheng Sun*, George Mason University, Using artificial intelligence to support smart agricultural irrigation practices 15 11:40 AM
Discussant Shiqi Tao 15 11:55 AM

To access contact information login