Events

Back to Listing

NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.

CAII Fall Seminar Series: "Our Roadmap of Using AI-physics-hybrid Methods to Scalably Quantify Field-level Carbon Intensity & Carbon Credit - introducing ARPA-E SMARTFARM projects at UIUC" Kaiyu Guan

Event Type
Seminar/Symposium
Sponsor
Center for Artificial Intelligence Innovation
Location
Zoom
Virtual
wifi event
Date
Oct 25, 2021   11:00 am - 12:00 pm  
Speaker
Kaiyu Guan, Blue Waters Associate Professor
Views
18
Originating Calendar
Center for Artificial Intelligence Innovation

Dr. Kaiyu Guan, Blue Waters Associate Professor in ecohydrology and remote sensing in the department of Natural Resources and Environmental Sciences (NRES) at the University of Illinois at Urbana-Champaign, will give a presentation during the CAII Seminar Series on Monday, October 25 at 11:00 a.m. The talk is titled “Our Roadmap of Using AI-physics-hybrid Methods to Scalably Quantify Field-level Carbon Intensity & Carbon Credit - introducing ARPA-E SMARTFARM projects at UIUC." 

View Seminar here: https://go.ncsa.illinois.edu/2021CAIIFallSeminarSeries 

Abstract: There is an increasing need to quantify carbon intensity for agricultural and biofuel production at the field level. Conventional carbon quantification methods, such as soil sampling or flux-tower/chamber measurements are too costly to be scalable. Modeling-based quantification methods contain high uncertainty due to the complexities of measuring ecosystem soil carbon and GHG emission and evaluating day-to-day sustainable growing practices.

A set of major efforts funded by the U.S. Department of Energy ARPA-E are leading the way in biofuel and agricultural carbon monitoring initiatives including the SMARTFARM Program. This program aims to make it possible and profitable to optimize biofuel crops for yield and carbon capture intensity. With this vision, SMARTFARM works in a two-phased approach, Phase 1 by setting scientifically rigorous baselines to better quantify soil conditions, and then Phase 2 by developing commercial tools to scale these measurements, which should help increase carbon offsets, and drive sustainable farming practices. Principally, the SMARTFARM initiative lends scientific rigor to the measurement of carbon offsets by analyzing them through this holistic data compilation and model-data integration.

Guan’s SMARTFARM Phase 2 Project at University of Illinois, named “SYMFONI”, aims to develop an unprecedented “system of systems” solution to quantify field-level carbon credit. This solution truly integrates different streams of remote sensing data and other sensor data with an advanced agroecosystem model, representing a comprehensive integration of data sets for accurate predictive modeling which can simulate energy, water, carbon, and nutrient fluxes. AI and supercomputing can then be used to scale this solution to each of the millions of fields in the US and ultimately, globally.

Speaker Bio: 

I am a Blue Waters Associate Professor in ecohydrology and remote sensing in the Department of Natural Resources and Environmental Sciences (NRES), College of Agricultural, Consumer and Environmental Sciences (ACES) at the University of Illinois at Urbana-Champaign, and at the National Center for Supercomputing Applications (NCSA). I use satellite data, computational models, fieldwork, and machine learning approaches to address how climate and human practices affect crop productivity, water resource availability, and ecosystem functioning. I have keen interests in applying my knowledge and skills in solving real-life problems, such as large-scale crop monitoring and forecasting, water management and sustainability, and global food security. My lab closely works with scientists in computer science (deep learning, high performance computing), plant physiologists, agronomists, and economists in addressing the above real-world challenges.

 

All presentations will be recorded and will available on the CAII website shortly after the presentation. 

link for robots only