Skip to main content

Calling for Artificial Intelligence Abstracts for AGU 2022

Submit your abstract for our Fall 2022 American Geophysical Union artificial intelligence sessions.

IMPACT team members Muthukumaran R. and Aaron Kaulfus will be convening sessions on AI while Manil Maskey, Iksha Gurung, Lillianne Thomas, and Slesa Adhikari will co-convene sessions on the same topic at the American Geophysical Union 2022 Conference #AGU22 in Chicago. All sessions are seeking abstracts. The submission deadline is August 3, 2022. Further details as well as links to the sessions can be found below.

AGU 2022 logo
Image Caption

IN019 — Leveraging Unsupervised Learning Techniques in Earth Science Observations

Muthukumaran will be convening this session on the use of unsupervised learning techniques in Earth science observations along with Iksha and Aaron as co-conveners. Owing to recent advances in remote sensing, we have access to large volumes of raw earth observation data. Earth scientists utilize the plethora of information to label features and create estimators using machine learning (ML). However, only a small fraction of available data is labeled which could be utilized by supervised ML algorithms.

This session invites speakers working with large scale unlabeled data in all modalities, including but not limited to geospatial rasters, text-based, and scalar datasets in the field of Earth science. Learn more about or submit an abstract to session IN019.

IN023 — Open Artificial Intelligence Utilizing Earth Observations for Advancement on Sustainable Development Goals

Aaron will be convening a session on the open science use of artificial intelligence with Earth observation data with Lillianne and Slesa co-convening. With more Earth observation (EO) data catalogs and artificial intelligence (AI) technologies available at a massive scale, data-driven insights can be rapidly discovered to support global policymaking and intervention for a healthy and safer society.

Open standards may include cloud-optimized formats, such as cloud-optimized GeoTIFFs, and the Spatial Temporal Asset Catalog (STAC) specification, as well as the available applications that utilize these formats such as the Machine Learning (ML) Model STAC extension and MLOps at production practices. These standardized data insight and discovery technologies and techniques need to be discussed more broadly, with thorough knowledge exchange between science and decision support communities.

This session seeks discussion on advancements of standard open data practices, AI/ML processes, application production pipelines, and end-user platforms in the communities for large-scale data insight discovery and decision-making support. Learn more about or submit an abstract to session IN023.

IN014 — Growing Opportunities for Multiparty Collaborations in Artificial Intelligence and Machine Learning for Science Research and Applications

Manil Maskey will be co-convening a session on multiparty collaborations in artificial intelligence and machine learning. The NASA Science Mission Directorate (SMD) seeks to expand the use of artificial intelligence and machine learning (AI/ML) for NASA science research and applications. Over the last two years, a cross-disciplinary NASA/SMD team has conducted a series of activities to this end; the past year has focused on developing benchmark training datasets and models in each of the NASA/SMD divisions (Planetary, Astrophysics, Heliophysics, Biological and Physical Sciences), with an emphasis on cross-divisional applications. This session will use short overviews of the benchmark training datasets and models to seed discussion among attendees on how to stimulate and expand AI/ML science research with other agencies, universities, companies, and nonprofits in order to cultivate sustainable partnerships and collaborations.

The session invites talks and posters on interdisciplinary and cross-organizational AI/ML science research, in particular with regard to (but by no means limited to) benchmark training datasets and models. The overall goal of enabling science research, while cultivating growing trust in evidence-based science, are in consonance with AGU’s strategic plan. Learn more about or submit an abstract to session IN014.

GC003 — Addressing environmental challenges and sustainable development through Earth science applications utilizing machine learning

Iksha Gurung will be co-convening a session focused on environmental challenges and sustainable development through Earth science applications utilizing machine learning. Applications of machine learning (ML), deep learning (DL), and artificial intelligence (AI) employing Earth observations have experienced a dramatic increase over the past decade. Examples of such applications to address ongoing environmental challenges and global initiatives include near real-time mapping of flooded areas, improved crop yield, type, and condition estimation, downscaled and locally calibrated air quality products, as well as enhanced land use and land cover methods.

This session calls for novel research and applications of ML, DL, and AI, in data-sparse regions, with the goal of addressing environmental development challenges while promoting open data access, cloud computing, capacity-building efforts, as well as data democracy. This session looks to bring together thought leaders, non-profits, and applied scientists to build cooperation and collaboration in leveraging cutting edge technology for driving a positive impact in developing regions and across the globe. Learn more about or submit an abstract to session GC003.

Details

Last Updated

Published