IMPACT team members John Mandel, Muthukumaran Ramasubramanian, Iksha Gurung, and Slesa Adhikari will be convening sessions at the American Geophysical Union (AGU) 2023 conference in San Francisco, CA. All four sessions are seeking relevant abstract submissions. The AGU abstract due date is August 2, 2023 at 10:59 CST. Further details, as well as links to the sessions, are shown below.
IN007: Advances and Opportunities in Multi-Source Data Harmonization in Remote Sensing
Earth observation data users often require information from multiple datasets and combine them on individual bases. Advances like multisensor data harmonization efforts between satellites (NASA’s Harmonized Landsat Sentinel-2 (HLS) and ESA’s Sen2like) offer advantages such as increased revisit times that benefit monitoring land cover changes, disaster response, and agricultural applications. Here, “harmonization” refers to normalizing the common characteristics of different datasets to an analysis-ready standard so they can be used interchangeably, allowing users to merge information from those datasets without needing to create individual algorithms for each. Analysis-ready data (ARD) products reduce barriers to entry for new users by simplifying access and limiting the number of required dependencies. Furthermore, providing harmonized ARD reduces elaborate processing requirements, facilitates collaboration across user communities, and promotes open science.
We invite presentations that demonstrate increased access to scientific data through harmonization and highlight future challenges and novel opportunities.
Over the years, geospatial technologies have amassed large volumes of raw earth observation and modeling data in several formats. This includes image and text datasets. However, limited human-hours and the sheer volume of data result in only a fraction of the datasets being labeled which can be utilized by supervised machine learning models. This presents opportunities for representation learning and foundation modeling to extract meaningful information from unlabeled geospatial data using unsupervised learning techniques. With this session, we aim to bring together researchers to share their work on a wide range of topics, including:
The United States Environmental Protection Agency (EPA) defines environmental justice as the fair treatment and meaningful involvement of all people regardless of race, color, national origin, or income with respect to the development, implementation, and enforcement of environmental laws, regulations, and policies. Artificial intelligence (AI) and machine learning (ML) algorithms in conjunction with proper datasets can be leveraged to analyze and understand the state of environmental justice. We intend to highlight works themed around the following aspects of using machine learning for environmental justice applications:
IN036: Next Generation of Advanced Visualization in Earth Science
Visualization plays a pivotal role in Earth Science by providing insights into complex data and information. In today’s era of technological innovation, immersive technologies, large-scale displays, and cloud-native visualization tools are transforming the landscape of data visualization. Researchers now have the capability to create sophisticated, interactive visualizations that enhance our understanding of the Earth and its complex systems, and make science more accessible and engaging to broader audiences.
This session aims to bring together experts in the field of Earth Science data and information visualization to highlight the state-of-the-art advancements in visualization approaches, modalities, hardware, and software. The session serves as a platform for exchanging ideas and fostering collaboration on cutting-edge visualizations.
We will explore these topics: