Down To Earth: A podcast for Geoscientists by Geoscientist

After covering many of the exciting possibilities and potential challenges of AI in Earth Observation (EO), the question still remains: Is AI in EO going to be more of a help, or a hindrance? The answer lies in whether or not we can use AI ethically. In this episode, we speak with Dr. Caroline Gevaert, Associate Professor at University of Twente and expert in geospatial technologies and artificial intelligence for sustainable development in Low and Lower Middle Income countries. From the potential biases in AI-driven geoscience research to the ownership and privacy concerns surrounding geospatial data, we shed light on the complex questions, challenges and potential solutions that arise when human decision-making meets machine learning.

Beyond the challenges inherent in using AI in earth observation, there are some incredibly valuable applications for tackling real-world problems. In particular, Geospatial Foundation Models are leading us to unique insights, discoveries, and solutions to real-world problems that we wouldn’t otherwise uncover. How do these models help us do this, and what challenges are they currently being applied to? We speak to Dr. Juan Bernabé-Moreno, the Director of IBM Research Europe, and Dr. Rahul Ramachandran, Project Manager and Senior Research Scientist at NASA to find out!

Now that we have the basics of AI use in the geosciences, the question becomes, how do we use and maximize these tools? Enter the supercomputer! With Dr. Dalton Lunga, Senior R&D Scientist and GeoAI Group Leader at Oak Ridge National Laboratory, we explore the cutting-edge world of supercomputers and their role in training large GeoAI models. Dr. Lunga shares insights on how supercomputers like Summit and Frontier are revolutionizing the field of geospatial AI, enabling faster and more accurate processing of vast amounts of data. He also discusses the challenges and opportunities in training large GeoAI models, highlighting the potential for breakthroughs in climate modeling, natural disaster response, and environmental monitoring. Through the conversation, we unravel the pivotal importance of these tools for unlocking new frontiers in earth observation and our understanding of the planet's dynamic processes.

We’ve heard repeatedly that reliable, validated training data is one of the most important, and also most challenging components of ensuring AI models provide accurate outputs. How are we overcoming this challenge? Through Data-centric AI! Data-centric AI emphasizes the value of good data rather than model. So what are some data-centric AI approaches? We speak to Dr. Manil Maskey, Data Science and Innovation Lead, NASA Office of Chief Science Data Officer and Dr. Rajat Shinde, Computer Scientist Level IV, NASA IMPACT, University of Alabama in Huntsville to find out!

Imagine a world where scientists can predict natural disasters before they strike, where we can monitor the health of our planet in real-time, and where we can uncover the secrets of Earth's hidden resources. Welcome to the future of geoscience, where AI is revolutionizing our understanding of the planet! In this season of Down to Earth, we’re exploring the uncharted territories of AI in geoscience, from the groundbreaking capabilities of supercomputing to the revelatory insights of Geospatial Foundation Models. As AI challenges and reshapes our understanding of Earth's systems, it also presents some complex, and sometimes unexpected, cultural and social implications. Through deep conversations with visionaries, innovators, and researchers, we'll explore the promises and pitfalls of this technological revolution and we’ll dare to ask the ultimate question: Will AI unlock the secrets of our planet, or, will it lead us down a precarious rabbit hole, we have yet to imagine? Find out this fall on season 6 of Down to Earth: A Podcast FOR Geoscientists BY Geoscientists!

According to the UNU Institute for Water, Environment and Health, water-related disasters (WRDs), including floods and droughts, account for 90% of natural disasters. These disasters result in significant loss of life each year, not to mention the billions spent on managing and rebuilding afterwards. As the global water crisis continues to grow, so too does our need for tools, techniques, and policy that will help us more effectively predict, respond to, and prevent WRDs. In this episode, we speak to Dr. Hamid Mehmood, Economic Affairs Officer with United Nations ESCAP to find out how we can address WRDs with technology.

As far back as 2014, Dr. Eric Rignot, specialist in glaciology, has been informing us that some of our glaciers are melting faster than we can save them. Yet, this knowledgeable and passionate scientist continues to advocate for hope. In this episode we’ll dive deep into the meltwater to not only understand glacier behaviour, but how we can proactively deal with the results.

Whenever we think of greenhouse gases, carbon dioxide is top of mind. But a more nefarious gas is gaining notoriety: Methane. Not just restricted to agricultural emissions, methane is also found in the Earth’s permafrost, which is melting at an increased rate due to climate change. It’s a vicious cycle that we seriously need to interrupt. So in this episode, we delve into the critical issue of permafrost thaw and its implications for methane release with Dr. Annett Bartsch. Dr. Bartsch, a leading researcher of permafrost, shares the satellite observations and modeling techniques used to track permafrost thaw and highlights the consequences of methane emissions on our climate system.

The Global Carbon Cycle refers to the continuous flow of carbon from the land and water, through the atmosphere and living organisms. Within the cycle there are carbon sinks and carbon emitters. As one of the largest reservoirs of carbon on Earth, forests play a huge role in the global carbon cycle. But how do we know? In this episode, we speak to geoscientist Dr. Ralph Dubayah to explore the applications of GEDI and NISAR in assessing carbon capture in Earth's forests. Dr. Dubayah sheds light on the incredible capabilities of GEDI, a lidar-based instrument on the International Space Station, which measures forest structure in three dimensions, providing precise estimates of biomass and carbon content. He also shares insights into NISAR, a forthcoming joint NASA-ISRO mission that uses synthetic aperture radar to track surface deformation and offer a comprehensive understanding of forest biomass changes. Throughout the episode, Dr. Dubayah showcases exciting discoveries made possible by these technologies, highlighting their potential for revolutionizing our understanding of forest carbon capture and its crucial role in mitigating climate change.

The open science movement is an experiment, but it’s an experiment that has a lot of merit when it comes to its vision of equitable transparency, accessibility and collaboration for better science, and a better world. So how do we begin to transition our own practices towards those of open science? In this episode, we speak with Julia Stewart Lowndes, Founding Director of Openscapes, and her collaborator, Erin Robinson, CEO and Co-Founder of Metadata Game Changers, about Openscapes, an organization that engages, empowers, and amplifies researchers with open habits and mindsets for data-intensive science.

Part of the thinking behind the open science movement is that, if science is open, more people will trust the scientific process. But, as previous guests have pointed out, opening up science requires more than just the act of making it open. It also requires letting people know the science is out there, and ensuring it is findable, accessible, and reproducible! In today's episode, we speak with Professor Christopher Jackson, Director of Sustainable Geoscience at Jacobs, Visiting Professor of Basin Analysis at Imperial College, and regular face on the BBC, about how we can use science communication to increase the general public's understanding of science. We also talk to Dr. Sara El-Gebali, Project leader at SciLifeLab-Data Centre and co-founder of FAIRPoints, about applying the FAIR principles to ensure that the science we communicate about is ethical and findable!

It’s all well and good to have open source software, but if end-users have no clue how to operate it, open data becomes useless. That’s why Open Education is another important component of open science. In this episode, we speak with Dr. Leah Wasser, Executive Director of pyOpenSci, who developed a publicly accessible curriculum to teach python and R to anyone who wants to learn!

Open science and open data easily go hand-in-hand, but one area of open science that’s often forgotten is open source. What is open source and how does it allow us to actually use open data? In this episode, we speak to Yuvi Panda, Co-Founder of 2i2C – a nonprofit devoted to developing, operating, and supporting infrastructure for interactive computing – about how we can make tools work for the open science movement.