The deadline to submit a session, town hall, or pre-conference workshop proposal for AGU25 has passed. Please search for and review proposed sessions below. Please note this site is frozen as of 4/29/25 and will not reflect any changes to proposals made after this date.


Conveners will be contacted by the AGU25 Program Committee with any requests for mergers or edits to proposals. Conveners will be notified of the acceptance of their proposal in mid-June.


Abstract submissions will also open in mid-June and the deadline for abstract submissions is 30 July, 2025.


Please visit the AGU25 website for more information or please contact AGU with any questions.

Session Proposal: Applying Machine Learning to better reconstruct and understand paleoclimates and paleoecology (AGU25)

PP005
Applying Machine Learning to better reconstruct and understand paleoclimates and paleoecology

Session ID#: 248990

Session Description:
Machine Learning (ML) offers exciting techniques for addressing long-standing problems in the fields of paleoclimates and paleoecology, through improving computational efficiency and accuracy, and enabling the management of large, complex datasets. In particular, ML techniques are capable of handling non-linear relationships and high-dimensional data, allowing for a more sophisticated analysis than using traditional approaches. We aim to bring together those from the modelling and proxy communities, along with experts in machine learning, to showcase existing work applying ML to paleoclimate/ecology problems. Topics include, but are not limited to:Emulators as surrogate models for ESMs to enable efficient paleoclimate/ecology simulations; Efficient model-tuning to enhance the performance in simulating paleoclimate/ecology;New model parameterisations developed through ML; Improvements in management and stratigraphic calibration of large proxy dataset; Advances in proxy calibration and quantifying uncertainties; Data assimilation and field reconstruction;Proxy system modelling;Downscaling model results for model-data comparisons
Co-Sponsor(s):
  • B - Biogeosciences
Index Terms:

4928 Global climate models [PALEOCEANOGRAPHY]
4950 Paleoecology [PALEOCEANOGRAPHY]
4999 General or miscellaneous [PALEOCEANOGRAPHY]
Primary Convener:  Dan John Lunt, University of Bristol, Bristol, BS8, United Kingdom
Conveners:  Junxuan Fan, Nanjing University, Nanjing, China and Xin Ren, University of Bristol, Bristol, BS8, United Kingdom
Student/Early Career Convener:  Tianyi Chu, University of Bristol, Bristol, United Kingdom
 
Machine Learning-Based Lithological Distribution Modeling for Evaluating Paleoclimate GCMs (1849266)
Linlin Chen, University of Bristol, Bristol, BS8, United Kingdom, Paul J Valdes, University of Bristol, Bristol, United Kingdom and Alexander Farnsworth, University of Bristol, BRIDGE, School of Geographical Sciences, Bristol, United Kingdom
 
Learning from the Past: Climate Model Emulators and Paleo Constraints for Efficient Climate Simulation (Invited) (1857702)
Duncan Watson-Parris, University of California San Diego, La Jolla, CA, United States
 
Extracting Paleoweather from Paleoclimate: Deep Learning Approaches to Reconstructions of Atmospheric Blocking and Related extremes. (Invited) (1857712)
Christina Karamperidou, University of Hawai’i at Mānoa, Department of Atmospheric Sciences, Honolulu, United States
 
New insights into reconstructing past wildfires: calibrating fire biomarker proxies in marine sediments using random forest models (1862750)
Nicholas A O'Mara, Yale University, Yale Institute for Biospheric Studies, New Haven, CT, United States, Peter deMenocal, Woods Hole Oceanographic Institution, Woods Hole, United States, Kevin T Uno, Harvard University, Human and Evolutionary Biology, Cambridge, MA, United States, Jessica E Tierney, University of Arizona, Department of Geosciences, Tucson, AZ, United States, Gisela Winckler, Columbia University, Department of Earth and Environmental Sciences, New York, United States, Jennifer Marlon, Yale University, School of the Environment, New Haven, United States and Pratigya J Polissar, University of California Santa Cruz, Ocean Sciences, Santa Cruz, United States
 
High-Resolution Paleoclimate Fields via Diffusion-Based Downscaling (1880459)
Deborah Khider, University of Southern California, Information Sciences Institute, Los Angeles, CA, United States and Armen Kemanian, Pennsylvania State University Main Campus, University Park, PA, United States
 
Detecting Anomalous Grains in Scientific Ocean Drilling Legacy Cores – Potential and Pitfalls of a New Machine Learning Based Detection and Classification Approach (1911676)
Gerald Auer1, David De Vleeschouwer2, Anna Joy Drury3, Arisa Seki4, Yusuke Kubo5, Minoru Ikehara6, Junichiro Kuroda7, Or Bialik8, Beth Anne Christensen9, Jing Lyu10, Theresa Nohl11, Tamara Hechemer1, Natsumi Okutsu12, An-Sheng Lee13, Werner E. Piller1, Xabier Puentes-Jorge1 and Jumpei Yoshioka14, (1)University of Graz, Department of Earth Sciences - NAWI Graz Geocenter, Graz, Austria, (2)University of Münster, Institute of Geology and Paleontology, Münster, Germany, (3)University of Leicester, Department of Geography, Geology, and the Environment, Leicester, United Kingdom, (4)Fukada Geological Institute, Tokyo, Japan, (5)JAMSTEC, Kochi Core Center, Nankoku, Japan, (6)Kochi University, Center of Advanced Marine Core Research, Kochi, Japan, (7)JAMSTEC, Yokosuka, Japan, (8)University of Münster, Münster, Germany, (9)Adelphi University, Garden City, NJ, United States, (10)University of Münster, Institute of Geology and Palaeontology, Münster, Germany, (11)University of Vienna, Institute of Palaeontology, Vienna, Austria, (12)Atmosphere and Ocean Research Institute University of Tokyo, Tokyo, Japan, (13)Kochi University, Marine Core Research Institute, Kochi, Japan, (14)NIPR National Institute of Polar Research, Research Organization of Information and Systems, Tokyo, Japan
 
Automated Robot Prototype with Probabilistic “Decision-making” for Foraminifera Identification and Selection for Geochemical Analysis (1926612)
Weihao Zeng1, Weimin Si2, Taehee Lee3, Stephanie Long1, Andong Hu4, Arjun Dasari5 and Timothy Herbert2, (1)Brown University, School of Engineering, Providence, United States, (2)Brown University, Department of Earth, Environmental, and Planetary Sciences, Providence, RI, United States, (3)Brown University, Department of Earth, Environmental, and Planetary Sciences, Providence, United States, (4)University of Colorado, CIRES, Boulder, United States, (5)The Wheeler School, Providence, United States
 
OneStratigraphy Database: Enabling curation of large proxy datasets and precise calibration to geological timescales (1964923)
Junxuan Fan, Jiao Yang, Xiaoli Ma, Yukun Shi and Xudong Hou, Nanjing University, School of Earth Sciences and Engineering, Nanjing, China
 
Applying machine learning to unravel state-dependent vegetation feedback in deep-time climate simulations (1973513)
Tianyi Chu1, Dan John Lunt2 and Junxuan Fan1, (1)Nanjing University, School of Earth Sciences and Engineering, Nanjing, China, (2)University of Bristol, Bristol, BS8, United Kingdom
 
Ordovician Latitudinal Temperature Gradient Evolution Revealed by Calibrated Isotopic Proxy Records (1985208)
Xiaoli Ma and Junxuan Fan, Nanjing University, School of Earth Sciences and Engineering, Nanjing, China
See more of: Paleoceanography and Paleoclimatology
<< Previous Session Proposal | Next Session Proposal >>