Climate Informatics 2022 – Agenda

Save the date banner for the Climate Informatics 2022 conference


  • Hackathon (hybrid): 9 May (afternoon) – 10 May (morning)
  • Main conference: 10 May (afternoon) – 13 May (morning)

9 May 2022 (Monday)

Time Talk Speaker / Format
12:00 – 13:00 Registration
13:00 – 17:00 Hack-a-thon session (hybrid) Hybrid

10 May 2022 (Tuesday)

Time Talk Speaker / Format
09:00 – 12:00 Registration & Hack-a-thon session (hybrid) Hybrid
12:00 – 13:00 Registration & Lunch break
13:00 – 13:10 Welcome & Conference Logistics
13:10 – 14:10 Data Science and Interdisciplinary Collaboration (Invited) Alyson Wilson
14:10 – 14:40 Coffee break
14:40 – 15:00 Towards data assimilation of ship induced aerosol-cloud interactions Lekha Patel
15:00 – 15:20 Exploring cirrus cloud microphysical properties using explainable machine learning Kai Jeggle
15:20 – 15:40 Stochastic Parameterization of Column Physics using Generative Adversarial Networks Balasubramanya T Nadiga
15:40 – 16:00 Deep prior in variational assimilation to estimate ocean circulation without explicit regularization Arthur Filoche
16:00 – 17:00 Virtual poster session 1 Virtual

11 May 2022 (Wednesday)

Time Talk Speaker / Format
09:00 – 09:10 Welcome remarks for Day 2
09:10 – 10:10 Challenges in machine learning for climate extremes (Invited) Brian White
10:10 – 10:40 Coffee break
10:40 – 11:00 ResDeepD: A Residual Super-Resolution Network for Deep Downscaling of Daily Precipitation over India Sumanta Chandra Mishra Sharma
11:00 – 11:20 Week-ahead Solar Irradiance Forecasting with Deep Sequence Learning Saumya Sinha
11:20 – 11:40 SWIFT-AI: Implicit Neural Representations for Stratospheric Ozone Chemistry Helge Mohn
11:40 – 12:00 Lightning: An Essential Climate Variable Steven J. Goodman
12:00 – 13:00 Lunch break
13:00 – 13:20 A Dependent Multi-model Approach to Climate Prediction with Gaussian Processes Marten Thompson
13:20 – 13:40 Physics-Informed Learning of Aerosol Microphysics Paula Harder
13:40 – 14:00 Detection and attribution of climate change: a Deep Learning and Variational approach Constantin Bône
14:00 – 14:20 Learning to construct Probabilistic Multi-Model Ensemble for Seasonal Predictions Nachiketa Acharya
14:20 – 15:00 Coffee break
15:00 – 16:00 Panel Discussion: Cloud Computing in Advancing Climate Informatics Panelists: Annie Burgess, ESIP; Maureen Taylor, NOAA; Jonathan Brannock, NCICS; Brian White, UNC-Chapel Hill
16:00 – 17:00 In-person Poster & Networking Reception In-person

12 May 2022 (Thursday)

Time Talk Speaker / Format
08:30 – 09:30 Climate-Invariant, Causally Consistent Neural Networks as Robust Emulators of Subgrid Processes across Climates (Invited) Tom Beucler (Virtual)
09:30 – 10:00 Coffee break
10:00 – 10:20 Constructing a graph metadatabase for more effective search and discovery of datasets Myranda R Uselton
10:20 – 10:40 An energy conserving method for simulating heat transfer in permafrost with hybrid modeling Brian Groenke
10:40 – 11:00 A comparison of explainable AI solutions for a climate change prediction task Philine L Bommer
11:00 – 11:20 Modeling Stratospheric Polar Vortex Variation and Identifying Vortex Extremes Using Explainable Neural Networks Zheng Wu
11:20 – 12:20 Virtual poster session 2 Virtual
12:20 – 13:25 (revised time) Lunch break
13:25 – 14:25 (revised time) Asking how the Southern Ocean responds to global heating and understanding why the answer emerged (Invited) Maike Sonnewald
14:25 – 14:40 (revised time) Coffee Break
14:40 – 15:00 Learning the spatio-temporal relationship between wind and significant wave height using deep learning Said Obakrim
15:00 – 15:20 A Gaussian Process State-space Model for Sea Surface Temperature Reconstruction from the Alkenone Paleotemperature Proxy Taehee Lee
15:20 – 15:40 SSH Super-Resolution using high resolution SST with a Subpixel Convolutional Residual Network Théo Archambault
15:40 – 16:00 Forecasting Marine Heatwaves using Machine Learning Ayush Prasad
16:00 – 17:00 Networking session

13 May 2022 (Friday)

Time Talk Speaker
09:00 – 10:00 Virtual Poster Session 3 Virtual
10:00 – 10:20 Coffee break
10:20 – 10:40 Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence Ashesh K Chattopadhyay
10:40 – 11:00 Neural embedding for closure models Said Ouala
11:00 – 12:00 Building Digital Twins of the Earth for NVIDIA’s E-2 Initiative (Invited) David M.  Hall (Virtual)
12:00 – 12:30 Closing session
12:30 Attendee depart

Virtual Poster Session 1

ID Presenter Title
7 Laura McGee Cloud-Free Reconstruction of Physical and Biochemical Variables Using a Machine Learning Method
15 Ivan Sudakow Machine Learning-Based Emulators of Sea Ice
19 Kalai Ramea AiBEDO: A hybrid AI model to capture the effects of cloud properties on global circulation and regional climate patterns
30 Katherine Goode Feature Importance with Deep Echo State Models for Long-Term Climate Forecasting
38 Brook Russell Modeling the Relationship Between Vertical Temperature Profiles and Acute Surface-level Ozone Events in the US Southwest by Spatially Smoothing a Functional Quantile Regression Estimator
39 Maggie Davis Standardized Metadata for Aerosol, and Meteorological Data Knowledge Management: A Brazil example drawing on the USDOE ARM program
51 Erich Seamon Random Forest Climatic Modeling of Agricultural Insurance Loss Across the Inland Pacific Northwest Region of the United States
55 Abdou-Razakou I. KIRIBOU Greenhouse Gas Emission In Road Transport And Urban Mobility In Ouagadougou: Evaluation And Modelling Of Its Effect On Air Pollution
57 Ronald Leeper An Evaluation of Machine Learning Techniques to Quality Control Soil Moisture Observations for U.S. Climate Reference Network
58 Naomi Goldenson Finding a subset of a GCM initial-condition large ensemble to maximize regional variance for downscaling
1 Kenza Tazi Improving the characterisation and prediction of Himalayan precipitation using Multi-Fidelity Deep Gaussian Processes

Virtual Poster Session 2

ID Presenter Title
20 Said Ouala End-To-End Kalman Filter In A High Dimensional Linear Embedding Of The Observations
3 Lukas Brunner Classifying climate models based on temperature patterns from a single day using a convolutional neural network
6 Arsene Nounangnon AIZANSI Monthly Rainfall Prediction Using Artificial Neural Network (Case Study: Republic of Benin)
11 Jose González-Abad Intercomparison of Deep Learning Techniques for Statistical Downscaling over North America
13 Cédric S Mesnage Desert Greening, a Silver Bullet?
14 Vibolroth Sambath Unsupervised domain adaptation for GPM satellite constellation using CycleGAN
21 Paula Harder Physics-Informed Learning of Aerosol Microphysics
27 George Miloshevich Predicting probability of heat waves using convolutional neural network
41 John M Nicklas CESM1 Simulations Show Reflective Particles Can Cool Earth
44 Eva Murphy Joint modeling of wind speed and wind direction through a conditional approach
45 Nicolas Lafon Learning Variational DA models and solvers with uncertainty quantification

Virtual Poster Session 3

ID Presenter Title
54 Carlos Alberto Gomez Gonzalez DL4DS – Deep Learning for empirical DownScaling
16 Deepayan Chakraborty Quantifying the Contributions of Teleconnections on Indian Summer Monsoon using Shapley Values
17 Abhijit Mukherjee Predicting Cyclone Landfall using Mutual Information and Dilated RNN
22 Peniel J. Y. Adounkpe Optimization of a Network of Hydrologic Stations: Case of the Sota Basin in Benin
24 Aurélien Colin Decreasing the rain-induced wind speed overestimation on SAR observations
26 Yeji Choi d-IMERG: A spatiotemporal benchmark dataset for precipitation forecasting
35 Catharina Elisabeth Graafland Using probabilistic network models to assess similarity of global climate models based on their spatial dependency structure
43 Manmeet Singh Deep learning to downscale urban precipitation for smart city applications
49 Aahelee Sarker A machine learning technique for Developing high-resolution precipitation dataset Over High Mountain zone of Bangladesh
59 Jacquelyn Shelton Towards generating stationary realizations of simulated Antarctic ice shelf melt rates from limited model output