Search

Previous research has demonstrated that specific states of the climate system can lead to enhanced subseasonal predictability (i.e., state-dependent predictability). However, biases in Earth system models can affect the representation of these states and their subsequent evolution. Here, we present a machine learning framework to identify state-dependent biases in Earth system models. In particular, we investigate the utility of transfer learning with explainable neural networks to identify tropical state-dependent biases in historical simulations of the Energy Exascale Earth System Model version 2 (E3SMv2) relevant for midlatitude subseasonal predictability. Using a perfect model framework, we find transfer learning may require substantially more data than provided by present-day reanalysis datasets to update neural network weights, imparting a cautionary tale for future transfer learning approaches focused on subseasonal modes of variability., Comment: This work has been submitted for publication in Artificial Intelligence for the Earth Systems (AIES). Copyright in this work may be transferred without further notice

It is largely understood that subseasonal-to-seasonal (S2S) predictability arises from the atmospheric initial state during early lead times, the land during intermediate lead times, and the ocean during later lead times. We examine whether this hypothesis holds for the S2S prediction of weather regimes by training a set of XGBoost models to predict weekly weather regimes over North America at 1-to-8-week lead times. Each model used a different predictor from one of the three considered Earth system components (atmosphere, ocean, or land) sourced from reanalyses. Three additional models were trained using land-, ocean-, or atmosphere-only predictors to capture process interactions and leverage multiple signals within the respective Earth system component. We found that each Earth system component performed more skillfully at different forecast horizons, with sensitivity to seasonality and observed (i.e., ground truth) weather regime. S2S predictability from the atmosphere was higher during winter, from the ocean during summer, and from land during spring and summer. Ocean heat content was the best predictor for most seasons and weather regimes beyond week 2, highlighting the importance of sub-surface ocean conditions for S2S predictability. Soil temperature and water content were also important predictors. Climate patterns were associated with changes in the likelihood of occurrence for specific weather regimes, including the El Ni\~no-Southern Oscillation, Madden Julian Oscillation, North Pacific Gyre, and Indian Ocean dipole. This study quantifies predictability from some previously identified processes on the large-scale atmospheric circulation and gives insight into new sources for future study., Comment: This work has been submitted for publication to Artificial Intelligence for the Earth Systems (AIES). Copyright in this work may be transferred without further notice

Although generative artificial intelligence (AI) is not new, recent technological breakthroughs have transformed its capabilities across many domains. These changes necessitate new attention from educators and specialized training within the atmospheric sciences and related fields. Enabling students to use generative AI effectively, responsibly, and ethically is critically important for their academic and professional preparation. Educators can also use generative AI to create engaging classroom activities, such as active learning modules and games, but must be aware of potential pitfalls and biases. There are also ethical implications in using tools that lack transparency, as well as equity concerns for students who lack access to more sophisticated paid versions of generative AI tools. This article is written for students and educators alike, particularly those who want to learn more about generative AI in education, including use cases, ethical concerns, and a brief history of its emergence. Sample user prompts are also provided across numerous applications in education and the atmospheric and related sciences. While we don't have solutions for some broader ethical concerns surrounding the use of generative AI in education, our goal is to start a conversation that could galvanize the education community around shared goals and values., Comment: This Work has been submitted to the Bulletin of the American Meteorological Society. Copyright in this Work may be transferred without further notice; 14 pages, 2 figures, 2 tables

Estimating and disentangling epistemic uncertainty (uncertainty that can be reduced with more training data) and aleatoric uncertainty (uncertainty that is inherent to the task at hand) is critically important when applying machine learning (ML) to high-stakes applications such as medical imaging and weather forecasting. Conditional diffusion models' breakthrough ability to accurately and efficiently sample from the posterior distribution of a dataset now makes uncertainty estimation conceptually straightforward: One need only train and sample from a large ensemble of diffusion models. Unfortunately, training such an ensemble becomes computationally intractable as the complexity of the model architecture grows. In this work we introduce a new approach to ensembling, hyper-diffusion, which allows one to accurately estimate epistemic and aleatoric uncertainty with a single model. Unlike existing Monte Carlo dropout based single-model ensembling methods, hyper-diffusion offers the same prediction accuracy as multi-model ensembles. We validate our approach on two distinct tasks: x-ray computed tomography (CT) reconstruction and weather temperature forecasting., Comment: 10 pages, 7 figures

Robust quantification of predictive uncertainty is critical for understanding factors that drive weather and climate outcomes. Ensembles provide predictive uncertainty estimates and can be decomposed physically, but both physics and machine learning ensembles are computationally expensive. Parametric deep learning can estimate uncertainty with one model by predicting the parameters of a probability distribution but do not account for epistemic uncertainty.. Evidential deep learning, a technique that extends parametric deep learning to higher-order distributions, can account for both aleatoric and epistemic uncertainty with one model. This study compares the uncertainty derived from evidential neural networks to those obtained from ensembles. Through applications of classification of winter precipitation type and regression of surface layer fluxes, we show evidential deep learning models attaining predictive accuracy rivaling standard methods, while robustly quantifying both sources of uncertainty. We evaluate the uncertainty in terms of how well the predictions are calibrated and how well the uncertainty correlates with prediction error. Analyses of uncertainty in the context of the inputs reveal sensitivities to underlying meteorological processes, facilitating interpretation of the models. The conceptual simplicity, interpretability, and computational efficiency of evidential neural networks make them highly extensible, offering a promising approach for reliable and practical uncertainty quantification in Earth system science modeling. In order to encourage broader adoption of evidential deep learning in Earth System Science, we have developed a new Python package, MILES-GUESS (https://github.com/ai2es/miles-guess), that enables users to train and evaluate both evidential and ensemble deep learning.