An official website of the United States government
Abstract We investigate coupled climate model initialized predictions of the Pacific Decadal Oscillation (PDO) prediction skill in the Community Earth System Model (CESM) Seasonal to Multi Year Large Ensemble (SMYLE). The PDO is predictable up to a year in advance in SMYLE; however, the predictability depends on verification month, with skill degrading most rapidly in boreal spring for all initializations. To examine the role of teleconnections from El Niño–Southern Oscillation (ENSO) in the prediction skill of the PDO, we use a multi‐linear regression model. The linear model shows that initial value persistence explains most of the PDO prediction skill in SMYLE. In addition, the PDO prediction skill's seasonal dependence is fully reproduced only when ENSO is included as a predictor. These results suggest that ENSO has a strong influence on the seasonality of PDO predictions.
more »
« less
This content will become publicly available on June 1, 2026
Long Term Predictability of Southern Ocean Surface Nutrients Using Explainable Neural Networks
Abstract The Southern Ocean is a region of high surface nutrient content, reflecting an inefficient biological carbon pump. The variability, predictability, and causes of changes in these nutrient levels on interannual to decadal time scales remain unclear. We employ a deep learning approach, specifically a Temporal Convolution Attention Neural Network (TCANN), to conduct multi‐year forecasting of surface based on oceanic physical drivers. The TCANN successfully replicates testing data with a prediction skill extending to at least 4 years with the GFDL‐ESM4‐driven model and 1 year with the observation‐driven model. To benchmark the results, we compare the prediction skill of TCANN with a simple persistence model and two regression methods, a linear regression and a ridge regression. The TCANN model was able to predict variability with a higher skill than persistence and the two regression methods indicating that non‐linearities present in the system become too high to predict inter‐annual variability with traditional regression methods. To enhance the interpretability of the predictions, we explore three explainable AI techniques: occlusion analysis, integrated gradients, and Gradient Shap. The outcomes suggest a crucial role played by salinity processes and buoyancy/potential density fluxes on the prediction of on annual time scales. The deep learning tools' ability to provide skillful forecasts well into the future presents a promising avenue for gaining insights into how the Southern Ocean's surface nutrients respond to climate change based on physical quantities.
more »
« less
- PAR ID:
- 10613931
- Publisher / Repository:
- AGU
- Date Published:
- Journal Name:
- Journal of Geophysical Research: Machine Learning and Computation
- Volume:
- 2
- Issue:
- 2
- ISSN:
- 2993-5210
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract An open question in the study of climate prediction is whether internal variability will continue to contribute to prediction skill in the coming decades, or whether predictable signals will be overwhelmed by rising temperatures driven by anthropogenic forcing. We design a neural network that is interpretable such that its predictions can be decomposed to examine the relative contributions of external forcing and internal variability to future regional sea surface temperature (SST) trend predictions in the near-term climate (2020–2050). We show that there is additional prediction skill to be garnered from internal variability in the Community Earth System Model version 2 Large Ensemble, even in a relatively high forcing future scenario. This predictability is especially apparent in the North Atlantic, North Pacific and Tropical Pacific Oceans as well as in the Southern Ocean. We further investigate how prediction skill covaries across the ocean and find three regions with distinct coherent prediction skill driven by internal variability. SST trend predictability is found to be associated with consistent patterns of decadal variability for the grid points within each region.more » « less
-
null (Ed.)Abstract Understanding the physical drivers of seasonal hydroclimatic variability and improving predictive skill remains a challenge with important socioeconomic and environmental implications for many regions around the world. Physics-based deterministic models show limited ability to predict precipitation as the lead time increases, due to imperfect representation of physical processes and incomplete knowledge of initial conditions. Similarly, statistical methods drawing upon established climate teleconnections have low prediction skill due to the complex nature of the climate system. Recently, promising data-driven approaches have been proposed, but they often suffer from overparameterization and overfitting due to the short observational record, and they often do not account for spatiotemporal dependencies among covariates (i.e., predictors such as sea surface temperatures). This study addresses these challenges via a predictive model based on a graph-guided regularizer that simultaneously promotes similarity of predictive weights for highly correlated covariates and enforces sparsity in the covariate domain. This approach both decreases the effective dimensionality of the problem and identifies the most predictive features without specifying them a priori. We use large ensemble simulations from a climate model to construct this regularizer, reducing the structural uncertainty in the estimation. We apply the learned model to predict winter precipitation in the southwestern United States using sea surface temperatures over the entire Pacific basin, and demonstrate its superiority compared to other regularization approaches and statistical models informed by known teleconnections. Our results highlight the potential to combine optimally the space–time structure of predictor variables learned from climate models with new graph-based regularizers to improve seasonal prediction.more » « less
-
Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.more » « less
-
Abstract The characteristics and dynamics of depth-average along-shelf currents at monthly and longer time scales are examined using 17 years of observations from the Martha’s Vineyard Coastal Observatory on the southern New England inner shelf. Monthly averages of the depth-averaged along-shelf current are almost always westward, with the largest interannual variability in winter. There is a consistent annual cycle with westward currents of 5 cm s −1 in summer decreasing to 1–2 cm s −1 in winter. Both the annual cycle and interannual variability in the depth-average along-shelf current are predominantly driven by the along-shelf wind stress. In the absence of wind forcing, there is a westward flow of ∼5 cm s −1 throughout the year. At monthly time scales, the depth-average along-shelf momentum balance is primarily between the wind stress, surface gravity wave–enhanced bottom stress, and an opposing pressure gradient that sets up along the southern New England shelf in response to the wind. Surface gravity wave enhancement of bottom stress is substantial over the inner shelf and is essential to accurately estimating the bottom stress variation across the inner shelf. Significance Statement Seventeen years of observations from the Martha’s Vineyard Coastal Observatory on the inner continental shelf of southern New England reveal that the depth-average along-shelf current is almost always westward and stronger in summer than in winter. Both the annual cycle and variations around the annual cycle are primarily driven by the along-shelf wind stress. The wind stress is opposed by a pressure gradient that sets up along the southern New England shelf and a surface gravity wave–enhanced bottom stress. The surface gravity wave enhancement of bottom stress is substantial in less than 30 m of water and is essential in determining the variation of the along-shelf current across the inner shelf.more » « less
