Using Explainable AI and Transfer Learning to understand and predict the maintenance of Atlantic blocking with limited observational data

• URL: http://arxiv.org/abs/2404.08613v1
• Date: Fri, 12 Apr 2024 17:22:29 GMT
• Title: Using Explainable AI and Transfer Learning to understand and predict the maintenance of Atlantic blocking with limited observational data
• Authors: Huan Zhang, Justin Finkel, Dorian S. Abbot, Edwin P. Gerber, Jonathan Weare,
• Abstract summary: Blocking events are an important cause of extreme weather, especially long-lasting blocking events that trap weather systems in place. Explainable Artificial Intelligence are a class of data analysis methods that can help identify physical causes of prolonged blocking events. We train a convolutional neural network (CNN) and build a sparse predictive model for the persistence of Atlantic blocking.
• Score: 7.72430072816717
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Blocking events are an important cause of extreme weather, especially long-lasting blocking events that trap weather systems in place. The duration of blocking events is, however, underestimated in climate models. Explainable Artificial Intelligence are a class of data analysis methods that can help identify physical causes of prolonged blocking events and diagnose model deficiencies. We demonstrate this approach on an idealized quasigeostrophic model developed by Marshall and Molteni (1993). We train a convolutional neural network (CNN), and subsequently, build a sparse predictive model for the persistence of Atlantic blocking, conditioned on an initial high-pressure anomaly. Shapley Additive ExPlanation (SHAP) analysis reveals that high-pressure anomalies in the American Southeast and North Atlantic, separated by a trough over Atlantic Canada, contribute significantly to prediction of sustained blocking events in the Atlantic region. This agrees with previous work that identified precursors in the same regions via wave train analysis. When we apply the same CNN to blockings in the ERA5 atmospheric reanalysis, there is insufficient data to accurately predict persistent blocks. We partially overcome this limitation by pre-training the CNN on the plentiful data of the Marshall-Molteni model, and then using Transfer Learning to achieve better predictions than direct training. SHAP analysis before and after transfer learning allows a comparison between the predictive features in the reanalysis and the quasigeostrophic model, quantifying dynamical biases in the idealized model. This work demonstrates the potential for machine learning methods to extract meaningful precursors of extreme weather events and achieve better prediction using limited observational data.

Related papers

• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
  This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which Generalizes weather forecasts to Finer-grained Temporal scales. Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale. We introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
  arXiv  Detail & Related papers  (2024-05-22T16:21:02Z)
• Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet [10.773673764125439]
  This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates, filtering estimates can remain accurate in the long-time horizon.
  arXiv  Detail & Related papers  (2024-05-21T20:06:12Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce a training-free extreme value enhancement strategy named ExEnsemble, which increases the variance of pixel values and improves the forecast robustness. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data [18.321586950937647]
  We present an approach that harnesses real-time Unified Model (UM) data, sidestepping the limitations of reanalysis data. Our model provides predictions at 6-hour intervals for up to 72 hours in advance and outperforms both state-of-the-art data-driven methods and numerical weather prediction models.
  arXiv  Detail & Related papers  (2024-01-28T18:28:33Z)
• Residual Diffusion Modeling for Km-scale Atmospheric Downscaling [51.061954281398116]
  A cost-effective downscaling model is trained from a high-resolution 2-km weather model over Taiwan. textitCorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes. Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to-km-scales machine learning weather predictions.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Spatio-temporal neural structural causal models for bike flow prediction [2.991894112851257]
  The fundamental issue of managing bike-sharing systems is bike flow prediction. Recent methods over-emphasize the contextual conditions on the transportation system. We propose a Spatiotemporal-temporal Structure Causal Model.
  arXiv  Detail & Related papers  (2023-01-19T01:39:21Z)
• Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting [22.434845478979604]
  We propose a mechanism for mining causal structures from continuous-time models. We train models to capture the causal structure by enforcing sparsity in the weights of the input layers of the dynamics models. We apply our method to a real-world problem, namely tsunami forecasting, where the exact causal-structures are difficult to characterize.
  arXiv  Detail & Related papers  (2022-10-10T18:53:13Z)
• Long-term hail risk assessment with deep neural networks [0.0]
  Hail risk assessment is necessary to estimate and reduce damage to crops, orchards, and infrastructure. There are no machine learning models for data-driven forecasting of changes in hail frequency for a given area. This study compares two approaches and introduces a model suitable for the task of forecasting changes in hail frequency for ongoing decades.
  arXiv  Detail & Related papers  (2022-08-31T18:24:39Z)
• An advanced spatio-temporal convolutional recurrent neural network for storm surge predictions [73.4962254843935]
  We study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history. This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations.
  arXiv  Detail & Related papers  (2022-04-18T23:42:18Z)
• Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
  We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
  arXiv  Detail & Related papers  (2022-02-10T11:37:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.