TECA: A Parallel Toolkit for Extreme Climate Analysis

Environmetrics, 2011

Extreme weather events such as thunderstorms and tornadoes are of great concern as these events pose a significant threat to life, property, and economic stability. Because of the difficulty of gathering data on extreme events, this paper proposes modeling the conditions for extreme weather through large-scale indicators. The advantage of using large-scale indicators is that climate models can be used to generate data whereas climate models cannot generate data on extreme events themselves. This paper focuses on comparing spatio-temporal models for reanalysis data of large-scale indicators for extreme weather observed across the continental United States and Mexico. Results indicate that rigorous treatment of spatial and temporal dynamics is necessary. The models find that the intensity of conditions for extreme weather is particularly high for the central United States and the intensity of these conditions is increasing over time but the amount of increase may not be practically significant.

Early warning systems of extreme events, such as floods, droughts, strong winds and wild fires as well as vector-borne diseases, at the global scale, are essential due to the combined threat of increased population settlement in vulnerable areas and potential increase in the intensity of extreme weather due to climate change. The European Centre for Medium-Range Weather Forecasts (ECMWF) has in the last year developed prototype early warning systems for floods, droughts, extreme winds, wild forest fires and malaria transmission. This paper assesses the performance of these systems. By providing a comprehensive skill assessment both on a global level and in selected regions, we aim to assess their suitability for eventual integration into decision-support frameworks.

In complex dynamic systems, accurate forecasting of extreme events, such as hurricanes, is a highly underdetermined, yet very important sustainability problem. While physics-based models deserve their own merits, they often provide unreliable predictions for variables highly related to extreme events. In this paper, we propose a new supervised machine learning problem, which we call a forecast oriented classification of spatiotemporal extreme events. We formulate three important real-world extreme event classification tasks, including seasonal forecasting of (a) tropical cyclones in Northern Hemisphere, (b) hurricanes and landfalling hurricanes in North Atlantic, and (c) North African rainfall. Corresponding predictor and predictand data sets are constructed. These data present unique characteristics and challenges that could potentially motivate future Artificial Intelligent and Data Mining research.

Geoscientific Model Development

Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning-when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create "ClimateNet"-an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in highresolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset Published by Copernicus Publications on behalf of the European Geosciences Union. Prabhat et al.: ClimateNet While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning. Prabhat et al.: ClimateNet Department of Energy, is gratefully acknowledged. The National Center for Atmospheric Research is sponsored by the National Science Foundation under cooperative agreement no. 1852977. Review statement. This paper was edited by David Topping and reviewed by Imme Ebert-Uphoff and one anonymous referee.

2000

Computing in Science & Engineering, 2000

Among the scenarios in the Decadal Survey Missions (DSM) report 1 (NRC, 2007), "Extreme Event Warning" is one of the top priority scenarios. It focuses on "discovering predictive relationships between meteorological and climatological events and less obvious precursor conditions from massive data sets." To achieve this, our approach is to deploy the "Coupled integrating existing NASA technologies such as the NASA multi-scale modeling system, the Goddard Cumulus Ensemble model, the finite-volume General Circulation Model, and concurrent visualization systems; (2) improving the parallel scalability of the coupled multi-scale modeling system to take full advantage of the next-generation peta-scale supercomputers; (3) significantly streamlining data flow for fast processing and 3D visualizations; and (4) developing visualization modules for the fusion of NASA satellite data. 2 In this paper, we will discuss the project progress and then discuss future tasks needed to support the DSM.

Focal Area(s) Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics-or knowledge-guided AI Science Challenge Impacts of climate are usually felt through extreme events such as droughts, floods, thunderstorms, windstorms, wildfires, and so on, that are intimately tied to the water cycle. Predicting the frequency and severity of extreme events under climate change remains a significant challenge; meanwhile, the mechanisms and impacts of these extremes are far from well understood. There are several major science challenges: (1) Lack of labelled extreme events data and missing standards in defining extremes; (2) Computational demand of high-resolution ensemble climate modeling; (3) Modeling the multiscale multi-physics hierarchical structure of compound extremes; (4) Lack of understanding of mechanisms of extreme events; (5) Large uncertainty in extreme events impacts on infrastructure; (6) Subjective assessment of weatherrelated risk from seasonal to multi-decadal time scales and lack of metrics for risk assessment and mitigation control. We identify the following high-priority research needs that artificial intelligence (AI), machine learning (ML) and deep learning (DL) may enable transformational breakthroughs, by integrating general purpose GPU, cloud, and edge computing as well as database management:

2007

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

Tracking and predicting extreme events in large-scale spatio-temporal climate data are long standing challenges in climate science. In this paper, we propose Convolutional LSTM (ConvLSTM)-based spatio-temporal models to track and predict hurricane trajectories from large-scale climate data; namely, pixel-level spatio-temporal history of tropical cyclones. To address the tracking problem, we model timesequential density maps of hurricane trajectories, enabling to capture not only the temporal dynamics but also spatial distribution of the trajectories. Furthermore, we introduce a new trajectory prediction approach as a problem of sequential forecasting from past to future hurricane density map sequences. Extensive experiment on actual 20 years record shows that our ConvLSTM-based tracking model significantly outperforms existing approaches, and that the proposed forecasting model achieves successful mapping from predicted density map to ground truth.

Discover Geosciences, 2024

There is a growing evidence-based concerns pointing to global increase of weather and climate extreme events (WCEE). What decides whether these hazards become a disaster is how the society and humanity prepare and responds to it. Although various researchers have step up efforts through scholarly contributions in response to WCEE. However, the task of utilizing the needed tools, selecting the most suitable approach, and choosing appropriate techniques for WCEE studies can be daunting for researchers. Moreover, the technicality and complexity associated with the wide array of models and methods present additional challenges when it comes to their practical implementationF in disaster applications. This review comprehensively explores four approaches in WCEE studies: statistical analysis, geospatial modeling, MCDA, and AI-based techniques. It evaluates their effectiveness in assessing impacts within WCEE and highlights AI's (ML and DL's) superior performance compared to other conventional methods in disaster-related studies.