An official website of the United States government
Geospatio-temporal data are pervasive across numerous application domains.These rich datasets can be harnessed to predict extreme events such as disease outbreaks, flooding, crime spikes, etc.However, since the extreme events are rare, predicting them is a hard problem. Statistical methods based on extreme value theory provide a systematic way for modeling the distribution of extreme values. In particular, the generalized Pareto distribution (GPD) is useful for modeling the distribution of excess values above a certain threshold. However, applying such methods to large-scale geospatio-temporal data is a challenge due to the difficulty in capturing the complex spatial relationships between extreme events at multiple locations. This paper presents a deep learning framework for long-term prediction of the distribution of extreme values at different locations. We highlight its computational challenges and present a novel framework that combines convolutional neural networks with deep set and GPD. We demonstrate the effectiveness of our approach on a real-world dataset for modeling extreme climate events.
more »
« less
Flexible and Fast Spatial Return Level Estimation Via a Spatially Fused Penalty
Spatial extremes are common for climate data as the observations are usually referenced by geographic locations and dependent when they are nearby. An important goal of extremes modeling is to estimate the T-year return level. Among the methods suitable for modeling spatial extremes, perhaps the simplest and fastest approach is the spatial generalized extreme value (GEV) distribution and the spatial generalized Pareto distribution (GPD) that assume marginal independence and only account for dependence through the parameters. Despite the simplicity, simulations have shown that return level estimation using the spatial GEV and spatial GPD still provides satisfactory results compared to max-stable processes, which are asymptotically justified models capable of representing spatial dependence among extremes. However, the linear functions used to model the spatially varying coefficients are restrictive and may be violated.We propose a flexible and fast approach based on the spatial GEV and spatial GPD by introducing fused lasso and fused ridge penalty for parameter regularization. This enables improved return level estimation for large spatial extremes compared to the existing methods. Supplemental files for this article are available online.
more »
« less
- PAR ID:
- 10291030
- Date Published:
- Journal Name:
- Journal of Computational and Graphical Statistics
- Volume:
- 00
- Issue:
- 2021
- ISSN:
- 1061-8600
- Page Range / eLocation ID:
- 1 to 19
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Extreme storm surges can overwhelm many coastal flooding protection measures in place and cause severe damages to private communities, public infrastructure, and natural ecosystems. In the US Mid-Atlantic, a highly developed and commercially active region, coastal flooding is one of the most significant natural hazards and a year-round threat from both tropical and extra-tropical cyclones. Mean sea levels and high-tide flood frequency has increased significantly in recent years, and major storms are projected to increase into the foreseeable future. We estimate extreme surges using hourly water level data and harmonic analysis for 1980–2019 at 12 NOAA tide gauges in and around the Delaware and Chesapeake Bays. Return levels (RLs) are computed for 1.1, 3, 5, 10, 25, 50, and 100-year return periods using stationary extreme value analysis on detrended skew surges. Two traditional approaches are investigated, Block Maxima fit to General Extreme Value distribution and Points-Over-Threshold fit to Generalized Pareto distribution, although with two important enhancements. First, the GEV r -largest order statistics distribution is used; a modified version of the GEV distribution that allows for multiple maximum values per year. Second, a systematic procedure is used to select the optimum value for r (for the BM/GEVr approach) and the threshold (for the POT/GP approach) at each tide gauge separately. RLs have similar magnitudes and spatial patterns from both methods, with BM/GEVr resulting in generally larger 100-year and smaller 1.1-year RLs. Maximum values are found at the Lewes (Delaware Bay) and Sewells Point (Chesapeake Bay) tide gauges, both located in the southwest region of their respective bays. Minimum values are found toward the central bay regions. In the Delaware Bay, the POT/GP approach is consistent and results in narrower uncertainty bands whereas the results are mixed for the Chesapeake. Results from this study aim to increase reliability of projections of extreme water levels due to extreme storms and ultimately help in long-term planning of mitigation and implementation of adaptation measures.more » « less
-
Normalizing flows—a popular class of deep generative models—often fail to represent extreme phenomena observed in real-world processes. In particular, existing normalizing flow architectures struggle to model multivariate extremes, characterized by heavy-tailed marginal distributions and asymmetric tail dependence among variables. In light of this shortcoming, we propose COMET (COpula Multivariate ExTreme) Flows, which decompose the process of modeling a joint distribution into two parts: (i) modeling its marginal distributions, and (ii) modeling its copula distribution. COMET Flows capture heavy-tailed marginal distributions by combining a parametric tail belief at extreme quantiles of the marginals with an empirical kernel density function at mid-quantiles. In addition, COMET Flows capture asymmetric tail dependence among multivariate extremes by viewing such dependence as inducing a low-dimensional manifold structure in feature space. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of COMET flows in capturing both heavy-tailed marginals and asymmetric tail dependence compared to other state-of-the-art baseline architectures. All code is available at https://github.com/andrewmcdonald27/COMETFlows.more » « less
-
null (Ed.)Abstract Global gridded precipitation products have proven essential for many applications ranging from hydrological modeling and climate model validation to natural hazard risk assessment. They provide a global picture of how precipitation varies across time and space, specifically in regions where ground-based observations are scarce. While the application of global precipitation products has become widespread, there is limited knowledge on how well these products represent the magnitude and frequency of extreme precipitation—the key features in triggering flood hazards. Here, five global precipitation datasets (MSWEP, CFSR, CPC, PERSIANN-CDR, and WFDEI) are compared to each other and to surface observations. The spatial variability of relatively high precipitation events (tail heaviness) and the resulting discrepancy among datasets in the predicted precipitation return levels were evaluated for the time period 1979–2017. The analysis shows that 1) these products do not provide a consistent representation of the behavior of extremes as quantified by the tail heaviness, 2) there is strong spatial variability in the tail index, 3) the spatial patterns of the tail heaviness generally match the Köppen–Geiger climate classification, and 4) the predicted return levels for 100 and 1000 years differ significantly among the gridded products. More generally, our findings reveal shortcomings of global precipitation products in representing extremes and highlight that there is no single global product that performs best for all regions and climates.more » « less
-
Accurate forecasting of extreme values in time series is critical due to the significant impact of extreme events on human and natural systems. This paper presents DeepExtrema, a novel framework that combines a deep neural network (DNN) with generalized extreme value (GEV) distribution to forecast the block maximum value of a time series. Implementing such a network is a challenge as the framework must preserve the inter-dependent constraints among the GEV model parameters even when the DNN is initialized. We describe our approach to address this challenge and present an architecture that enables both conditional mean and quantile prediction of the block maxima. The extensive experiments performed on both real-world and synthetic data demonstrated the superiority of DeepExtrema compared to other baseline methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1080/10618600.2021.1938584
