Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.1
2.9
Journals
Atmosphere
Special Issues
Machine Learning for Extreme Events
share announcement

Machine Learning for Extreme Events

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Climatology".

Deadline for manuscript submissions: closed (15 July 2021) | Viewed by 12738

Special Issue Editors

Dr. Zhangshuan Hou

E-Mail Website
Guest Editor
Earth System Data Science, Pacific Northwest National Laboratory, Richland, Washington, DC 99352, USA
Interests: artificial intelligence; machine learning; deep learning; complex systems; extreme events
Dr. David Judi

E-Mail Website
Guest Editor
Earth System Prediction and Resiliency, Pacific Northwest National Laboratory, Richland, WA 9935, USA
Interests: extreme events; flood modeling; risk assessment and mitigation

Special Issue Information

Dear Colleagues,

Extreme events, such as heat waves, droughts, wildfires, floods, landslides, tornadoes, and hurricanes, are of interest worldwide due to their social, ecological, and technical impacts and consequences. Our ability to fully understand and manage the earth system’s extreme events is usually hindered by the lack of characterization data and reliable modeling of these extremes. Novel scientific machine learning (ML) approaches have been introduced and integrated with success and have the potential to enable transformational advances in the efficiency and effectiveness of predicting and managing earth system extremes by automatically learning multiphysics and multiscale processes based on observational or simulation data and extracting meaningful metrics for making decisions.

We invite you to consider submitting your research for publication in this Special Issue of the journal, focusing on “Machine Learning for Extreme Events”. The aim of this Special Issue is to collect a selection of papers on the current state of science and engineering on applying machine learning for studying extreme events. Relevant current issues include data quality, sparsity, imbalance, and lack of labels, which need to be addressed for accurate representation of extreme events and adverse impacts. We seek contributions in ML-based extreme event analyses which include but are not limited to: (1) data engineering to make extreme events information findable, accessible, interoperable, and reusable (FAIR) for ML; (2) exploratory data analysis, pattern recognition, and signature discovery for extreme event understanding; (3) system complexity reduction or identification of influential drivers of extremes; and (4) physics-informed ML and ML-guided numerical modeling, experimental design, and decision-making.

Dr. Zhangshuan Hou
Dr. David Judi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Atmosphere is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Extreme events
  • Characterization and modeling
  • Multiphysics-informed machine learning
  • Data-driven models
  • Data engineering
  • FAIR data

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 3112 KiB  
Article
Big Data Analytics for Long-Term Meteorological Observations at Hanford Site
by Huifen Zhou, Huiying Ren, Patrick Royer, Hongfei Hou and Xiao-Ying Yu
Atmosphere 2022, 13(1), 136; https://doi.org/10.3390/atmos13010136 - 14 Jan 2022
Cited by 4 | Viewed by 2724
Abstract
A growing number of physical objects with embedded sensors with typically high volume and frequently updated data sets has accentuated the need to develop methodologies to extract useful information from big data for supporting decision making. This study applies a suite of data [...] Read more.
A growing number of physical objects with embedded sensors with typically high volume and frequently updated data sets has accentuated the need to develop methodologies to extract useful information from big data for supporting decision making. This study applies a suite of data analytics and core principles of data science to characterize near real-time meteorological data with a focus on extreme weather events. To highlight the applicability of this work and make it more accessible from a risk management perspective, a foundation for a software platform with an intuitive Graphical User Interface (GUI) was developed to access and analyze data from a decommissioned nuclear production complex operated by the U.S. Department of Energy (DOE, Richland, USA). Exploratory data analysis (EDA), involving classical non-parametric statistics, and machine learning (ML) techniques, were used to develop statistical summaries and learn characteristic features of key weather patterns and signatures. The new approach and GUI provide key insights into using big data and ML to assist site operation related to safety management strategies for extreme weather events. Specifically, this work offers a practical guide to analyzing long-term meteorological data and highlights the integration of ML and classical statistics to applied risk and decision science. Full article
(This article belongs to the Special Issue Machine Learning for Extreme Events)
►▼ Show Figures

Figure 1

23 pages, 4871 KiB  
Article
Calibration of X-Band Radar for Extreme Events in a Spatially Complex Precipitation Region in North Peru: Machine Learning vs. Empirical Approach
by Rütger Rollenbeck, Johanna Orellana-Alvear, Rodolfo Rodriguez, Simon Macalupu and Pool Nolasco
Atmosphere 2021, 12(12), 1561; https://doi.org/10.3390/atmos12121561 - 26 Nov 2021
Cited by 5 | Viewed by 1988
Abstract
Cost-efficient single-polarized X-band radars are a feasible alternative due to their high sensitivity and resolution, which makes them well suited for complex precipitation patterns. The first horizontal scanning weather radar in Peru was installed in Piura in 2019, after the devastating impact of [...] Read more.
Cost-efficient single-polarized X-band radars are a feasible alternative due to their high sensitivity and resolution, which makes them well suited for complex precipitation patterns. The first horizontal scanning weather radar in Peru was installed in Piura in 2019, after the devastating impact of the 2017 coastal El Niño. To obtain a calibrated rain rate from radar reflectivity, we employ a modified empirical approach and draw a direct comparison to a well-established machine learning technique used for radar QPE. For both methods, preprocessing steps are required, such as clutter and noise elimination, atmospheric, geometric, and precipitation-induced attenuation correction, and hardware variations. For the new empirical approach, the corrected reflectivity is related to rain gauge observations, and a spatially and temporally variable parameter set is iteratively determined. The machine learning approach uses a set of features mainly derived from the radar data. The random forest (RF) algorithm employed here learns from the features and builds decision trees to obtain quantitative precipitation estimates for each bin of detected reflectivity. Both methods capture the spatial variability of rainfall quite well. Validating the empirical approach, it performed better with an overall linear regression slope of 0.65 and r of 0.82. The RF approach had limitations with the quantitative representation (slope = 0.44 and r = 0.65), but it more closely matches the reflectivity distribution, and it is independent of real-time rain-gauge data. Possibly, a weighted mean of both approaches can be used operationally on a daily basis. Full article
(This article belongs to the Special Issue Machine Learning for Extreme Events)
►▼ Show Figures

Figure 1

15 pages, 5514 KiB  
Article
Machine Learning-Based Front Detection in Central Europe
by Bogdan Bochenek, Zbigniew Ustrnul, Agnieszka Wypych and Danuta Kubacka
Atmosphere 2021, 12(10), 1312; https://doi.org/10.3390/atmos12101312 - 08 Oct 2021
Cited by 4 | Viewed by 2359
Abstract
Extreme weather phenomena such as wind gusts, heavy precipitation, hail, thunderstorms, tornadoes, and many others usually occur when there is a change in air mass and the passing of a weather front over a certain region. The climatology of weather fronts is difficult, [...] Read more.
Extreme weather phenomena such as wind gusts, heavy precipitation, hail, thunderstorms, tornadoes, and many others usually occur when there is a change in air mass and the passing of a weather front over a certain region. The climatology of weather fronts is difficult, since they are usually drawn onto maps manually by forecasters; therefore, the data concerning them are limited and the process itself is very subjective in nature. In this article, we propose an objective method for determining the position of weather fronts based on the random forest machine learning technique, digitized fronts from the DWD database, and ERA5 meteorological reanalysis. Several aspects leading to the improvement of scores are presented, such as adding new fields or dates to the training database or using the gradients of fields. Full article
(This article belongs to the Special Issue Machine Learning for Extreme Events)
►▼ Show Figures

Figure 1

18 pages, 4816 KiB  
Article
Forecasting of Extreme Storm Tide Events Using NARX Neural Network-Based Models
by Fabio Di Nunno, Francesco Granata, Rudy Gargano and Giovanni de Marinis
Atmosphere 2021, 12(4), 512; https://doi.org/10.3390/atmos12040512 - 17 Apr 2021
Cited by 31 | Viewed by 3684
Abstract
The extreme values of high tides are generally caused by a combination of astronomical and meteorological causes, as well as by the conformation of the sea basin. One place where the extreme values of the tide have a considerable practical interest is the [...] Read more.
The extreme values of high tides are generally caused by a combination of astronomical and meteorological causes, as well as by the conformation of the sea basin. One place where the extreme values of the tide have a considerable practical interest is the city of Venice. The MOSE (MOdulo Sperimentale Elettromeccanico) system was created to protect Venice from flooding caused by the highest tides. Proper operation of the protection system requires an adequate forecast model of the highest tides, which is able to provide reliable forecasts even some days in advance. Nonlinear Autoregressive Exogenous (NARX) neural networks are particularly effective in predicting time series of hydrological quantities. In this work, the effectiveness of two distinct NARX-based models was demonstrated in predicting the extreme values of high tides in Venice. The first model requires as input values the astronomical tide, barometric pressure, wind speed, and direction, as well as previously observed sea level values. The second model instead takes, as input values, the astronomical tide and the previously observed sea level values, which implicitly take into account the weather conditions. Both models proved capable of predicting the extreme values of high tides with great accuracy, even greater than that of the models currently used. Full article
(This article belongs to the Special Issue Machine Learning for Extreme Events)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop