Severe Thunderstorm Detection by Visual Learning Using Satellite Images

Computers are widely utilized in today's weather forecasting as a powerful tool to leverage an enormous amount of data. Yet, despite the availability of such data, current techniques often fall short of producing reliable detailed storm forecasts. Each year severe thunderstorms cause significant damage and loss of life, some of which could be avoided if better forecasts were available. We propose a computer algorithm that analyzes satellite images from historical archives to locate visual signatures of severe thunderstorms for short-term predictions. While computers are involved in weather forecasts to solve numerical models based on sensory data, they are less competent in forecasting based on visual patterns from both current and past satellite images. In our system, we extract and summarize important visual storm evidence from satellite image sequences in the way that meteorologists interpret the images. In particular, the algorithm extracts and fits local cloud motion from image sequences to model the storm-related cloud patches. Image data from the year 2008 have been adopted to train the model, and historical severe thunderstorm reports in continental U.S. from 2000 to 2013 have been used as the ground truth and priors in the modeling process. Experiments demonstrate the usefulness and potential of the algorithm for producing more accurate severe thunderstorm forecasts.

[1]  R. Scofield.  The NESDIS Operational Convective Precipitation- Estimation Technique , 1987 .

[2]  J. G. Charney,et al.  The Use of the Primitive Equations of Motion in Numerical Prediction , 1955 .

[3]  Arnold Tafferner,et al.  Cb-TRAM: Tracking and monitoring severe convection from onset over rapid development to mature phase using multi-channel Meteosat-8 SEVIRI data , 2008 .

[4]  Jun Chang,et al.  A novel approach to improve numerical weather prediction skills by using anomaly integration and historical data , 2013 .

[5]  Adam J. Clark,et al.  Climatology of Storm Reports Relative to Upper-Level Jet Streaks , 2009 .

[6]  Andrew C. Lorenc,et al.  4D‐Var and the butterfly effect: Statistical four‐dimensional data assimilation for a wide range of scales , 2007 .

[7]  Stéphane Laroche,et al.  Implementation of a 3D variational data assimilation system at the Canadian Meteorological Centre. Part I: The global analysis , 1999 .

[8]  G. Arfken,et al.  Mathematical methods for physicists 6th ed. , 1996 .

[9]  F. Molteni,et al.  The ECMWF Ensemble Prediction System: Methodology and validation , 1996 .

[10]  R. Temam.  Navier-Stokes Equations , 1977 .

[11]  Amy McGovern,et al.  Open problem: Dynamic Relational Models for Improved Hazardous Weather Prediction , 2006 .

[12]  Shen-Shyang Ho,et al.  Automated cyclone discovery and tracking using knowledge sharing in multiple heterogeneous satellite data , 2008, KDD.

[13]  Frederic Vitart,et al.  Evolution of ECMWF sub‐seasonal forecast skill scores , 2014 .

[14]  J. Stroeve,et al.  Onboard Detection of Snow, Ice, Clouds and Other Geophysical Processes Using Kernel Methods , 2003 .

[15]  C. Keil,et al.  A Displacement and Amplitude Score Employing an Optical Flow Technique , 2009 .

[16]  Javier Sánchez Pérez,et al.  TV-L1 Optical Flow Estimation , 2013, Image Process. Line.

[17]  Hyelim Yoo,et al.  Diagnosis and improvement of cloud parameterization schemes in NCEP/GFS using multiple satellite products , 2013 .

[18]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[19]  Xiaolei Zou,et al.  Observation, theory and modeling of atmospheric variability : selected papers of Nanjing Institute of Meteorology Alumni in commemoration of professor Jijia Zhang , 2004 .

[20]  J. C. Price.  Using spatial context in satellite data to infer regional scale evapotranspiration , 1990 .

[21]  R. Barry,et al.  Atmosphere, Weather and Climate , 1968 .

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  Charles A. Doswell,et al.  Weather Forecasting by Humans—Heuristics and Decision Making , 2004 .

[24]  V. F. Dvorak.  Tropical Cyclone Intensity Analysis and Forecasting from Satellite Imagery , 1975 .

[25]  Peter Lynch,et al.  The origins of computer weather prediction and climate modeling , 2008, J. Comput. Phys..

[26]  G. Arfken.  Mathematical Methods for Physicists , 1967 .

[27]  Toby N. Carlson,et al.  Airflow Through Midlatitude Cyclones and the Comma Cloud Pattern , 1980 .

[28]  Guosheng Liu,et al.  SATELLITE MICROWAVE REMOTE SENSING OF CLOUDS AND PRECIPITATION , 2004 .

[29]  Tinku Acharya,et al.  Image Processing: Principles and Applications , 2005, J. Electronic Imaging.

[30]  P. Moin,et al.  Eddies, streams, and convergence zones in turbulent flows , 1988 .

[31]  J. Marshall,et al.  Atmosphere, Ocean and Climate Dynamics: An Introductory Text , 1961 .

[32]  Tobias Zinner,et al.  Detection of convective initiation using Meteosat SEVIRI: implementation in and verification with the tracking and nowcasting algorithm Cb-TRAM , 2013 .

[33]  Jos Stam,et al.  Stable fluids , 1999, SIGGRAPH.

[34]  Nigel Roberts,et al.  Characteristics of high-resolution versions of the Met Office unified model for forecasting convection over the United Kingdom , 2008 .

[35]  J. Otkin,et al.  Objective Satellite-Based Detection of Overshooting Tops Using Infrared Window Channel Brightness Temperature Gradients , 2010 .

[36]  J. Wallace,et al.  Atmospheric Science: An Introductory Survey , 1977 .

[37]  Günter Mahringer,et al.  SATMOD: An Interactive System Combining Satellite Images and Model Output Parameters , 1990 .

[38]  J.-Y. Bouguet,et al.  Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[39]  J. G. Charney,et al.  THE DYNAMICS OF LONG WAVES IN A BAROCLINIC WESTERLY CURRENT , 1947 .

[40]  S. Sorooshian,et al.  Daytime Precipitation Estimation Using Bispectral Cloud Classification System , 2010 .

[41]  James D. Doyle,et al.  Initial Condition Sensitivity and Predictability of a Severe Extratropical Cyclone Using a Moist Adjoint , 2014 .

[42]  J. Beven,et al.  Tropical Cyclone Report Hurricane Sandy , 2013 .

[43]  John P. Snyder,et al.  Map Projections: A Working Manual , 2012 .

[44]  Weizhong Zheng,et al.  Improvement of daytime land surface skin temperature over arid regions in the NCEP GFS model and its impact on satellite data assimilation , 2012 .

[45]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[46]  Stephen Burt,et al.  THE GREAT STORM OF 15–16 OCTOBER 1987 , 1988 .

[47]  Kristopher M. Bedka,et al.  Overshooting cloud top detections using MSG SEVIRI Infrared brightness temperatures and their relationship to severe weather over Europe , 2011 .

[48]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[49]  George W. Platzman,et al.  The ENIAC Computations of 1950—Gateway to Numerical Weather Prediction , 1979 .

[50]  Robert L Winkler,et al.  The Importance of Communicating Uncertainties in Forecasts: Overestimating the Risks from Winter Storm Juno , 2015, Risk analysis : an official publication of the Society for Risk Analysis.

[51]  Y. Hong,et al.  Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System , 2004 .

[52]  Adrian N. Evans,et al.  Cloud motion analysis using multichannel correlation-relaxation labeling , 2006, IEEE Geoscience and Remote Sensing Letters.