Evaluation of Thunderstorm Predictors for Finland Using Reanalyses and Neural Networks

AbstractThis work evaluates numerous thunderstorm predictors and investigates the use of artificial neural networks (ANNs) for identifying occurrences of thunderstorms in reanalysis data. Environmental conditions favorable for deep, moist convection are derived from 6-hourly ERA-Interim reanalyses, while thunderstorm occurrence in the following 6 h over Finland is derived from lightning location data. By taking advantage of the consistency and large sample size (14 summers) provided by the reanalysis, complex multivariate models can be trained for a robust estimation of convective weather events from model data. This and other methods are used to yield information on the most effective convective predictors in a multivariate setting, which can also benefit the forecasting community. The best ANN found uses 15 inputs and received a Heidke skill score (HSS) of 0.51 on an independent test sample. This is a substantial improvement over the best predictor when used alone, the most unstable lifted index (MULI) ...

[1]  R. Trapp,et al.  The Geospatial and Temporal Distributions of Severe Thunderstorms from High-Resolution Dynamical Downscaling , 2013 .

[2]  Agostino Manzato,et al.  The Use of Sounding-Derived Indices for a Neural Network Short-Term Thunderstorm Forecast , 2005 .

[3]  M. Hanel,et al.  On the value of hourly precipitation extremes in regional climate model simulations , 2010 .

[4]  Matthew S. Gilmore,et al.  The Influence of Midtropospheric Dryness on Supercell Morphology and Evolution , 1998 .

[5]  M. Kunz,et al.  Recent trends and variabilities of convective parameters relevant for hail events in Germany and Europe , 2013 .

[6]  Agostino Manzato,et al.  A Note On the Maximum Peirce Skill Score , 2007 .

[7]  Antti Mäkelä,et al.  A decade of high‐latitude lightning location: Effects of the evolving location network in Finland , 2010 .

[8]  Harold E. Brooks,et al.  Severe thunderstorms and climate change , 2011 .

[9]  A. V. Delden,et al.  Thunderstorm predictors and their forecast skill for the Netherlands , 2003 .

[10]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[11]  D. McCann.  A Neural Network Short-Term Forecast of Significant Thunderstorms , 1992 .

[12]  Erik N. Rasmussen,et al.  The Effect of Neglecting the Virtual Temperature Correction on CAPE Calculations , 1994 .

[13]  H. Brooks.  Proximity soundings for severe convection for Europe and the United States from reanalysis data , 2009 .

[14]  Thomas M. Hamill,et al.  Measuring forecast skill: is it real skill or is it the varying climatology? , 2006 .

[15]  Agostino Manzato,et al.  Evaluating the sounding instability with the Lifted Parcel Theory , 2003 .

[16]  C. Taylor,et al.  The scale dependence and structure of convergence fields preceding the initiation of deep convection , 2014 .

[17]  A. Mäkelä,et al.  Nordic Lightning Information System: Thunderstorm climate of Northern Europe for the period 2002–2011 , 2014 .

[18]  P. Berg,et al.  Benefit of convection permitting climate model simulations in the representation of convective precipitation , 2014, Climate Dynamics.

[19]  J. Thepaut,et al.  The ERA‐Interim reanalysis: configuration and performance of the data assimilation system , 2011 .

[20]  Pao K. Wang,et al.  Cross Tropopause Transport of Water by Mid-Latitude Deep Convective Storms: A Review , 2011 .

[21]  R. Johns,et al.  Severe Local Storms Forecasting , 1992 .

[22]  C. Schär,et al.  Evaluation of the convection‐resolving regional climate modeling approach in decade‐long simulations , 2014 .

[23]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[24]  Gilbert Laporte,et al.  Metaheuristics: A bibliography , 1996, Ann. Oper. Res..

[25]  Adam L. Houston,et al.  Empirical Examination of the Factors Regulating Thunderstorm Initiation , 2014 .

[26]  C. P. Jacovides,et al.  An evaluation of stability indices for Thunderstorm prediction in greater cyprus , 1990 .

[27]  Harri Hohti,et al.  Climatology of Severe Hail in Finland: 1930–2006 , 2009 .

[28]  Agostino Manzato,et al.  Hail in Northeast Italy: Climatology and Bivariate Analysis with the Sounding-Derived Indices , 2012 .

[29]  A. Mäkelä,et al.  Synoptic Classification of Thunderstorms in Finland , 2003 .

[30]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[31]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[32]  M. Kunz.  The skill of convective parameters and indices to predict isolated and severe thunderstorms , 2007 .

[33]  D. Lüthi,et al.  Towards European-scale convection-resolving climate simulations with GPUs: a study with COSMO 4.19 , 2016 .

[34]  Charles A. Doswell,et al.  The Distinction between Large-Scale and Mesoscale Contribution to Severe Convection: A Case Study Example , 1987 .

[35]  G. Zhang,et al.  Evaluation of Trigger Functions for Convective Parameterization Schemes Using Observations , 2014 .

[36]  Paul Markowski,et al.  A Numerical Investigation of the Effects of Dry Air Aloft on Deep Convection , 2009 .

[37]  Fuqing Zhang,et al.  Evaluation of NCEP-CFSR, NCEP-NCAR, ERA-Interim, and ERA-40 Reanalysis Datasets against Independent Sounding Observations over the Tibetan Plateau , 2013 .

[38]  J. Kain,et al.  Sensitivity of Several Performance Measures to Displacement Error, Bias, and Event Frequency , 2006 .

[39]  S. Changnon.  Damaging Thunderstorm Activity in the United States , 2001 .

[40]  Harold E. Brooks,et al.  Climate Extremes and Society: The spatial distribution of severe convective storms and an analysis of their secular changes , 2008 .

[41]  H. Huntrieser,et al.  Comparison of Traditional and Newly Developed Thunderstorm Indices for Switzerland , 1997 .

[42]  D. Schultz,et al.  Significant-hail-producing storms in Finland: Convective-storm environment and morphology , 2015 .

[43]  C. Kottmeier,et al.  Recent trends of thunderstorm and hailstorm frequency and their relation to atmospheric characteristics in southwest Germany , 2009 .

[44]  Agostino Manzato,et al.  Sounding-derived indices for neural network based short-term thunderstorm and rainfall forecasts , 2007 .

[45]  Victor A. Gensini,et al.  Severe-Thunderstorm Reanalysis Environments and Collocated Radiosonde Observations , 2014 .

[46]  D. Lüthi,et al.  Aspects of the diurnal cycle in a regional climate model , 2008 .

[47]  David M. Schultz,et al.  The Use of Moisture Flux Convergence in Forecasting Convective Initiation: Historical and Operational Perspectives , 2005 .