Detection of Convective Initiation Using Meteorological Imager Onboard Communication, Ocean, and Meteorological Satellite Based on Machine Learning Approaches

As convective clouds in Northeast Asia are accompanied by various hazards related with heavy rainfall and thunderstorms, it is very important to detect convective initiation (CI) in the region in order to mitigate damage by such hazards. In this study, a novel approach for CI detection using images from Meteorological Imager (MI), a payload of the Communication, Ocean, and Meteorological Satellite (COMS), was developed by improving the criteria of the interest fields of Rapidly Developing Cumulus Areas (RDCA) derivation algorithm, an official CI detection algorithm for Multi-functional Transport SATellite-2 (MTSAT-2), based on three machine learning approaches—decision trees (DT), random forest (RF), and support vector machines (SVM). CI was defined as clouds within a 16 × 16 km window with the first detection of lightning occurrence at the center. A total of nine interest fields derived from visible, water vapor, and two thermal infrared images of MI obtained 15–75 min before the lightning occurrence were used as input variables for CI detection. RF produced slightly higher performance (probability of detection (POD) of 75.5% and false alarm rate (FAR) of 46.2%) than DT (POD of 70.7% and FAR of 46.6%) for detection of CI caused by migrating frontal cyclones and unstable atmosphere. SVM resulted in relatively poor performance with very high FAR ~83.3%. The averaged lead times of CI detection based on the DT and RF models were 36.8 and 37.7 min, respectively. This implies that CI over Northeast Asia can be forecasted ~30–45 min in advance using COMS MI data.

[1]  Terri Betancourt,et al.  NCAR Auto-Nowcast System , 2003 .

[2]  Itamar M. Lensky,et al.  Satellite-Based Insights into Precipitation Formation Processes in Continental and Maritime Convective Clouds , 1998 .

[3]  Richard E. Carbone,et al.  A Climatology of Warm-Season Cloud Patterns over East Asia Based on GMS Infrared Brightness Temperature Observations , 2004 .

[4]  Kristopher M. Bedka,et al.  A Statistical Evaluation of GOES Cloud-Top Properties for Nowcasting Convective Initiation , 2008 .

[5]  J. Rhee,et al.  Relationship between land cover patterns and surface temperature in urban areas , 2014 .

[6]  Bryan A. Baum,et al.  Remote sensing of cloud properties using MODIS airborne simulator imagery during SUCCESS: 1. Data and models , 2000 .

[7]  Faisal Hossain,et al.  Assessment of current passive-microwave- and infrared-based satellite rainfall remote sensing for flood prediction , 2004 .

[8]  Stavros Kolios,et al.  An automated nowcasting system of mesoscale convective systems for the Mediterranean basin using Meteosat imagery. Part II: Verification statistics , 2013 .

[9]  Steven A. Rutledge,et al.  Nowcasting Storm Initiation and Growth Using GOES-8 and WSR-88D Data , 2003 .

[10]  Hyung Woo Kim,et al.  An observational study of mesoscale convective systems with heavy rainfall over the Korean Peninsula , 2006 .

[11]  John L. Cintineo,et al.  Evolution of Severe and Nonsevere Convection Inferred from GOES-Derived Cloud Properties , 2013 .

[12]  Steven A. Ackerman,et al.  Global Satellite Observations of Negative Brightness Temperature Differences between 11 and 6.7 µm , 1996 .

[13]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[14]  Francesca Bovolo,et al.  A Novel Approach to Unsupervised Change Detection Based on a Semisupervised SVM and a Similarity Measure , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[15]  John R. Walker,et al.  An Enhanced Geostationary Satellite–Based Convective Initiation Algorithm for 0–2-h Nowcasting with Object Tracking , 2012 .

[16]  John R. Mecikalski,et al.  Adjusting thresholds of satellite‐based convective initiation interest fields based on the cloud environment , 2013 .

[17]  Tianle Yuan,et al.  General Macro- and Microphysical Properties of Deep Convective Clouds as Observed by MODIS , 2010 .

[18]  Luis Rivas Soriano,et al.  Relationship between Convective Precipitation and Cloud-to-Ground Lightning in the Iberian Peninsula , 2001 .

[19]  Philip A. Durkee,et al.  The Definition of GOES Infrared Lightning Initiation Interest Fields , 2010 .

[20]  C. Morel,et al.  A climatology of mesoscale convective systems over Europe using satellite infrared imagery. I: Methodology , 2002 .

[21]  Aaron E. Maxwell,et al.  Comparison of NAIP orthophotography and RapidEye satellite imagery for mapping of mining and mine reclamation , 2014 .

[22]  Steven A. Ackerman,et al.  The Temporal Evolution of Convective Indices in Storm-Producing Environments , 2008 .

[23]  Jia Zong,et al.  Algorithm Theoretical Basis , 1999 .

[24]  Steven A. Ackerman,et al.  Satellite Regional Cloud Climatology over the Great Lakes , 2013, Remote. Sens..

[25]  Anthony M. Filippi,et al.  River-flow boundary delineation from digital aerial photography and ancillary images using Support Vector Machines , 2013 .

[26]  Jungho Im,et al.  Forest biomass estimation from airborne LiDAR data using machine learning approaches , 2012 .

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

[28]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[29]  John R. Mecikalski,et al.  Application of Meteosat second generation data towards improving the nowcasting of convective initiation , 2010 .

[30]  J. Mecikalski,et al.  Cloud-Top Properties of Growing Cumulus prior to Convective Initiation as Measured by Meteosat Second Generation. Part II: Use of Visible Reflectance , 2010 .

[31]  D. H. Kim,et al.  Introduction of the in-orbit test and its performance for the first meteorological imager of the Communication, Ocean, and Meteorological Satellite , 2013 .

[32]  Ronald M. Welch,et al.  Cumulus Cloud Properties Derived Using Landsat Satellite Data , 1986 .

[33]  Sverre Grimnes.  Chapter 7 – Data and models , 2000 .

[34]  J. Mecikalski,et al.  Forecasting Convective Initiation by Monitoring the Evolution of Moving Cumulus in Daytime GOES Imagery , 2004 .

[35]  Norbert Pfeifer,et al.  Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types , 2014, Remote. Sens..

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

[37]  Kyung-Ja Ha,et al.  Characteristic Differences of Rainfall and Cloud-to-Ground Lightning Activity over South Korea during the Summer Monsoon Season , 2003 .

[38]  Stavros Kolios,et al.  An automated nowcasting system of mesoscale convective systems for the Mediterranean basin using Meteosat imagery. Part I: System description , 2013 .

[39]  Wayne M. MacKenzie,et al.  Cloud-Top Properties of Growing Cumulus prior to Convective Initiation as Measured by Meteosat Second Generation. Part I: Infrared Fields , 2010 .

[40]  W. Paul Menzel,et al.  Remote sensing of cloud properties using MODIS airborne simulator imagery during SUCCESS: 2. Cloud thermodynamic phase , 2000 .

[41]  Michael E. Baldwin,et al.  A Case Study of Severe Storm Development along a Dryline within a Synoptically Active Environment. Part II: Multiple Boundaries and Convective Initiation , 2002 .

[42]  J. Mecikalski,et al.  Application of Satellite-Derived Atmospheric Motion Vectors for Estimating Mesoscale Flows , 2005 .

[43]  A. Bárdossy,et al.  Use of geostationary meteorological satellite images in convective rain estimation for flash-flood forecasting , 2008 .

[44]  Charles A. Doswell,et al.  The AVHRR Channel 3 Cloud Top Reflectivity of Convective Storms , 1991 .

[45]  V. Levizzani,et al.  IR‐based satellite and radar rainfall estimates of convective storms over northern Italy , 2000 .

[46]  Angela Lausch,et al.  Extraction of Plant Physiological Status from Hyperspectral Signatures Using Machine Learning Methods , 2014, Remote. Sens..

[47]  C. Morel,et al.  A climatology of mesoscale convective systems over Europe using satellite infrared imagery. II: Characteristics of European mesoscale convective systems , 2002 .

[48]  Bardan Ghimire,et al.  An Evaluation of Bagging, Boosting, and Random Forests for Land-Cover Classification in Cape Cod, Massachusetts, USA , 2012 .

[49]  Michael D. King,et al.  Simulations of Infrared Radiances over a Deep Convective Cloud System Observed during TC4: Potential for Enhancing Nocturnal Ice Cloud Retrievals , 2012, Remote. Sens..

[50]  Johannes Schmetz,et al.  Monitoring deep convection and convective overshooting with METEOSAT , 1997 .

[51]  Aisheng Wu,et al.  Initial Stability Assessment of S-NPP VIIRS Reflective Solar Band Calibration Using Invariant Desert and Deep Convective Cloud Targets , 2014, Remote. Sens..

[52]  Xin Huang,et al.  A multiscale feature fusion approach for classification of very high resolution satellite imagery based on wavelet transform , 2008 .

[53]  D. Lu,et al.  A comparative analysis of approaches for successional vegetation classification in the Brazilian Amazon , 2014 .

[54]  Kristopher M. Bedka,et al.  Nowcasting Convective Storm Initiation Using Satellite-Based Box-Averaged Cloud-Top Cooling and Cloud-Type Trends , 2011 .

[55]  R. Lawrence.  Rule-Based Classification Systems Using Classification and Regression Tree (CART) Analysis , 2001 .

[56]  K. Cummins,et al.  Combined Satellite- and Surface-Based Estimation of the Intracloud Cloud-to-Ground Lightning Ratio over the Continental United States , 2001 .

[57]  J. Im,et al.  Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest , 2013 .

[58]  Vincenzo Levizzani,et al.  Multispectral, high-resolution satellite observations of plumes on top of convective storms , 1996 .

[59]  Wayne F. Feltz,et al.  Improving Satellite-Based Convective Cloud Growth Monitoring with Visible Optical Depth Retrievals , 2014 .

[60]  Christian Igel,et al.  Evolutionary tuning of multiple SVM parameters , 2005, ESANN.

[61]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[62]  S. Ha,et al.  Machine learning approaches to coastal water quality monitoring using GOCI satellite data , 2014 .

[63]  Shunlin Liang,et al.  NOAA NESDIS CENTER FOR SATELLITE APPLICATIONS AND RESEARCH Vegetation Index (VI) Product ALGORITHM THEORETICAL BASIS DOCUMENT , 2013 .

[64]  Paquita Zuidema,et al.  Convective Clouds over the Bay of Bengal , 2003 .

[65]  Tobias Zinner,et al.  Validation of the Meteosat storm detection and nowcasting system Cb-TRAM with lightning network data – Europe and South Africa , 2013 .

[66]  E. Anagnostou,et al.  Improving Convective Precipitation Forecasting through Assimilation of Regional Lightning Measurements in a Mesoscale Model , 2003 .