Development of a hybrid classification technique based on deep learning applied to MSG / SEVIRI multispectral data

Abstract The approach developed in this paper for the classification of precipitation intensities is based on deep learning of neural network. Multispectral data from the MSG satellite (Meteosat Second Generation) providing information about the cloud's physical and optical characteristics are exploited and used as inputs to a deep neural network model. The model is a combination of CNN (Convolutional Neural Network) and DMLP (Deep Multi-Layer Peceptron) which is learned and validated by comparison with the corresponding Radar data during the rainy seasons 2006/2007 and 2010/2011 respectively. The CNN extracts spatial characteristics from MSG multi-spectral images. Then, the set of spatial and multi-spectral information are used as inputs for the DMLP. The results show an improvement compared to the three other classifiers (Random Forest, Support Vector Machine and Artificial Neural Network). The CNN-DMLP method was also compared to the technique combining the three classifiers (SAR). The results indicate a percentage correct (PC) of 97% and a probability of detection (POD) of 90% for CNN-DMLP method compared to 94% and 87% for of the SAR technique, respectively. In terms of bias, the CNN-DMLP method gives 1.08 compared 1.10 for SAR technique.

[1]  Tim Appelhans,et al.  Improving the accuracy of rainfall rates from optical satellite sensors with machine learning — A random forests-based approach applied to MSG SEVIRI , 2014 .

[2]  Mourad Lahdir,et al.  Analysis of drought areas in northern Algeria using Markov chains , 2015, Journal of Earth System Science.

[3]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[4]  William J. Emery,et al.  A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification , 2009 .

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jörg Bendix,et al.  Rainfall-Rate Assignment Using MSG SEVIRI Data—A Promising Approach to Spaceborne Rainfall-Rate Retrieval for Midlatitudes , 2010 .

[7]  Klaus Kofler,et al.  Performance and Scalability of GPU-Based Convolutional Neural Networks , 2010, 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing.

[8]  Slimane Hameg,et al.  Using naive Bayes classifier for classification of convective rainfall intensities based on spectral characteristics retrieved from SEVIRI , 2016, Journal of Earth System Science.

[9]  J. Testud,et al.  Identification of raining clouds using a method based on optical and microphysical cloud properties from Meteosat second generation daytime and nighttime data , 2013, Applied Water Science.

[10]  T. Nauss,et al.  Weather type dependent quality assessment of a satellite-based rainfall detection scheme for the mid-latitudes , 2010 .

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  M. Lazri,et al.  A satellite rainfall retrieval technique over northern Algeria based on the probability of rainfall intensities classification from MSG-SEVIRI , 2016 .

[13]  Jörg Bendix,et al.  Precipitation process and rainfall intensity differentiation using Meteosat Second Generation Spinning Enhanced Visible and Infrared Imager data , 2008 .

[14]  Soltane Ameur,et al.  Improvement of rainfall estimation from MSG data using Random Forests classification and regression , 2018, Atmospheric Research.

[15]  Soltane Ameur,et al.  Novel SVM-based technique to improve rainfall estimation over the Mediterranean region (north of Algeria) using the multispectral MSG SEVIRI imagery , 2017 .

[16]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[17]  Using cloud water path and cloud top temperature for estimating convective and stratiform rainfall from SEVIRI daytime data , 2016, Arabian Journal of Geosciences.

[18]  M. Lazri,et al.  Instantaneous rainfall estimation using neural network from multispectral observations of SEVIRI radiometer and its application in estimation of daily and monthly rainfall , 2014 .

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

[20]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Haralambos Feidas,et al.  Classifying convective and stratiform rain using multispectral infrared Meteosat Second Generation satellite data , 2011, Theoretical and Applied Climatology.

[22]  B. N. Meisner,et al.  The Relationship between Large-Scale Convective Rainfall and Cold Cloud over the Western Hemisphere during 1982-84 , 1987 .

[23]  Amy Loutfi,et al.  Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks , 2016, Remote. Sens..

[24]  Shihong Du,et al.  Learning multiscale and deep representations for classifying remotely sensed imagery , 2016 .

[25]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[26]  R. A. Roebeling,et al.  Validation of Cloud Liquid Water Path Retrievals from SEVIRI Using One Year of CloudNET Observations , 2008 .

[27]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[28]  Soltane Ameur,et al.  Combination of support vector machine, artificial neural network and random forest for improving the classification of convective and stratiform rain using spectral features of SEVIRI data , 2018 .

[29]  Fabio Del Frate,et al.  Use of Neural Networks for Automatic Classification From High-Resolution Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[30]  W. Paul Menzel,et al.  Cloud Properties inferred from 812-µm Data , 1994 .

[31]  Domenico Cimini,et al.  A statistical approach for rain intensity differentiation using Meteosat Second Generation–Spinning Enhanced Visible and InfraRed Imager observations , 2014 .

[32]  Elizabeth E. Ebert,et al.  Methods for Verifying Satellite Precipitation Estimates , 2007 .

[33]  Soltane Ameur,et al.  Convective rainfall estimation from MSG/SEVIRI data based on different development phase duration of convective systems (growth phase and decay phase) , 2014 .

[34]  B. Baum,et al.  Introduction to MODIS Cloud Products , 2006 .

[35]  Soltane Ameur,et al.  Rainfall estimation over a Mediterranean region using a method based on various spectral parameters of SEVIRI-MSG , 2013 .

[36]  M. Lazri,et al.  Novel WkNN-based technique to improve instantaneous rainfall estimation over the north of Algeria using the multispectral MSG SEVIRI imagery , 2019, Journal of Atmospheric and Solar-Terrestrial Physics.