Lightning severity classification utilizing the meteorological parameters: a neural network approach

This paper presents a technique of predicting lightning severity on daily basis by using meteorological data. The data used is supplied by Global Lightning Network (GLN) from WSI Corporation. The input of the system consists of seven meteorology parameters which had been provided by Malaysia Meteoro...

Full description

Bibliographic Details
Main Authors: Omar, Muhammad Azhar, Hassan, Mohd Khair, Che Soh, Azura, Ab Kadir, Mohd Zainal Abidin
Format: Conference or Workshop Item
Language:English
Published: IEEE 2013
Online Access:http://psasir.upm.edu.my/id/eprint/68852/
http://psasir.upm.edu.my/id/eprint/68852/1/Lightning%20severity%20classification%20utilizing%20the%20meteorological%20parameters%20a%20neural%20network%20approach.pdf
_version_ 1848856244146667520
author Omar, Muhammad Azhar
Hassan, Mohd Khair
Che Soh, Azura
Ab Kadir, Mohd Zainal Abidin
author_facet Omar, Muhammad Azhar
Hassan, Mohd Khair
Che Soh, Azura
Ab Kadir, Mohd Zainal Abidin
author_sort Omar, Muhammad Azhar
building UPM Institutional Repository
collection Online Access
description This paper presents a technique of predicting lightning severity on daily basis by using meteorological data. The data used is supplied by Global Lightning Network (GLN) from WSI Corporation. The input of the system consists of seven meteorology parameters which had been provided by Malaysia Meteorology Service with minimal fees. Input parameters are the Minimum Humidity, Maximum Humidity, Minimum Temperature, Maximum Temperature, Rainfall, Week and Month. The output of the system determines the severity of lightning predictions in three stages; Class1: Hazardous; Class2: Warning; and Class3: Low Risk. Two training algorithms that have been tested in this study namely the Gradient Descent with Momentum Backpropagation (traingdm) and the Scaled Conjugated Gradient Backpropagation (trainscg). The traingdm has indicated better accuracy of 70% compared to the trainscg whilst in contrast; trainscg has demonstrated approximately 4 times faster training compare to traingdm.
first_indexed 2025-11-15T11:38:34Z
format Conference or Workshop Item
id upm-68852
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T11:38:34Z
publishDate 2013
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling upm-688522019-06-11T01:36:39Z http://psasir.upm.edu.my/id/eprint/68852/ Lightning severity classification utilizing the meteorological parameters: a neural network approach Omar, Muhammad Azhar Hassan, Mohd Khair Che Soh, Azura Ab Kadir, Mohd Zainal Abidin This paper presents a technique of predicting lightning severity on daily basis by using meteorological data. The data used is supplied by Global Lightning Network (GLN) from WSI Corporation. The input of the system consists of seven meteorology parameters which had been provided by Malaysia Meteorology Service with minimal fees. Input parameters are the Minimum Humidity, Maximum Humidity, Minimum Temperature, Maximum Temperature, Rainfall, Week and Month. The output of the system determines the severity of lightning predictions in three stages; Class1: Hazardous; Class2: Warning; and Class3: Low Risk. Two training algorithms that have been tested in this study namely the Gradient Descent with Momentum Backpropagation (traingdm) and the Scaled Conjugated Gradient Backpropagation (trainscg). The traingdm has indicated better accuracy of 70% compared to the trainscg whilst in contrast; trainscg has demonstrated approximately 4 times faster training compare to traingdm. IEEE 2013 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/68852/1/Lightning%20severity%20classification%20utilizing%20the%20meteorological%20parameters%20a%20neural%20network%20approach.pdf Omar, Muhammad Azhar and Hassan, Mohd Khair and Che Soh, Azura and Ab Kadir, Mohd Zainal Abidin (2013) Lightning severity classification utilizing the meteorological parameters: a neural network approach. In: 2013 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2013), 29 Nov.-1 Dec. 2013, Penang, Malaysia. (pp. 111-116). 10.1109/ICCSCE.2013.6719942
spellingShingle Omar, Muhammad Azhar
Hassan, Mohd Khair
Che Soh, Azura
Ab Kadir, Mohd Zainal Abidin
Lightning severity classification utilizing the meteorological parameters: a neural network approach
title Lightning severity classification utilizing the meteorological parameters: a neural network approach
title_full Lightning severity classification utilizing the meteorological parameters: a neural network approach
title_fullStr Lightning severity classification utilizing the meteorological parameters: a neural network approach
title_full_unstemmed Lightning severity classification utilizing the meteorological parameters: a neural network approach
title_short Lightning severity classification utilizing the meteorological parameters: a neural network approach
title_sort lightning severity classification utilizing the meteorological parameters: a neural network approach
url http://psasir.upm.edu.my/id/eprint/68852/
http://psasir.upm.edu.my/id/eprint/68852/
http://psasir.upm.edu.my/id/eprint/68852/1/Lightning%20severity%20classification%20utilizing%20the%20meteorological%20parameters%20a%20neural%20network%20approach.pdf