Performance Analysis of Artificial Intelligence Approaches for LEMP Classification
Lightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LE...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/24/5635 |
| _version_ | 1827573711113289728 |
|---|---|
| author | Adonis F. R. Leal Gabriel A. V. S. Ferreira Wendler L. N. Matos |
| author_facet | Adonis F. R. Leal Gabriel A. V. S. Ferreira Wendler L. N. Matos |
| author_sort | Adonis F. R. Leal |
| collection | DOAJ |
| description | Lightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LEMPs, which makes their classification virtually impossible to carry out manually. The lightning classification is important to distinguish the types of thunderstorms and to know their severity. Lightning type is also related to aerosol concentration and can reveal wildfires. Artificial Intelligence (AI) is a good approach to recognizing patterns and dealing with huge datasets. AI is the general denomination for different Machine Learning Algorithms (MLAs) including deep learning and others. The constant improvements in the AI field show us that most of the Lightning Location Systems (LLS) will soon incorporate those techniques to improve their performance in the lightning-type classification task. In this study, we assess the performance of different MLAs, including a SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), FCN (Fully Convolutional Network), and Residual Neural Network (ResNet) in the task of LEMP classification. We also address different aspects of the dataset that can interfere with the classification problem, including data balance, noise level, and LEMP recorded length. |
| first_indexed | 2024-03-08T20:24:12Z |
| format | Article |
| id | doaj.art-7e7524f681864097b96eb72bdf7dbc61 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T20:24:12Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7e7524f681864097b96eb72bdf7dbc612023-12-22T14:38:48ZengMDPI AGRemote Sensing2072-42922023-12-011524563510.3390/rs15245635Performance Analysis of Artificial Intelligence Approaches for LEMP ClassificationAdonis F. R. Leal0Gabriel A. V. S. Ferreira1Wendler L. N. Matos2Langmuir Laboratory and Physics Department, New Mexico Institute of Mining and Technology, 801 Leroy Place, Socorro, NM 87801, USAGraduate Program in Electrical Engineering, Federal University of Para, Belem 66075110, BrazilGraduate Program in Electrical Engineering, Federal University of Para, Belem 66075110, BrazilLightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LEMPs, which makes their classification virtually impossible to carry out manually. The lightning classification is important to distinguish the types of thunderstorms and to know their severity. Lightning type is also related to aerosol concentration and can reveal wildfires. Artificial Intelligence (AI) is a good approach to recognizing patterns and dealing with huge datasets. AI is the general denomination for different Machine Learning Algorithms (MLAs) including deep learning and others. The constant improvements in the AI field show us that most of the Lightning Location Systems (LLS) will soon incorporate those techniques to improve their performance in the lightning-type classification task. In this study, we assess the performance of different MLAs, including a SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), FCN (Fully Convolutional Network), and Residual Neural Network (ResNet) in the task of LEMP classification. We also address different aspects of the dataset that can interfere with the classification problem, including data balance, noise level, and LEMP recorded length.https://www.mdpi.com/2072-4292/15/24/5635LEMP classificationartificial intelligencemachine learning algorithmslightning |
| spellingShingle | Adonis F. R. Leal Gabriel A. V. S. Ferreira Wendler L. N. Matos Performance Analysis of Artificial Intelligence Approaches for LEMP Classification Remote Sensing LEMP classification artificial intelligence machine learning algorithms lightning |
| title | Performance Analysis of Artificial Intelligence Approaches for LEMP Classification |
| title_full | Performance Analysis of Artificial Intelligence Approaches for LEMP Classification |
| title_fullStr | Performance Analysis of Artificial Intelligence Approaches for LEMP Classification |
| title_full_unstemmed | Performance Analysis of Artificial Intelligence Approaches for LEMP Classification |
| title_short | Performance Analysis of Artificial Intelligence Approaches for LEMP Classification |
| title_sort | performance analysis of artificial intelligence approaches for lemp classification |
| topic | LEMP classification artificial intelligence machine learning algorithms lightning |
| url | https://www.mdpi.com/2072-4292/15/24/5635 |
| work_keys_str_mv | AT adonisfrleal performanceanalysisofartificialintelligenceapproachesforlempclassification AT gabrielavsferreira performanceanalysisofartificialintelligenceapproachesforlempclassification AT wendlerlnmatos performanceanalysisofartificialintelligenceapproachesforlempclassification |