Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan
Sand and dust storms significantly challenge microwave and millimeter-wave communications, particularly in arid and semi-arid regions. Various models have been developed to predict attenuation caused by these storms theoretically and empirically based on two meteorological parameters, namely visibil...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843207/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586840531533824 |
|---|---|
| author | Elfatih A. A. Elsheikh E. I. Eltahir Abdulkadir Tasdelen Mosab Hamdan Md Rafiqul Islam Mohamed Hadi Habaebi Aisha H. Abdullah Hashim |
| author_facet | Elfatih A. A. Elsheikh E. I. Eltahir Abdulkadir Tasdelen Mosab Hamdan Md Rafiqul Islam Mohamed Hadi Habaebi Aisha H. Abdullah Hashim |
| author_sort | Elfatih A. A. Elsheikh |
| collection | DOAJ |
| description | Sand and dust storms significantly challenge microwave and millimeter-wave communications, particularly in arid and semi-arid regions. Various models have been developed to predict attenuation caused by these storms theoretically and empirically based on two meteorological parameters, namely visibility and humidity. However, these models are found unable to predict most of the attenuation measurements. This study presents a hybrid Machine Learning (ML) model that predicts dust storm attenuation for 22 GHz terrestrial links using meteorological data. The received signal levels were measured for a 22 GHz link over a month in Khartoum, Sudan. The visibility, humidity, atmospheric pressure, temperature and wind speed were also monitored simultaneously by Automatic Weather Station (AWS). The proposed model incorporates XGBoost for feature selection and combines Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers to capture both short-term and long-term dependencies in meteorological data. The results demonstrate a strong correlation between meteorological parameters and dust storm attenuation. The model’s performance is validated against the measured data at 22 GHz, outperforming existing empirical and theoretical models. The RMSE for the proposed model is 0.07, while all existing theoretical and empirical models are higher than 0.25. Furthermore, the proposed model demonstrates significant enhancements over the available ML model for dust attenuation prediction. This hybrid ML approach offers a more accurate and robust solution for predicting microwave and millimetre wave attenuation during dust storms, enhancing the reliability of communication systems in affected regions. |
| format | Article |
| id | doaj-art-1408718afe004d928cd4ccbbaff7bf6d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1408718afe004d928cd4ccbbaff7bf6d2025-01-25T00:01:33ZengIEEEIEEE Access2169-35362025-01-0113125541256510.1109/ACCESS.2025.353026110843207Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in SudanElfatih A. A. Elsheikh0https://orcid.org/0000-0001-9556-5861E. I. Eltahir1https://orcid.org/0000-0003-0891-5144Abdulkadir Tasdelen2https://orcid.org/0000-0003-4402-1463Mosab Hamdan3Md Rafiqul Islam4https://orcid.org/0000-0003-0808-2840Mohamed Hadi Habaebi5https://orcid.org/0000-0002-2263-0850Aisha H. Abdullah Hashim6https://orcid.org/0000-0001-6331-1373Department of Electrical Engineering, College of Engineering, King Khalid University, Abha, Saudi ArabiaDepartment of Electrical and Computer Engineering, Faculty of Engineering, International Islamic University Malaysia, Kuala Lumpur, MalaysiaDepartment of Electrical and Computer Engineering, Faculty of Engineering, International Islamic University Malaysia, Kuala Lumpur, MalaysiaSchool of Computing, National College of Ireland, Dublin 15, IrelandDepartment of Electrical and Computer Engineering, Faculty of Engineering, International Islamic University Malaysia, Kuala Lumpur, MalaysiaDepartment of Electrical and Computer Engineering, Faculty of Engineering, International Islamic University Malaysia, Kuala Lumpur, MalaysiaDepartment of Electrical and Computer Engineering, Faculty of Engineering, International Islamic University Malaysia, Kuala Lumpur, MalaysiaSand and dust storms significantly challenge microwave and millimeter-wave communications, particularly in arid and semi-arid regions. Various models have been developed to predict attenuation caused by these storms theoretically and empirically based on two meteorological parameters, namely visibility and humidity. However, these models are found unable to predict most of the attenuation measurements. This study presents a hybrid Machine Learning (ML) model that predicts dust storm attenuation for 22 GHz terrestrial links using meteorological data. The received signal levels were measured for a 22 GHz link over a month in Khartoum, Sudan. The visibility, humidity, atmospheric pressure, temperature and wind speed were also monitored simultaneously by Automatic Weather Station (AWS). The proposed model incorporates XGBoost for feature selection and combines Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers to capture both short-term and long-term dependencies in meteorological data. The results demonstrate a strong correlation between meteorological parameters and dust storm attenuation. The model’s performance is validated against the measured data at 22 GHz, outperforming existing empirical and theoretical models. The RMSE for the proposed model is 0.07, while all existing theoretical and empirical models are higher than 0.25. Furthermore, the proposed model demonstrates significant enhancements over the available ML model for dust attenuation prediction. This hybrid ML approach offers a more accurate and robust solution for predicting microwave and millimetre wave attenuation during dust storms, enhancing the reliability of communication systems in affected regions.https://ieeexplore.ieee.org/document/10843207/Dust storm attenuationmicrowave propagationmeteorological parametersterrestrial communicationmachine learningXGBoost |
| spellingShingle | Elfatih A. A. Elsheikh E. I. Eltahir Abdulkadir Tasdelen Mosab Hamdan Md Rafiqul Islam Mohamed Hadi Habaebi Aisha H. Abdullah Hashim Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan IEEE Access Dust storm attenuation microwave propagation meteorological parameters terrestrial communication machine learning XGBoost |
| title | Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan |
| title_full | Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan |
| title_fullStr | Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan |
| title_full_unstemmed | Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan |
| title_short | Dust Storm Attenuation Prediction Using a Hybrid Machine Learning Model Based on Measurements in Sudan |
| title_sort | dust storm attenuation prediction using a hybrid machine learning model based on measurements in sudan |
| topic | Dust storm attenuation microwave propagation meteorological parameters terrestrial communication machine learning XGBoost |
| url | https://ieeexplore.ieee.org/document/10843207/ |
| work_keys_str_mv | AT elfatihaaelsheikh duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT eieltahir duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT abdulkadirtasdelen duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT mosabhamdan duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT mdrafiqulislam duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT mohamedhadihabaebi duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan AT aishahabdullahhashim duststormattenuationpredictionusingahybridmachinelearningmodelbasedonmeasurementsinsudan |