Machine Learning Applications to Dust Storms: A Meta-Analysis
Abstract Dust storms are natural hazards that affect both people and properties. Therefore, it is important to mitigate their risks by implementing an early notification system. Different methods are used to predict dust storms, such as observing satellite images, analyzing meteorological data, and...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-10-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.220183 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825197495392665600 |
|---|---|
| author | Reem K. Alshammari Omer Alrwais Mehmet Sabih Aksoy |
| author_facet | Reem K. Alshammari Omer Alrwais Mehmet Sabih Aksoy |
| author_sort | Reem K. Alshammari |
| collection | DOAJ |
| description | Abstract Dust storms are natural hazards that affect both people and properties. Therefore, it is important to mitigate their risks by implementing an early notification system. Different methods are used to predict dust storms, such as observing satellite images, analyzing meteorological data, and using numerical weather prediction model forecasts. However, recent studies have shown that machine learning algorithms have higher capacities to predict dust storms in less time and with fewer processing operations compared to numerical weather models. This paper conducted a meta-analysis review to examine studies that addressed the areas associated with the application of machine learning to dust storm prediction. It aims to compare the applied models and the types of data used in the literature under study. Given that the location of a dust storm event is essential, the properties of dust storms are discussed in relation to the region. The output classes and the various performance metrics observed in each reviewed paper are also summarized. Subsequently, the present paper offers a detailed analysis highlighting the capabilities of machine learning models in predicting dust storms. The analysis shows two main categories: early detection and dust storm prediction. Most models used for dust storm early detection from satellite images are support vector machines (SVM). In contrast, the most used models for dust storm prediction are SVM and random forests that predict the occurrence of dust storms from meteorological data. Finally, the paper highlights the challenges and future trends in the field, illustrating the potential directions for applying deep learning algorithms and providing long-range predictions with assessments of dust storm duration and intensity. |
| format | Article |
| id | doaj-art-3d456becdbf7406f9f0c3caddf061f5c |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2022-10-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-3d456becdbf7406f9f0c3caddf061f5c2025-02-09T12:18:15ZengSpringerAerosol and Air Quality Research1680-85842071-14092022-10-01221211210.4209/aaqr.220183Machine Learning Applications to Dust Storms: A Meta-AnalysisReem K. Alshammari0Omer Alrwais1Mehmet Sabih Aksoy2Information Systems Department, King Saud UniversityInformation Systems Department, King Saud UniversityInformation Systems Department, King Saud UniversityAbstract Dust storms are natural hazards that affect both people and properties. Therefore, it is important to mitigate their risks by implementing an early notification system. Different methods are used to predict dust storms, such as observing satellite images, analyzing meteorological data, and using numerical weather prediction model forecasts. However, recent studies have shown that machine learning algorithms have higher capacities to predict dust storms in less time and with fewer processing operations compared to numerical weather models. This paper conducted a meta-analysis review to examine studies that addressed the areas associated with the application of machine learning to dust storm prediction. It aims to compare the applied models and the types of data used in the literature under study. Given that the location of a dust storm event is essential, the properties of dust storms are discussed in relation to the region. The output classes and the various performance metrics observed in each reviewed paper are also summarized. Subsequently, the present paper offers a detailed analysis highlighting the capabilities of machine learning models in predicting dust storms. The analysis shows two main categories: early detection and dust storm prediction. Most models used for dust storm early detection from satellite images are support vector machines (SVM). In contrast, the most used models for dust storm prediction are SVM and random forests that predict the occurrence of dust storms from meteorological data. Finally, the paper highlights the challenges and future trends in the field, illustrating the potential directions for applying deep learning algorithms and providing long-range predictions with assessments of dust storm duration and intensity.https://doi.org/10.4209/aaqr.220183Machine learningDust storm detectionDust storm predictionDeep learning algorithms |
| spellingShingle | Reem K. Alshammari Omer Alrwais Mehmet Sabih Aksoy Machine Learning Applications to Dust Storms: A Meta-Analysis Aerosol and Air Quality Research Machine learning Dust storm detection Dust storm prediction Deep learning algorithms |
| title | Machine Learning Applications to Dust Storms: A Meta-Analysis |
| title_full | Machine Learning Applications to Dust Storms: A Meta-Analysis |
| title_fullStr | Machine Learning Applications to Dust Storms: A Meta-Analysis |
| title_full_unstemmed | Machine Learning Applications to Dust Storms: A Meta-Analysis |
| title_short | Machine Learning Applications to Dust Storms: A Meta-Analysis |
| title_sort | machine learning applications to dust storms a meta analysis |
| topic | Machine learning Dust storm detection Dust storm prediction Deep learning algorithms |
| url | https://doi.org/10.4209/aaqr.220183 |
| work_keys_str_mv | AT reemkalshammari machinelearningapplicationstoduststormsametaanalysis AT omeralrwais machinelearningapplicationstoduststormsametaanalysis AT mehmetsabihaksoy machinelearningapplicationstoduststormsametaanalysis |