A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula

<p dir="ltr">Accurate forecasting of environmental pollution indicators holds significant importance in diverse fields, including climate modeling, environmental monitoring, and public health. In this study, we investigate a wide range of machine learning and deep learning models to...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ahmad Qadeib Alban (16855206) (author)
مؤلفون آخرون: Ammar Abulibdeh (15785928) (author), Lanouar Charfeddine (10705000) (author), Rawan Abulibdeh (19206115) (author), Abdelgadir Abuelgasim (21841442) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513543055867904
author Ahmad Qadeib Alban (16855206)
author2 Ammar Abulibdeh (15785928)
Lanouar Charfeddine (10705000)
Rawan Abulibdeh (19206115)
Abdelgadir Abuelgasim (21841442)
author2_role author
author
author
author
author_facet Ahmad Qadeib Alban (16855206)
Ammar Abulibdeh (15785928)
Lanouar Charfeddine (10705000)
Rawan Abulibdeh (19206115)
Abdelgadir Abuelgasim (21841442)
author_role author
dc.creator.none.fl_str_mv Ahmad Qadeib Alban (16855206)
Ammar Abulibdeh (15785928)
Lanouar Charfeddine (10705000)
Rawan Abulibdeh (19206115)
Abdelgadir Abuelgasim (21841442)
dc.date.none.fl_str_mv 2024-04-29T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s41748-024-00398-w
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Comprehensive_Machine_and_Deep_Learning_Approach_for_Aerosol_Optical_Depth_Forecasting_New_Evidence_from_the_Arabian_Peninsula/29714987
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Earth sciences
Atmospheric sciences
Environmental sciences
Environmental management
Health sciences
Public health
Information and computing sciences
Machine learning
Aerosol optical depth
Time series forecasting
Deseasonalization
Machine and deep learning models
Feature extraction
dc.title.none.fl_str_mv A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Accurate forecasting of environmental pollution indicators holds significant importance in diverse fields, including climate modeling, environmental monitoring, and public health. In this study, we investigate a wide range of machine learning and deep learning models to enhance Aerosol Optical Depth (AOD) predictions for the Arabian Peninsula (AP) region, one of the world’s main dust source regions. Additionally, we explore the impact of feature extraction and their different types on the forecasting performance of each of the proposed models. Preprocessing of the data involves inputting missing values, data deseasonalization, and data normalization. Subsequently, hyperparameter optimization is performed on each model using grid search. The empirical results of the basic, hybrid and combined models revealed that the convolutional long short-term memory and Bayesian ridge models significantly outperformed the other basic models. Moreover, for the combined models, specifically the weighted averaging scheme, exhibit remarkable predictive accuracy, outperforming individual models and demonstrating superior performance in longer-term forecasts. Our findings emphasize the efficacy of combining distinct models and highlight the potential of the convolutional long short-term memory and Bayesian ridge models for univariate time series forecasting, particularly in the context of AOD predictions. These accurate daily forecasts bear practical implications for policymakers in various areas such as tourism, transportation, and public health, enabling better planning and resource allocation.</p><h2>Other Information</h2><p dir="ltr">Published in: Earth Systems and Environment<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s41748-024-00398-w" target="_blank">https://dx.doi.org/10.1007/s41748-024-00398-w</a></p>
eu_rights_str_mv openAccess
id Manara2_db1ea088f8693990fa0ff1b2372e90d7
identifier_str_mv 10.1007/s41748-024-00398-w
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29714987
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian PeninsulaAhmad Qadeib Alban (16855206)Ammar Abulibdeh (15785928)Lanouar Charfeddine (10705000)Rawan Abulibdeh (19206115)Abdelgadir Abuelgasim (21841442)Earth sciencesAtmospheric sciencesEnvironmental sciencesEnvironmental managementHealth sciencesPublic healthInformation and computing sciencesMachine learningAerosol optical depthTime series forecastingDeseasonalizationMachine and deep learning modelsFeature extraction<p dir="ltr">Accurate forecasting of environmental pollution indicators holds significant importance in diverse fields, including climate modeling, environmental monitoring, and public health. In this study, we investigate a wide range of machine learning and deep learning models to enhance Aerosol Optical Depth (AOD) predictions for the Arabian Peninsula (AP) region, one of the world’s main dust source regions. Additionally, we explore the impact of feature extraction and their different types on the forecasting performance of each of the proposed models. Preprocessing of the data involves inputting missing values, data deseasonalization, and data normalization. Subsequently, hyperparameter optimization is performed on each model using grid search. The empirical results of the basic, hybrid and combined models revealed that the convolutional long short-term memory and Bayesian ridge models significantly outperformed the other basic models. Moreover, for the combined models, specifically the weighted averaging scheme, exhibit remarkable predictive accuracy, outperforming individual models and demonstrating superior performance in longer-term forecasts. Our findings emphasize the efficacy of combining distinct models and highlight the potential of the convolutional long short-term memory and Bayesian ridge models for univariate time series forecasting, particularly in the context of AOD predictions. These accurate daily forecasts bear practical implications for policymakers in various areas such as tourism, transportation, and public health, enabling better planning and resource allocation.</p><h2>Other Information</h2><p dir="ltr">Published in: Earth Systems and Environment<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s41748-024-00398-w" target="_blank">https://dx.doi.org/10.1007/s41748-024-00398-w</a></p>2024-04-29T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s41748-024-00398-whttps://figshare.com/articles/journal_contribution/A_Comprehensive_Machine_and_Deep_Learning_Approach_for_Aerosol_Optical_Depth_Forecasting_New_Evidence_from_the_Arabian_Peninsula/29714987CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/297149872024-04-29T09:00:00Z
spellingShingle A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
Ahmad Qadeib Alban (16855206)
Earth sciences
Atmospheric sciences
Environmental sciences
Environmental management
Health sciences
Public health
Information and computing sciences
Machine learning
Aerosol optical depth
Time series forecasting
Deseasonalization
Machine and deep learning models
Feature extraction
status_str publishedVersion
title A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
title_full A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
title_fullStr A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
title_full_unstemmed A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
title_short A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
title_sort A Comprehensive Machine and Deep Learning Approach for Aerosol Optical Depth Forecasting: New Evidence from the Arabian Peninsula
topic Earth sciences
Atmospheric sciences
Environmental sciences
Environmental management
Health sciences
Public health
Information and computing sciences
Machine learning
Aerosol optical depth
Time series forecasting
Deseasonalization
Machine and deep learning models
Feature extraction