Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance
Abstract Microplastic (MP) contamination on land has been estimated to be 32 times higher than in the oceans, and yet there is a distinct lack of research on soil MPs compared to marine MPs. Beaches are bridges between land and ocean and present equally understudied sites of microplastic pollution....
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-33207-x |
| _version_ | 1797841080813617152 |
|---|---|
| author | Faisal Raiyan Huda Florina Stephanie Richard Ishraq Rahman Saeid Moradi Clarence Tay Yuen Hua Christabel Anfield Sim Wanwen Ting Lik Fong Aazani Mujahid Moritz Müller |
| author_facet | Faisal Raiyan Huda Florina Stephanie Richard Ishraq Rahman Saeid Moradi Clarence Tay Yuen Hua Christabel Anfield Sim Wanwen Ting Lik Fong Aazani Mujahid Moritz Müller |
| author_sort | Faisal Raiyan Huda |
| collection | DOAJ |
| description | Abstract Microplastic (MP) contamination on land has been estimated to be 32 times higher than in the oceans, and yet there is a distinct lack of research on soil MPs compared to marine MPs. Beaches are bridges between land and ocean and present equally understudied sites of microplastic pollution. Visible-near-infrared (vis–NIR) has been applied successfully for the measurement of reflectance and prediction of low-density polyethylene (LDPE), polyethylene terephthalate (PET), and polyvinyl chloride (PVC) concentrations in soil. The rapidity and precision associated with this method make vis–NIR promising. The present study explores PCA regression and machine learning approaches for developing learning models. First, using a spectroradiometer, the spectral reflectance data was measured from treated beach sediment spiked with virgin microplastic pellets [LDPE, PET, and acrylonitrile butadiene styrene (ABS)]. Using the recorded spectral data, predictive models were developed for each microplastic using both the approaches. Both approaches generated models of good accuracy with R2 values greater than 0.7, root mean squared error (RMSE) values less than 3 and mean absolute error (MAE) < 2.2. Therefore, using this study’s method, it is possible to rapidly develop accurate predictive models without the need of comprehensive sample preparation, using the low-cost option ASD HandHeld 2 VNIR Spectroradiometer. |
| first_indexed | 2024-04-09T16:25:15Z |
| format | Article |
| id | doaj.art-77a07da20d6644ad9585e5c3bbf08886 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T16:25:15Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-77a07da20d6644ad9585e5c3bbf088862023-04-23T11:16:42ZengNature PortfolioScientific Reports2045-23222023-04-0113111010.1038/s41598-023-33207-xComparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectanceFaisal Raiyan Huda0Florina Stephanie Richard1Ishraq Rahman2Saeid Moradi3Clarence Tay Yuen Hua4Christabel Anfield Sim Wanwen5Ting Lik Fong6Aazani Mujahid7Moritz Müller8Faculty of Engineering, Computing and Science, Swinburne University of TechnologyFaculty of Engineering, Computing and Science, Swinburne University of TechnologyFaculty of Engineering, Computing and Science, Swinburne University of TechnologyFaculty of Science, Thompson Rivers UniversityFaculty of Engineering, Computing and Science, Swinburne University of TechnologyFaculty of Engineering, Computing and Science, Swinburne University of TechnologyFaculty of Engineering, Computing and Science, Swinburne University of TechnologyInstitute of Sustainable and Renewable Energy (ISuRE), Universiti Malaysia SarawakFaculty of Engineering, Computing and Science, Swinburne University of TechnologyAbstract Microplastic (MP) contamination on land has been estimated to be 32 times higher than in the oceans, and yet there is a distinct lack of research on soil MPs compared to marine MPs. Beaches are bridges between land and ocean and present equally understudied sites of microplastic pollution. Visible-near-infrared (vis–NIR) has been applied successfully for the measurement of reflectance and prediction of low-density polyethylene (LDPE), polyethylene terephthalate (PET), and polyvinyl chloride (PVC) concentrations in soil. The rapidity and precision associated with this method make vis–NIR promising. The present study explores PCA regression and machine learning approaches for developing learning models. First, using a spectroradiometer, the spectral reflectance data was measured from treated beach sediment spiked with virgin microplastic pellets [LDPE, PET, and acrylonitrile butadiene styrene (ABS)]. Using the recorded spectral data, predictive models were developed for each microplastic using both the approaches. Both approaches generated models of good accuracy with R2 values greater than 0.7, root mean squared error (RMSE) values less than 3 and mean absolute error (MAE) < 2.2. Therefore, using this study’s method, it is possible to rapidly develop accurate predictive models without the need of comprehensive sample preparation, using the low-cost option ASD HandHeld 2 VNIR Spectroradiometer.https://doi.org/10.1038/s41598-023-33207-x |
| spellingShingle | Faisal Raiyan Huda Florina Stephanie Richard Ishraq Rahman Saeid Moradi Clarence Tay Yuen Hua Christabel Anfield Sim Wanwen Ting Lik Fong Aazani Mujahid Moritz Müller Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance Scientific Reports |
| title | Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance |
| title_full | Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance |
| title_fullStr | Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance |
| title_full_unstemmed | Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance |
| title_short | Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance |
| title_sort | comparison of learning models to predict ldpe pet and abs concentrations in beach sediment based on spectral reflectance |
| url | https://doi.org/10.1038/s41598-023-33207-x |
| work_keys_str_mv | AT faisalraiyanhuda comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT florinastephanierichard comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT ishraqrahman comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT saeidmoradi comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT clarencetayyuenhua comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT christabelanfieldsimwanwen comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT tinglikfong comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT aazanimujahid comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance AT moritzmuller comparisonoflearningmodelstopredictldpepetandabsconcentrationsinbeachsedimentbasedonspectralreflectance |