Integration of PIGE, ANN, and MCNPX: From Accurate Detection of Microplastics to Global Standardization of Plastic Pollutant Monitoring | ||
| Pollution | ||
| دوره 12، شماره 1، بهار 2026، صفحه 46-57 اصل مقاله (1.15 M) | ||
| نوع مقاله: Original Research Paper | ||
| شناسه دیجیتال (DOI): 10.22059/poll.2025.391716.2846 | ||
| نویسندگان | ||
| Marjan Atghaei* 1؛ Mohammad Reza Rezaie1؛ Hossein Afarideh2؛ Javad Tayebi1 | ||
| 1Department of Nuclear Engineering, Faculty of Sciences and Modern Technologies, Graduate University of Advanced Technology, P.O.Box 76315-117, Kerman, Iran | ||
| 2Department of Nuclear Engineering, Faculty of Physics and Energy Engineering, Amirkabir University of Technology, P.O.Box 15875- 4413, Tehran, Iran | ||
| چکیده | ||
| Microplastic pollution in water sources poses a serious threat to human health and natural ecosystems. This research examines the efficiency of the proton-induced gamma emission (PIGE) method combined with bidirectional long short-term memory (Bi-LSTM) neural networks and MCNPX numerical simulations for the accurate detection of microplastics. Utilizing MCNPX simulations, the optimal proton energy (3 to 7 MeV) and predicted gamma spectra for environmental samples were determined. Results showed that the PIGE method is most effective at energies of 3 to 7 MeV for high concentrations and at higher energies for concentrations below 1%. The Bi-LSTM model, a subset of artificial neural networks with bidirectional architecture, was configured with a learning rate of 0.001 and trained over 100 epochs (with a batch size of 32). To prevent overfitting, Dropout and Batch Normalization layers were used, while Early Stopping and (ReduceLROnPlateau) mechanisms optimized the training process by monitoring the validation loss and dynamically adjusting the learning rate. This hybrid system achieved an accuracy of 95%, sensitivity of 93%, and an F1 score of 94%, indicating significant improvement over conventional methods. This approach offers a reliable solution for tracking microplastics and, due to its applicability in complex environments like oceans and groundwater, has the potential to become a global standard such as ISO. In the future, it can be integrated with the Internet of Things (IoT) for real-time monitoring and better environmental protection. | ||
| کلیدواژهها | ||
| Integration of Technologies؛ Microplastic Detection؛ MCNPX Simulation؛ Global Standardization؛ Artificial Intelligence؛ Environmental Science | ||
| مراجع | ||
|
| ||
|
آمار تعداد مشاهده مقاله: 384 تعداد دریافت فایل اصل مقاله: 307 |
||