GNSS Time-Series Prediction Using Moving Average Filter and Multi-Layer Perceptron Neuron Network

• Autorzy: Do Tuan Minh , Nguyen Huynh Dinh Quoc , Pham Quang Ngoc , Le Duc Tinh , Nguyen Long Quoc , Tran Van Anh , Gia Trong Nguyen

Identyfikatory

DOI

10.29227/IM-2024-02-98

Warianty tytułu

PL

Przewidywanie szeregów czasowych GNSS przy użyciu filtra średniej ruchomej i wielowarstwowej sieci neuronowej perceptronu

• Języki publikacji: EN

Abstrakty

EN

The Mekong Delta and Ho Chi Minh City in Vietnam are recognized as areas significantly impacted by land subsidence. This phenomenon has led to notable consequences, including increased vulnerability to issues such as saline intrusion and tidal flooding. GNSS-CORS technology, known for its capability to provide continuous time-series data, plays a crucial role in accurately monitoring changes in the land surface. Despite the existence of traditional algorithms for analyzing continuous measurement data collected through GNSS-CORS technology, their effectiveness is constrained by challenges in handling diverse input data and limitations in forecasting future displacements. Consequently, there is a growing trend towards the adoption of artificial intelligence techniques, particularly artificial neural networks (ANN), for predicting Up component in GNSS time-serries daily solution. This study leverages data from the CTHO GNSS CORS station located in the Mekong Delta to evaluate proposed models. An innovative hybrid approach, which integrates the Moving Average Filter (MAF) and Multilayer Perceptron Neural Network (MLPNN), is introduced to enhance the accuracy of forecasting. Performance evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) are utilized to assess the effectiveness of the models. Results demonstrate the superior performance of the MLPNN model, achieving high prediction accuracy with metrics including MAE = 0.001, MSE = 0.000, and RMSE = 0.002. This research underscores the robustness of the proposed model in forecasting GNSS time-serries daily solution, highlighting its potential for practical applications in geodetic research.

PL

Delta Mekongu i Ho Chi Minh City w Wietnamie są uznawane za obszary w znacznym stopniu dotknięte osiadaniem gruntu. Zjawisko to doprowadziło do znaczących konsekwencji, w tym zwiększonej podatności na takie zjawiska, jak wnikanie soli i powodzie pływowe. Technologia GNSS-CORS, znana ze swojej zdolności do dostarczania ciągłych danych szeregów czasowych, odgrywa kluczową rolę w dokładnym monitorowaniu zmian powierzchni ziemi. Pomimo istnienia tradycyjnych algorytmów do analizy ciągłych danych pomiarowych zebranych za pomocą technologii GNSS-CORS, ich skuteczność jest ograniczona wyzwaniami związanymi z obsługą różnorodnych danych wejściowych i ograniczeniami w prognozowaniu przyszłych przemieszczeń. W związku z tym istnieje rosnąca tendencja do przyjmowania technik sztucznej inteligencji, w szczególności sztucznych sieci neuronowych (ANN), do przewidywania komponentu Up w codziennym rozwiązaniu GNSS. Niniejsze badanie wykorzystuje dane ze stacji CTHO GNSS CORS zlokalizowanej w delcie Mekongu do oceny proponowanych modeli. Innowacyjne podejście hybrydowe, które integruje filtr średniej ruchomej (MAF) i wielowarstwową perceptronową sieć neuronową (MLPNN), zostało wprowadzone w celu zwiększenia dokładności prognozowania. Do oceny skuteczności modeli wykorzystano wskaźniki oceny wydajności, takie jak średni błąd bezwzględny (MAE), średni błąd kwadratowy (MSE) i średni błąd kwadratowy (RMSE). Wyniki pokazują doskonałą wydajność modelu MLPNN, osiągając wysoką dokładność przewidywania.

Słowa kluczowe

EN

land vertical movement; plate tectonic; Gamit/Globk; GNSS data analysis; machine learning; GNSS time series

PL

ruch pionowy lądu; tektonika płyt; Gamit/Globk; analiza danych GNSS; uczenie maszynowe; serie czasowe GNSS

• Wydawca: Polskie Towarzystwo Przeróbki Kopalin
• Czasopismo: Inżynieria Mineralna
• Rocznik: 2024
• Tom: Vol. 3, no. 2
• Strony: art. no. 98
• Opis fizyczny: Bibliogr. 28 poz., rys., tab., wykr., zdj.

Twórcy

autor

Do Tuan Minh

• Ho Chi Minh city of Natural Resources and Environment, Hochiminh city, Vietnam

• https://orcid.org/0000-0003-3172-5330

autor

Nguyen Huynh Dinh Quoc

• Ho Chi Minh city of Natural Resources and Environment, Hochiminh city, Vietnam

• https://orcid.org/0009-0007-8447-9045

autor

Pham Quang Ngoc

• Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam
• Geodesy and Environment research group, Hanoi University of Mining and Geology, Hanoi, Vietnam

• https://orcid.org/0009-0006-0765-245X

autor

Le Duc Tinh

• Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam

• https://orcid.org/0000-0003-2311-7351

autor

Nguyen Long Quoc

• Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam
• Innovations for Sustainable and Responsible Mining (ISRM) Research Group, Hanoi University of Mining and Geology, Hanoi, Vietnam

• https://orcid.org/0000-0002-0022-3453

autor

Tran Van Anh

• Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam
• Innovations for Sustainable and Responsible Mining (ISRM) Research Group, Hanoi University of Mining and Geology, Hanoi, Vietnam

• https://orcid.org/0000-0002-4792-3684

autor

Gia Trong Nguyen

• Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam
• Geodesy and Environment research group, Hanoi University of Mining and Geology, Hanoi, Vietnam

• https://orcid.org/0009-0003-1616-8625

Bibliografia

• 1. Abidin, H., et al. (2013). "Land subsidence in coastal city of Semarang (Indonesia): characteristics, impacts and causes." Geomatics, Natural Hazards and Risk 4(3): 226-240.
• 2. Abidin, H., et al. (2015). "On correlation between urban development, land subsidence and flooding phenomena in Jakarta." Proceedings of IAHS 370: 15-20.
• 3. Abidin, H. Z., et al. (2011). "Land subsidence of Jakarta (Indonesia) and its relation with urban development." Natural Hazards 59: 1753-1771.
• 4. Al Bitar, N. and A. Gavrilov (2021). "A new method for compensating the errors of integrated navigation systems using artificial neural networks." Measurement 168: 108391.
• 5. Catalao, J., et al. (2013). "Mapping vertical land movement in Singapore using InSAR GPS." ESA Spec. Publ 722: 54.
• 6. Chen, B., et al. (2017). "Characterization and causes of land subsidence in Beijing, China." International Journal of Remote Sensing 38(3): 808-826.
• 7. Chen, H., et al. (2023). "An Improved VMD-LSTM Model for Time-Varying GNSS Time Series Forcastion with Temporally Correlated Noise." Remote Sensing 15(14): 3694.
• 8. Construction, M. o. (2019). Trouble underground - Land Subsidence in the Mekong Delta. Vietnam.
• 9. Dinh, T. T., et al. (2023). "Crustal displacement in Vietnam using CORS data during 2018-2021." Earth Sciences Research Journal 27(1): 27-36.
• 10. Duong, N. A., et al. (2013). "Contemporary horizontal crustal movement estimation for northwestern Vietnam inferred from repeated GPS measurements." Earth, Planets and Space 65(12): 1399-1410.
• 11. Duong Van Phong, N. G. T., Nguyen Van Chien. Nguyen Ha Thanh, Ly Lam Ha, Nguyen Viet Quan, Pham Ngoc Quang (2023). "Analysis of land vertical movement using ANN function from the results of processing GNSS time series data." Vietnam Journal of Hydro-Meteorology: 41-50.
• 12. Ezquerro, P., et al. (2020). "Vulnerability assessment of buildings due to land subsidence using InSAR data in the ancient historical city of Pistoia (Italy)." Sensors 20(10): 2749.
• 13. Gao, W., et al. (2022). "Modelling and forcastion of GNSS time series using GBDT, LSTM and SVM machine learning approaches." Journal of Geodesy 96(10): 71.
• 14. Goudarzi, M. A. (2016). GPS inferred velocity and strain rate fields in eastern Canada, Université Laval.
• 15. Hammond, W. C., et al. (2021). "GPS imaging of global vertical land motion for studies of sea level rise." Journal of Geophysical Research: Solid Earth 126(7): e2021JB022355.
• 16. Kall, T., et al. (2019). "The noise properties and velocities from a time-series of Estonian permanent GNSS stations." Geosciences 9(5): 233.
• 17. Kiani, M. (2020). "Lateral land movement forcastion from GNSS position time series in a machine learning aided algorithm." arXiv preprint arXiv:2006.07891.
• 18. Lau, N. N., et al. (2021). "Determination of tectonic velocities of some continuously operating reference stations (CORS) in Vietnam 2016-2018 by using precise point positioning."
• 19. Li, Y. (2021). "Analysis of GAMIT/GLOBK in high-precision GNSS data processing for crustal deformation." Earthquake Research Advances 1(3): 100028.
• 20. Nguyễn Gia Trọng, L. T. T., Nguyễn Hà Thành, Phạm Ngọc Quang, Nguyễn Văn Cương (2021). First step determination the movement of some CORS stations in the Northern of Vietnam using Gamit/Globk software. National conference on Geospatial technology in Earth sicence and Environment, Hanoi University of Mining and Geology.
• 21. Orhan, O., et al. (2021). "Land subsidence and its relations with sinkhole activity in Karapınar region, Turkey: a multi-sensor InSAR time series study." Sensors 21(3): 774.
• 22. Quân, N. V., et al. (2021). "Ứng dụng mạng lưới trạm định vị vệ tinh quốc gia (VNGEONET) trong hoạt động đo đạc bản đồ, nghiên cứu khoa học Trái Đất và một số lĩnh vực khác trong thời kỳ chuyển đổi số." Hội nghị khoa học quốc gia về công nghệ địa không gian trong khoa học Trái Đất và môi trường, Hà Nội.
• 23. Shahvandi, M. K. and B. Soja (2021). Modified Deep Transformers for GNSS Time Series Forcastion. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS.
• 24. Sivavaraprasad, G., et al. (2020). "Performance evaluation of neural network TEC forecasting models over equatorial low-latitude Indian GNSS station." Geodesy and Geodynamics 11(3): 192-201.
• 25. Trần, Đ. T., et al. (2013). "Recent crustal movements of northern Vietnam from GPS data." Journal of Geodynamics 69: 5-10.
• 26. Trọng, N. G., et al. (2022). "Determination of tectonic velocities in Vietnam territory based on data of CORS stations of VNGEONET network." Vietnam Journal of Hydro-Meteorology: 59 - 66.
• 27. Wang, J., et al. (2021). "A new multi-scale sliding window LSTM framework (MSSW-LSTM): a case study for GNSS time-series forcastion." Remote Sensing 13(16): 3328.
• 28. Zhao, Q., et al. (2023). "The vertical velocity field of the Tibetan Plateau and its surrounding areas derived from GPS and surface mass loading models." Earth and Planetary Science Letters 609: 118107

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).