Archives
 
Year 2025
 
Vol 66, Issue 5, [10 - 2025]

Optimizing the Prophet model using Bayesian Optimization for land subsidence prediction in central wards and communes of Ca Mau

DOI:10.46326/JMES.2025.66(5).04

  • Affiliations:

    1 Hanoi University of Civil Enginerring, Hanoi, Vietnam
    2 Hanoi University of Mining and Geology, Hanoi, Vietnam
    3 Hanoi University of Natural Resources and Environment, Hanoi, Vietnam

  • *Corresponding:
    This email address is being protected from spambots. You need JavaScript enabled to view it.
  • Received: 9th-July-2025
  • Revised: 3rd-Sept-2025
  • Accepted: 8th-Sept-2025
  • Online: 1st-Oct-2025
Pages: 41 - 51
Views: 42
View onlineView online
Downloads: 1
Downdload PDF
★★★★★Rating: , Total rating: 0
  • ★
  • ★
  • ★
  • ★
  • ★
Yours rating

Abstract:

Land subsidence in the Ca Mau region has become increasingly complex, posing a significant threat to the sustainable development of this coastal delta area. In this context, the temporal monitoring and forecasting of land subsidence are essential for early warning systems and for supporting disaster response and spatial planning. This study proposes the application of an advanced machine learning model-Prophet-integrated with Bayesian Optimization (BO) to improve the accuracy of temporal subsidence prediction. The dataset comprises time series of ground deformation at 1817 points, extracted using Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technology. These data were collected continuously from January 2015 to January 2019, with a total of 178 temporal acquisitions. Experimental results demonstrate that the Prophet model combined with BO achieves high predictive performance, with an average Root Mean Square Error (RMSE) of 3,4 mm and a Mean Absolute Error (MAE) of 2,6 mm. Notably, at the reference date of January 31, 2019, the predicted values exhibited a strong correlation with PS-InSAR observations (R²= 0,96). Given this level of accuracy, the proposed model shows great potential for long-term subsidence trend monitoring and risk mapping, particularly in areas with slow and stable subsidence such as the Ca Mau coastal plain.

How to Cite
Ha, K.Trung, Tran, A.Van, Pham, N.Quy, Luong, D.Ngoc, Vu, C.Dinh, Dang, H.Dieu and Nguyen, H.Dinh 2025. Optimizing the Prophet model using Bayesian Optimization for land subsidence prediction in central wards and communes of Ca Mau (in Vietnamese). Journal of Mining and Earth Sciences. 66, 5 (Oct, 2025), 41-51. DOI:https://doi.org/10.46326/JMES.2025.66(5).04.
References

Anh, T. V. , Dong, K. T., Khien H. T., Hanh, T. H., Nghi, L. T., Hoa, P. T. T., Dung, N., Anh, L. H., Dinh, N. Q. (2023). Land Subsidence Susceptibility Mapping Using Machine Learning in the Google Earth Engine Platform. Trong N.N. Dao, T. N. Thinh, N. T. Nguyen (Ed.), Intelligence of Things: Technologies and Applications (pp. 55 - 64). Springer. 

Anh, T. V., Khiên H.T.; Đông, K.T.; Nghị, L.T.; Hạnh, T.H.; and Phong, D.H. (2024). Nghiên cứu khả năng của mô hình học máy GB và SVR trong thành lập bản đồ nguy cơ lún đất khu vực bán đảo Cà Mau, Việt Nam. Tạp chí Khí tượng Thuỷ văn, số 757, trang 60-73. 

Bernd, B., Martin, B., Michel, L., Tobias, P., Jakob, R., Stefan, C., Janek, T., Theresa, U., Marc, B., Anne-Laure, B., Difan, D., and Marius, L. (2023). Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 13(4), 1474. 

Chang, H., Yang, Z., and Zhang, Y. (2025). Forecasting daily freight flow in cold regions of China using the hybrid Prophet model considering the importance of festivals and epidemic prevention policy. Research in Transportation Business and Management, 59, 101294. 

Chunlin, L. (2014). A simplified method for prediction of embankment settlement in clays. J. R. M. Geo. China, 6, 61-66. 

Dao, H. H.,  Nguyen, D. T. (2018). Assessment of the impacts of climate change on groundwater resources in Ca Mau peninsula. VNUHCM Journal of Engineering and Technology, 1, 43-52.

Đinh, X. V., Lê, T. N., and Nguyễn, V. Q. (2018). Xác định biến dạng của công trình xây dựng theo mô hình tham số ứng dụng lọc Kalman và mô hình phi tham số ứng dụng chuỗi thời gian. Tạp chí Khoa học ĐHQGHN: Các Khoa học Trái đất và Môi trường, số 34(3), trang 86-99.

Do, T. M., Nguyen, H. D. Q., Pham, Q. N., Le, D. T., Nguyen, L. Q., Tran, V. A., Gia, T. N. (2024). GNSS Time-Series Prediction Using Moving Average Filter and Multi-Layer Perceptron Neuron Network. Journal of the Polish Mineral Engineering Society, 121-131. 

Doãn, H. P., Trần, H. T. (2023). Ứng dụng trí tuệ nhân tạo trong xây dựng bản đồ nguy cơ ngập do nước biển dâng cho thành phố Hồ Chí Minh. Tạp chí Khí tượng Thuỷ văn, số 2, trang 96-107. 

Dongwei, Q., Yuci, T., Yuzheng, W., Keliang, D., Tiancheng, L., and Shanshan, W. (2024). Land subsidence analysis along high-speed railway based on EEMD‑Prophet method. Scientific Reports, 14(1). 

Drucker, H., Burges, C. J. C., Kaufman, L.; Smola, A; and Vapnik, V. (1997). Support Vector Regression Machines. Conference: Advances in NeuralInformandon Processing Systems 9, 155-161. 

EMSN062 (2019). Assessing changes in ground subsidence rates, Mekong Delta, Vietnam. https://mapping.emergency.copernicus.eu/activations/EMSN062/.

Erban, L., Gorelick, S., and Zebker, H. (2014). Groundwater extraction, land subsidence, and sea-level rise in the Mekong Delta, Vietnam. Environmental Research Letters, 9, 084010. 

Hung, W. C., Hwang, C., Tosi, L., Lin, G.-Z., Lin, S.-H., and Chen, Y.-A. . (2024). Near real-time subsidence monitoring and AI forecasting with multi-depth extensometers. SSRN. 

Karlsrud, K., Vangelsten, B. V., and Frauenfelder, R. (2017). Subsidence and Shoreline Retreat in the Ca Mau Province - Vietnam. Causes, Consequences and Mitigation Options. Geotechnical Engineering Journal of the SEAGS and AGSSEA, 48, 26-32. 

Ku, C.-Y., and Liu, C.-Y. (2023). Modeling of land subsidence using GIS-based artificial neural network in Yunlin County, Taiwan. Scientific Reports, 13, 4090.

Liu, J., Liu, W., Allechy, F., Zheng, Z., Liu, R., and Kouadio, L. (2024). Machine learning-based techniques for land subsidence simulation in an urban area. Journal of environmental management, 352, 120078. 

Liu, Z., Ng, A. H.-M., Wang, H., Chen, J., Du, Z., and Ge, L.. (2023). Land subsidence modeling and assessment in the West Pearl River Delta from combined InSAR time series, land use and geological data. International Journal of Applied Earth Observation and Geoinformation, 118, 103228.

Phạm, M. H., Vũ K. L. (2019). Nghiên cứu ứng dụng phương pháp học máy (machine learning) trong phân loại rừng ngập mặn trên ảnh viễn thám spot6 với khu vực thử nghiệm tại tỉnh Cà Mau. Tạp chí Khoa học Đo đạc và Bản đồ, số 40-6/2019, trang 17-21. 

Sekkeravani, A. M., Bazrafshan, O., Pourghasemi, H. R., and Holisaz, A. (2022). Spatial modeling of land subsidence using machine learning models and statistical methods. Environmental Science and Pollution Research, 29, 28866-28883. 

Shi, X. W., J., Ye, S., Zhang, Y., Xue, Y., Wei, Z., and Yu, J. (2008). Regional land subsidence simulation in Su-xi-Chang area and Shanghai City, China. Engineering Geology, 100(12), 27-42. 

Willmott, C.J. and Matsuura, K. (2005). Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in assessing average model performance. Climate Research, 30, 79-82.

Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. Proceedings of the 26th International Conference on Neural Information Processing Systems. December 03-06, Lake Tahoe, NV, United States, 2951-2959. 

Taylor, S. J., and Letham, B. (2018). Forecasting at scale. The American Statistician, 72, 37-45.

Tran, A. V., Brovelli, M. A., Ha, K. T., Khuc, D. T., Tran, D. N., Tran, H. H., and Le, N. T. . (2024). Land subsidence susceptibility mapping in Ca Mau

Province, Vietnam, using boosting models. SPRS International Journal of Geo-Information, 13(5), 161. 

Tran, Q. C., Vu, T. T., Batelaan, O., Pham, Q.-N. . (2024). Factors controlling land subsidence in the Southern Hau River Region, Vietnam. Groundwater for Sustainable Development, 27, 101383. 

Vân Anh, T., Hạnh, T. H., Hòa, P. T. T., Anh, T. Q., Vân Anh, N. T., Thu, P. T., and Thọ, T. Q. (2023). Nghiên cứu một số phương pháp học máy trong thành lập bản đồ lớp phủ bề mặt tỉnh Cà Mau trên nền tảng Google Earth Engine. Tạp chí Khoa học Đo đạc và Bản đồ, Số 55, trang 18-26.

Wang, H., Jia, C., Ding, P., Feng, K., Yang, X., and Zhu, X. (2023). Analysis and Prediction of Regional Land Subsidence with InSAR Technology and Machine Learning Algorithm. KSCE Journal of Civil Engineering, 27, 782-793.

Other articles