Browse > Article
http://dx.doi.org/10.5389/KSAE.2022.64.6.035

Development of a Stochastic Snow Depth Prediction Model Using a Bayesian Deep Learning Method  

Jeong, Youngjoon (Department of Rural Systems Engineering, Seoul National University)
Lee, Sang-ik (Department of Rural Systems Engineering, Research Institute of Agriculture and Life Sciences, Seoul National University)
Lee, Jonghyuk (Department of Rural Systems Engineering, Global Smart Farm Convergence Major, Seoul National University)
Seo, Byunghun (Department of Rural Systems Engineering, Global Smart Farm Convergence Major, Seoul National University)
Kim, Dongsu (Department of Rural Systems Engineering, Global Smart Farm Convergence Major, Seoul National University)
Seo, Yejin (Department of Rural Systems Engineering, Global Smart Farm Convergence Major, Seoul National University)
Choi, Won (Department of Rural Systems Engineering, Research Institute of Agriculture and Life Sciences, Global Smart Farm Convergence Major, Seoul National University)
Publication Information
Journal of The Korean Society of Agricultural Engineers / v.64, no.6, 2022 , pp. 35-41 More about this Journal
Abstract
Heavy snow damage can be prevented in advance with an appropriate security system. To develop the security system, we developed a model that predicts snow depth after a few hours when the snow depth is observed, and utilized it to calculate a failure probability with various types of greenhouses and observed snow depth data. We compared the Markov chain model and Bayesian long short-term memory models with varying input data. Markov chain model showed the worst performance, and the models that used only past snow depth data outperformed the models that used other weather data with snow depth (temperature, humidity, wind speed). Also, the models that utilized 1-hour past data outperformed the models that utilized 3-hour data and 6-hour data. Finally, the Bayesian LSTM model that uses 1-hour snow depth data was selected to predict snow depth. We compared the selected model and the shifting method, which uses present data as future data without prediction, and the model outperformed the shifting method when predicting data after 11-24 hours.
Keywords
Snow depth prediction; long short-term memory; Bayesian model; deep learning; time-series modeling;
Citations & Related Records
Times Cited By KSCI : 8  (Citation Analysis)
연도 인용수 순위
1 Kim, Y., N. Kang, S. Kim, and H. Kim, 2013. Evaluation for Snowfall Depth Forecasting using Neural Network and Multiple Regression Models. Korean Society of Hazard Mitigation, 13(2): 269-280. doi:10.9798/KOSHAM.2013.13.2.269. (in Korean).    DOI
2 Kim, Y., S. Kim, N. Kang, T. Kim, and H. Kim, 2014. Estimation of Frequency Based Snowfall Depth Considering Climate Change Using Neural Network. Journal of Korean Society of Hazard Mitigation, 14(1): 93-107. doi:10.9798/KOSHAM.2014.14.1.93. (in Korean).    DOI
3 Kwon, S. H., and G. Chung, 2017. Estimation of Snow Damages using Multiple Regression Model - The Case of Gangwon Province -. KSCE Journal of Civil and Environmental Engineering Research, 37(1): 61-72. doi:10.12652/Ksce.2017.37.1.0061. (in Korean).    DOI
4 Lee, H. J., and G. Chung, 2019. Categorical Prediction and Improvement Plan of Snow Damage Estimation using Random Forest. Journal of Wetlands Research, 21(2): 157-162. doi:10.17663/JWR.2019.21.2.157. (in Korean).    DOI
5 Lee, S. I., Y. J. Jeong, J. H, Lee, G. Chung, and W. Choi, 2020. Development of a heavy snowfall alarm model using  a Markov chain for disaster prevention to greenhouses. Biosystems Engineering, 200: 353-365. doi:10.1016/j.biosystemseng.2020.10.019.    DOI
6 Liang, H., M. Zhang, and H. Wang, 2019. A neural network model for wildfire scale prediction using meteorological factors. IEEE Access, 7: 176746-176755. doi:10.1109/ACCESS.2019.2957837.    DOI
7 Lu, H., M. Chen, and W. Kuang, 2020. The impacts of abnormal weather and natural disasters on transport and strategies for enhancing ability for disaster prevention and mitigation. Transport Policy, 98: 2-9. doi:10.1016/j.tranpol.2019.10.006.    DOI
8 Ministry of the Interior and Safety (2021), 2020 Disaster Report. pp. 276-352. 
9 Oh, Y., and G. Chung, 2017. Estimation of Snow Damage and Proposal of Snow Damage Threshold based on Historical Disaster Data. KSCE Journal of Civil and Environmental Engineering Research, 37(2): 325-331. doi:10.12652/Ksce.2017.37.2.0325. (in Korean).    DOI
10 Oh, Y., G. Lee, K. S. Jun, W. Sunwoo, S. Baek, and G. Chung, 2020. A Study on the Prediction of 390 Daily Snowmelt Depth using Multiple Linear Regression. Journal of the Korean Society of Hazard Mitigation, 20(6): 311-321. doi:10.9798/KOSHAM.2020.20.6.311. (in Korean).    DOI
11 Scherer, W. T., and D. M. Glagola, 1994. Markovian models for bridge maintenance management. Journal of Transportation Engineering, 120(1): 37-51. doi:10.1061/(ASCE)0733-947X(1994)120:1(37).    DOI
12 Park, H., S. Jeong, and G. Chung, 2014. Frequency Analysis of Future Fresh Snow Days and Maximum Fresh Snow Depth using Artificial Neural Network under Climate Change Scenarios. Journal of Korean Society of Hazard Mitigation, 14(6): 365-377. doi:10.9798/KOSHAM.2014.14.6.365. (in Korean).    DOI
13 Perera, A. T. D., V. M. Nik, D. Chen, J. L. Scartezzini, and T. Hong, 2020. Quantifying the impacts of climate change and extreme climate events on energy systems. Nature Energy, 5(2): 150-159. doi:10.1038/s41560-020-0558-0.    DOI
14 Roosli, T., C. Appenzeller, and D. N. Bresch, 2021. Towards operational impact forecasting of building damage from winter windstorms in Switzerland. Meteorological Applications, 28(6): e2035. doi:10.1002/met.2035.    DOI
15 Song, M. S., H. S. Yun, J. J. LeeD. M. S. G. Yum, 2022. A Comparative Analysis of Machine Learning Algorithms for Snowfall Prediction Models in South Korea, Natural Hazards and Earth System Sciences, preprint. doi:10.5194/nhess-2022-118.    DOI
16 Zhang, X., X. Li, L. Li, S. Zhang, and Q. Qin, 2019. Environmental factors influencing snowfall and snowfall prediction in the Tianshan Mountains, Northwest China. Journal of Arid Land, 11(1): 15-28. doi:10.1007/s40333-018-0110-2.    DOI
17 Blundell, C., J. Cornebise, K. Kavukcuoglu, and D. Wierstra, 2015. Weight Uncertainty in Neural Networks. arXiv preprint arXiv:1505.05424. doi:10.48550/arXiv.1505.05424.    DOI
18 Choi, C., J. Kim, J. Kim, D. Kim, Y. Bae, and H. S. Kim, 2018. Development of heavy rain damage prediction model using machine learning based on big data. Advances in Meteorology, 2018. doi:10.1155/2018/5024930.    DOI
19 Hamidi, O., L. Tapak, H. Abbasi, and Z. Maryanaji, 2018. Application of random forest time series, support vector regression and multivariate adaptive regression splines models in prediction of 365 snowfall (a case study of Alvand in  the middle Zagros, Iran). Theoretical and Applied Climatology, 134(3-4): 769-776. doi:10.1007/s00704-017-2300-9.    DOI
20 Hajikhodaverdikhan, P., M. Nazari, M. Mohsenizadeh, S. Shamshirband, and K. W. Chau, 2018. Earthquake prediction with meteorological data by particle filter-based support vector regression. Engineering Applications of Computational Fluid Mechanics, 12(1): 679-688. doi:10.1080/19942060.2018.1512010.    DOI
21 Hart, E., K. Sim, K. Kamimura, C. Meredieu, D. Guyon, and B. Gardiner, 2019. Use of machine learning techniques to model wind damage to forests. Agricultural and Forest Meteorology, 265: 16-29. doi:10.1016/j.agrformet.2018.10.022.    DOI
22 Hu, Y., T. Che, L. Dai, and L. Xiao, 2021. Snow depth fusion based on machine learning methods for the Northern Hemisphere. Remote Sensing, 13(7): 1250. doi:10.3390/rs13071250.    DOI
23 Kim, D., Y. Jeong, S, I, Lee, J, Lee, K. Hwang, and W. Choi, 2021. Development of Snow Load Sensor and Analysis of Warning Criterion for Heavy Snow Disaster Prevention Alarm System in Plastic Greenhouse. Journal of The Korean Society of Agricultural Engineers, 63(2): 75-84. doi:10.5389/KSAE.2021.63.2.075. (in Korean).    DOI