Blasting is an effective method to prevent avalanches, but it is difficult to determine the appropriate blasting time, blasting location and blasting energy. This study began by collecting and preprocessing indicator data about avalanches. Then we conducted exploratory data analysis on the data, and found a strong seasonal pattern in avalanche occurrences. Using 80% of the data as the training set and 20% as the test set, the support vector machine, random forest and perceptron neural network models were established, with parameters optimized using the Bayesian optimization algorithm. The results showed that the perceptron neural network achieved the highest accuracy. Subsequently, the three models were integrated according to the loss degree, and three integration strategies were compared. The results showed that the highest accuracy of the SVM-RF-MLP model was 0.952. A basic blasting energy model was then developed, taking into account the changes in mountain height and snow layer density over time. Using historical data, a dynamic avalanche stability blasting energy model was built to identify the distribution patterns in snow layer stability. The data is simulated and verified, and a three-dimensional mountain visualization analysis is performed to obtain the optimal blasting timing, blasting location and blasting energy.
[1] 段仕美, 刘时银, 朱钰, 等. 梅里雪山1991年和2019年雪崩事件重建及影响因素分析[J]. 冰川冻土, 2022, 44(3): 771-783. Duan S M, Liu S Y, Zhu Y, et al. Reconstruction of avalanche events in Meili Snow Mountain in 1991 and 2019 and analysis of influencing factors [J]. Journal of Glaciology and Geocryology, 2022, 44(3): 771-783. (in Chinese)
[2] Keylock C J, Mcclung D M, Magnússon M M. Avalanche risk mapping by simulation [J]. Journal of Glaciology, 1999, 45(150): 303-314.
[3] Eckert N, Giacona F. Towards a holistic paradigm for long-term snow avalanche risk assessment and mitigation [J]. Ambio, 2023, 52(4): 711-732.
[4] Schweizer J, Mitterer C, Techel F, et al. On the relation between avalanche occurrence and avalanche danger level [J]. The Cryosphere, 2020, 14(2): 737-750.
[5] Alruhaymi A Z, Kim C J. Study on the missing data mechanisms and imputation methods [J]. Open Journal of Statistics, 2021, 11(4): 477-492.
[6] Fees A, Van Herwijnen A, Lombardo M, et al. Glide-snow avalanches: a mechanical, threshold-based release area model [J]. Natural Hazards and Earth System Sciences, 2024, 24(10): 3387-3400.
[7] Roebber P J, Bruening S L, Schultz D M, et al. Improving snowfall forecasting by diagnosing snow density [J]. Weather and Forecasting, 2003, 18: 264-287.
[8] Yang Y Q, Lyu H J, Chen N. A survey on ensemble learning under the era of deep learning [J]. Artificial Intelligence Review, 2023, 56(6): 5545-5589.
[9] 林报嘉, 刘晓东, 杨川, 等. XGBoost机器学习模型与GIS技术结合的公路崩塌灾害易发性研究[J]. 公路, 2020, 65(7): 20-26. Lin B J, Liu X D, Yang C, et al. Study on the susceptibility of highway collapse disasters based on XGBoost machine learning model and GIS technology [J]. Highway, 2020, 65(7): 20-26. (in Chinese)
[10] 张远汀, 龚伟伟, 叶钰, 等. 应用机器学习技术预测强雨雪天气过程中的积雪[J]. 科学技术与工程, 2019, 19(15): 58-69. Zhang Y T, Gong W W, Ye Y, et al. Application of machine learning technology to predict snow accumulation during heavy rain and snow weather [J]. Science Technology and Engineering, 2019, 19(15): 58-69. (in Chinese)
[11] 杨倩, 秦莉, 高培, 等. 基于RBF网络的新疆特重雪灾区最大积雪深度预测研究[J]. 沙漠与绿洲气象, 2024, 18(1): 89-95. Yang Q, Qin L, Gao P, et al. Research on prediction of maximum snow depth in Xinjiang heavy snow disaster area based on RBF network [J]. Desert and Oasis Meteorology, 2024, 18(1): 89-95. (in Chinese)
[12] Kundu S, Chakrabarti B K, Biswas S. Inequality of avalanche sizes in models of fracture [J]. Physical Review E, 2023, 108(1): 014103.
[13] Maissen A, Techel F, Volpi M. A three-stage model pipeline predicting regional avalanche danger in Switzerland (RAvaFcast v1.0.0): a decision-support tool for operational avalanche forecasting [J]. Geoscientific Model Development, 2024, 17(21): 7569-7593.
[14] 文洪, 巫锡勇, 赵思远, 等. 基于机器学习法的青藏高原沙鲁里山系中段雪崩易发性评价研究[J]. 冰川冻土, 2022, 44(6): 1694-1706. Wen H, Wu X Y, Zhao S Y, et al. Snow avalanche susceptibility evaluation in the central Shaluli Mountains of Tibetan Plateau based on machine learing method [J]. Journal of Glaciology and Geocryology, 2022, 44(6): 1694-1706. (in Chinese)
[15] Hendrick M, Techel F, Volpi M, et al. Automated prediction of wet-snow avalanche activity in the Swiss Alps [J]. Journal of Glaciology, 2023, 69(277): 1365-1378.
[16] Reuter B, Hagenmuller P, Eckert N. Snow and avalanche climates in the French Alps using avalanche problem frequencies [J]. Journal of Glaciology, 2023, 69(277): 1292-1304.
[17] Salazar S, Dahle H, Dupuy B, et al. Multisensor UAS testing to support avalanche forecasting and monitoring [C]//84th EAGE Annual Conference & Exhibition. European Association of Geoscientists & Engineers, 2023, 2023(1): 1-71.
[18] Horton S, Haegeli P. Using snow depth observations to provide insight into the quality of snowpack simulations for regional-scale avalanche forecasting [J]. The Cryosphere, 2022, 16(8): 3393-3411.
[19] 赵征, 刘赛恒, 王金, 等. 基于ISSA-ELM-NARMAX的垃圾焚烧炉燃烧过程动态建模及多目标优化 [J]. 动力工程学报, 2024, 44(8): 1264-1271. Zhao Z, Liu S H, Wang J, et al. Dynamic modeling and multi-objective optimization of waste incinerator combustion process based on ISSA-ELM-NARMAX [J]. Journal of Power Engineering, 2024, 44(8): 1264-1271. (in Chinese)
[20] 段仕美. 梅里雪山重大雪崩事件重建与雪崩风险评估研究[D]. 昆明: 云南大学, 2022.
[21] 陈联君. 基于多源数据的雪崩危险性评价[D]. 武汉: 中国地质大学, 2021.
[22] Afrifa-Yamoah E, Mueller U A, Taylor S M, et al. Missing data imputation of highresolution temporal climate time series data [J]. Meteorological Applications, 2020, 27(1): e1873.
[23] Blagovechshenskiy V, Medeu A, Gulyayeva T, et al. Application of artificial intelligence in the assessment and forecast of avalanche danger in the Ile Alatau Ridge [J]. Water, 2023, 15(7): 1438.
[24] Mayer S, Techel F, Schweizer J, et al. Prediction of natural dry-snow avalanche activity using physics-based snowpack simulations [J]. Natural Hazards and Earth System Sciences, 2023, 23(11): 3445-3465.
[25] Toft H B, Müller K, Hendrikx J, et al. Can big data and random forests improve avalanche runout estimation compared to simple linear regression? [J]. Cold Regions Science and Technology, 2023, 211: 103844.
