台灣因位處熱帶與副熱帶交界且四面環海，山地面積占比約是整體面積三分之二，除了帶有水氣的季風隨著地勢抬升造成的降雨外，每年五、六月固定會經過之滯留鋒和夏季對流旺盛所產生之降雨，甚至於夏季和秋季，還會有颱風的侵犯，使每年的降雨量在世界排名中名列前茅。而於降雨後，水會透過滲透等方式，從地表漸漸流至土壤或岩石縫隙中，隨之而來的就是地下水位的變化，導致邊坡可能變得不穩定進而產生破壞。而台灣山地面積高占比之原因，則是因台灣位處環太平洋地震帶及位處多板塊之交界處，屬新褶曲山脈，板塊的擠壓導致地震頻繁，故於邊坡穩定之分析中，考慮地震之影響也相當重要。
本研究考慮台灣之所處之氣候，以及特殊之地理位置、地質條件、和地形變化，透過考慮不同地下水位，以及不同水平地震力係數 (kh) 之影響，對岩石邊坡進行分析，於 OPTUM G2軟體設定數值分析模型，使用Hoek-Brown破壞準則設定岩石參數，並於模型中設置相對地下水位，以擬靜態的方式進行多組邊坡穩定性分析後，結合人工智慧方法，將結果應用於iOS系統之行動裝置應用程式，並透過結合斜坡單元概念，於地理資訊系統（Geographic Information System, GIS）軟體ArcGIS pro 內開發安全係數地圖之製作流程，可視化數值分析之結果。

Located at the boundary between the tropics and subtropics, surrounded by the sea, Taiwan has about two-thirds of its total area covered by mountains. In addition to rainfall caused by the uplifting of moist monsoons due to the terrain, there are fixed periods of stagnant fronts and intense convective rainfall in May and June. Furthermore, typhoons during the summer and autumn seasons often affect Taiwan, leading to high annual precipitation rankings worldwide. Following rainfall, water gradually infiltrates through the surface and seeps into the soil or rock fractures, resulting in changes in the groundwater level. This fluctuation can destabilize slopes and lead to destructive events. The significant proportion of mountainous terrain in Taiwan is attributed to its location along the Pacific Ring of Fire and the convergence of multiple tectonic plates. Being part of the neo-tectonic orogenic belt, the squeezing of plates induces frequent earthquakes, making seismic considerations crucial in slope stability analyses.
This study takes into account Taiwan's climate, unique geographical position, geological conditions, and topographical variations. Analyzing rock slopes with consideration for different groundwater levels and varying horizontal seismic coefficients (kh), the research employs the OPTUM G2 software to establish numerical analysis models. The Hoek-Brown failure criterion is used to define rock parameters and relative groundwater levels are incorporated into the model. Multiple slope stability analyses are then conducted in a pseudo-static manner. By integrating artificial intelligence (AI) techniques, the results are applied to a mobile application for iOS devices. Furthermore, leveraging the concept of slope units, the study develops a workflow within the GIS system (ArcGIS Pro) to create safety factor maps, visualizing the outcomes of numerical analyses.

[1] 陳威翰（2019）。運用人工智慧評估受地震影響之岩石邊坡 穩定性及可靠度。﹝碩士論文。國立臺灣科技大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/5y6n66。
[2] 賴忠其（2020）。運用人工智慧評估受地下水位影響之岩石邊坡 穩定性及可靠度。﹝碩士論文。國立臺灣科技大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/26xjyp 。
[3] 陳立軒（2021）。人工智慧技術運用於岩石邊坡穩定性及可靠度評估。﹝碩士論文。國立臺灣科技大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/53j5yn 。
[4] Hoek, E., & Bray, J. D. (1981). Rock slope engineering. CRC press.
[5] Coulomb, C. A. (1776). Essai Sur Une Application Des Maximis et Minimis a Queques problems Des Statique Relatifsa1‟ Architecture. Nem. Div. Sav. Acad, Sci, 7.
[6] Brown, E. T., & Hoek, E. (1980). Underground excavations in rock. CRC Press.
[7] RowN, E. T. (1988). The Hoek-Brown failure criterion–a 1988 update. In Proc. 15th Can. Rock Mech. Symp, Toronto, Canada.
[8] Hoek, E., Carranza-Torres, C., & Corkum, B. (2002). Hoek-Brown failure criterion-2002 edition. Proceedings of NARMS-Tac, 1(1), 267-273.
[9] Hoek, E., & Brown, E. T. (2019). The Hoek–Brown failure criterion and GSI–2018 edition. Journal of Rock Mechanics and Geotechnical Engineering, 11(3), 445-463.
[10] Hoek, E., & Marinos, P. (2000). Predicting tunnel squeezing problems in weak heterogeneous rock masses. Tunnels and tunnelling international, 32(11), 45-51.
[11] Hoek, E. (1998). Reliability of Hoek-Brown estimates of rock mass properties and their impact on design. International Journal of Rock Mechanics and Mining Sciences, 35(1), 63-68.
[12] Li, A. J., Merifield, R. S., & Lyamin, A. V. (2008). Stability charts for rock slopes based on the Hoek–Brown failure criterion. International Journal of Rock Mechanics and Mining Sciences, 45(5), 689-700.
[13] Drucker, D. C., Greenberg, H. J., & Prager, W. (1951). The safety factor of an elastic-plastic body in plane strain.
[14] Drucker, D. C., Prager, W., & Greenberg, H. J. (1952). Extended limit design theorems for continuous media. Quarterly of applied mathematics, 9(4), 381-389.
[15] Sloan, S. W. (2013). Geotechnical stability analysis. Géotechnique, 63(7), 531-571.
[16] Lyamin, A. V., & Sloan, S. W. (2002). Lower bound limit analysis using non‐linear programming. International journal for numerical methods in engineering, 55(5), 573-611.
[17] Lyamin, A. V., & Sloan, S. W. (2002). Upper bound limit analysis using linear finite elements and non‐linear programming. International Journal for Numerical and Analytical Methods in Geomechanics, 26(2), 181-216.
[18] Li, A. J., Lyamin, A. V., & Merifield, R. S. (2009). Seismic rock slope stability charts based on limit analysis methods. Computers and Geotechnics, 36(1-2), 135-148.
[19] Michalowski, R. L. (2010). Limit analysis and stability charts for 3D slope failures. Journal of Geotechnical and Geoenvironmental Engineering, 136(4), 583-593.
[20] Li, A. J., Merifield, R. S., & Lyamin, A. V. (2011). Effect of rock mass disturbance on the stability of rock slopes using the Hoek–Brown failure criterion. Computers and Geotechnics, 38(4), 546-558.
[21] Shen, J., Karakus, M., & Xu, C. (2013). Chart-based slope stability assessment using the Generalized Hoek–Brown criterion. International Journal of Rock Mechanics and Mining Sciences, 64, 210-219.
[22] Tschuchnigg, F., Schweiger, H. F., & Sloan, S. W. (2015). Slope stability analysis by means of finite element limit analysis and finite element strength reduction techniques. Part I: Numerical studies considering non-associated plasticity. Computers and Geotechnics, 70, 169-177.
[23] Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985). A learning algorithm for Boltzmann machines. Cognitive science, 9(1), 147-169.
[24] Abeles, M. (1991). Neural circuits of the cerebral cortex. Corticonics.
[25] Abbott, L. F., Varela, J. A., Sen, K., & Nelson, S. B. (1997). Synaptic depression and cortical gain control. Science, 275(5297), 221-224.
[26] Agam, Y., Bullock, D., & Sekuler, R. (2005). Imitating unfamiliar sequences of connected linear motions. Journal of Neurophysiology, 94(4), 2832-2843.
[27] Medsker, L. R., & Jain, L. C. (2001). Recurrent neural networks. Design and Applications, 5(64-67), 2.
[28] Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
[29] Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993). Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural networks, 6(6), 861-867.
[30] Li, A. J., Khoo, S., Lyamin, A. V., & Wang, Y. (2016). Rock slope stability analyses using extreme learning neural network and terminal steepest descent algorithm. Automation in Construction, 65, 42-50.
[31] Xu, Jingshu, Pan, Qiujing, Yang, X. L., and Li, Wentao. "Stability charts for rock slopes subjected to water drawdown based on the modified nonlinear Hoek-Brown failure criterion." International Journal of Geomechanics 18.1 (2017): 04017133.
[32] Carrara, A., Guzzetti, F., Cardinali, M., and Reichenbach, P. (1991). Use of GIS technology in the prediction and monitoring of landslide hazard. Nat. Hazards, 4(2-3), 117-135.
[33] Giles, D., and Franklin, S. (1998). Recognizing geomorphic features from DEMs using fuzzy logic. J. Geogr. Syst., 1(3), 251-267.
[34] Guzzetti, F., Carrara, A., Cardinali, M., and Reichenbach, P. (1999). Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, central Italy. Geomorphology, 31(1-4), 181-216.
[35] Jackson, L. E. (1997). Slope unit theory and geographic information systems. Soil Sci. Soc. Am. J., 61(6), 1719-1730.
[36] Xie, M., Chen, X., and Zou, S. (2004). Debris flow hazard assessment for land-use planning. Geomorphology, 60(3-4), 335-354.