Ren Dan, Jia Zhiqiang
College of Earth Science, Guilin University of Technology, Guilin, China
It is crucial to undertake thorough study and data mining on factors that determine the occurrence of geohazards to prevent and anticipate their occurrence. A small-sample learning method with a strong theoretical underpinning, the classical support vector machine model provides considerable expressive power in dealing with the interaction of nonlinear characteristics and lessens reliance on the entire data set. However, its excellent generalization capabilities result in an excessively large optimal search space, which impacts the search for kernel parameters and reduces the model’s accuracy. The particle swarm algorithm, which has a robust search capability, is thus introduced to improve it. This paper's research area is Chian Town, China. The prediction study of geological hazard susceptibility in Chian town was validated using Gaofen 2 remote sensing imagery in conjunction with a support vector machine regression model enhanced by the particle swarm algorithm. The findings show that the high-risk zone comprises 17% of the overall area and has an 88.88% prediction accuracy. The results imply that integrating high-resolution remote sensing imagery-based and optimized machine learning algorithm models has prospective applications in investigating geological hazard susceptibility with small samples, numerous feature factors, and large-scale data.
High-resolution remote sensing, PSO-SVR, Geological hazard
Ren Dan, Jia Zhiqiang. Geological Hazard Susceptibility Assessment Based on RS and PSO-SVR Model. Academic Journal of Environment & Earth Science (2023) Vol. 5 Issue 1: 62-70. https://doi.org/10.25236/AJEE.2023.050109.
 BA. Akgun et al., “An easy-to-use MATLAB program (MamLand) for the assessment of landslide susceptibility using a Mamdani fuzzy algorithm [J].” Computers & Geosciences. 38(1):23-34(2012)
 Wang Shang-qing et al., “Early warning method of landslide danger in Baishui River of Three Gorges Reservoir [J].” Journal of Wuhan University (Information Science Edition).34(10):1218-1221(2009)
 He Manchao. “Remote monitoring and forecasting system for landslide geological hazards and its engineering application[J].” Journal of Rock Mechanics and Engineering.28(06):1081-1090(2009)
 J, Mathew, et al., “Landslide susceptibility zonation mapping and its validation in part of Garhwal Lesser Himalaya, India, using binary logistic regression analysis and receiver operating characteristic curve method[J].” Landslides. 6(1): 17-26. DOI: 10.1007/s10346-008-0138-z (2009) doi.org/10.1007/s 10346-008-0138-z
 E.A. Sezer, et al., “Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping: Klang valley, Malaysia[J].” Expert Systems with Application. 38(7):8208-8219(2011)
 B.Pradhan, “Approaches for Delineating Landslide Hazard Areas Using Different Training Sites in an Advanced Artificial Neural Network Model[J].” Journal of Geospatial Information Science. 13(2): 93-102. doi.org/10.1007/s11806-010-0236-7
 ZHANG Baolei, “Investigation and Assessment of Landslides and Debris Flows in Sichuan Province of China by Remote Sensing Technique[J].” China Geoscience. 16(3):223-228(2006)doi.org/10.1007/ s11769-006-0223-y
 Yu Bu et al., “Geological hazard zoning and evaluation of landslide hazard in Hangzhou[J].” Geotechnics.33(S1):193-199+216. 10.16285/j.rsm.2012.s1.007
 R, Samanef et al. “Mapping landslide susceptibility with frequency ratio, statistical index, and weights of evidence models: a case study in northern Iran[J].” Environmental earth sciences. 76(14) (2017) doi.org/10.1007/s12665-017-6839-7
 Hu Yan et al., “Evaluation of landslide hazard susceptibility in Badong County based on the right-of-evidence method[J].” Geological Science and Technology Bulletin.39(03):187-194(2020) 10.19509/j. cnki.dzkq.2020.0320.
 A.D. Regmi et al., “Application of frequency ratio, statistical index, and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya[J].” Arabian journal of geosciences. 7(2):725-742(2014) doi.org/10.1007/s12517-012-0807-z
 Tian Shu-jun et al., “Comparative study of landslide susceptibility evaluation based on different evaluation units[J].” Journal of Natural Hazards. 28(06):137-145(2019) 10.13577/j.jnd.2019.0615
 Huo Ai-di et al., “The method of dividing geological hazard susceptibility evaluation units--an example of Huangling County, Shaanxi Province”[J]. Journal of Jilin University (Earth Science Edition). 41(02):523-528+535(2011) 10.3969/j.issn.1671-5888.2011.02.027
 T-Zhang. “An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods[J].” AI magazine: Artificial intelligence. 22(2):103-104(2001)
 Z, Xue-gong. “On statistical learning theory and support vector machines[J].” Journal of Automation. 01:36-46(2000) 10.16383/j.aas.2000.01.005.
 Vapink V. “Nature of Statistical Learning Theory[M].”New York: Wiley(1995) doi.org/10.1007 /978-1-4757-2440-0
 J. Kennedy, R. Eberhart. “Particle swarm optimization[C].” Neural Networks, 1995. Proceedings., IEEE International Conference on vol.4. pp. 1942-1948, Perth, Australia (1995)
 Y. Shi, R.C. Eberhart. INSTITUTE OF ELECTRIC AND ELECTRONIC ENGINEER. “Empirical study of particle swarm optimization[C].” //Evolutionary Computation, 1999. CEC 99. Proceedings of the 1999 Congress on Vol. 3. pp. 1945-1950, DC, USA (1999)
 Li QING et al., “An improved ant colony algorithm based on particle swarm parameter optimization[J].” Control and Decision Making. 28(06):873-878+883(2013) 10.13195/j.cd.2013.06. 75.liq.016.
 Yi-Tung Kao, et al., “A hybrid genetic algorithm and particle swarm optimization for multimodal functions [J].” Applied Soft Computing. 8(2):849-857(2008) doi.org/10.1016/j.asoc.2007.07.002
 I.C. Trelea. “The particle swarm optimization algorithm: convergence analysis and parameter selection [J].” Information processing letters. 85(6):317-325(2003) doi.org/10.1016/S0020-0190(02) 00447-7
 L.Zhi-xiong et al., “Setting and experimental analysis of random number parameters in particle swarm algorithm[J].” Control Theory and Applications. 27(11):1489-1496(2010)
 AP. Bradley. “The Use Of The Area Under The Roc Curve In The Evaluation Of Machine Learning Algorithms [J]. " Pattern Recognition: The Journal of the Pattern Recognition Society. 30(7):1145-1159(1997) doi.org/10.1016/S0031- 3203(96)00142-2
 F.TOM. “An introduction to ROC analysis [J].” Pattern recognition letters. 27(8):861-874(2006)