Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm: A case study of Baihetan Reservoir Area
Journal of Mountain Science - 2024
Tóm tắt
Landslide hazard susceptibility evaluation takes on critical significance in early warning and disaster prevention and reduction. In order to solve the problems of poor effectiveness of landslide data and complex calculation of weights for multiple evaluation factors in the existing landslide susceptibility evaluation models, in this study, a method of landslide hazard susceptibility evaluation is proposed by combining SBAS-InSAR (Small Baseline Subsets-Interferometric Synthetic Aperture Radar) and SSA-BP (Sparrow Search Algorithm-Back Propagation) neural network algorithm. The SBAS-InSAR technology is adopted to identify potential landslide hazards in the study area, update the cataloging data of landslide hazards, and 11 evaluation factors are chosen for constructing the SSA-BP model for training and validation. Baihetan Reservoir area is selected as a case study for validation. As indicated by the results, the application of SBAS-InSAR technology, combined with both ascending and descending orbit data, effectively addresses the incomplete identification of landslide hazards caused by geometric distortion of single orbit SAR data (e.g., shadow, overlay, and perspective contraction) in deep canyon areas, thereby enabling the acquisition of up-to-date landslide hazard data. Moreover, in comparison to the conventional BP (Back Propagation) algorithm, the accuracy of the model constructed by the SSA-BP algorithm exhibits a significant increase, with mean squared error and mean absolute error reduced by 0.0142 and 0.0607, respectively. Additionally, during the process of susceptibility evaluation, the SSA-BP model effectively circumvents the issue of considerable manual interventions in calculating the weight of evaluation factors. The area under the curve of this model reaches 0.909, surpassing BP (0.835), random forest (0.792), and the information value method (0.699). The risk of landslide occurrence in the Baihetan Reservoir area is positively correlated with slope, surface temperature, and deformation rate, while it is negatively correlated with fault distance and normalized difference vegetation index. Geological lithology exerts minimal influence on the occurrence of landslides, with the risk being low in forest land and high in grassland. The method proposed in this study provides a useful reference for disaster prevention and mitigation departments to perform landslide hazard susceptibility evaluations in deep canyon areas under complex geological conditions.
Từ khóa
Tài liệu tham khảo
Berardino P, Fornaro G, Lanari R, et al. (2002) A new algorithm for surface deformation monitoring based on small baseline differential sar interferograms. IEEE Trans Geosci Remote Sens 40:2375–2383. https://doi.org/10.1109/TGRS.2002.803792
Brabb EE (1985) Innovative approaches to landslide hazard and risk mapping. In, International landslide symposium proceedings, Toronto, Canada, pp 17–22.
Cao J, Zhang Z, Du J, et al. (2020) Multi-geohazards susceptibility mapping based on machine learning—a case study in jiuzhaigou, china. Natural Hazards 102:851–871. https://doi.org/10.1007/s11069-020-03927-8
Dai KR, Chen C, Shi XL, et al. (2023) Dynamic landslides susceptibility evaluation in baihetan dam area during extensive impoundment by integrating geological model and insar observations. Int J Appl Earth Obs Geoinfor 116:103157. https://doi.org/10.1016/j.jag.2022.103157
Dai KR, Shen Y, Wu MT, et al. (2022) Identification of potential landslides in baihetan dam area before the impoundment by combining insar and uav survey. Acta Geod Cartogr Sin 51:2069–2082 (In Chinese). https://doi.org/10.11947/j.AGCS.2022.20220305
Deng H, Wu XT, Zhang WJ, et al. (2022) Slope-unit scale landslide susceptibility mapping based on the random forest model in deep valley areas. Remote Sens 14:4245. https://doi.org/10.3390/rs14174245
Ding SF, Su CY, Yu JZ (2011) An optimizing bp neural network algorithm based on genetic algorithm. Artif Intell Rev 36:153–162. https://doi.org/10.1007/s10462-011-9208-z
Ding YK, Liu R, Fan YF, et al. (2022) Monitoring glaciers in the chenab basin with sbas insar technology. J Mt Sci 19:2622–2633. https://doi.org/10.1007/s11629-021-7266-5
Dou J, Yamagishi H, Pourghasemi HR, et al. (2015) An integrated artificial neural network model for the landslide susceptibility assessment of Osado island, Japan. Natural Hazards 78:1749–1776. https://doi.org/10.1007/s11069-015-1799-2
Draper NR, Smith H (1998) Applied regression analysis. John Wiley & Sons.
Dun JW, Feng WK, Yi XY, et al. (2021) Detection and mapping of active landslides before impoundment in the baihetan reservoir area (China) based on the time-series insar method. Remote Sens 13:3213. https://doi.org/10.3390/rs13163213
Fan ZY, Gou XF, Qin MY, et al. (2018) Information and logistic regression models based coupl-ing analysis for susceptibility of geological hazards. J Eng Geol 26:340–347. (In Chinese). https://doi.org/10.13544/j.cnki.jeg.2017-052
Feng Z, Wu ZH, Cao JW, et al. (2019) Engineering geological characteristics of gigantic pre-historic landslide along qiaojia section of the xiaojiang fault. Acta Geosci Sin 40:629–636. https://doi.org/10.3975/cagsb.2019.012401
Guo FY, Meng XM, Qi TJ, et al. (2022a) Rapid onset hazards, fault-controlled landslides and multi-method emergency decision-making. J Mt Sci 19:1357–1369. https://doi.org/10.1007/s11629-021-6941-x
Guo R, Li SM, Chen YN, et al. (2021) Identification and monitoring landslides in longitudinal range-gorge region with insar fusion integrated visibility analysis. Landslides 18:551–568. https://doi.org/10.1007/s10346-020-01475-7
Guo SP, Ji YJ, Tian X, et al. (2020) Deformation velocity monitoring in kunming city using ascending and descending sentinel-1a data with sbas-insar technique. In, IGARSS 2020–2020 IEEE Int Geosci Remote Sens Symp. IEEE. pp 1993–1996.
Guo W, Zhao CP, Zuo KZ, et al. (2022b) Characteristics of seismicity before and after impoundment of baihetan dam in the lower reaches of jinsha river. Chin J Geophy 65:4659–4671. (In Chinese). https://doi.org/10.6038/cjg2022Q0119
He HD, Hu D, Sun Q, et al. (2019) A landslide susceptibility assessment method based on gis technology and an ahpweighted information content method: A case study of southern anhui, china. ISPRS Int J Geo-inf 8:266. https://doi.org/10.3390/ijgi8060266
He Q, Wang M, Liu K (2021) Rapidly assessing earthquake-induced landslide susceptibility on a global scale using random forest. Geomorphology 391:107889. https://doi.org/10.1016/j.geomorph.2021.107889
He XH, Tan JM, Pei LZ (2017) Influence of faults on geohazards: Take anhua county as an example. Chin J Geol Hazard Control 28:150–155. (In Chinese). https://doi.org/10.16031/j.cnki.issn.1003-8035.2017.03.23
Huang CC, Jou YJ, Cho HJ (2016) A new multicollinearity diagnostic for generalized linear models. J Appl Stat 43:2029–2043. https://doi.org/10.1080/02664763.2015.1126239
Huang HN, Zhang XB, Li ZR, et al. (2021) Stability evaluation at xishan loess landslide using insar technique applying ascending and descending sar data. J Appl Remote Sens 15:034519–034519. https://doi.org/10.1117/1.JRS.15.034519
Huo AD, Zhang J, Lu YD, et al. (2011) Method of classification for susceptibility evaluation unit for geological hazards: A case study of huangling county, shaanxi, china. J Jilin Unive (Earth Sci Ed) 41:523–528. (In Chinese). https://doi.org/10.13278/j.cnki.jjuese.2011.02.031
Ji J, Cui HZ, Zhang T, et al. (2022) A gis-based tool for probabilistic physical modelling and prediction of landslides: Gis-form landslide susceptibility analysis in seismic areas. Landslides 19:2213–2231. https://doi.org/10.1007/s10346-022-01885-9
Jin W, Li ZJ, Wei LS, et al. (2000) The improvements of bp neural network learning algorithm. In, WCC 2000-ICSP 2000. 2000 5th international conference on signal processing proceedings. 16th world computer congress 2000. IEEE. pp 1647–1649.
Lee S, Hong SM, Jung HS (2017) A support vector machine for landslide susceptibility mapping in gangwon province, korea. Sustainability 9:48. https://doi.org/10.3390/su9010048
Lima P, Steger S, Glade T, et al. (2022) Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility. J Mt Sci 19:1670–1698. https://doi.org/10.1007/s11629-021-7254-9
Liu MY, Xu B, Li ZW, et al. (2023a) Landslide susceptibility zoning in yunnan province based on sbas-insar technology and a random forest model. Remote Sens 15:2864. https://doi.org/10.3390/rs15112864
Liu ZQ, Yang ZQ, Chen M, et al. (2023b) Research hotspots and frontiers of mountain flood disaster: Bibliometric and visual analysis. Water 15:673. https://doi.org/10.3390/w15040673
Ma JR, Wang XD, Yuan GX (2023) Evaluation of geological hazard susceptibility based on the regional division information value method. ISPRS Int J Geo-Inf 12:17. https://doi.org/10.3390/ijgi12010017
Meng CX, Wu D, Lei Y (2022) Bp neural network for satellite clock bias prediction based on sparrow search algorithm. J Geod Geodyn 42:125–131. (In Chinese). https://doi.org/10.14075/j.jgg.2022.02.004
Ortiz JAV, Martínez-Graña AM (2018) A neural network model applied to landslide susceptibility analysis (Capitanejo, Colombia). Geomatics, Natural Hazards Risk 9 https://doi.org/10.1080/19475705.2018.1513083
Osmanoğlu B, Sunar F, Wdowinski S, et al. (2016) Time series analysis of insar data: Methods and trends. ISPRS J Photogramm Remote Sens 115:90–102. https://doi.org/10.1016/j.isprsjprs.2015.10.003
Pradhan B, Lee S (2010) Regional landslide susceptibility analysis using back-propagation neural network model at cameron highland, malaysia. Landslides 7:13–30. https://doi.org/10.1007/s10346-009-0183-2
Ren TH, Gong WP, Gao L, et al. (2022) An interpretation approach of ascending-descending sar data for landslide identification. Remote Sens 14:1299. https://doi.org/10.3390/rs14051299
Reyes-Carmona C, Barra A, Galve JP, et al. (2020) Sentinel-1 dinsar for monitoring active landslides in critical infrastructures: The case of the rules reservoir (southern spain). Remote Sens 12:809. https://doi.org/10.3390/rs12050809
Shano L, Raghuvanshi TK, Meten M (2020) Landslide susceptibility evaluation and hazard zonation techniques–a review. Geoenviron Disasters 7:1–19. https://doi.org/10.1186/s40677-020-00152-0
She YW, Yu FG, Qian Z, et al. (2021) Simulating changes of gravity and coulomb stress caused by the impoundment of the baihetan hydropower station. Chin J Geophys 64:1925–1936. (In Chinese). https://doi.org/10.6038/cjg2021O0163
Wang D, Yang RH, Wang X, et al. (2023) Evaluation of deep learning algorithms for landslide susceptibility mapping in an alpine-gorge area: A case study in jiuzhaigou county. J Mt Sci 20:484–500. https://doi.org/10.1007/s11629-022-7326-5
Wu MT, Cui ZH, Yi XY, et al. (2023a) Ldentification of geohazards in xiangbiling-yezhutang section of baihetan reservoir area using multi-source remote sensing data. Journal of Changjiang River Scientific Research Institute 40:155–163. https://doi.org/10.11988/ckyyb.20211219
Wu XY, Song YB, Chen W, et al. (2023b) Analysis of geological hazard susceptibility of landslides in muli county based on random forest algorithm. Sustainability 15:4328. https://doi.org/10.3390/su15054328
Wu YL, Li WP, Liu P, et al. (2016) Application of analytic hierarchy process model for landslide susceptibility mapping in the Gangu County, Gansu Province, China. Environ Earth Sci 75:1–11. https://doi.org/10.1007/s12665-015-5194-9
Xiang MS, Duan LS, Wei FR, et al. (2022) Analysis on the spatial differentiation characteristics of poverty risk caused by disaster under the stress of geological disasters: A case study of sichuan province. Environ Sci Pollut Res 29:52111–52122. https://doi.org/10.1007/s11356-022-19485-4
Xiao B, Zhao JS, Li DS, et al. (2022) Combined sbas-insar and pso-rf algorithm for evaluating the susceptibility prediction of landslide in complex mountainous area: A case study of Ludian County, China. Sensors 22:8041. https://doi.org/10.3390/s22208041
Xu WB, Yu WJ, Jing SC, et al. (2013) Debris flow susceptibility assessment by gis and information value model in a large-scale region, sichuan province (china). Natural hazards 65:1379–1392. https://doi.org/10.1007/s11069-012-0414-z
Xu XM, Peng LY, Ji ZS, et al. (2021) Research on substation project cost prediction based on sparrow search algorithm optimized bp neural network. Sustainability 13:13746. https://doi.org/10.3390/su132413746
Xue KK, Xiong LY, Zhu SJ, et al. (2018) Extraction of loess dissected saddle and its terrain analysis by using digital elevation models. J Geo-inf Scie 20:1710–1720 (In Chinese). https://doi.org/10.12082/dqxxkx.2018.180358
Yang ZQ, Wei L, Liu YQ, et al. (2023a) Discussion on the relationship between debris flow provenance particle characteristics, gully slope, and debris flow types along the karakoram highway. Sustainability 15:5998. https://doi.org/10.3390/su15075998
Yang ZQ, Zhao XG, Chen M, et al. (2023b) Characteristics, dynamic analyses and hazard assessment of debris flows in niumiangou valley of wenchuan county. Appl Sci 13:1161. https://doi.org/10.3390/app13021161
Yang ZR, Xi WF, Shi ZT, et al. (2022a) Deformation analysis in the bank slopes in the reservoir area of baihetan hydropower station based on sbas-insar technology. Chin J Geol Hazard Control 33:83–92 (In Chinese). https://doi.org/10.16031/j.cnki.issn.1003-8035.202202056
Yang ZR, Xi WF, Yang ZQ, et al. (2022b) Monitoring and prediction of glacier deformation in the meili snow mountain based on insar technology and ga-bp neural network algorithm. Sensors 22:8350. https://doi.org/10.3390/s22218350
Yeh YL, Chen TC (2004) Application of grey correlation analysis for evaluating the artificial lake site in pingtung plain, Taiwan. Can J Civil Eng 31:56–64. https://doi.org/10.1139/l03-074
Zhang CL, Ding SF (2021) A stochastic configuration network based on chaotic sparrow search algorithm. Knowl-Based Syst 220:106924. https://doi.org/10.1016/j.knosys.2021.106924
Zhang LL, Dai KR, Deng J, et al. (2021) Identifying potential landslides by stacking-insar in southwestern china and its performance comparison with sbas-insar. Remote Sens 13:3662. https://doi.org/10.3390/rs13183662
Zhang XC, Chen LX, Zhou C (2023) Deformation monitoring and trend analysis of reservoir bank landslides by combining time-series insar and hurst index. Remote Sens 15:619. https://doi.org/10.3390/rs15030619
Zhao CY, Kang Y, Zhang Q, et al. (2018) Landslide identification and monitoring along the jinsha river catchment (wudongde reservoir area), china, using the insar method. Remote Sens 10:993. https://doi.org/10.3390/rs10070993
Zhao JQ, Zhang Q, Wang DZ, et al. (2022) Machine learning-based evaluation of susceptibility to geological hazards in the hengduan mountains region, china. Int J Disaster Risk Sci 13:305–316. https://doi.org/10.1007/s13753-022-00401-w
Zheng Q, Lyu HM, Zhou AN, et al. (2021) Risk assessment of geohazards along cheng-kun railway using fuzzy ahp incorporated into gis. Geomatics, Nat Hazards Risk 12:1508–1531. https://doi.org/10.1080/19475705.2021.1933614