XGBoost ve SHAP ile Heyelan Duyarlılık Haritalaması İçin Alternatif CBS Veri Modeli Yöntemlerinin Karşılaştırılması

Year 2024, Volume: 14 Issue: 3, 1204 - 1224, 15.09.2024

Şevket Bediroğlu

https://doi.org/10.31466/kfbd.1446997

Abstract

Coğrafi Bilgi Sistemleri ve makine öğrenimi algoritmaları, heyelan duyarlılık haritalarının üretilmesi için iyi alternatifler önermektedir. Bu haritaların makine öğrenmesi ile üretilmesi sürecinde alternatif veri modeli seçenekleri mevcuttur. Tercih edilen veri yöntemine göre analizlerin başarı oranı değişebilir. Bu çalışmada XGBoost algoritması ile farklı veri modellerini geçerek 6 farklı makine öğrenmesi modeli oluşturulmuştur. Çalışma alanı Türkiye'nin Ordu ve Giresun illerinde bulunmaktadır. 14 farklı faktör ve ilgili coğrafi veri katmanları kullanıldı. Çalışma sonucunda en başarılı model performansı, birleştirilmiş heyelan kayıt poligonlarının tüm piksellerinin ortalama değerleri alınarak elde edilmiştir. Makine öğrenmesi sonuçlarının daha iyi yorumlanması için SHAP yöntemi uygulandı. İdeal model ile üretilen duyarlılık haritası, bölgedeki 57.556 bina ile örtüştü. Binalar 4 grupta (düşük, orta, yüksek ve çok yüksek) sınıflandırılarak risk düzeyleri belirtilerek haritalanmıştır.

Keywords

Heyelan duyarlılık haritası, Makine öğrenmesi, SHAP, CBS, Coğrafi veri modeli

A Comparison of Alternative GIS Data Model Methods for Landslide Susceptibility Mapping with XGBoost and SHAP

Abstract

Geographic Information Systems and machine learning algorithms suggest good alternatives for producing landslide susceptibility maps. In the process of producing these maps with machine learning, alternative data model options exist. Success rate of analyses may change according to the preferred data method. In this study, 6 different machine learning models were created by passing different data models with the XGBoost algorithm. Study area is located in the cities of Ordu and Giresun, Turkiye. 14 different factors and related geographic data layers were used. As a result of the study, the most successful model performance was achieved by taking the average values of all pixels of the combined landslide record polygons (Accuracy=0,88, Precision=0,86, F1 score=0,87). SHAP method was applied for better interpretation of machine learning results The susceptibility map produced with the ideal model, overlapped with 57.556 buildings in the region. The buildings were classified in 4 groups (low, moderate, high, and very high) and mapped, indicating their risk level.

Keywords

Landslide susceptibility mapping, machine learning, SHAP, GIS, geospatial data model

References

• Abedini M, Ghasemian B, Shirzadi A, Shahabi H, Chapi K, Pham BT, Bin Ahmad B, and Tien Bui D. 2019. A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment. Geocarto International. 34(13):1427-1457.
• Aghdam IN., Varzandeh MHM., and Pradhan B. (2016). Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran). Environmental Earth Sciences. 75(7):553.
• Aghlmand, M., Onur M. İ. and Talaei R. (2020). Heyelan Duyarlılık Haritalarının Üretilmesinde Analitik Hiyerarşi Yönteminin ve Coğrafi Bilgi Sistemlerinin Kullanımı. Avrupa Bilim ve Teknoloji Dergisi Özel Sayı, S. 224-230, Nisan 2020
• Akinci H., Kilicoglu C., and Dogan S. (2020). Random Forest-Based Landslide Susceptibility Mapping in Coastal Regions of Artvin, Turkey. ISPRS International Journal of Geo-Information. 2020; 9(9):553
• Althuwaynee OF., Pradhan B., Park H-J., and Lee JH. (2014). A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping. CATENA. 114:21-36.
• Althuwaynee OF., Pradhan B., and Lee S. (2016). A novel integrated model for assessing landslide susceptibility mapping using CHAID and AHP pair-wise comparison. International Journal of Remote Sensing. 37(5):1190-1209.
• Arabameri, A., Chandra Pal, S., Rezaie, F., Chakrabortty, R., Saha, A., Blaschke, T., di Napoli, M., Ghorbanzadeh, O., and Thi Ngo, P. T. (2022). Decision tree based ensemble machine learning approaches for landslide susceptibility mapping. Geocarto International, 37(16), 4594–4627. https://doi.org/10.1080/10106049.2021.1892210
• Atkinson PM., and Massari R. (1998). Generalised Linear Modelling of Susceptibility to Landsliding in the Central Apennines, ITALY. Computers & Geosciences. 24(4):373-385.
• Beguería S. (2006). Validation and Evaluation of Predictive Models in Hazard Assessment and Risk Management. Natural Hazards. 37(3):315-329.
• Breiman L. (2001). Random Forests. Machine Learning. Kluwer Academic Publishers. 45(1):5-32.
• Chang Z., Du Z., Zhang F., Huang .F, Chen J., Li W., and Guo Z. (2020). Landslide Susceptibility Prediction Based on Remote Sensing Images and GIS: Comparisons of Supervised and Unsupervised Machine Learning Models. Remote Sensing. 12(3).
• Ciampalini, A., Bardi, F., Bianchini, S., Frodella, W., del Ventisette, C., Moretti, S., and Casagli, N. (2014). Analysis of building deformation in landslide area using multisensor PSInSARTM technique. International Journal of Applied Earth Observation and Geoinformation, 33, 166–180.
• Chen W., Peng J., Hong H., Shahabi H., Pradhan B., Liu J., Zhu AX., Pei X., and Duan Z. (2018). Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Science of The Total Environment. 626:1121-1135.
• Chen W. and Li Y. (2020). GIS-based evaluation of landslide susceptibility using hybrid computational intelligence models. CATENA. 195:104777.
• Chen T. and Guestrin C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). Association for Computing Machinery, New York, NY, USA, 785–794.
• Ching J. and Phoon K-K. (2019). Constructing Site-Specific Multivariate Probability Distribution Model Using Bayesian Machine Learning. Journal of Engineering Mechanics. 145(1):04018126.
• Constantin M., Bednarik M., Jurchescu MC., and Vlaicu M. (2011). Landslide susceptibility assessment using the bivariate statistical analysis and the index of entropy in the Sibiciu Basin (Romania). Environmental Earth Sciences. 63(2):397-406.
• Dai FC., Lee CF., and Zhang XH. (2001). GIS-based geo-environmental evaluation for urban land-use planning: a case study. Engineering Geology. 61(4):257-271.
• Dehnavi A., Aghdam IN., Pradhan B., and Morshed Varzandeh MH. (2015). A new hybrid model using step-wise weight assessment ratio analysis (SWARA) technique and adaptive neuro-fuzzy inference system (ANFIS) for regional landslide hazard assessment in Iran. CATENA. 135:122-148.
• De Sy V., Schoorl JM., Keesstra SD., Jones KE., and Claessens L. (2013). Landslide model performance in a high resolution small-scale landscape. Geomorphology. 190:73-81.
• Fang, Z., Wang, Y., Peng, L., and Hong, H. (2020). Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping. Computers & Geosciences, 139, 104470.
• Fanos, A. M. and Pradhan, B. (2019). A novel rockfall hazard assessment using laser scanning data and 3D modelling in GIS. CATENA, 172, 435–450.
• Feizizadeh B., Shadman Roodposhti M., Jankowski P., and Blaschke T. (2014). A GIS-based extended fuzzy multi-criteria evaluation for landslide susceptibility mapping. Computers & Geosciences. 73:208-221.
• Froude M. and Petley D. (2018). Global fatal landslide occurrence 2004 to 2016. Natural Hazards and Earth System Sciences Discussions.1-44.
• Fu, S., Chen, L., Woldai, T., Yin, K., Gui, L., Li, D., Du, J., Zhou, C., Xu, Y., and Lian, Z. (2020). Landslide hazard probability and risk assessment at the community level: a case of western Hubei, China. Nat. Hazards Earth Syst. Sci., 20(2), 581–601.
• Girshick, R. (2015). Fast R-CNN. Proceedings of the IEEE international conference on computer vision 1440–1448.
• Greedy F. J. function approximation: a gradient boosting machine. Annals of Statistics, 29(5):1189{1232, 2001.
• Gorsevski, P.V., Gessler, P.E., Foltz, R.B. and Elliot, W.J. (2006), Spatial Prediction of Landslide Hazard Using Logistic Regression and ROC Analysis. Transactions in GIS, 10: 395-415.
• Guzzetti F., Reichenbach P., Ardizzone F., Cardinali M., and Galli M. (2006). Estimating the quality of landslide susceptibility models. Geomorphology. 81(1):166-184.
• Hong H., Miao Y., Liu J., and Zhu AX. (2019). Exploring the effects of the design and quantity of absence data on the performance of random forest-based landslide susceptibility mapping. CATENA. 176:45-64.
• Hong H., Naghibi SA., Pourghasemi HR., and Pradhan B. (2016). GIS-based landslide spatial modeling in Ganzhou City, China. Arabian Journal of Geosciences. 9(2):112.
• Hong H., Pradhan B., Sameen MI., Kalantar B., Zhu A., and Chen W. (2018). Improving the accuracy of landslide susceptibility model using a novel region-partitioning approach. Landslides. 15(4):753-772.
• Hong H., Liu J., and Zhu AX. (2020). Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble. Science of The Total Environment. 718:137231.
• Hong, H. (2023). Assessing landslide susceptibility based on hybrid Best-first decision tree with ensemble learning model. Ecological Indicators, 147, 109968.
• Huang, W., Ding, M., Li, Z.; Zhuang, J., Yang, J., Li, X., Meng, L., Zhang, H., and Dong, Y. An Efficient User-Friendly Integration Tool for Landslide Susceptibility Mapping Based on Support Vector Machines: SVM-LSM Toolbox. Remote Sens. 2022, 14, 3408.
• Hussin HY., Zumpano V., Reichenbach P., Sterlacchini S., Micu M., van Westen C., and Bălteanu D. (2016). Different landslide sampling strategies in a grid-based bi-variate statistical susceptibility model. Geomorphology. 253:508-523.
• Kavzoglu, T.,and Teke, A. (2022). Predictive Performances of Ensemble Machine Learning Algorithms in Landslide Susceptibility Mapping Using Random Forest, Extreme Gradient Boosting (XGBoost) and Natural Gradient Boosting (NGBoost). Arab J Sci Eng 47, 7367–7385
• Lary DJ., Alavi AH., Gandomi AH., and Walker AL. (2016). Machine learning in geosciences and remote sensing. Geoscience Frontiers. 7(1):3-10.
• Lecun Y., Bottou L., Bengio Y., and Haffner P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE. 86(11):2278-2324.
• Li X., Zhang L., Xiao T., Zhang S., and Chen C. (2019). Learning failure modes of soil slopes using monitoring data. Probabilistic Engineering Mechanics. 56:50-57.
• Li P. (2010). Robust Logitboost and adaptive base class (ABC)Logitboost. In Proceedings of the Twenty-Sixth Conference Annual Conference on Uncertainty in Artifcial Intelligence(UAI'10), pages 302{311, 2010.
• Liu Y., Fan B., Wang L., Bai J., Xiang S., and Pan C. (2018). Semantic labeling in very high resolution images via a self-cascaded convolutional neural network. ISPRS Journal of Photogrammetry and Remote Sensing. 145:78-95.
• Lo MK., and Leung YF. (2018). Bayesian updating of subsurface spatial variability for improved prediction of braced excavation response. Canadian Geotechnical Journal. 56(8):1169-1183.
• Mathew J., Jha VK., and Rawat GS. (2009). 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. Landslides. 6(1):17-26.
• Martha, T. R., van Westen, C. J., Kerle, N., Jetten, V., and Vinod Kumar, K. (2013). Landslide hazard and risk assessment using semi-automatically created landslide inventories. Geomorphology, 184, 139–150.
• Mezaal MR., Pradhan B., Sameen MI., Mohd Shafri HZ., and Yusoff ZM. (2017). Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning Data. Applied Sciences. 7(7).
• Nefeslioglu HA., Gokceoglu C., and Sonmez H. (2008). An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps. Engineering Geology. 97(3):171-191.
• Nguyen H-L., Le T-H., Pham C-T., Le T-T., Ho LS., Le VM., Pham BT., and Ly H-B. (2019). Development of Hybrid Artificial Intelligence Approaches and a Support Vector Machine Algorithm for Predicting the Marshall Parameters of Stone Matrix Asphalt. Applied Sciences. 9(15):3172.
• Nsengiyumva, J. B., and Valentino, R. (2020). Predicting landslide susceptibility and risks using GIS-based machine learning simulations, case of upper Nyabarongo catchment. Geomatics, Natural Hazards and Risk, 11(1), 1250–1277. https://doi.org/10.1080/19475705.2020.1785555
• Orhan, O., Bilgilioglu, S. S., Kaya, Z., Ozcan, A. K., and Bilgilioglu, H. (2022). Assessing and mapping landslide susceptibility using different machine learning methods. Geocarto International, 37(10), 2795–2820. https://doi.org/10.1080/10106049.2020.1837258
• Ou C., Liu J., Qian Y., Chong W., and He X. (2020). Rupture risk assessment for cerebral aneurysm using interpretable machine learning on multidimensional data. Front. Neurol., 11.
• Papaioannou I, Straub D. (2017). Learning soil parameters and updating geotechnical reliability estimates under spatial variability – theory and application to shallow foundations. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards. 11(1):116-128.
• Park S., and Kim J. (2019). Landslide Susceptibility Mapping Based on Random Forest and Boosted Regression Tree Models, and a Comparison of Their Performance. Applied Sciences. 9(5).
• Pham BT., Phong TV., Nguyen-Thoi T., Trinh PT., Tran QC., Ho LS., Singh SK., Duyen TT., Nguyen LT., and Le HQ. (2020). GIS-based ensemble soft computing models for landslide susceptibility mapping. Advances in Space Research. 66(6):1303-1320.
• Pham BT., Prakash I., Singh SK., Shirzadi A., Shahabi H., Tran T-T., and Bui DT. (2019). Landslide susceptibility modelling using Reduced Error Pruning Trees and different ensemble techniques: Hybrid machine learning approaches. CATENA. 175:203-218.
• Pradhan, B., and Sameen, M. I. (2018). Manifestation of SVM-Based Rectified Linear Unit (ReLU) Kernel Function in Landslide Modelling. In W. Suparta, M. Abdullah, & M. Ismail (Eds.), Space Science and Communication for Sustainability (pp. 185–195). Springer Singapore. https://doi.org/10.1007/978-981-10-6574-3_16
• Pourghasemi HR., Kornejady A., Kerle N., and Shabani F. (2020). Investigating the effects of different landslide positioning techniques, landslide partitioning approaches, and presence-absence balances on landslide susceptibility mapping. CATENA. 187:104364.
• Prasad P., Loveson VJ., Das B., and Kotha M. (2021). Novel ensemble machine learning models in flood susceptibility mapping. Geocarto International.1-23.
• Rahmati O., Tahmasebipour N., Haghizadeh A., Pourghasemi HR., and Feizizadeh B. (2017). Evaluating the influence of geo-environmental factors on gully erosion in a semi-arid region of Iran: An integrated framework. Science of The Total Environment. 579:913-927.
• Sagi Ö. and Rokach L. (2021). Approximating XGBoost with an interpretable decision tree, Information Sciences, Volume 572, Pages 522-542, ISSN 0020-0255.
• Sahin, E.K. (2023). Implementation of free and open-source semi-automatic feature engineering tool in landslide susceptibility mapping using the machine-learning algorithms RF, SVM, and XGBoost. Stoch Environ Res Risk Assess 37, 1067–1092
• Sameen MI., Pradhan B., Bui DT., and Alamri AM. (2020). Systematic sample subdividing strategy for training landslide susceptibility models. CATENA. 187:104358.
• Singh, A., Pal, S., and Kanungo, D. P. (2021). An integrated approach for landslide susceptibility–vulnerability–risk assessment of building infrastructures in hilly regions of India. Environment, Development and Sustainability, 23(4), 5058–5095. https://doi.org/10.1007/s10668-020-00804-z
• T.C. Orman ve Su Işleri Bakanlığı. (2016). Meteoroloji Genel Müdürlüğü, Köppen iklim siniflandirmasina göre Türkiye iklimi, Climatology Report.
• Thi-Thu-Huong L., Kim H., Kang H. and Kim H. (2022). "Classification and Explanation for Intrusion Detection System Based on Ensemble Trees and SHAP Method" Sensors 22, no. 3:
• Url, 2. https://en.wikipedia.org/wiki/Logistic_regression, 2020
• Van Westen CJ., Van Asch TWJ., and Soeters R. (2006). Landslide hazard and risk zonation—why is it still so difficult? Bulletin of Engineering Geology and the Environment. 65(2):167-184.
• Wang H., Zhang L., Yin K., Luo H., and Li J. (2021). Landslide identification using machine learning. Geoscience Frontiers. 12(1):351-364.
• Wang Y., Fang Z., and Hong H. (2019). Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China. Science of The Total Environment. 666:975-993.
• Wang Y., Feng L., Li S., Ren F., and Du Q. (2020). A hybrid model considering spatial heterogeneity for landslide susceptibility mapping in Zhejiang Province, China. CATENA. 188:104425.
• Wu Z., Wu Y., Yang Y., Chen F., Zhang N., Ke Y., and Li W. (2017). A comparative study on the landslide susceptibility mapping using logistic regression and statistical index models. Arabian Journal of Geosciences. 10(8):187.
• Yamaguchi, S., and Kasai, M. (2022). A new index representative of seismic cracks to assess post-seismic landslide susceptibility. Transactions in GIS, 26, 1040– 1061.
• Yi Y., Zhang Z., Zhang W., Jia H., and Zhang J. (2020). Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network: A case study in Jiuzhaigou region. CATENA. 195:104851.
• Yilmaz I. (2010). The effect of the sampling strategies on the landslide susceptibility mapping by conditional probability and artificial neural networks. Environmental Earth Sciences. 60(3):505-519.
• Youssef AM., and Pourghasemi HR. (2021). Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin, Asir Region, Saudi Arabia. Geoscience Frontiers. 12(2):639-655.
• Zhang W., Goh ATC., Zhang Y., Chen Y., and Xiao Y. (2015). Assessment of soil liquefaction based on capacity energy concept and multivariate adaptive regression splines. Engineering Geology. 188:29-37.
• Zhang W., and Goh ATC. (2016). Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geoscience Frontiers. 7(1):45-52.
• Zhao, Z., He, Y., Yao, S., Yang, W., Wang, W., Zhang, L., and Sun, Q. (2022). A comparative study of different neural network models for landslide susceptibility mapping. Advances in Space Research, 70(2), 383–401.
• Zhang, K., Wu, X., Niu, R., Yang, K. and Zhao, L. (2017). The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environmental Earth Sciences. Vol: 11 – 76, pages 1-20
• Zhang J., Ma X., Zhang J., Sun D., Zhou X., Mi C. and Wen H. (2023). Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model, Journal of Environmental Management, Volume 332, 2023, 117357, ISSN 0301-4797.
• Zhu AX., Miao Y., Yang L., Bai S., Liu J., and Hong H. (2018). Comparison of the presence-only method and presence-absence method in landslide susceptibility mapping. CATENA. 171:222-233.