Results and Discussion

Importance of the Conditioning Factors on the Occurrences of Landslides

After the initial analysis the importance of all causative factors and their associated sub-factors was assessed w ith the help of frequency ratio. In the case of distance to structure, the high weightages are confirmed to lie between 0 to 4619.772 (1.033) and 4619.772 to 9349.540 (1.272). For the geology, high importance was associated with the Lingste granite gneiss (1.243) and the Gorubathan formation (1.080). In the case of geomorphology, high importance was associated with Glacial Lake and Nunatak (8.704), moderately dissected hills and valleys (1.083), and waterbody- river/waterbodies-other (1.091). In lithology, high importance w'as associated with quartzite (7.588), mylonitic granite gneiss (1.442), meta greywacke (3.489), and biotite quartzite (3.782). In LULC, high importance was associated with: barren land (1.502), built-up areas (1.404), and water bodies (2.068). In soil texture, high importance w'as associated w'ith: loamy-skeletal lithic udorthents (1.169), fine- loamy fluventic eutrudepts (1.305), coarse-loamy humic pachic dystrudepts (1.106), fine-loamy typic argiudolls (1.260), and coarse-loamy typic hapludolls (1.458). In slope aspect, high importance was associated with the south-east (1.159), southwest (1.335), north-east (1.039), and north (1.064). In the case of the distance to road, the nearest distance such as 0-629.755 m (1.377) is favorable for the occurrence of landslides. Very high drainage density such as 1.371-2.106 (1.613) is favorable for the occurrence of landslides. In elevation, high importance was associated with 272-1165 m (1.103), 1165-1801 m (1.087), and 2561-3453 m (1.149). In lineament density, high importance was associated with 0.0170-0.049 sq. km (1.237) which is very optimistic regarding the occurrence of landslides. In NDVI, high importance was associated with -0.357 to -0.071 (1.184), -0.071 to 0.143 (2.048), and 0.143 to 0.400 (1.294). Here the lower values of NDVI indicate higher occurrences of landslides. In plan curvature, high importance was associated with -16.103 to -1.645 (1.105), -0.488 to 0.436 (1.053), 0.436 to 1.593 (1.120), and 1.593 to 13.390 (1.021). In profile curvature, high importance was associated with -16.123 to -2.106 (1.396) which is very optimistic regarding the occurrence of landslides in this region.

In the case of rainfall, high importance was associated with 2312.940-2384.397 mm (1.208) and 2439.365-2501.661 (1.180). In the case of slope angle, high weightage was associated with 32.176-41.623 (1.355) and 41.623-75.276 (1.299). In SPI, high importance was associated with 13.158-15.878 (1.141) and 15.878- 21.644 (2.263); here the positive relationship is associated between the higher SPI and occurrences of landslides. In the case of TWI, high importance was associated with 16.336-19.933 (1.250) and 19.933-27.192 (3.849); here the positive relationship is associated between the higher TWI and occurrences of landslides (Table 4.1).

Application of Hybrid Biogeography-Based Optimization for Landslide Susceptibility Assessment

Different causal factors have been considered for estimation of the landslide susceptible areas using the hybrid BBO model on a GIS platform. This was constructed on the basis of all causative factors and landslide inventory points. The landslide point is randomly split into a 70:30 ratio as training and validation datasets. The very high (0.729-1.00) landslide susceptible areas are found mainly in the middle portion of this region and its areal coverage is 91.70 sq. km (9.69%). High (0.517-0.729) landslide susceptible areas are found mainly in the northern, middle, and eastern portions of this region and its areal coverage is 128.65 sq. km (13.59%) (Figure 4.7). Moderate (0.309-0.517) landslide susceptible areas are found mainly in the northern, middle, western, and eastern portions of this region and its areal coverage is 143.39 sq. km (15.15%). Low (0.113-0.309) landslide susceptible areas are found mainly in the northern, middle, western, and eastern portions of this region and its areal coverage is 158.95 sq. km (16.79%). Very low (0.00-0.113) landslide susceptible areas are found in most portions of this region and its areal coverage is 423.81 sq. km (44.78%) (Figure 4.8).

Landslide susceptibility map

FIGURE 4.7 Landslide susceptibility map.

Landslide susceptibility areas

FIGURE 4.8 Landslide susceptibility areas.

Conclusion

This research work presents a landslide susceptibility map to predict present and future hazard locations. Nowadays researchers are trying to investigate landslide susceptible zones using multiple models. Here the hybrid BBO machine learning model has been used to obtain a susceptibility map through the information about known and unknown landslide points. The model presented a spatial database by considering different geo-environment factors. From the AUC values of ROC it is established that hybrid BBO for the success rate and prediction rate are 0.9237 and 0.8979, respectively (Figure 4.9). All primary and secondary data were used to prepare the susceptibility map with the help of a hybrid BBO with three ensemble models. From that it is seen that there is a high tendency to occurrences of landslides and that the causative factors are very strong in creating such types of severe hazards. This hybrid machine learning is now used for many susceptibility and potentiality analyses. The hybrid BBO is also used for other susceptibilities like flood, soil erosion and gully erosion, and potentiality analysis for groundwater, minerals, and so on. The major limitations of this study is that the hybrid BBO model cannot give the major factors for landslide occurrences and, due to the physical barrier of east Sikkim, many inaccessible landslide locations have not been considered. Landslide-related information and landslide susceptibility mapping will help the government as well as researchers to take steps in hazard management and stabilizing natural conditions.

Validation

FIGURE 4.9 Validation.

References

Ahmed, B. “Landslide susceptibility mapping using multi-criteria evaluation techniques in Chittagong Metropolitan Area, Bangladesh.” Landslides 12. no. 6 (2015): 1077-1095.

Bhattacharya, A. and P. K. Chattopadhyay. Hybrid differential evolution with biogeography- based optimization for solution of economic load dispatch IEEE Transactions on Power Systems 25, no. 4 (2010): 1955-1964.

Borgatti, L. and M. Soldati. “Landslides as a geomorphological proxy for climate change: A record from the Dolomites (northern Italy).” Geomorphology 120, no. 1-2 (2010): 56-64.

Bui, D. T.. T. A. Tuan, H. Klempe. B. Pradhan, and I. Revhaug. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree Landslides 13, no. 2 (2016): 361-378.

Chakraborty, I., S. Ghosh, D. Bhattacharya, and A. Bora. “Earthquake induced landslides in the Sikkim-Darjeeling Himalayas—An aftermath of the 18th September 2011 Sikkim earthquake.” Earth Quake Report. The best independent Earthquake reporting site in the world (2011): 1-8.

Chakrabortty. R., S. C. Pal. I. Chowdhuri, S. Malik, and B. Das. “Assessing the importance of static and dynamic causative factors on erosion potentiality using SWAT. EBF with uncertainty and plausibility, logistic regression and novel ensemble model in a subtropical environment.” Journal of the Indian Society of Remote Sensing 48 (2020): 765-789.

Chakrabortty. R., S. C. Pal. S. Malik, and B. Das. “Modeling and mapping of groundwater potentiality zones using AHP and GIS technique: A case study of Raniganj Block. Paschim Bardhaman, West Bengal.” Modeling Earth Systems and Environment 4, no. 3 (2018): 1085-1110.

Choubey, V. D. “Landslide hazards and their mitigation in the Himalayan region." In International Symposium on Landslides, Japan, pp. 1849-1868. 1995.

Chowdhuri, I., S. C. Pal, and R. Chakrabortty. “Flood susceptibility mapping by ensemble evidential belief function and binomial logistic regression model on river basin of eastern India.” Advances in Space Research 65, no. 5 (2020): 1466-1489.

Das, B. and S. C. Pal. “Assessment of groundwater recharge and its potential zone identification in groundwater-stressed Goghat-I block of Hugh District. West Bengal, India.” Environment, Development and Sustainability (2019a): 1-19.

Das, B. and S. C. Pal. “Assessment of groundwater vulnerability to over-exploitation using MCDA, AHP, fuzzy logic and novel ensemble models: A case study of Goghat-I and II blocks of West Bengal. India.” Environmental Earth Sciences 79, no. 5 (2020): 1-16

Das, B. and S. C. Pal. “Combination of GIS and fuzzy-AHP for delineating groundwater recharge potential zones in the critical Goghat-II block of West Bengal. India.” HydroResearch 2 (2019b): 21-30.

Das, B., S. C. Pal, S. Malik, and R. Chakrabortty. “Modeling groundwater potential zones of Puruliya district. West Bengal. India using remote sensing and GIS techniques.” Geology, Ecology, and Landscapes 3, no. 3 (2019a): 223-237.

Das, B., S. C. Pal, S. Malik, and R. Chakrabortty. “Living with floods through geospatial approach: A case study of Arambag CD Block of Hugh District. West Bengal, India.” SN Applied Sciences 1, no. 4 (2019b): 329.

Das, H.. A. K. Jena. J. Nayak, B. Naik, and H. S. Behera. “A novel PSO based back propagation learning-MLP (PSO-BP-MLP) for classification.” In L.C. Jain. H.S. Behera. J.K. Mandal, and D.P. Mohapatra (Eds.), Computational Intelligence in Data Mining, Volume 2, pp. 461-471. Springer. New Delhi. 2015.

Das, H.. B. Naik, and H. S. Behera. “A hybrid neuro-fuzzy and feature reduction model for classification Advances in Fuzzy Systems 2020 (2020a): 1-15.

Das, H.. B. Naik. and H. S. Behera. “An experimental analysis of machine learning classification algorithms on biomedical data.” In Proceedings of the 2nd International Conference on Communication. Devices and Computing, pp. 525-539. Springer, Singapore, 2020b.

Das, H., B. Naik. and H. S. Behera. “Classification of diabetes mellitus disease (DMD): A data mining (DM) approach." In Progress in Computing, Analytics and Networking, pp. 539-549. Springer, Singapore, 2018.

Das, H.. B. Naik. and H. S. Behera. “Medical disease analysis using neuro-fuzzy with feature extraction model for classification.” Informatics in Medicine Unlocked 18 (2020c): 100288.

Das, H., B. Naik, H. S. Behera, S. Jaiswal, P. Mahato, and M. Rout. “Biomedical data analysis using neuro-fuzzy model with post-feature reduction.” Journal of King Saud University- Computer and Information Sciences (2020d).

Das, H.. N. Dey, and V. E. Balas, eds. Real-Time Data Analytics for Large Scale Sensor Data. Academic Press, London. UK, 2019c.

Dey, N.. A. S. Ashour, H. Kalia, R. T. Goswami. and H. Das, eds. Histopatliological Image Analysis in Medical Decision Making. IGI Global, Hershey. PA, 2018.

Dey. N.. H. Das. B. Naik. and H. S. Behera, eds. Big Data Analytics for Intelligent Healthcare Management. Academic Press, Boston. MA, 2019.

Fell, R.. J. Corominas. C. Bonnard. L. Cascini, E. Leroi. and W. Z. Savage. “Guidelines for landslide susceptibility, hazard and risk zoning for land-use planning.” Engineering Geology 102, no. 3-4 (2008): 99-111.

Glade. T. and M. J. Crozier. “The nature of landslide hazard impact.” In Landslide Hazard and Risk. Wiley. Chichester, 2005, pp. 43-74.

Gong, W„ Z. Cai. and С. X. Ling. “DE/BBO: A hybrid differential evolution with biogeogra- phy-based optimization for global numerical optimization.” Soft Computing 15. no. 4 (2010): 645-665.

Kaur, H., S. Gupta. S. Parkash. R. Thapa. A. Gupta, and G. C. Khanal. “Evaluation of landslide susceptibility in a hill city of Sikkim Himalaya with the perspective of hybrid modelling techniques.” Annals of CIS 25, no. 2 (2019): 113-132.

Malik. S., S. Chandra Pal. B. Das. and R. Chakrabortty. “Assessment of vegetation status of Sali River basin, a tributary of Damodar River in Bankura District. West Bengal, using satellite data.” Environment, Development and Sustainability (2019): 1-35.

Pal. S. C. and I. Chowdhuri. GIS-based spatial prediction of landslide susceptibility using frequency ratio model of Lachung River basin. North Sikkim. India. SN Applied Sciences 1, no. 5 (2019): 416.

Pal, S. С. B. Das. and S. Malik. “Potential landslide vulnerability zonation using integrated analytic hierarchy process and GIS technique of upper rangit catchment area, West Sikkim. India.” Journal of the Indian Society■ of Remote Sensing 47. no. 10 (2019): 1643-1655.

Pal. S. C., R. Chakrabortty, S. Malik, and B. Das. “Application of forest canopy density model for forest cover mapping using LISS-IV satellite data: A case study of Sali watershed, West Bengal.” Modeling Earth Systems and Environment 4, no. 2 (2018): 853-865.

Rawat. M. S., V. Joshi, D. P. Uniyal, and B. S. Rawat. Investigation of hill slope stability and mitigation measures in Sikkim Himalaya International Journal of Landslide and Environment 3, no. 1-3 (2016): 8-15.

Rout. M.. A. K. Jena. J. K. Rout, and H. Das. “Teaching-learning optimization based cascaded low-complexity neural network model for exchange rates forecasting. In Smart Intelligent Computing and Applications, pp. 635-645. Springer, Singapore. 2020.

Sassa, K. and P. Canuti, eds. Landslides-Disaster Risk Reduction. Springer Science & Business Media. Berlin. 2008.

Savsani, P. R. L. Jhala, and V. Savsani. “Effect of hybridizing biogeography-based optimization (BBO) technique with artificial immune algorithm (AIA) and ant colony optimization (ACO).” Applied Soft Computing 21 (2014): 542-553.

Simon. D. “Biogeography-based optimization.” IEEE Transactions on Evolutionary Computation 12, no. 6 (2008): 702-713.

Tambe, S.. G. Kharel, M. L. Arrawatia. H. Kulkarni, K. Mahamuni, and Anil K. Ganeriwala. “Reviving dying springs: Climate change adaptation experiments from the Sikkim Himalaya.” Mountain Research and Development 32, no. 1 (2012): 62-73.

Yalcin, A. “The effects of clay on landslides: A case study.” Applied Clav Science 38, no. 1-2 (2007): 77-85.

Zheng. Y., X. Lu. M. Zhang, and S. Chen. Biogeography-Based Optimization: Algorithms and Applications. Springer Nature. Singapore, 2019.

 
Source
< Prev   CONTENTS   Source   Next >