{"type":"ScholarlyArticle","title":"Predicting Landslides Using Locally Aligned Convolutional Neural Networks","authors":[{"name":"Ainaz Hajimoradlou","slug":"ainaz-hajimoradlou","given":"Ainaz","family":"Hajimoradlou","affiliation":"University of British Columbia"},{"name":"Gioachino Roberti","slug":"gioachino-roberti","given":"Gioachino","family":"Roberti","affiliation":"Minerva Intelligence"},{"name":"David Poole","slug":"david-poole","given":"David","family":"Poole","affiliation":"University of British Columbia"}],"abstract":"Landslides, movement of soil and rock under the influence of gravity, are common phenomena that cause significant human and economic losses every year. Experts use heterogeneous features such as slope, elevation, land cover, lithology, rock age, and rock family to predict landslides.\r\nTo work with such features, we adapted convolutional neural networks to consider relative spatial information for the prediction task. Traditional filters in these networks either have a fixed orientation or are rotationally invariant. Intuitively, the filters should orient uphill, but there is not enough data to learn the concept of uphill; instead, it can be provided as prior knowledge. We propose a model called Locally Aligned Convolutional Neural Network, LACNN, that follows the ground surface at multiple scales to predict possible landslide occurrence for a single point. To validate our method, we created a standardized dataset of georeferenced images consisting of the heterogeneous features as inputs, and compared our method to several baselines, including linear regression, a neural network, and a convolutional network, using log-likelihood error and Receiver Operating Characteristic curves on the test set. Our model achieves 2-7% improvement in terms of accuracy and 2-15% boost in terms of log likelihood compared to the other proposed baselines.","doi":"10.24963/ijcai.2020/462","url":"https://ijcai.org/proceedings/2020/462","pdf":"https://ijcai.org/proceedings/2020/0462.pdf","markdown":"https://ijcai.org/proceedings/2020/462.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/462","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning Applications","track":"Main track","number":462,"pages":{"first":3342,"last":3348},"keywords":["Machine Learning Applications: Applications of Supervised Learning","Machine Learning: Knowledge-based Learning","Machine Learning Applications: Environmental"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25255/file_25255.m3u8","length_sec":260,"provider":"hls"}],"references":[{"position":1,"raw":"[Aitken et al., 2017] Andrew P. Aitken, Christian Ledig, Lu- cas Theis, Jose Caballero, Zehan Wang, and Wenzhe Shi. Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolu- tion resize. CoRR, abs/1707.02937, 2017.","title":"Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize","authors":"Andrew P Aitken, Christian Ledig, Lucas Theis, Jose Caballero, Zehan Wang, Wenzhe Shi","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Atkinson and Massari, 1998] Peter M. Atkinson and R. Massari. Generalised linear modelling of susceptibility to landsliding in the central apennines, italy. Computers and Geosciences, 24(4):373-385, 5 1998. M1 -4.","title":"Generalised linear modelling of susceptibility to landsliding in the central apennines, italy","authors":"M Peter, R Atkinson, Massari","year":"1998","venue":"Computers and Geosciences","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ayalew and Yamagishi, 2005] Lulseged Ayalew and Hi- romitsu Yamagishi. The application of gis-based logis- tic regression for landslide susceptibility mapping in the kakuda-yahiko mountains, central japan. Geomorphology, 65:15-31, 02 2005.","title":"Lulseged Ayalew and Hiromitsu Yamagishi. The application of gis-based logistic regression for landslide susceptibility mapping in the kakuda-yahiko mountains, central japan","authors":"Yamagishi Ayalew","year":"2005","venue":"Geomorphology","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Baron and Ottowitz, 2012] Supper R. Baron, I. and D. (Eds.) Ottowitz. Safeland deliverable d2.8: Rec- ommended procedures for validating landslide hazard and risk models and maps. living with landslide risk in europe: Assessment, effects of global change, and risk management strategies, 2012.","title":"Ottowitz. Safeland deliverable d2.8: Recommended procedures for validating landslide hazard and risk models and maps. living with landslide risk in europe: Assessment, effects of global change, and risk management strategies","authors":null,"year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Behnia and Blais-Stevens, 2017] Pouran Behnia and Blais- Stevens. Landslide susceptibility modelling using the quantitative random forest method along the northern por- tion of the yukon alaska highway corridor, canada. Natural Hazards, 11 2017.","title":"Landslide susceptibility modelling using the quantitative random forest method along the northern portion of the yukon alaska highway corridor, canada","authors":"Blais-Stevens ; Behnia, Pouran Behnia, Blais-Stevens","year":"2017","venue":"Natural Hazards","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Catani et al., 2013] F. Catani, D. Lagomarsino, S. Segoni, and V. Tofani. Landslide susceptibility estimation by ran- dom forests technique: sensitivity and scaling issues. Nat- ural Hazards and Earth System Sciences, 13(11):2815- 2831, 2013.","title":"Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues","authors":"F Catani, D Lagomarsino, S Segoni, V Tofani","year":"2013","venue":"Natural Hazards and Earth System Sciences","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Davis et al., 2006] John Davis, Chang-Jo Chung, and Gre- gory Ohlmacher. Two models for evaluating landslide haz- ards. Computers & Geosciences -COMPUT GEOSCI, 32:1120-1127, 10 2006.","title":"Two models for evaluating landslide hazards","authors":"John Davis, Chang-Jo Chung, Gregory Ohlmacher","year":"2006","venue":"Computers & Geosciences -COMPUT GEOSCI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Drozdzal et al., 2016] Michal Drozdzal, Eugene Vorontsov, Gabriel Chartrand, Samuel Kadoury, and Chris Pal. The importance of skip connections in biomedical image seg- mentation. CoRR, abs/1608.04117, 2016.","title":"The importance of skip connections in biomedical image segmentation","authors":"Michal Drozdzal, Eugene Vorontsov, Gabriel Chartrand, Samuel Kadoury, Chris Pal","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guzzetti et al., 2012] Fausto Guzzetti, Alessandro Mondini, Mauro Cardinali, Federica Fiorucci, Michele Santangelo, and Kang-tsung Chang. Landslide inventory maps: New tools for an old problem. Earth-Science Reviews, 112:42- 66, 03 2012.","title":"Landslide inventory maps: New tools for an old problem","authors":"Fausto Guzzetti, Alessandro Mondini, Mauro Cardinali, Federica Fiorucci, Michele Santangelo, Kang-Tsung Chang","year":"2012","venue":"Earth-Science Reviews","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Heckmann et al., 2015] Tobias Heckmann, Wolfgang Schwanghart, and Jonathan D. Phillips. Graph the- ory-recent developments of its application in geomor- phology. 2015.","title":"Graph theory-recent developments of its application in geomorphology","authors":"Heckmann","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[LeCun et al., 1999] Yann LeCun, Patrick Haffner, Léon Bottou, and Yoshua Bengio. Object recognition with gradient-based learning. In Shape, Contour and Group- ing in Computer Vision, pages 319-, London, UK, 1999. Springer-Verlag.","title":"Object recognition with gradient-based learning","authors":"Yann Lecun, Patrick Haffner, Léon Bottou, Yoshua Bengio","year":"1999","venue":"Shape, Contour and Grouping in Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lombardo et al., 2018] Luigi Lombardo, Thomas Opitz, and Raphael Huser. Point process-based modeling of mul- tiple debris flow landslides using inla: an application to the 2009 messina disaster -. Stochastic Environmental Re- search and Risk Assessment, 02 2018.","title":"Point process-based modeling of multiple debris flow landslides using inla: an application to the 2009 messina disaster","authors":"Luigi Lombardo, Thomas Opitz, Raphael Huser","year":"2018","venue":"Stochastic Environmental Research and Risk Assessment","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Luo X., 2019] Zhu S Yu M Zhang Z Meng L et al. Luo X., Lin F. Mine landslide susceptibility assessment using IVM, ANN and SVM models considering the contribution of affecting factors. 2019.","title":"Mine landslide susceptibility assessment using IVM, ANN and SVM models considering the contribution of affecting factors","authors":"S Zhu, M Yu, Z Zhang, L Meng","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mao et al., 2016] Xiaojiao Mao, Chunhua Shen, and Yu- Bin Yang. Image restoration using very deep convolu- tional encoder-decoder networks with symmetric skip con- nections. In Advances in Neural Information Processing Systems 29, pages 2802-2810. 2016.","title":"Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections","authors":"Mao","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Micheletti et al., 2013] Natan Micheletti, Loris Foresti, Syl- vain Robert, Michael Leuenberger, Andrea Pedrazzini, Michel Jaboyedoff, and Mikhail Kanevski. Machine learn- ing feature selection methods for landslide susceptibility mapping. Mathematical geosciences, 46, 12 2013.","title":"Machine learning feature selection methods for landslide susceptibility mapping","authors":"Natan Micheletti, Loris Foresti, Sylvain Robert, Michael Leuenberger, Andrea Pedrazzini, Michel Jaboyedoff, Mikhail Kanevski","year":null,"venue":"Mathematical geosciences","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Noh et al., 2015] Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. Learning deconvolution network for se- mantic segmentation. In The IEEE International Confer- ence on Computer Vision (ICCV), December 2015.","title":"Learning deconvolution network for semantic segmentation","authors":"Noh","year":"2015","venue":"The IEEE International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Petley, 2012] David Petley. Global patterns of loss of life from landslides. Geology, 40(10):927-930, 10 2012.","title":"Global patterns of loss of life from landslides","authors":"David Petley","year":"2012","venue":"Geology","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Reichenbach et al., 2018] Paola Reichenbach, Mauro Rossi, Bruce D. Malamud, Monika Mihir, and Fausto Guzzetti. A review of statistically-based landslide suscep- tibility models. Earth-Science Reviews, 180(March):60- 91, 2018.","title":"A review of statistically-based landslide susceptibility models","authors":"Paola Reichenbach, Mauro Rossi, Bruce D Malamud, Monika Mihir, Fausto Guzzetti","year":"2018","venue":"Earth-Science Reviews","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ronneberger et al., 2015] O. Ronneberger, P.Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), volume 9351 of LNCS, pages 234-241. Springer, 2015. (available on arXiv:1505.04597 [cs.CV]).","title":"U-net: Convolutional networks for biomedical image segmentation","authors":"O Ronneberger, P Fischer, T Brox","year":"2015","venue":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shelhamer et al., 2017] Evan Shelhamer, Jonathan Long, and Trevor Darrell. Fully convolutional networks for se- mantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):640-651, April 2017.","title":"Fully convolutional networks for semantic segmentation","authors":"Evan Shelhamer, Jonathan Long, Trevor Darrell","year":"2017","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tien Bui et al., 2015] Dieu Tien Bui, Tran Tuan, Harald Klempe, Biswajeet Pradhan, and Inge Revhaug. Spatial prediction models for shallow landslide hazards: a com- parative assessment of the efficacy of support vector ma- chines, artificial neural networks, kernel logistic regres- sion, and logistic model tree. Landslides, pages 1-18, 01 2015.","title":"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","authors":"Tien Dieu, Tran Bui, Harald Tuan, Biswajeet Klempe, Inge Pradhan, Revhaug","year":"2015","venue":"Landslides","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2019] Yi Wang, Zhice Fang, and Haoyuan Hong. Comparison of convolutional neural networks for landslide susceptibility mapping in yanshan county, china. Science of The Total Environment, 666:975-993, 05 2019.","title":"Comparison of convolutional neural networks for landslide susceptibility mapping in yanshan county, china","authors":"Wang","year":"2019","venue":"Science of The Total Environment","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xiao L, 2018] Peng G. Xiao L, Zhang Y. Landslide sus- ceptibility assessment using integrated deep learning al- gorithm along the China-Nepal highway. sensors (Basel, Switzerland), 18, 2018.","title":"Landslide susceptibility assessment using integrated deep learning algorithm along the China-Nepal highway. sensors","authors":"G Peng, L Xiao, Y Zhang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Youssef et al., 2014] Dr. Ahmed Youssef, Mohamed Al- Kathery, and Biswajeet Pradhan. Landslide susceptibility mapping at al-hasher area, jizan (saudi arabia) using gis- based frequency ratio and index of entropy models. Geo- sciences Journal, 19, 07 2014.","title":"Landslide susceptibility mapping at al-hasher area, jizan (saudi arabia) using gisbased frequency ratio and index of entropy models","authors":"Ahmed Dr, Mohamed Youssef, Biswajeet Al-Kathery, Pradhan","year":"2014","venue":"Geosciences Journal","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}