Landslide Forecast by Time Series Modeling and Analysis of High-Dimensional and Non-Stationary Ground Motion Data

High-dimensional, non-stationary vector time-series data are often seen in ground motion monitoring of geo-hazard events, e.g., landslides. For timely and reliable forecasts from such data, we developed a new statistical approach based on two advanced econometric methods, i.e., error-correction cointegration (ECC) and vector autoregression (VAR), and a newly developed dimension reduction technique named empirical dynamic quantiles (EDQ). Our ECC–VAR–EDQ method was born by analyzing a big landslide dataset, comprising interferometric synthetic-aperture radar (InSAR) measurements of ground displacement that were observed at 5090 time states and 1803 locations on a slope. The aim was to develop an early warning system for reliably forecasting any impending slope failure whenever a precursory slope deformation is on the horizon. Specifically, we first reduced the spatial dimension of the observed landslide data by representing them as a small set of EDQ series with negligible loss of information. We then used the ECC–VAR model to optimally fit these EDQ series, from which forecasts of future ground motion can be efficiently computed. Moreover, our method is able to assess the future landslide risk by computing the relevant probability of ground motion to exceed a red-alert threshold level at each future time state and location. Applying the ECC–VAR–EDQ method to the motivating landslide data gives a prediction of the incoming slope failure more than 8 days in advance.

A New Integrated Approach for Landslide Data Balancing and Spatial Prediction Based on Generative Adversarial Networks (GAN)

Landslide susceptibility mapping has significantly progressed with improvements in machine learning techniques. However, the inventory / data imbalance (DI) problem remains one of the challenges in this domain. This problem exists as a good quality landslide inventory map, including a complete record of historical data, is difficult or expensive to collect. As such, this can considerably affect one’s ability to obtain a sufficient inventory or representative samples. This research developed a new approach based on generative adversarial networks (GAN) to correct imbalanced landslide datasets. The proposed method was tested at Chukha Dzongkhag, Bhutan, one of the most frequent landslide prone areas in the Himalayan region. The proposed approach was then compared with the standard methods such as the synthetic minority oversampling technique (SMOTE), dense imbalanced sampling, and sparse sampling (i.e., producing non-landslide samples as many as landslide samples). The comparisons were based on five machine learning models, including artificial neural networks (ANN), random forests (RF), decision trees (DT), k-nearest neighbours (kNN), and the support vector machine (SVM). The model evaluation was carried out based on overall accuracy (OA), Kappa Index, F1-score, and area under receiver operating characteristic curves (AUROC). The spatial database was established with a total of 269 landslides and 10 conditioning factors, including altitude, slope, aspect, total curvature, slope length, lithology, distance from the road, distance from the stream, topographic wetness index (TWI), and sediment transport index (STI). The findings of this study have shown that both GAN and SMOTE data balancing approaches have helped to improve the accuracy of machine learning models. According to AUROC, the GAN method was able to boost the models by reaching the maximum accuracy of ANN (0.918), RF (0.933), DT (0.927), kNN (0.878), and SVM (0.907) when default parameters used. With the optimum parameters, all models performed best with GAN at their highest accuracy of ANN (0.927), RF (0.943), DT (0.923) and kNN (0.889), except SVM obtained the highest accuracy of (0.906) with SMOTE. Our finding suggests that RF balanced with GAN can provide the most reasonable criterion for landslide prediction. This research indicates that landslide data balancing may substantially affect the predictive capabilities of machine learning models. Therefore, the issue of DI in the spatial prediction of landslides should not be ignored. Future studies could explore other generative models for landslide data balancing. By using state-of-the-art GAN, the proposed model can be considered in the areas where the data are limited or imbalanced.

Counteracting flawed landslide data in statistically based landslide susceptibility modelling for very large areas: a national-scale assessment for Austria

The reliability of input data to be used within statistically based landslide susceptibility models usually determines the quality of the resulting maps. For very large territories, landslide susceptibility assessments are commonly built upon spatially incomplete and positionally inaccurate landslide information. The unavailability of flawless input data is contrasted by the need to identify landslide-prone terrain at such spatial scales. Instead of simply ignoring errors in the landslide data, we argue that modellers have to explicitly adopt their modelling design to avoid misleading results. This study examined different modelling strategies to reduce undesirable effects of error-prone landslide inventory data, namely systematic spatial incompleteness and positional inaccuracies. For this purpose, the Austrian territory with its abundant but heterogeneous landslide data was selected as a study site. Conventional modelling practices were compared with alternative modelling designs to elucidate whether an active counterbalancing of flawed landslide information can improve the modelling results. In this context, we compared widely applied logistic regression with an approach that allows minimizing the effects of heterogeneously complete landslide information (i.e. mixed-effects logistic regression). The challenge of positionally inaccurate landslide samples was tackled by elaborating and comparing the models for different terrain representations, namely grid cells, and slope units. The results showed that conventional logistic regression tended to reproduce incompleteness inherent in landslide training data in case the underlying model relied on explanatory variables directly related to the data bias. The adoption of a mixed-effects modelling approach appeared to reduce these undesired effects and led to geomorphologically more coherent spatial predictions. As a consequence of their larger spatial extent, the slope unit–based models were able to better cope with positional inaccuracies of the landslide data compared to their grid-based equals. The presented research demonstrates that in the context of very large area susceptibility modelling (i) ignoring flaws in available landslide data can lead to geomorphically incoherent results despite an apparent high statistical performance and that (ii) landslide data imperfections can actively be diminished by adjusting the research design according to the respective input data imperfections.

Spatial Temporal Tracking of Landslide Events: A Crowdsourced Mobile App

<p>Monsoons are characterised by the widespread occurrence of  landslides. Tracking each landslide event, developing early warning thresholds, understanding triggers, and initiating disaster rescue and relief efforts are complex for researchers and administration. The ever increasing landslides demand real-time data collection of events to enhance disaster management. In this work we designed and developed a dedicated crowd sourced mobile application, for systematic way of collection, validation, summarization, and dissemination of landslide data in real-time. This unique design of mobile app uses a scalable real-time data collection methodology for tracking landslide events through citizen science, and is available on Google Play Store for free, and at http://landslides.amrita.edu, with software conceived and developed by Amrita University in the context of the UK NERC/FCDO funded LANDSLIP research project (http://www.landslip.org/). This work implemented a structured database that integrates heterogeneous data such as text, numerical, GPS location, landmarks, and images. This methodology enables real-time tracking of landslides utilizing the details such as GPS location, date & time of occurrence, images, type, material, size, impact, area, geology, geomorphology, and comments in real-time. The mobile application has been uniquely designed to avoid missing landslide events and to handle the tradeoff between real-time spatial data collection without compromising the reliability of the data.  To achieve this a multi level user account was created based on their expert levels such as Tracker, Investigator, Expert.  A basic tracking form is presented for the Tracker level, and an extensive form is presented to the Expert level. The reliability of landslide data enhances as the user level increases from Tracker to Expert. Unique UI designs have been utilized to capture, and track the events. The tracking interface is divided into multiple screens; the main screen captures the landslide location through GPS enabled map interface and captures the date/time of the occurrence. Three additional screens capture images, additional details and comments. The 40 questions for landslide event collection used by the Geological Survey of India has been adapted through the collaborative effort of LANDSLIP partners to collect the additional details. The submitted landslides are immediately available for all users to view. The User can view entered landslides through the landslide image listing, Google maps interface, or tabular listing. The landslides can be filtered by date/time and other parameters. The mobile app is designed to be intuitive and fast, and aims to increase awareness about landslide risk through the integrated short documents, and videos. It has guidelines for safety, capturing images, mapping, and choosing the data from the multiple options. The uniqueness of the proposed methodology is that it enhances community participation, integrates event data collection, event data organizing, spatial and temporal summarization, and validation of landslide events and the impact. It pinpoints, maps and alerts real-time landslide events to initiate right disaster management activities to reduce the risk level. The Landslide tracker app was released during the 2020 monsoon season, and more than 250 landslides were recorded through the app.</p>