An attention-based teacher-student model for multivariate short-term landslide displacement prediction incorporating weather forecast data

Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same time.In order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement prediction.Through MIC,a suitable input sequence length is selected for the LSTM model.To investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different lengths.The teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://rp5.ru)to improve the model’s expression capability,and the student model learns sequence information from other time series.An attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention mode.Finally,the predicted displacement is obtained through a linear layer.The proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention models.It achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PCCS)of 0.85.Additionally,it exhibits enhanced prediction stability and interpretability,rendering it an indispensable tool for landslide disaster prevention and mitigation.

Uncertainties of landslide susceptibility prediction:influences of different study area scales and mapping unit scales

This study aims to investigate the effects of different mapping unit scales and study area scales on the uncertainty rules of landslide susceptibility prediction(LSP).To illustrate various study area scales,Ganzhou City in China,its eastern region(Ganzhou East),and Ruijin County in Ganzhou East were chosen.Different mapping unit scales are represented by grid units with spatial resolution of 30 and 60 m,as well as slope units that were extracted by multi-scale segmentation method.The 3855 landslide locations and 21 typical environmental factors in Ganzhou City are first determined to create spatial datasets with input-outputs.Then,landslide susceptibility maps(LSMs)of Ganzhou City,Ganzhou East and Ruijin County are pro-duced using a support vector machine(SVM)and random forest(RF),respectively.The LSMs of the above three regions are then extracted by mask from the LSM of Ganzhou City,along with the LSMs of Ruijin County from Ganzhou East.Additionally,LSMs of Ruijin at various mapping unit scales are generated in accordance.Accuracy and landslide suscepti-bility indexes(LSIs)distribution are used to express LSP uncertainties.The LSP uncertainties under grid units significantly decrease as study area scales decrease from Ganzhou City,Ganzhou East to Ruijin County,whereas those under slope units are less affected by study area scales.Of course,attentions should also be paid to the broader representativeness of large study areas.The LSP accuracy of slope units increases by about 6%–10%compared with those under grid units with 30 m and 60 m resolution in the same study area's scale.The significance of environmental factors exhibits an averaging trend as study area scale increases from small to large.The importance of environmental factors varies greatly with the 60 m grid unit,but it tends to be consistent to some extent in the 30 m grid unit and the slope unit.

Uncertainties in landslide susceptibility prediction:Influence rule of different levels of errors in landslide spatial position

The accuracy of landslide susceptibility prediction(LSP)mainly depends on the precision of the landslide spatial position.However,the spatial position error of landslide survey is inevitable,resulting in considerable uncertainties in LSP modeling.To overcome this drawback,this study explores the influence of positional errors of landslide spatial position on LSP uncertainties,and then innovatively proposes a semi-supervised machine learning model to reduce the landslide spatial position error.This paper collected 16 environmental factors and 337 landslides with accurate spatial positions taking Shangyou County of China as an example.The 30e110 m error-based multilayer perceptron(MLP)and random forest(RF)models for LSP are established by randomly offsetting the original landslide by 30,50,70,90 and 110 m.The LSP uncertainties are analyzed by the LSP accuracy and distribution characteristics.Finally,a semi-supervised model is proposed to relieve the LSP uncertainties.Results show that:(1)The LSP accuracies of error-based RF/MLP models decrease with the increase of landslide position errors,and are lower than those of original data-based models;(2)70 m error-based models can still reflect the overall distribution characteristics of landslide susceptibility indices,thus original landslides with certain position errors are acceptable for LSP;(3)Semi-supervised machine learning model can efficiently reduce the landslide position errors and thus improve the LSP accuracies.

Uncertainties of landslide susceptibility prediction: Influences of random errors in landslide conditioning factors and errors reduction by low pass filter method

In the existing landslide susceptibility prediction(LSP)models,the influences of random errors in landslide conditioning factors on LSP are not considered,instead the original conditioning factors are directly taken as the model inputs,which brings uncertainties to LSP results.This study aims to reveal the influence rules of the different proportional random errors in conditioning factors on the LSP un-certainties,and further explore a method which can effectively reduce the random errors in conditioning factors.The original conditioning factors are firstly used to construct original factors-based LSP models,and then different random errors of 5%,10%,15% and 20%are added to these original factors for con-structing relevant errors-based LSP models.Secondly,low-pass filter-based LSP models are constructed by eliminating the random errors using low-pass filter method.Thirdly,the Ruijin County of China with 370 landslides and 16 conditioning factors are used as study case.Three typical machine learning models,i.e.multilayer perceptron(MLP),support vector machine(SVM)and random forest(RF),are selected as LSP models.Finally,the LSP uncertainties are discussed and results show that:(1)The low-pass filter can effectively reduce the random errors in conditioning factors to decrease the LSP uncertainties.(2)With the proportions of random errors increasing from 5%to 20%,the LSP uncertainty increases continuously.(3)The original factors-based models are feasible for LSP in the absence of more accurate conditioning factors.(4)The influence degrees of two uncertainty issues,machine learning models and different proportions of random errors,on the LSP modeling are large and basically the same.(5)The Shapley values effectively explain the internal mechanism of machine learning model predicting landslide sus-ceptibility.In conclusion,greater proportion of random errors in conditioning factors results in higher LSP uncertainty,and low-pass filter can effectively reduce these random errors.

Runout prediction of potential landslides based on the multi-source data collaboration analysis on historical cases

Long runout landslides involve a massive amount of energy and can be extremely hazardous owing to their long movement distance,high mobility and strong destructive power.Numerical methods have been widely used to predict the landslide runout but a fundamental problem remained is how to determine the reliable numerical parameters.This study proposes a framework to predict the runout of potential landslides through multi-source data collaboration and numerical analysis of historical landslide events.Specifically,for the historical landslide cases,the landslide-induced seismic signal,geophysical surveys,and possible in-situ drone/phone videos(multi-source data collaboration)can validate the numerical results in terms of landslide dynamics and deposit features and help calibrate the numerical(rheological)parameters.Subsequently,the calibrated numerical parameters can be used to numerically predict the runout of potential landslides in the region with a similar geological setting to the recorded events.Application of the runout prediction approach to the 2020 Jiashanying landslide in Guizhou,China gives reasonable results in comparison to the field observations.The numerical parameters are determined from the multi-source data collaboration analysis of a historical case in the region(2019 Shuicheng landslide).The proposed framework for landslide runout prediction can be of great utility for landslide risk assessment and disaster reduction in mountainous regions worldwide.

Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.

Prediction of the instability probability for rainfall induced landslides:the effect of morphological differences in geomorphology within mapping units

Slope units is an effective mapping unit for rainfall landslides prediction at regional scale.At present,slope units extracted by hydrology and morphological method report very different morphological feature and boundaries.In order to investigate the effect of morphological difference on the prediction performance,this paper presents a general landslide probability analysis model for slope units.Monte Carlo method was used to describe the spatial uncertainties of soil mechanical parameters within slope units,and random search technique was performed to obtain the minimum safety factor;transient hydrological processes simulation was used to provide key hydrological parameters required by the model,thereby achieving landslide prediction driven by quantitative precipitation estimation and forecasting data.The prediction performance of conventional slope units(CSUs)and homogeneous slope units(HSUs)were analyzed in three case studies from Fengjie County,China.The results indicate that the mean missing alarm rate of CSUs and HSUs are 31.4% and 10.6%,respectively.Receiver Operating Characteristics(ROC)analysis also reveals that HSUs is capable of improving the overall prediction performance,and may be used further for rainfall-induced landslide prediction at regional scale.

Landslide susceptibility prediction using slope unit-based machine learning models considering the heterogeneity of conditioning factors

To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method proposed by the authors promotes the application of slope units.However,LSP modeling based on these slope units has not been performed.Moreover,the heterogeneity of conditioning factors in slope units is neglected,leading to incomplete input variables of LSP modeling.In this study,the slope units extracted by the MSS method are used to construct LSP modeling,and the heterogeneity of conditioning factors is represented by the internal variations of conditioning factors within slope unit using the descriptive statistics features of mean,standard deviation and range.Thus,slope units-based machine learning models considering internal variations of conditioning factors(variant slope-machine learning)are proposed.The Chongyi County is selected as the case study and is divided into 53,055 slope units.Fifteen original slope unit-based conditioning factors are expanded to 38 slope unit-based conditioning factors through considering their internal variations.Random forest(RF)and multi-layer perceptron(MLP)machine learning models are used to construct variant Slope-RF and Slope-MLP models.Meanwhile,the Slope-RF and Slope-MLP models without considering the internal variations of conditioning factors,and conventional grid units-based machine learning(Grid-RF and MLP)models are built for comparisons through the LSP performance assessments.Results show that the variant Slopemachine learning models have higher LSP performances than Slope-machine learning models;LSP results of variant Slope-machine learning models have stronger directivity and practical application than Grid-machine learning models.It is concluded that slope units extracted by MSS method can be appropriate for LSP modeling,and the heterogeneity of conditioning factors within slope units can more comprehensively reflect the relationships between conditioning factors and landslides.The research results have important reference significance for land use and landslide prevention.

A Simplified Numerical Approach for the Prediction of Rainfall-Induced Retrogressive Landslides

Retrogressive landslides are common geological phenomena in mountainous areas and on onshore and offshore slopes. The impact of retrogressive landslides is different from that of other landslide types due to the phenomenon of retrogression. The hazards caused by retrogressive landslides may be increased because retrogressive landslides usually affect housing, facilities, and infrastructure located far from the original slopes. Additionally, substantial geomorphic evidence shows that the abundant supply of loose sediment in the source area of a debris flow is usually provided by retrogressive landslides that are triggered by the undercutting of water. Moreover, according to historic case studies, some large landslides are the evolution result of retrogressive landslides. Hence the ability to understand and predict the evolution of retrogressive landslides is crucial for the purpose of hazard mitigation. This paper discusses the phenomenon of a retrogressive landslide by using a model experiment and suggests a reasonably simplified numerical approach for the prediction of rainfall-induced retrogressive landslides. The simplified numerical approach, which combines the finite element method for seepage analysis, the shear strength reduction finite element method, and the analysis criterion for the retrogression and accumulation effect, is presented and used to predict the characteristics of a retrogressive landslide. The results show that this numerical approach is capable of reasonably predicting the characteristics of retrogressive landslides under rainfall infiltration, particularly the magnitude of each landslide, the position of the slip surface, and the development processes of the retrogressive landslide. Therefore, this approach is expected to be a practical method for the mitigation of damage caused by rainfall-induced retrogressive landslides.

Prediction of landslide displacement with dynamic features using intelligent approaches

Landslide displacement prediction can enhance the efficacy of landslide monitoring system,and the prediction of the periodic displacement is particularly challenging.In the previous studies,static regression models(e.g.,support vector machine(SVM))were mostly used for predicting the periodic displacement.These models may have bad performances,when the dynamic features of landslide triggers are incorporated.This paper proposes a method for predicting the landslide displacement in a dynamic manner,based on the gated recurrent unit(GRU)neural network and complete ensemble empirical decomposition with adaptive noise(CEEMDAN).The CEEMDAN is used to decompose the training data,and the GRU is subsequently used for predicting the periodic displacement.Implementation procedures of the proposed method were illustrated by a case study in the Caojiatuo landslide area,and SVM was also adopted for the periodic displacement prediction.This case study shows that the predictors obtained by SVM are inaccurate,as the landslide displacement is in a pronouncedly step-wise manner.By contrast,the accuracy can be significantly improved using the dynamic predictive method.This paper reveals the significance of capturing the dynamic features of the inputs in the training process,when the machine learning models are adopted to predict the landslide displacement.

Preliminary studies on the dynamic prediction method of rainfall-triggered landslide

Rainfall-triggered landslides have posed significant threats to human lives and property each year in China. This paper proposed a meteorologicalgeotechnical early warning system GRAPES-LFM(GRAPES: Global and Regional Assimilation and Pr Ediction System; LFM: Landslide Forecast Model),basing on the GRAPES model and the landslide predicting model TRIGRS(Transient Rainfall Infiltration and Grid-based Regional Slope-Stability Model) for predicting rainfall-triggered landslides.This integrated system is evaluated in Dehua County,Fujian Province, where typhoon Bilis triggered widespread landslides in July 2006. The GRAPES model runs in 5 km×5 km horizontal resolution, and the initial fields and lateral boundaries are provided by NCEP(National Centers for Environmental Prediction) FNL(Final) Operational Global Analysis data. Quantitative precipitation forecasting products of the GRAPES model are downscaled to 25 m×25 m horizontal resolution by bilinear interpolation to drive the TRIGRS model. Results show that the observed areas locate in the high risk areas, and the GRAPES-LFM model could capture about 74% of the historical landslides with the rainfall intense 30mm/h. Meanwhile, this paper illustrates the relationship between the factor of safety(FS) and different rainfall patterns. GRAPES-LFM model enables us to further develop a regional, early warning dynamic prediction tool of rainfall-induced landslides.

A WD-GA-LSSVM model for rainfall-triggered landslide displacement prediction

This paper proposes a WD-GA-LSSVM model for predicting the displacement of a deepseated landslide triggered by seasonal rainfall,in which wavelet denoising(WD)is used in displacement time series of landslide to eliminate the GPS observation noise in the original data,and genetic algorithm(GA)is applied to obtain optimal parameters of least squares support vector machines(LSSVM)model.The model is first trained and then evaluated by using data from a gentle dipping(~2°-5°)landslide triggered by seasonal rainfall in the southwest of China.Performance comparisons of WD-GA-LSSVM model with Back Propagation Neural Network(BPNN)model and LSSVM are presented,individually.The results indicate that the adoption of WD-GA-LSSVM model significantly improves the robustness and accuracy of the displacement prediction and it provides a powerful technique for predicting the displacement of a rainfall-triggered landslide.

A novel CGBoost deep learning algorithm for coseismic landslide susceptibility prediction

The accurate prediction of landslide susceptibility shortly after a violent earthquake is quite vital to the emergency rescue in the 72-h‘‘golden window”.However,the limited quantity of interpreted landslides shortly after a massive earthquake makes landslide susceptibility prediction become a challenge.To address this gap,this work suggests an integrated method of Crossing Graph attention network and xgBoost(CGBoost).This method contains three branches,which extract the interrelations among pixels within a slope unit,the interrelations among various slope units,and the relevance between influencing factors and landslide probability,respectively,and obtain rich and discriminative features by an adaptive fusion mechanism.Thus,the difficulty of susceptibility modeling under a small number of coseismic landslides can be reduced.As a basic module of CGBoost,the proposed Crossing graph attention network(Crossgat)could characterize the spatial heterogeneity within and among slope units to reduce the false alarm in the susceptibility results.Moreover,the rainfall dynamic factors are utilized as prediction indices to improve the susceptibility performance,and the prediction index set is established by terrain,geology,human activity,environment,meteorology,and earthquake factors.CGBoost is applied to predict landslide susceptibility in the Gorkha meizoseismal area.3.43%of coseismic landslides are randomly selected,of which 70%are used for training,and the others for testing.In the testing set,the values of Overall Accuracy,Precision,Recall,F1-score,and Kappa coefficient of CGBoost attain 0.9800,0.9577,0.9999,0.9784,and 0.9598,respectively.Validated by all the coseismic landslides,CGBoost outperforms the current major landslide susceptibility assessment methods.The suggested CGBoost can be also applied to landslide susceptibility prediction in new earthquakes in the future.

A graph deep learning method for landslide displacement prediction based on global navigation satellite system positioning

The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning.This study focuses on a landslide in Wenzhou Belt Highway and proposes a novel multivariate landslide displacement prediction method that relies on graph deep learning and Global Navigation Satellite System(GNSS)positioning.First model the graph structure of the monitoring system based on the engineering positions of the GNSS monitoring points and build the adjacent matrix of graph nodes.Then construct the historical and predicted time series feature matrixes using the processed temporal data including GNSS displacement,rainfall,groundwater table and soil moisture content and the graph structure.Last introduce the state-of-the-art graph deep learning GTS(Graph for Time Series)model to improve the accuracy and reliability of landslide displacement prediction which utilizes the temporal-spatial dependency of the monitoring system.This approach outperforms previous studies that only learned temporal features from a single monitoring point and maximally weighs the prediction performance and the priori graph of the monitoring system.The proposed method performs better than SVM,XGBoost,LSTM and DCRNN models in terms of RMSE(1.35 mm),MAE(1.14 mm)and MAPE(0.25)evaluation metrics,which is provided to be effective in future landslide failure early warning.

Uncertainties of landslide susceptibility prediction:Influences of different spatial resolutions,machine learning models and proportions of training and testing dataset

This study aims to reveal the impacts of three important uncertainty issues in landslide susceptibility prediction(LSP),namely the spatial resolution,proportion of model training and testing datasets and selection of machine learning models.Taking Yanchang County of China as example,the landslide inventory and 12 important conditioning factors were acquired.The frequency ratios of each conditioning factor were calculated under five spatial resolutions(15,30,60,90 and 120 m).Landslide and non-landslide samples obtained under each spatial resolution were further divided into five proportions of training and testing datasets(9:1,8:2,7:3,6:4 and 5:5),and four typical machine learning models were applied for LSP modelling.The results demonstrated that different spatial resolution and training and testing dataset proportions induce basically similar influences on the modeling uncertainty.With a decrease in the spatial resolution from 15 m to 120 m and a change in the proportions of the training and testing datasets from 9:1 to 5:5,the modelling accuracy gradually decreased,while the mean values of predicted landslide susceptibility indexes increased and their standard deviations decreased.The sensitivities of the three uncertainty issues to LSP modeling were,in order,the spatial resolution,the choice of machine learning model and the proportions of training/testing datasets.

Support principles of NPR bolt/cable and control techniques of large-deformation disasters

Deep mining has been paid much more attention because of the depletion of shallow mining resources.Traditional bolts could be invalid to accommodate large displacement and deformation in geomaterials.Consequently, alternative support and reinforcement bolts need to be studied and their constitutive models also need to be developed to help understanding for the complex stress-strain responses of rock masses under loadings. The effect of Negative Poisson's Ratio(NPR) that is attributed to the swelling phenomenon along the lateral direction may appear in metal materials under tensional loadings. Thence NPR materials often have an advantage over NPR ones in mechanical behavior such as impact resistance, antishearing, and energy absorbed. From the characteristics of NPR materials, a series of bolt and cable supports with the effect of NPR and constant-resistance have been recently developed. We here firstly introduce the structural features of NPR support. Then the constitutive model of NPR support is presented and its corresponding equation of energy equilibrium. Its basic principle interacted on rock masses is further discussed. Finally, NPR cables are employed to support the slope of an open-pit mine. The applications show that NPR cables can ease failure within the slope and play an important role in predicting and providing early warning of slope failure, together with a monitoring system of slope stability.