Landslide prediction from machine learning

Predicting where and when landslides are likely to occur in a specific region of interest remains a key challenge in natural hazards research and mitigation. While the basic mechanics of slope‐failure initiation and runout can be cast into physical and numerical models, a scarcity of sufficiently detailed and real‐time measurements of soil, rock‐mass and groundwater conditions prohibits accurate landslide forecasting. Researchers are therefore increasingly exploring multivariate data analysis techniques from the fields of data mining or machine learning in order to approximate future occurrences of landslides from past distribution patterns. This work has elucidated patterns of spatial susceptibility, but temporal forecasts have remained largely empirical. Most machine learning techniques achieve overall success rates of 75–95 percent. Whilst this may seem very promising, issues remain with data input quality, potential overfitting and commensurate inadequate choice of prediction models, inadvertent inclusion of redundant or noise variables, and technical limits to predicting only certain types and sizes of landslides. Simpler models provide only slightly inferior predictions to more complex models, and should guide the way for a more widespread application of data mining in regional landslide prediction. This approach should especially be communicated to planners and decision makers. Future research may want to develop: (1) further best‐practice guidelines for model selection; (2) predictions of occurrence and runout of large slope failures at the regional scale; and (3) temporal forecasts of landslides.     

Spatiotemporal modelling of rainfall-induced landslides using machine learning

Landslides - Natural terrain landslides are mainly triggered by rainstorms in Hong Kong, which pose great threats to life and property. To mitigate landslide risk, building a prediction model which...     

Modelling of shallow landslides with machine learning algorithms

This paper introduces three machine learning(ML)algorithms,the‘ensemble'Random Forest(RF),the‘ensemble'Gradient Boosted Regression Tree(GBRT)and the Multi Layer Perceptron neural network(MLP)and applies them to the spatial modelling of shallow landslides near Kvam in Norway.In the development of the ML models,a total of 11 significant landslide controlling factors were selected.The controlling factors relate to the geomorphology,geology,geo-environment and anthropogenic effects:slope angle,aspect,plan curvature,profile curvature,flow accumulation,flow direction,distance to rivers,water content,saturation,rainfall and distance to roads.It is observed that slope angle was the most significant controlling factor in the ML analyses.The performance of the three ML models was evaluated quantitatively based on the Receiver Operating Characteristic(ROC)analysis.The results show that the‘ensemble'GBRT machine learning model yielded the most promising results for the spatial prediction of shallow landslides,with a 95%probability of landslide detection and 87%prediction efficiency.     

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.     

Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method

Landslide displacement prediction is an essential component for developing landslide early warning systems. In the Three Gorges Reservoir area (TGRA), landslides experience step-like deformations (i.e., periods of stability interrupted by abrupt accelerations) generally from April to September due to the influence of precipitation and reservoir scheduled level variations. With respect to many traditional machine learning techniques, two issues exist relative to displacement prediction, namely the random fluctuation of prediction results and inaccurate prediction when step-like deformations take place. In this study, a novel and original prediction method was proposed by combining the wavelet transform (WT) and particle swarm optimization-kernel extreme learning machine (PSO-KELM) methods, and by considering the landslide causal factors. A typical landslide with a step-like behavior, the Baishuihe landslide in TGRA, was taken as a case study. The cumulated total displacement was decomposed into trend displacement, periodic displacement (controlled by internal geological conditions and external triggering factors respectively), and noise. The displacement items were predicted separately by multi-factor PSO-KELM considering various causal factors, and the total displacement was obtained by summing them up. An accurate prediction was achieved by the proposed method, including the step-like deformation period. The performance of the proposed method was compared with that of the multi-factor extreme learning machine (ELM), support vector regression (SVR), backward propagation neural network (BPNN), and single-factor PSO-KELM. Results show that the PSO-KELM outperforms the other models, and the prediction accuracy can be improved by considering causal factors.     

An extreme learning machine approach for slope stability evaluation and prediction

This paper presents slope stability evaluation and prediction with the approach of a fast robust neural network named the extreme learning machine (ELM). The circular failure mechanism of a slope is formulated based on its material, geometrical and environmental parameters such as the unit weight, the cohesion, the internal friction angle, the slope inclination, slope height and the pore water ratio. The ELM is proposed to evaluate the stability of slopes subjected to potential circular failures by means of prediction of the factor of safety (FS). Substantial slope cases collected worldwide are utilized to illustrate and assess the capability and predictability of the ELM on slope stability analysis. Based on the mean absolute percentage errors and the correlation coefficients between the original and predicted FS values, comparisons are demonstrated between the ELM and the generalized regression neural network (GRNN) as well as the prediction models generated from the genetic algorithms. Moreover, sensitivity analysis of the slope parameters and the ELM model parameters is carried out based on the two utilized evaluation functions. The time expense of the ELM on slope stability analysis is also investigated. The results prove that the ELM is advantageous to the GRNN and the genetic algorithm based models in the analysis of slope stability. Hence, the ELM can be a promising technique for approaching the problems in geotechnical engineering.     

基于机器学习的洋岛玄武岩主量元素预测稀土元素

地学共享数据库(如GEOROC、PetDB等)可为地球科学研究提供重要基础数据。然而,这些数据库均存在一个明显缺陷:样品的9种主量元素(SiO2、TiO2、Al2O3、CaO、MgO、MnO、K2O、Na2O和P2O5)均有准确数据,但稀土元素(rare earth elements,REE)数据大量缺失。鉴于REE在地球化学领域的重要作用,我们尝试为数据库缺失的REE值提供一个补全方案,即利用机器学习中的随机森林方法实现由9种主量元素预测REE值。以洋岛玄武岩(ocean island basalt,OIB)为例,把从GEOROC库中搜集到的1 283组OIB数据按8∶2的比例分为两组,其中80%的数据作为训练数据集用于建模,20%的数据作为测试数据集验证模型。比较了随机森林和多元线性回归方法对相同数据进行建模和预测的效果差异,发现无论是回归建模还是预测,随机森林方法都优于多元线性回归,且随着输入参数与输出参数之间关系的复杂化,这种优势更加明显。随机森林对测试数据集的预测效果整体较好,只是随着REE原子序数的增大,预测效果逐渐减弱。这一方面可能是因为原子序数大的REE与主量元素的关系更弱;另一方面可能是由于原子序数大的REE与主量元素的关系更加复杂。其次,随机森林方法预测的REE配分曲线与实际配分曲线吻合度较高,且预测所得配分曲线的区分能力较强,能够反映实际配分曲线之间的相对差异,这一点对推断地球化学过程尤为重要。随机森林方法随着训练数据的增多,其建立的模型也将越稳定,预测结果也会更精确。因此,随着数据库的不断完善,对数据库中REE值的预测也将更为可信、可行。     

Non-parametric machine learning methods for interpolation of spatially varying non-stationary and non-Gaussian geotechnical properties

Spatial interpolation has been frequently encountered in earth sciences and engineering.A reasonable appraisal of subsurface heterogeneity plays a significant role in planning,risk assessment and decision making for geotechnical practice.Geostatistics is commonly used to interpolate spatially varying properties at un-sampled locations from scatter measurements.However,successful application of classic geostatistical models requires prior characterization of spatial auto-correlation structures,which poses a great challenge for unexperienced engineers,particularly when only limited measurements are available.Data-driven machine learning methods,such as radial basis function network(RBFN),require minimal human intervention and provide effective alternatives for spatial interpolation of non-stationary and non-Gaussian data,particularly when measurements are sparse.Conventional RBFN,however,is direction independent(i.e.isotropic)and cannot quantify prediction uncertainty in spatial interpolation.In this study,an ensemble RBFN method is proposed that not only allows geotechnical anisotropy to be properly incorporated,but also quantifies uncertainty in spatial interpolation.The proposed method is illustrated using numerical examples of cone penetration test(CPT)data,which involve interpolation of a 2D CPT cross-section from limited continuous 1D CPT soundings in the vertical direction.In addition,a comparative study is performed to benchmark the proposed ensemble RBFN with two other non-parametric data-driven approaches,namely,Multiple Point Statistics(MPS)and Bayesian Compressive Sensing(BCS).The results reveal that the proposed ensemble RBFN provides a better estimation of spatial patterns and associated prediction uncertainty at un-sampled locations when a reasonable amount of data is available as input.Moreover,the prediction accuracy of all the three methods improves as the number of measurements increases,and vice versa.It is also found that BCS prediction is less sensitive to the number of measurement data and outperforms RBFN and MPS when only limited point observations are available.     

高斯过程机器学习在边坡稳定性评价中的应用

针对边坡工程是复杂的非线性系统,采用常规的理论分析和数值计算方法难以满足对边坡稳定性评价的高精度与快速性的要求,为此,提出对处理非线性复杂问题具有很好的适应性一种有概率意义的核学习机--高斯过程机器学习方法来解决边坡稳定性的合理评价问题,建立了相应的边坡稳定性预测模型。工程应用研究结果表明,采用高斯过程机器学习方法进行边坡稳定性评价是科学可行的,该方法能很好地表达边坡稳定性与各影响因素之间的非线性映射关系,能方便快捷地给出合理可靠且具有概率意义的边坡稳定状态评价结果,为实现边坡快速设计的工程实践要求提供了一条新的途径。     

极限学习机模型在季冻区深基坑地表沉降预测中的应用

针对传统数据驱动模型存在收敛速度慢、过度拟合等问题,提出了基于极限学习机算法的基坑地表沉降预测方法。结合季冻区地铁车站基坑的特点,提取基坑开挖时间、开挖深度、围护桩顶位移、围护桩内力、支撑轴力及地表温度等特征信息,建立极限学习机回归预测模型,选用实例数据进行算例分析,并将其与传统回归预测模型进行对比,实验结果表明,极限学习机模型收敛速度快,泛化能力强,其预测精度优于传统预测模型,且在学习速度方面优势明显,对深基坑安全监控有一定的实用价值。     

Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms

Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.     

基于机器学习的三维矿产定量预测——以四川拉拉铜矿为例

在大数据蓬勃发展的时代背景下,矿产资源定量预测作为地质大数据的核心部分,其综合分析挖掘多元信息的基本思路与大数据的理念不谋而合。以四川拉拉铜矿为例,开展基于机器学习的三维矿产资源定量预测。通过建立三维地质模型,提取成矿有利信息,构建研究区定量预测模型;基于"立方块预测模型"找矿方法,采用机器学习随机森林算法,计算出研究区成矿概率分布,以此圈定出5个找矿远景区。结果表明,随机森林具有更高的预测准确度与稳定性,且能够对控矿要素重要性做出定量评价。该研究成功地将机器学习应用于三维矿产定量预测,为今后的矿产资源预测评价做出了积极的探索。     

基于机器学习和测井数据的碳酸盐岩孔隙度与渗透率预测

准确预测碳酸盐岩储层孔隙度和渗透率对于碳酸盐岩油气藏储层评价具有重要意义。碳酸盐岩储层裂缝与溶孔广泛发育,基于经验公式从测井曲线预测储层孔隙度和渗透率具有较大误差。以中东某碳酸盐岩油藏为研究对象,选取914块取心井岩心,测定孔隙度与渗透率,利用随机森林（RF）、K-近邻（KNN）、支持向量机（SVM）和长短期记忆网络（LSTM）4种不同机器学习方法,通过测井数据进行孔隙度与渗透率预测,优化机器学习参数,筛选出适用于碳酸盐岩油藏的测井孔隙度与渗透率预测方法。研究结果表明：4种机器学习方法预测储层孔隙度结果差异不大,通过调整输入参数种类,可进一步提高孔隙度与渗透率预测效果,当以补偿中子（NPHI）、岩性密度（RHOB）和声波时差（DT）3种测井参数数据作为输入时,基于LSTM的储层孔隙度预测精度最高,孔隙度预测结果均方根误差（RMSE）为4.536 2;由于碳酸盐岩储层的强非均质性,基于机器学习的测井储层渗透率预测效果较差,相对而言,仅以NPHI作为机器学习输入参数时,基于RF的储层渗透率预测精度最高,渗透率预测结果的RMSE为45.882 3。     

Displacement prediction model of landslide based on a modified ensemble empirical mode decomposition and extreme learning machine

In this paper, an M–EEMD–ELM model (modified ensemble empirical mode decomposition (EEMD)-based extreme learning machine (ELM) ensemble learning paradigm) is proposed for landslide displacement prediction. The nonlinear original surface displacement deformation monitoring time series of landslide is first decomposed into a limited number of intrinsic mode functions (IMFs) and one residual series using EEMD technique for a deep insight into the data structure. Then, these sub-series except the high frequency are forecasted, respectively, by establishing appropriate ELM models. At last, the prediction results of the modeled IMFs and residual series are summed to formulate an ensemble forecast for the original landslide displacement series. A case study of Baishuihe landslide in the Three Gorges reservoir area of China is presented to illustrate the capability and merit of our model. Empirical results reveal that the prediction using M–EEMD–ELM model is consistently better than basic artificial neural networks (ANNs) and unmodified EEMD–ELM in terms of the same measurements.     

Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models

Research on the dynamics of landslide displacement forms the basis for landslide hazard prevention. This paper proposes a novel data-driven approach to monitor and predict the landslide displacement. In the first part, autoregressive moving average time series models are constructed to analyze the autocorrelation of landslide triggering factors. A linear ensemble-based extreme learning machine using the least absolute shrinkage and selection operator is applied in predicting the displacement of landslides. Five benchmarking data-driven models, the support vector machine, neural network, random forest, k-nearest neighbor, and the classical extreme learning machine, are considered as baseline models for validating the ensemble-based extreme learning machines. Numerical experiments demonstrated that the proposed prediction model produces the smallest prediction errors among all the algorithms tested. In the second part, parametric copula models are fitted on the predicted displacement, to investigate the relationship between the triggering factors and landslide displacement values. The Gumbel-Hougaard copula model performs best, which indicates strong upper tail correlation between the triggering factors and displacement values. Thresholds for the triggering factors can be obtained by monitoring the landslide moving patterns with large displacement values. The effectiveness and utility of the proposed data-driven approach have been confirmed with the landslide case study in the region of the Three Gorges Reservoir.     

龙门山前陆盆地深层海相碳酸盐岩储层地震预测研究

本文论及龙门山前陆盆地深层海相碳酸盐储层地震预测的岩石物理学基础与有效的预测方法技术问题。龙门山前陆盆地深层震旦系至中三叠统海相沉积以碳酸盐岩为主,厚4000~7000m, 天然气资源蕴藏量巨大而探明率低, 油气勘探的关键在于寻找优质储层。基于对地震资料和井资料的分析,认为该区段的储层主要是生物礁滩相白云岩和发育构造裂缝的碳酸盐岩。依据井资料,总结介绍了该区三叠系马鞍塘组、雷口坡组和嘉陵江组地层与碳酸盐岩储层的地震波速度、密度、电阻率等物性参数特征。在分析介绍储层地震预测原理方法与碳酸盐岩储层地震预测问题的基础上,介绍了作者研究提出的地震纹分析方法的概念、原理及其在含气储层检测中确定的应用效果。     

Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors

In the evolution of landslides, besides the geological conditions, displacement depends on the variation of the controlling factors. Due to the periodic fluctuation of the reservoir water level and the precipitation, the shape of cumulative displacement-time curves of the colluvial landslides in the Three Gorges Reservoir follows a step function. The Baijiabao landslide in the Three Gorges region was selected as a case study. By analysing the response relationship between the landslide deformation, the rainfall, the reservoir water level and the groundwater level, an extreme learning machine was proposed in order to establish the landslide displacement prediction model in relation to controlling factors. The result demonstrated that the curves of the predicted and measured values were very similar, with a correlation coefficient of 0.984. They showed a distinctive step-like deformation characteristic, which underlined the role of the influencing factors in the displacement of the landslide. In relation to controlling factors, the proposed extreme learning machine (ELM) model showed a great ability to predict the Baijiabao landslide and is thus an effective displacement prediction method for colluvial landslides with step-like deformation in the Three Gorges Reservoir region.     

基于岩石物理模版的碳酸盐岩含气储层定量解释

笔者针对碳酸盐岩储层勘探开发面临的储层预测与流体识别难度大的问题,基于岩石物理理论,提出了一种对碳酸盐岩含气储层进行定量解释的方法:首先,综合碳酸盐岩地质和测井信息,以岩石物理理论为依据,实现了适用的碳酸盐岩岩石物理模型的构建;然后基于岩石物理模型优选出对孔隙度、含气饱和度较为敏感的参数λρ和μρ,构建能够反映储层孔隙度与含气饱和度的碳酸盐岩岩石物理模版;最后,将岩石物理模版与工区反演提取的参数相结合,确定储层分布范围,并对储层范围内孔隙度和含气饱和度数值进行了定量解释。实例分析表明,基于该模版定量解释得到的孔隙度和含气饱和度与实际地层孔隙度及产气结果基本一致,经验证碳酸盐岩岩石物理模版的可靠性和适用性较好。     

Using logistic regression model selection towards interpretable machine learning in mineral prospectivity modeling

Regression or regression-like models are often employed in mineral prospectivity modeling, i.e., for the targeting of resources, either based on 2D map images or 3D geomodels both in raster mode or based on spatial point processes. Machine learning techniques like artificial neural networks are often applied and give decent results in the prediction of target events. However, they typically provide little insight into the problem regarding the importance, or relevance, of covariables. On the other hand, logistic regression has a well understood statistical foundation and uses an explicit model from which knowledge can be gained about the underlying phenomenon. Establishing such an explicit model is rather difficult for real world problems. In the context of mineral prospectivity modeling additional challenges arise, such as rare events, i.e. only a small fraction of data instances describes a positive target event, which is the event of interest.In this paper, we propose a model selection procedure applied to logistic regression incorporating explicit nonlinearities. The model selection procedure, based on the Wald test and the Bayes' information criterion (BIC), as proposed in this paper is new. The performance regarding the predictive power of the obtained model is comparable to logistic regression using a stepwise model selection and to neural networks on several real world datasets, one of them a dataset for the detection of gold mineralizations in Ghana. However, our new method is significantly faster than standard stepwise selection, while selecting fewer variables for the final model. In our numerical experiments, the prediction accuracy is also comparable to a neural network, which is currently in use in industry.In applications, the method can aid the model building process through an explicit model. Furthermore, it may be used as preprocessing step for other machine learning algorithms such as neural networks. In this paper, we intend to present mathematics of prospectivity modeling with the potential to contribute to bridging the gap between statistical and machine learning. Big Data and Artificial Intelligence are of increasing importance in mineral exploration. At the same time there is a growing demand for mathematically rigorous machine learning methods, which can still be interpreted by experts. This paper is a contribution to this field.