A hybrid ensemble method for improved prediction of slope stability

Accurate prediction of slope stability is a significant issue in geomechanics with many artificial intelligence (AI) techniques being utilised. However, the application of AI has not reached its full potential because of the lack of more robust algorithms. In this paper, we proposed a hybrid ensemble method for the improved prediction of slope stability using classifier ensembles and genetic algorithm. Gaussian process classification, quadratic discriminant analysis, support vector machine, artificial neural networks, adaptive boosted decision trees, and k‐nearest neighbours were chosen to be individual AI techniques, and the weighted majority voting was used as the combination method. Validation method was chosen to be the 10‐fold cross‐validation, and performance measures were selected to be the accuracy, the receiver operating characteristic curve, and the area under the receiver operating characteristic curve (AUC). Grid search and genetic algorithm were used for the hyperparameter tuning and weight tuning respectively. The results show that the proposed hybrid ensemble method has great potential in improving the prediction of slope stability. Compared with individual classifiers, the optimum ensemble classifier achieved the highest AUC value (0.943) and the highest accuracy (0.902) on the testing set, denoting that the predictive performance has been improved. The optimum ensemble classifier with the Youden's cut‐off was recommended for slope stability prediction with respect to the AUC value, the accuracy, the true positive rate, and the true negative rate. This research indicates that the use of the classifier ensembles, rather than the search for the ideal individual classifiers, might help for the slope stability prediction.     

Pseudo-fractal interpolation for risk analysis

This paper describes a new method of analyzing the risk incurred when the outcome of a decision depends on interpolated values, for example, on the flow through an aquifer sparsely sampled for permeability or on the ratio of waste to ore in a mineral deposit sparsely sampled for grade. The method uses large families of interpolations constructed between sample values using adaptations of the well-known midpoint displacement method for generating pseudo-fractional Brownian motion trajectories. The parameters defining each family are chosen interactively by specialists to incorporate their expert knowledge. Each family, or ensemble, then defines a population of values for any global characteristic (functional) such as flow rate or waste ratio. The probabilities of various outcomes are estimated by counting them and calculating their ratios. For example, if 900 out of 1000 are acceptable the chance of success is estimated to be 90%.     

面向复杂地形的坡位K-means聚类划分研究

土壤植被研究建立在精准坡位划分的基础上。但现有的坡位大多采用手工划分的方式,存在着自动化程度低、划分精度不高且耗时较长等问题。本文提出一种顾及复杂地形的坡位自动划分算法,尝试采用机器学习K-means方法解决高海拔山区坡位划分的问题,并在山峰区域提取、聚类数确定、以及初始聚类中心选取等关键技术进行了算法的优化。为了验证算法的有效性,以云南省姚安县为研究区,运用提出的算法对研究区坡位进行自动划分,再采用Calinski-Harabasz聚类评价指标、调整兰德系数ARI和误差平方和SSE等一系列方法对坡位K-means聚类划分实验进行分析和评价。研究结果表明,利用该算法所生成的复杂地形坡位与研究区实测等高线相匹配。其次,再从姚安县规划风电场任选4个场址,比较13×13、25×25、37×37三种适宜窗口下坡位自动划分结果,结果表明选取25×25适宜窗口进行坡位划分可靠性最强。再者,计算的规划风电场内山脊、坡肩及背坡比例高达57.13%,也从一个侧面证实了利用该算法划分的坡位结果良好。     

地震分析预报实用化软件联调系统简介

本文主要介绍各学科实用化攻关与综合预报以及专家系统等软件组成的统一软件系统,使该软件系统与在 IBM 机和 VAX 机上建立的数据库联接起来,并介绍了该系统的主要功能。     

A prototype earthquake warning system for strike-slip earthquakes

A prototype expert system has been developed to provide rapid warning of earthquakes while they are occurring. Warning times of up to 100 seconds will be possible. In the complete system, several accelerometers are distributed at intervals within a few kilometers of a known fault; data are telemetered to a central computer which implements the expert system. The expert system incorporates specific information about the type of fault to be monitored, and includes simple rules for estimating the fault slip, rupture length, and seismic moment, all in real time. If the seismic moment exceeds a preset value, an alarm may be issued. The prototype is designed for deployment on near-surface strike-slip faults such as the San Andreas and has been successfully tested with data from the 1979 Imperial Valley and 1984 Morgan Hill earthquakes. Crucial concepts have also been tested using synthetic data calculated for a model of the 1857 Fort Tejon earthquake. Parkfield, California, could be used as a test site.     

区域地壳稳定性评价“安全岛”理论及方法

阐述了区域地壳稳定性和“安全岛”的概念和定义,以及在重大工程选址中研究它的重要作用。该课题从６０年代至今经历了三个不同的研究发展阶段,已形成具有我国特色的学科领域。文章探讨了区域地壳稳定“安全岛”理论和评价方法,归纳为三种评价方法：主要指标分级评价法;分区评价法;区域稳定（ＣＲＵＳＴＡＢ）专家系统及风险度评价法。最后提出相对稳定地块──安全岛”的识别标志以及从地表构造、深部构造和地震活动图象三方面与“地震空区”的主要区别。     

基于多光谱影像和DEM的泥石流堆积扇识别研究——以白龙江流域武都段为例

选取中国泥石流多发区白龙江流域武都段作为研究区,在对该区域泥石流堆积扇的形态特征和堆积范围进行实地调绘的基础上,利用高分辨率影像(SPOT)进行目视解译,获得研究区部分泥石流堆积扇和非泥石流堆积区的分布范围,将其作为已知样本区。利用该区域多光谱遥感影像(ASTER)和数字高程模型(DEM),提取包含波段比和主分量的几十种特征指标。通过运用方差分析和聚类分析等方法对各指标进行分析计算,选取对区别泥石流堆积扇最具显著意义的指标进行输入,进而采用基于像元的分类方法识别泥石流堆积扇。得到如下结论:SPOT与ASTER融合影像的波段比、主分量指标可以有效地突出土壤岩石中的矿物成分,对泥石流堆积扇的识别具有显著意义;利用筛选出的遥感指标和地形指标作为输入,进行监督分类识别泥石流堆积扇,能够有效地将遥感指标和地形指标相结合,提取的堆积扇覆盖范围与实际情况较为接近。     

Prediction of categorical spatial data via Bayesian updating

This study introduces a transition probability-based Bayesian updating (BU) approach for spatial classification through expert system. Transition probabilities are interpreted as expert opinions for updating the prior marginal probabilities of categorical response variables. The main objective of this paper is to provide a spatial categorical variable prediction method which has a solid theoretical foundation and yields relatively higher classification accuracy compared with conventional ones. The basic idea is to first build a linear Bayesian updating (LBU) model that corresponds to an application of Bayes’ theorem. Since the linear opinion pool is intrinsically suboptimal and underconfident, the beta-transformed Bayesian updating (BBU) model is proposed to overcome this limitation. Another type of BU approach, conditional independent Bayesian updating (CIBU), is derived based on conditional independent experts. It is shown that traditional Markovian-type categorical prediction (MCP) is equivalent to a particular CIBU model with specific parameters. As three variants of the BU method, these techniques are illustrated in synthetic and real-world case studies, comparison results with both the LBU and MCP favor the BBU model.     

Bridging the knowledge divide between public and experts using PGIS for land use planning in Malaysia

Ineffective public participation in land-use planning contributes to the lack of communication and understanding between the public and experts, acting as a barrier to successful planning outcomes. In this study, we assess whether Participatory GIS (PGIS) is a suitable method to bridge the communication gap between the public and expert knowledge for planning in the developing country context of Malaysia. Through a mixed methods approach, we investigate whether expert knowledge converges or diverges with the public's perceived knowledge obtained through a PGIS process and assess the potential benefits of PGIS from public and expert planning perspectives. The results indicate more convergence than divergence in knowledge and perspective, indicating that a PGIS process can communicate local knowledge to planning authorities to inform land use and development planning in Malaysia. Both the public and planning experts recognize the potential benefits of PGIS, but successful implementation will require major changes in traditional Malaysian public participation processes.