A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment

Abstract

A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC?=?0.930). However, RS model (AUROC?=?0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC?=?0.972), MB (AUROC?=?0.970) and AB (AUROC?=?0.957) models, respectively.     

A New Formation Mechanism of Coesite without the Plate Deeply-Subduction and Fast-Exhumation——Comment on the Article “Discussion on Some Problems of Quartz-Coesite Phase Transition”

本文分析评论了嵇少丞等(2010)发表的“石英—柯石英相变研究中若干问题讨论”一文.指出他们对柯石英非俯冲折返新机制的一些误解,对某些热力学、物理学概念,及其在地学问题中的解释理解的不同.分析了机械球磨的作用机制;论证了机械球磨作用本质与构造挤压剪切作用本质的同一性.分析了岩石糜棱岩化过程的两个阶段;讨论了地震波形成柯石英机制的可能性.围绕比较标准问题,论证了高能机械球磨(预处理)能大大降低α-石英转变成柯石英的压力、温度和合成时间,促进柯石英的形成.用小尺度不均匀局域高压微区模型解释了人工合成柯石英的规律性、南极洲天然矿物的行为,柯石英的寄生矿物、岩石——锆石、榴辉岩包裹体、非包裹体的形成.列举事例澄清了“球磨引进的Fe杂质提高柯石英形成压力迟缓合成”的说法;讨论了第二相存在对石英—柯石英转变的影响和“应变禁区”边界区的应力梯度相变驱动力可以形成柯石英问题.指出了机械球磨石英原料预处理和静高压合成柯石英后处理两步法,是一种实验室研究柯石英形成规律的有效物理方法;小尺度不均匀局域高压微区模型和无需板块深俯冲快折返的柯石英形成机制,是一种有希望的柯石英形成新机制.     

一种非板块深俯冲快折返的柯石英形成新机制——评析“石英—柯石英相变研究中若干问题讨论”一文

本文分析评论了嵇少丞等(2010)发表的"石英—柯石英相变研究中若干问题讨论"一文。指出他们对柯石英非俯冲折返新机制的一些误解,对某些热力学、物理学概念,及其在地学问题中的解释理解的不同。分析了机械球磨的作用机制;论证了机械球磨作用本质与构造挤压剪切作用本质的同一性。分析了岩石糜棱岩化过程的两个阶段;讨论了地震波形成柯石英机制的可能性。围绕比较标准问题,论证了高能机械球磨(预处理)能大大降低α-石英转变成柯石英的压力、温度和合成时间,促进柯石英的形成。用小尺度不均匀局域高压微区模型解释了人工合成柯石英的规律性、南极洲天然矿物的行为,柯石英的寄生矿物、岩石——锆石、榴辉岩包裹体、非包裹体的形成。列举事例澄清了"球磨引进的Fe杂质提高柯石英形成压力迟缓合成"的说法;讨论了第二相存在对石英—柯石英转变的影响和"应变禁区"边界区的应力梯度相变驱动力可以形成柯石英问题。指出了机械球磨石英原料预处理和静高压合成柯石英后处理两步法,是一种实验室研究柯石英形成规律的有效物理方法;小尺度不均匀局域高压微区模型和无需板块深俯冲快折返的柯石英形成机制,是一种有希望的柯石英形成新机制。     

基于模糊理论和典型线路的地质灾害评价的GIS方法研究

根据影响区域地质灾害发生的地质因素、地形因素、诱发因素和人为因素,建立区域地质灾害评价指标体系,对典型线路穿越的评价试验区进行地质灾害区域评价.由于地质灾害数据不仅含有不确定性而且还有复杂的模糊性,因而选用模糊评价方法.本文主要通过选取典型线路,采用模糊综合评判,利用GIS来进行,该研究结果表明是科学的、合理的和客观的...     

基于力学思想的空间聚类有效性评价

从力学的角度来考虑空间聚类问题,并结合地理学基本规律提出了一种基于力学思想的空间聚类有效性评价指标(简称SCV)。实验分析表明,本文提出的评价指标能够更准确、高效地对二维地理空间数据的硬聚类结果进行有效性评价。     

Hydropower licensing and climate change: Insights from cooperative game theory

Cooperative game theory solutions can provide useful insights into how parties may use water and environmental resources and share any benefits of cooperation. Here, a method based on Nash and Nash-Harsanyi bargaining solutions is developed to explore the Federal Energy Regulatory Commission (FERC) relicensing process, in which owners of non-federal hydropower projects in the United States have to negotiate their allowable operations, with other interest groups (mainly environmental). Linkage of games to expand the feasible solution range and the “strategic loss” concept are discussed and a FERC relicensing bargaining model is developed for studying the bargaining stage (third stage) of the relicensing process. Based on the suggested solution method, how the lack of incentive for cooperation results in long delay in FERC relicensing in practice is explained. Further, potential effects of climate change on the FERC relicensing are presented and how climate change may provide an incentive for cooperation among the parties to hasten the relicensing is discussed. An “adaptive FERC license” framework is proposed, based on cooperative game theory, to improve the performance and adaptability of the system to future changes with no cost to the FERC, in face of uncertainty about future hydrological and ecological conditions.     

城市近地层湍流特征分析

利用中国科学院大气物理研究所在北京的325 m铁塔观测资料,本文分析了47、140和280 m三个高度的湍流统计特征.结果表明,城市近地层的湍流速度方差和湍流温度方差都较好地满足局地相似关系,140 m和280 m的湍流特征非常接近,而47 m的湍流特征与之相比表现出明显的差异,说明由于城市冠层动力和热力非均匀性的影响...     

Artificial neural network forward modelling and inversion of electrokinetic logging data

An artificial neural network method is proposed as a computationally economic alternative to numerical simulation by the Biot theory for predicting borehole seismoelectric measurements given a set of formation properties. Borehole seismoelectric measurements are simulated using a finite element forward model, which solves the Biot equations together with an equation for the streaming potential. The results show that the neural network method successfully predicts the streaming potentials at each detector, even when the input pressures are contaminated with 10% Gaussian noise. A fast inversion methodology is subsequently developed in order to predict subsurface material properties such as porosity and permeability from streaming potential measurements. The predicted permeability and porosity results indicate that the method predictions are more accurate for the permeability predictions, with the inverted permeabilities being in excellent agreement with the actual permeabilities. This approach was finally verified by using data from a field experiment. The predicted permeability results seem to predict the basic trends in permeabilities from a packer test. As expected from synthetic results, the predicted porosity is less accurate. Investigations are also carried out to predict the zeta potential. The predicted zeta potentials are in agreement with values obtained through experimental self potential measurements.     

再谈黎平敖市金刚石异常——贵州省当前最佳金刚石找矿靶区分析

诸多迹象表明,敖市金刚石异常为一浓集异常,且叠加在一辉石重砂异常之上,显示出强烈的近源补给特征,其补给源极有可能是具工业价值的金刚石原生矿.鉴于湘黔金刚石成矿区内已知的含金刚石钾镁煌斑岩及其相关岩体的同位素年龄值均在375～475 Ma范围,其成矿期显然属加里东晚期,而紧邻敖市异常尚有后加里东盖层残留,作为幔源火山作用...     

基于大炮初至的近地表层析反演方法研究及应用

详细研究了射线追踪、层析反演方法原理以及层析反演数值求解算法,提出了利用大炮初至直接建立初始地震模型,由小折射和微测井进行约束的层析反演近地表速度模型的处理流程,提出了基于多次回溯的高精度快速射线追踪算法和层析反演数值求解算法。采用双重网格技术提高正演模拟计算精度和层析反演的成像质量,另外,充分考虑多种质量控制方案,确保最终的反演速度模型精确。设计了10种不同地表地质条件的理论模型,进行模型试算,并在实际生产中应用,理论模型试算和实际资料反演结果证明了本文方法的正确性。