基于生成对抗网络的建筑物损毁检测EI北大核心CSCD

建筑物作为自然灾害中最受影响的承灾体之一,其损毁信息的准确提取对灾后应急救援具有十分重要的意义。本文借鉴多模态的思想,提出了一种自动检测损毁建筑物的recursive-generative adversarial networks(RS-GAN)方法,将损毁建筑物检测分为灾前建筑物识别和灾后损毁建筑物检测两个任务,且分别在两个GAN分支中完成。RS-GAN加入联合损失函数将两个GAN分支进行连接,充分利用两个任务之间的潜在互利性提升检测效果。RS-GAN利用第1条GAN分支识别建筑物灾前形状与位置,并将识别结果作为第2条GAN分支的输入进行损毁建筑物检测任务,从而使检测结果具有更清晰的轮廓。该方法为端到端模型,在不需要过多的人工干预情形下,实现了损毁建筑物的自动检测。为了验证RS-GAN模型的效果,在圣罗莎和密苏里两个数据集上进行了测试。试验结果表明,RS-GAN方法拥有更好的检测性能,在圣罗莎数据集上的总体精度和平均精度分别达到了0.90和0.86。     

论矿物改造机制研究

矿物改造机制是容易被岩矿研究人员忽视的“成因矿物学”新领域之一,主要涉及矿物诞生之后的变化过程.变形矿物及岩石显微构造定性研究已经发展成熟,但造岩矿物显微构造变形与流体运动学和动力学关系的定量研究仍是地学前缘问题.从解析构造学原理出发,将国内外定量研究问题概括出三方面:(1)变形-变质期次与同变形变质温压计;(2)利用同位素年代学分析某期次变形年龄;(3)某期次矿物蠕变机制、差异应力估算及岩石流动定律.并从理论和应用两方面评述了一些实例,认为建立“成因矿物学”实验室,对于系统研究矿物学问题具有重要意义.     

甘肃及其边邻地区断层形变特征强度时序变化与强震关系

利用甘肃及其边邻地区20世纪80年代末至2009年11月跨断层短水准流动观测资料,提取相关断裂带各段的断层形变特征强度指标,分析其可能揭示的构造变形动态演化特征及与资料积累以来MS5.8级以上地震孕育—发生过程的关系。研究表明:各断裂段断层形变特征强度时序曲线对其内、边缘附近MS5.8级以上地震反映较好,震前数月至1年左右时间内多数对应与构造背景一致的逆断异常;震后异常消失,或者出现短暂的正断异常,反映调整状态。     

Spatial interpolation using conditional generative adversarial neural networks

ABSTRACT

Spatial interpolation is a traditional geostatistical operation that aims at predicting the attribute values of unobserved locations given a sample of data defined on point supports. However, the continuity and heterogeneity underlying spatial data are too complex to be approximated by classic statistical models. Deep learning models, especially the idea of conditional generative adversarial networks (CGANs), provide us with a perspective for formalizing spatial interpolation as a conditional generative task. In this article, we design a novel deep learning architecture named conditional encoder-decoder generative adversarial neural networks (CEDGANs) for spatial interpolation, therein combining the encoder-decoder structure with adversarial learning to capture deep representations of sampled spatial data and their interactions with local structural patterns. A case study on elevations in China demonstrates the ability of our model to achieve outstanding interpolation results compared to benchmark methods. Further experiments uncover the learned spatial knowledge in the model’s hidden layers and test the potential to generalize our adversarial interpolation idea across domains. This work is an endeavor to investigate deep spatial knowledge using artificial intelligence. The proposed model can benefit practical scenarios and enlighten future research in various geographical applications related to spatial prediction.     

A human-machine adversarial scoring framework for urban perception assessment using street-view images

ABSTRACT

Though global-coverage urban perception datasets have been recently created using machine learning, their efficacy in accurately assessing local urban perceptions for other countries and regions remains a problem. Here we describe a human-machine adversarial scoring framework using a methodology that incorporates deep learning and iterative feedback with recommendation scores, which allows for the rapid and cost-effective assessment of the local urban perceptions for Chinese cities. Using the state-of-the-art Fully Convolutional Network (FCN) and Random Forest (RF) algorithms, the proposed method provides perception estimations with errors less than 10%. The driving factor analysis from both the visual and urban functional aspects demonstrated its feasibility in facilitating local urban perception derivations. With high-throughput and high-accuracy scorings, the proposed human-machine adversarial framework offers an affordable and rapid solution for urban planners and researchers to conduct local urban perception assessments.     

油库建筑总图综合设计

介绍油库设计类型,并结合工程设计实例,说明油库建筑总平面设计,竖向设计相关的综合设计的关系和需要考虑的内容。     

Estimating Injury and Loss of Life in Floods: A Deterministic Framework

This paper presents an outline methodology and an operational framework for assessing and mapping the risk of death or serious harm to people from flooding, covering death and physical injuries as a direct and immediate consequence of deep and/or fast flowing floodwaters (usually by drowning), and deaths and physical injuries associated with the flood event (but occurring in the immediate aftermath). The main factors that affect death or injury to people during floods include flow velocity, flow depth, and the degree to which people are exposed to the flood. The exposure potential is related to such factors as the “suddenness” of flooding (and amount of flood warning), the extent of the floodplain, people’s location on the floodplain, and the character of their accommodation. In addition, risks to people are affected by social factors including their vulnerability and behaviour. A methodology is described for estimating the likely annual number of deaths/injuries. This is based on defining zones of different flood hazard and, for each zone, estimating the total number of people located there, the proportion that are likely to be exposed to a flood, and the proportion of those exposed who are likely to be injured or killed during a flood event. The results for each zone are combined to give an overall risk for each flood cell and/or community. The objective of the research reported here is to develop a method which could be applied using a map-based approach in which flood risks to people are calculated and displayed spatially for selected areas or communities. The information needed for each part of the process is described in the paper, and the further research to provide the required information is identified.     

P点铅及其应用意义

在铅同位素研究中，异常铅是经常遇到并难于解释的问题。在一个矿区或矿带范围内，某些矿床的铅同位素资料中往往显示存在两种类型的铅：具有单阶段演化历史的正常铅和具有两个(或多个)阶段演化历史的异常铅。在常规的铅同位素组成图解上，这两种铅的数据点有时构成异常铅等时线，正常铅则位于等时线上含放射性成因铅最低的位置处。如果这种正常铅能给出合理的矿化年龄，并且该年龄与容矿围岩的成岩年龄基本一致，但显著老于异常铅瞬间增长模式年龄，那么，这种正常铅可能是异常铅等时线的起点，笔者称其为P点铅。显然，异常铅是后期放射性成因铅加入到P点铅形成的，P点铅的模式年龄为异常铅来源区的年龄：利用P点铅及异常铅等时线的资料，可以计算获得异常铅的矿化年龄。因此，P点铅这个概念的提出，为探讨矿化年龄问题开辟了一条新途径。文章还以加拿大和北欧地区某些矿床的铅同位素资料为例，讨论了在实际成矿过程中是否有P点铅存在的问题，讨论了P点铅在矿床成因研究中的重要意义。并给出了如何判断P点铅的具体条件。     

随钻伽马测井快速正演算法及地质导向应用

在定向井及水平井钻井过程中,常采用地质导向技术;地质导向的关键在于实时确定地层界面和产状、实现地层模型的实时更新和井眼轨迹的及时调整,从而最大限度地提高油层的钻遇率.利用基于地层模型的测井响应正演曲线与随钻测井曲线进行对比是确定地层界面的有效方法;本文基于伽马射线在地层中的衰减规律,导出了不同地层模型中随钻伽马测井响应快速正演算法,克服了目前难以将蒙特卡罗算法用于实时随钻伽马测井正演的困难.应用实例表明该方法可以有效地辅助实时判定实际地层界面,更好地实现地质导向.