利用乌鲁木齐遥测地震台记录识别人工爆破与地震

选取乌鲁木齐遥测地震台记录的乌鲁木齐市附近人工爆破与天然地震资料 ,运用波谱分析、波形空间线性度等方法作对比研究 ,发现人工爆破与天然地震的波谱特征量和波形空间线性度多数情况下差异较大。在震级与震中距相近的条件下 ,主要差异表现在天然地震的纵、横波拐角频率 fc P和 fc S明显大于人工爆破 ,两者比值约为 2∶ 1 ;天然地震的最大谱值比 Ωm P/ Ωm S也明显大于人工爆破 ,两者比值约为 3∶ 1 ;地震 P波功率谱的频谱特征量 fm W、Δf W也比人工爆破大很多。这些差异可以作为识别人工爆破与天然地震的测震学指标。     

Using an Artificial Intelligence Method to Recognize Seismic Precursory Anomaly (SPA)

In this work,we seek for a new way to recognize and analyze the Seismic Precursory Anomaly(SPA)quantitatively.For further study of the mechanism of SPA,an artificial intelligence method,the Machine Discovery(MD)method,is proposed to process the Seismic Precursor Observation(SPO)data and to fit an analytic function to them.The analytic function is used as a criterion to identify the SPA.The algorithm of MD is worked out based on the theory of Recursive Function(RF).The data of Amplitude Factor of Solid Tide(7 value)are processed by the proposed method.We find that the subsequent data fit to the extrapolation of the discovered function during the quiet period,whereas they deviate from it before a strong earthquake.Finally,the feasibility of quantitative analysis of the SPA is testified.     

人工神经网络及其在地震预报中的应用

文概述了人工神经网络的原理和算法，利用１９８５－１９９２年全国年度趋势会商报告的资料来训练的检验神经网络。结果表明，网络经训练后具有较高的识别能力，在地震预报中有深入研究和进一步应用的价值。最后讨论了神经网络中几个重要参数的取值问题。     

An intelligent and autonomous MEMS IMU/GPS integration scheme for low cost land navigation applications

An intelligent scheme to integrate inertial navigation system/global positioning system (GPS) is proposed using a constructive neural network (CNN) to overcome the limitations of current schemes, namely Kalman filtering (KF). The proposed CNN technique does not require prior knowledge or empirical trials to implement the proposed architecture since it is able to construct its architecture “on the fly,” based on the complexity of the vehicle dynamic variations. The proposed scheme is implemented and tested using Micro-electro-mechanical systems inertial measurement unit data collected in a land-vehicle environment. The performance of the proposed scheme is then compared with the multi-layer feed-forward neural networks (MFNN) and KF- based schemes in terms of positioning accuracy during GPS signal outages. The results are then analyzed and discussed in terms of positioning accuracy and learning time. The preliminary results presented in this article indicate that the positioning accuracy were improved by more than 55% when the MFNN and CNN-based schemes were implemented. In addition, the proposed CNN was able to construct the topology by itself autonomously on the fly and achieve similar prediction performance with less hidden neurons compared to MFNN-based schemes.     

高光谱遥感图像混合像元分解的群智能算法

近年来,通过群智能算法求解组合优化或连续优化问题以实现高光谱图像混合像元分解方面取得了重要进展和显著成果.本文首先回顾了高光谱图像混合像元分解的研究背景和群智能算法的特点,然后梳理了光谱混合模型及对应的最优化模型,进而介绍了基于群智能算法的端元提取和丰度反演方法,最后通过2组实验比较了群智能算法和其他传统算法在端元提取和丰度反演方面的精度,对基于群智能算法的混合像元分解效果进行了评价.另外,本文也对群智能算法在高光谱图像信息提取中应用的优势和存在的问题进行了总结.     

Superintelligence and Natural Resources: Morality and Technology in a Brave New World

A growing majority of artificial intelligence (AI) scientists and engineers believe human-level intelligence will be attained before the dawn of the 22nd century, while a large number believe this will happen much sooner. At this point, the elevation to “superintelligence,” or systems that have superhuman levels of general intelligence, would likely proceed very rapidly. With this in mind, this commentary has three goals: (1) to provide an overview of how a leading scholar, Nick Bostrom, conceives of superintelligence, with its potential and risks, (2) to bring attention to a burgeoning form of common pool resource extraction, space mining, that may benefit from superintelligence management, and (3) to suggest that environmental social scientists should play a key role in programming seed AI, infusing it not only with our existing collective knowledge, but also with just values.     

人工智能技术发展概述

近年来,以深度学习为核心的人工智能技术,取得了一系列重大突破.本文将就人工智能的产业化热潮,主要研究流派及发展历史,以深度学习为核心的成功应用,以及存在的一些问题和今后的可能研究方向做一个介绍.     

Modeling heat and mass transfer during ground freezing subjected to high seepage velocities

Natural or induced groundwater flow may negatively influence the performance of artificial ground freezing: high water flow velocities can prevent frozen conditions from developing. Reliable models that take into consideration hydraulic mechanisms are then needed to predict the ground freezing development. For forty years, numerous thermo-hydraulic coupled numerical models have been developed. Some of these models have been validated against experimental data but only one has been tested under high water flow velocity conditions. This paper describes a coupled thermo-hydraulic numerical model completely thermodynamically consistent and designed to simulate artificial ground freezing of a saturated and non-deformable porous medium under seepage flow conditions. On some points, less restrictive assumptions than the ones usually used in the literature are considered. As for the constant-porosity assumption, its validity is verified. The model appears to be well validated against analytical solutions and a three-dimensional ground freezing experiment under high seepage flow velocity conditions. It is used to highlight key thermo-hydraulic mechanisms associated with phase change in a porous medium.     

Material type and roughness influence structure of inter‐tidal communities on coastal defenses

On a global scale, urbanization has resulted in substantial proportions of coasts being replaced by artificial structures such as marinas, breakwaters and seawalls. There is broad consensus that coastal defense structures are poor surrogates of the natural habitats that they replace. Here we investigated the effects of the type and roughness of materials used for the construction of artificial structures on the surrounding biota by comparing abundances and distribution of key inter‐tidal taxa between natural shores and coastal defenses. Lower abundances of gastropods and barnacles were found on artificial coastal defense structures (regardless of the material type). At small spatial scales, abundances of key taxa increased with increasing roughness. Our results suggest that the choice of materials used for the construction of coastal defense structures has little effect on community structure per se, but that enhanced roughness could make coastal defenses better surrogates of natural habitats by supporting assemblages that are more similar to those found on natural shores.     

Artificial Neural Networks for the analysis of spread⿿mooring configurations for floating production systems

This work presents the development of Artificial Neural Networks for the analysis of any arbitrarily defined spread-mooring configuration for floating production systems (FPS), considering a given scenario characterized by the water depth, metocean data, characteristics of the platform hull, and the riser layout. The methodology is applied to recent designs of deepwater semi-submersible platforms connected to a large number of risers with asymmetrical layout. In such cases, the design variables may include values for the azimuthal spacing and mooring radius varying along the corners of the platform, besides the pretension and material of the lines. The results of the case study indicated that, given any mooring configuration characterized by the combination of all these design variables, the ANNs provide fairly accurate values for the parameters of the response that are required for the design of mooring systems (typically platform offsets and line tensions).