LSTM神经网络在地震资料初至拾取中的应用

本文引入RNN的升级算法LSTM神经网络技术,建立了一套海量数据、高精度的自动拾取地震资料初至流程。相比于其他神经网络方法,LSTM神经网络能够提取数据的时序特征,加强学习初至前噪音时序特征,从而提高初至拾取的精度,为地震资料的初至拾取提供一套新的思路。首先设计样本制作过程并建立、训练模型,通过模拟资料验证方法的有效性,应用于胜利油田浅海与西部山地地震勘探资料的初至拾取,取得理想效果,证明LSTM神经网络初至拾取具有较高的精度与适用性。     

Instance‐based learning compared to other data‐driven methods in hydrological forecasting

Data‐driven techniques based on machine learning algorithms are becoming popular in hydrological modelling, in particular for forecasting. Artificial neural networks (ANNs) are often the first choice. The so‐called instance‐based learning (IBL) has received relatively little attention, and the present paper explores the applicability of these methods in the field of hydrological forecasting. Their performance is compared with that of ANNs, M5 model trees and conceptual hydrological models. Four short‐term flow forecasting problems were solved for two catchments. Results showed that the IBL methods often produce better results than ANNs and M5 model trees, especially if used with the Gaussian kernel function. The study showed that IBL is an effective data‐driven method that can be successfully used in hydrological forecasting. Copyright © 2007 John Wiley & Sons, Ltd.     

NONHYDROSTATIC NUMERICAL SIMULATION FOR THE“96.8”EXTRAORDINARY RAINSTORM AND THE DEVELOPING STRUCTURE OF MESOSCALE SYSTEM

During the period of 3—5 August 1996(for short “96.8”),an extraordinary rainstorm eventoccurred in Henan,Hebei and Shanxi Provinces in China,resulting in severe flood catastrophe.Synoptic analyses indicated that the stable gross col field and the interaction between a northwardmoving typhoon(down into low pressure)and its east lateral Pacific subtropical high were thelarge-and meso-scale circulation conditions of the “96.8” extraordinary rainstorm.The mesoscaletyphoon-low and its specific dynamical and thermodynamical structures were directly related to thisrainstorm event.The nonhydrostatic version of mesoscale numerical model MM5 was used toconduct investigation of numerical simulation for this case.The simulation with the full physicalprocesses of nonhydrostatic version MM5 was basically possessed of a capability to reproduce thegenesis,development and evolution of the large-scale and meso-α scale synoptic systems.Thesimulative results using a two-way interactive nesting procedure revealed that the typhoon-low waspossessed of an intensive coupled mechanism between the dynamical and thermodynamical fields,namely,the developing typhoon-low was possessed of a structure of the.cyclonic vorticity columnwith warm center and high humidity,the vorticity column on the lower levels was the moistconvective instability and negative moist potential vorticity structure:the intensive ascendingvertical motion and the intense divergence on upper levels and intensive convergence on the lowerlevels as well as the development of the convective cloud cluster were intercoupling:the intensesouthern wind jet companied by the typhoon-low was not only the interaccompanying andintercoupling condition of the development and maintenance of the typhoon-low and convectivecloud cluster,but also was the transportable belt of the moisture source and heat energy of the“96.8”extraordinary rainstorm.The analysis of simulative results of precipitation indicated thatthe distribution of the rainfall belt and rainfall rate was basically consistent with that of theobservation in spite of some rainfall centers less or larger than those of the observation for coarseor fine mesh domain,respectively.     

交际教学互动作用的分析、研究与探讨

阐述了英语交际教学中，教学双方的锐意进取不仅能保证外语教学的顺利进行，而且还能有效促进大学英语教学，提高教学质量。详细研究了互动作用及非语言因素对教学的影响。     

Incorporation of perception-based information in robot learning using fuzzy reinforcement learning agents

Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.     

外语学习中的行为动机

对大学英语本科专业生的学习动机进行了研究，并试图发现这些学生在进行外语学习过程的不同阶段中的行为动机是什么。运用试验方法，通过问卷调查和结果分析，对中国学生英语学习活动的主要动机进行了探讨，并就在外语学习过程中目标、考试、社会期待，以及对所学语言和文化的兴趣之间的关系进行了分析。     

基于递归学习的组合电路等价性检验方法研究

等价性检验方法通常包括功能性和结构性的验证方法。分析了等价性检验的一般方法；并讨论了基于递归学习的组合电路等价性检验方法；算法利用直接蕴含和间接蕴含的方法，解决了布尔可满足问题。实验结果表明了该方法的有效性和可行性。     

基于CSCW的远程教育系统研究与设计

基于CSCW的远程教育系统以协同理论为指导,提出了支持自主式学习、协同学习两种主要学习模式下的网络学习环境, 突破了传统教育时间和空间的限制.     

基于小样本卷积神经网络的主动源P 波初至拾取方法

地震走时成像结果的准确性取决于初至到时的拾取精度,人工挑选初至效率低、成本高。前人研究表明深度学习可以应用于初至的自动拾取,然而传统的深度学习方法往往需要大量人工挑选的初至作为神经网络的训练集。文章利用U型卷积神经网络拾取单炮多道P波初至,研究表明P波初至拾取的均方根误差会随着训练集数量的增加而减少。训练集分别采用35炮和597炮数据时,对应的均方根误差分别为11.4和6.5 ms。参考半监督学习中数据增强方法,选取适合主动源数据的增强方法（随机剪裁、随机擦除等）用于拓展训练集。结果显示,以人工拾取总数据量的5%（35炮）作为小样本并进行随机擦除数据增强后,实现了均方根误差在5.5 ms（约3个采样点）以内,比未经增强的误差减少51%。与前人的深度学习方法相比,本文应用的数据增强方法可以在小样本的情况下实现主动源地震初至的高精度拾取。     

基于深度学习的岩体遥感智能解译模型研究——以苇河镇、亚布力镇、绥阳镇地区为例

在东北地区选取试验区,对比多种分类模型,提出一种基于多源多模态数据和多流CNN的岩体分类模型. 其中包括两个子模型:一是基于大尺度邻域和深度卷积神经网络的岩体提取模型;二是基于波段组合和多模态数据的多流CNN融合模型. 研究结果表明,预测结果图整体区域预测分布正确,总体精度评价指标达到84.4%,具有智能化程度高、客观性强的特点,能够为地质工作者提供辅助决策依据. 此外,还采用迁移学习策略对样本数量进行扩容,解决了CNN模型小样本问题.