1990年景泰6.2级地震前后甘肃东南部地区的区域异常——地震前兆与后效区分

在分析地震活动性，地壳形变和其它前兆资料基础上指出，１９９０年景泰６．２级地震前后甘肃东南部地区的区域异常具有变化速率小，起始时间不同步，异常反央的力学性质不一致等特征，其中以异常变化速率小了为显著。     

The expert system for earthquake prediction (I)—the overall design and main structure

The Expert System For Earthquake Prediction (ESEP) is summarized in this paper. ESEP embraces three subsystems: long-middle term prediction system, annual prediction system and middle-short term prediction system. Each of the subsystems is composed of seven modules: the controlling module, the data base module, the expert knowledge base module, the method base module, the fact preparation module, the reasoning and decision-making module and the plotting and displaying module. The reasoning model ESEP/R and the knowledge expression model ESEP/K are set up in the ESEP, and new evidence combinations, CON (confine), W (weigh), and SYN (synthesize), have been proposed. The distinctive features of the ESEP are: (1) systemized; (2) several experts’ knowledge can be synthesized; (3) a large amount of data and experts’ experience is embraced; (4) four reasoning models and the synthetic decision-making technic are adopted; (5) several software environments are used; (6) modularization; and (7) possessing the friendly user interfaces. The Chinese version of this paper appeared in the Chinese edition ofActa Seismologica Sinica,14, 1–8, 1992.     

自组织人工神经网络在滇东震旦系—寒武系分界线岩相古地理研究中的应用

运用T.Kohonen自组织人工神经网络,根据滇东24个剖面的渔户村组中谊村段的各种单元素(包括岩段厚度、组成岩段的岩石薄片单因素-白云质、硅质、泥质、磷质、陆屑及盆屑,和岩段的24种光谱元素)的统计资料,建立了该地区震旦系-寒武系分界线的岩相古地理相区识别的计算机智能专家系统,其识别成功率达100％。结果表明,该方法性能良好,可望成为岩相古地理定量研究的一种有效的辅助手段。     

山西地下水氡中短期异常识别标志及预报方法研究

采用“九五”地震科技攻关地下水化学及 EIS2 0 0 0提供的多种数据处理和异常识别方法 ,对山西省地下水氡观测资料进行了较详细的处理 ,筛选出较好的数据处理方法和异常标志。结果表明 ,除常规的数学处理方法外 ,用水氡的基值变化率和滑动变化率提取异常效果较好 ,如果基值变化率 R0 ≥ 0 .0 6 ,持续时间大于等于 12个月 ,滑动变化率 R≥ 0 .0 5 ,持续时间大于等于 12个月 ,则视为异常     

交会图和Carbon软件在火山碎屑岩识别中的应用

针对火山岩储层的特殊性(复杂性、离散性和随机性),应用交会图及Carbon软件对火山岩测井解释中岩性识别问题进行了研究。该方法的技术关键是交会图的选取,以交会图和Carbon软件为基础实现对岩性的识别。将研究方法应用在海拉尔地区火山碎屑岩岩性识别问题中,取得了很好的效果,岩性解释符合率80%。     

卫星+AI时代遥感专业模式识别课程的教学实践与改革

在人工智能时代深化遥感产业发展背景下,遥感专业人才培养需要与时俱进,以提高人工智能应用能力。本文针对目前遥感科学与技术专业人工智能核心课程模式识别教学现状及存在的问题,提出面向遥感专业应用导向的模式识别课程建设思路,从教学内容和实践环节两个方面设计了以提高遥感专业学生人工智能应用能力为目的的教学方案。从教学反馈结果来看,本文提出的教学思路不仅激发了学生对模式识别课程学习的兴趣,而且提高了学生应用模式识别方法进行遥感信息解译的能力。     

苏北地区老井复查测井综合评价技术及方法研究

随着苏北小油田勘探开发程度的提高,非常规储层日益成为重点勘探开发的对象。苏北地区老井测井资料复查,立足现有的常规测井资料,结合测试等资料,通过扎实的基础工作和测井评价技术和分析方法的进步和提高,重点在干、密、水、无中全方位找油,并对以往相对忽视和评价认识手段方法相对不足的低孔渗储层、特殊含灰低孔渗储层与低阻油层作为重点研究分析对象,对测井资料进行全面复查评价,取得了良好的油气成果。     

一种语音识别的可定制云计算方法

以云的方式提供语音识别服务是1种新的趋势。当前市场上的语音云都是面向通用领域的,针对这一现状,提出了1种面向特定领域,可定制的,可满足用户个性化需求的云计算方案。首先介绍了语音识别的MapReduce过程,接着描述了基于Sector/Sphere的语音识别系统组成及语音识别的Sphere处理流程,并给出了语音识别系统的云计算架构,然后探讨了语音识别的可定制实现,最后进行实验评估,证明云计算架构的语音识别系统与传统C/S架构的语音识别系统相比更具优势,且具有一定的可扩展性。     

Assessing seawater quality with a variable fuzzy recognition model

With the rapid development of the marine economy industry, human exploitation of marine resources is increasing, which is contributing to the growing trend of eutrophication and frequent occurrence of red tide. Accordingly, investigations of seawater quality have attracted a great deal of attention. This study was conducted to construct a seawater environmental quality assessment model based on the variable fuzzy recognition model. The uncertainty and ambiguity of the seawater quality assessment were then considered, combining the monitoring values of evaluation indicators with the standard values of seawater quality. Laizhou Bay was subsequently selected for a case study. In this study, the correct variable model for different parameters was obtained according to the linear and nonlinear features of evaluation objects. Application of the variable fuzzy recognition model for Laizhou Bay, water quality evaluation and comparison with performance obtained using other approaches revealed that the generated model is more reliable than traditional methods, can more reasonably determine the water quality of various samples, and is more suitable for evaluation of a multi-index, multi-level, nonlinear marine environment system; accordingly, the generated model will be an effective tool for seawater quality evaluation.     

江苏沿海滩涂利用模式遥感影像解译和时空变化分析

为了弄清江苏沿海滩涂利用模式分布情况,定量分析其时空变化趋势,本文基于Google Earth Engine云计算平台和Landsat卫星遥感影像数据,结合随机森林分类方法,通过机器学习建立了滩涂利用模式自动识别分类方法,样本训练后识别准确率达93％以上.利用该方法提取了2002年、2014年和2019年江苏沿海的土地...