地面数字化测图网络自主学习系统的设计与实现     

花向红  向东  张涛  邹进贵 《测绘信息与工程》2012,37(1):46-48,54

以地面数字化测图模拟与仿真平台为基础,研究基于GIS技术的地面数字化测图模拟与仿真平台可视化仿真方法,建立地面数字化测图网络自主学习系统,引导学生在提出问题的基础上自主选择解决问题的方法、途径和工具,建立探究性实验教学模式,从而培养学生的实践和创新能力。  相似文献   

A conceptual framework for analysing adaptive capacity and multi-level learning processes in resource governance regimes   总被引：8，自引：0，他引：8  

Claudia Pahl-Wostl   《Global Environmental Change》2009,19(3):354-365

Governance failures are at the origin of many resource management problems. In particular climate change and the concomitant increase of extreme weather events has exposed the inability of current governance regimes to deal with present and future challenges. Still our knowledge about resource governance regimes and how they change is quite limited. This paper develops a conceptual framework addressing the dynamics and adaptive capacity of resource governance regimes as multi-level learning processes. The influence of formal and informal institutions, the role of state and non-state actors, the nature of multi-level interactions and the relative importance of bureaucratic hierarchies, markets and networks are identified as major structural characteristics of governance regimes. Change is conceptualized as social and societal learning that proceeds in a stepwise fashion moving from single to double to triple loop learning. Informal networks are considered to play a crucial role in such learning processes. The framework supports flexible and context sensitive analysis without being case study specific.First empirical evidence from water governance supports the assumptions made on the dynamics of governance regimes and the usefulness of the chosen approach. More complex and diverse governance regimes have a higher adaptive capacity. However, it is still an open question how to overcome the state of single-loop learning that seem to characterize many attempts to adapt to climate change. Only further development and application of shared conceptual frameworks taking into account the real complexity of governance regimes can generate the knowledge base needed to advance current understanding to a state that allows giving meaningful policy advice.  相似文献   

SVM方法在武汉区域夏季暴雨预报业务中的应用   总被引：5，自引：1，他引：4  

韦惠红  李才媛  邓红  熊秋芬 《气象科技》2009,37(2):145-148

以2003～2006年ECMWF数值预报产品、Japan和T213降水预报场资料为基础,应用支持向量机（SVM）方法和CMSVM应用软件平台,通过对训练样本进行交叉验证和模型核参数的逐渐逼近,分区建立了武汉区域16,个区SVM24h暴雨预报模型,并在武汉区域5～7月进行实时业务应用。通过预报结果检验,5～7月武汉区域暴雨预报TS评分为33．59％,其中湖北省平均成绩为34．69％、湖南省平均成绩为34．15％、河南省平均成绩为31．71％。检验结果较好,表明SVM方法在区域性暴雨预报中具有一定的预报能力和参考价值。  相似文献   

A three-tiered approach to participatory vulnerability assessment in the Solomon Islands   总被引：1，自引：0，他引：1  

Ioan Fazey  Mike Kesby  Anna Evely  Ian Latham  Daniel Wagatora  Jude-Edward Hagasua  Mark S. Reed  Mike Christie 《Global Environmental Change》2010,20(4):713-728

Greater recognition of the seriousness of global environmental change has led to an increase in research that assesses the vulnerability of households, communities and regions to changing environmental or economic conditions. So far, however, there has been relatively little attention given to how assessments can be conducted in ways that help build capacity for local communities to understand and find their own solutions to their problems. This paper reports on an approach that was designed and used to work with a local grass roots organization in the Solomon Islands to promote inclusivity and participation in decision-making and to build the capacity of the organization to reduce the vulnerability of communities to drivers of change. The process involved working collaboratively with the organization and training its members to conduct vulnerability assessments with communities using participatory and deliberative methods. To make best use of the learning opportunities provided by the research process, specific periods for formal reflection were incorporated for the three key stakeholders involved: the primary researchers; research assistants; and community members. Overall, the approach: (1) promoted learning about the current situation in Kahua and encouraged deeper analysis of problems; (2) built capacity for communities to manage the challenges they were facing; and (3) fostered local ownership and responsibility for problems and set precedents for future participation in decision-making. While the local organization and the communities it serves still face significant challenges, the research approach set the scene for greater local participation and effort to maintain and enhance livelihoods and wellbeing. The outcomes highlight the need for greater emphasis on embedding participatory approaches in vulnerability assessments for communities to benefit fully from the process.  相似文献   

粒子群算法与支持向量机相结合的热带气旋强度预报试验     

顾锦荣  刘华强  孙预前 《气象与减灾研究》2010,33(3):22-26

支持向量机(SVM)的惩罚参数及核参数的选择直接影响到模型效果,通过粒子群算法(PSO)解决支持向量机的参数选择问题,实现了参数选择的自动化。将该方法应用于热带气旋强度预报,利用气候持续性因子,挑选了1990年的100个左右样本进行预报检验,预报时效为12 h、24 h、36 h、48 h的强度平均绝对误差分别为3.00、4.35、4.93和6.68 m/s。另外,还与国外预报结果及采用最小二乘回归法的预报结果进行了效果的比较,SVM方法显示了更好的预报能力。  相似文献   

Forecasting the western Pacific subtropical high index during typhoon activity using a hybrid deep learning model     

Jianyin Zhou  Mingyang Sun  Jie Xiang  Jiping Guan  Huadong Du  Lei Zhou 《海洋学报(英文版)》2022,41(4):101-108

Seasonal location and intensity changes in the western Pacific subtropical high(WPSH) are important factors dominating the synoptic weather and the distribution and magnitude of precipitation in the rain belt over East Asia. Therefore, this article delves into the forecast of the western Pacific subtropical high index during typhoon activity by adopting a hybrid deep learning model. Firstly, the predictors, which are the inputs of the model, are analysed based on three characteristics: the first...  相似文献   

多特征差分核支持向量机模型的湿地变化检测   总被引：1，自引：0，他引：1  

潘琛  冯琰  林怡  陈映鹰 《测绘科学》2014,39(12):104-108,119

文章通过对不同特征空间、不同时相信息和不同类别引入多核函数组合和类别加权方式,构建了基于多特征差分核的加权支持向量机变化检测模型,能够获得平衡样本大小、综合多特征空间的变化检测结果.以上海崇明岛东端地区为例,利用4期ETM+/TM影像数据,基于构建的SVM变化检测模型,最终得到研究区湿地资源的空间变化格局,结果表明检测模型能够有效、准确地提取多种湿地变化类别的空间分布信息;并从景观水平上对检测结果进行格局分析,为湿地保护和管理提供科学参考.  相似文献   

General seismic wave and phase detection software driven by deep learning     

《地震研究进展（英文）》2021,1(3):100029

We developed an automatic seismic wave and phase detection software based on PhaseNet, an efficient and highly generalized deep learning neural network for P- and S-wave phase picking. The software organically combines multiple modules including application terminal interface, docker container, data visualization, SSH protocol data transmission and other auxiliary modules. Characterized by a series of technologically powerful functions, the software is highly convenient for all users. To obtain the P- and S-wave picks, one only needs to prepare three-component seismic data as input and customize some parameters in the interface. In particular, the software can automatically identify complex waveforms (i.e. continuous or truncated waves) and support multiple types of input data such as SAC, MSEED, NumPy array, etc. A test on the dataset of the Wenchuan aftershocks shows the generalization ability and detection accuracy of the software. The software is expected to increase the efficiency and subjectivity in the manual processing of large amounts of seismic data, thereby providing convenience to regional network monitoring staffs and researchers in the study of Earth's interior.  相似文献   

IEU-Net高分辨率遥感影像房屋建筑物提取   总被引：1，自引：0，他引：1  

王振庆  周艺  王世新  王福涛  徐知宇 《遥感学报》2021,25(11):2245-2254

房屋建筑物作为人类活动的主要场所,快速准确地将其从高分辨率遥感影像中提取出来,对促进遥感信息在防灾减灾、城镇管理等方面的应用具有重要意义。本文基于深度学习,提出了高分辨率遥感影像房屋建筑物像素级精确提取方法。首先,针对样本图像边缘像素特征不足现象,以U-Net模型为基础提出IEU-Net模型,设计了全新的忽略边缘交叉熵函数IELoss并将其作为损失函数,另外添加Dropout和BN层在避免过拟合的同时提高模型训练速度和鲁棒性。其次,为解决模型特征丰富度有限的问题,引入形态学建筑物指数MBI,与遥感影像RGB波段一同参与到模型的分类过程。最后,在模型预测时与IELoss相对应采用忽略边缘预测策略从而获得最佳建筑物提取结果。实验对比分析表明：本文方法能有效克服样本边缘像素特征不足问题并抑制道路、建筑物阴影对结果的影响,提升高分辨率遥感影像中房屋建筑物的提取精度。  相似文献   

深度学习遥感图像标注系统研究     

俞宵  张大富  张鹏  范俊甫 《测绘与空间地理信息》2021,44(4):69-71,75

随着深度学习的发展,遥感影像处理技术也从传统机器学习算法向深度学习转变,然而,用于遥感图像的训练数据集却十分稀少,且数据标注困难。本文将GIS技术与图像标注技术相结合,基于Flask Web框架设计一个可用于海量遥感数据的标注系统。该系统可用于海量遥感数据的数据框标注、数据类别标注,以及目标关键点标注,同时能将标注数据导出为深度学习训练最常用的COCO数据集和VOC2007两种格式。  相似文献