Relations between professional groups in the Atlantic and Mediterranean fishing enclaves of Andalusia (Spain): A personal networks approach with clustered graphs

This paper proposes a new network-based approach to analyse intergroup relations in fishing ports. The technique of clustered graphs is applied to the case of the Andalusian fishing ports to assess the balance between intra and inter-professional relationships. The patterns of sociability in Mediterranean and Atlantic fishing enclaves in the southern region of Spain were compared, examining their implications for participatory governance of marine resources. The personal networks of 53 fishermen, ship owners or skippers and key individuals of 18 Andalusian fisheries were analysed. The personal networks were compared in terms of fishing ground (Atlantic versus Mediterranean) and port type (by size and form of participation). The data of 45 individuals with whom each respondent usually interacts in the harbour was summarised in clustered graphs of intra-group and inter-group relationships between 8 professional roles in the harbour. Results show primarily that personal networks of Mediterranean ports are overall denser, in comparison with those of the Atlantic, which are more centralised and have a higher average betweenness. Secondly, in the Atlantic a clear difference of roles between ship owners and skippers is observed. A strong link between ship owners and the crew was found, and also between the ship owner and commercial roles in the Mediterranean. Small ports seem to be more apt for the artisanalisation of fisheries, as well as for the European Union’s Common Fisheries Policy.     

基于灵敏度分析的海洋油气资源BP神经网络预测模型的优化

作者针对BP神经网络结构设计中存在的问题,提出利用灵敏度分析方法对BP神经网络预测模型进行优化。通过BP算法与参数灵敏度分析的结合,寻找网络输入属性与输出属性之间的影响因子;在保证精度的前提下优选网络输入属性,简化网络结构,以增强网络的泛化能力,减少人为主观因素对网络设计的影响。最后以海洋油气资源预测为例,结合实测资料建立BP神经网络预测模型并进行了优化及预测精度评价,表明优化后的模型既能有效提高油气资源预测结果的稳定性,又不损失预测精度。     

中国装备制造业产学研合作创新网络初探

产学研合作是区域创新的主要途径和重要来源.以中国装备制造产业为例,基于中国知识产权局1985-2012年间的合作发明专利数据,借助SPSS,UCINET,ArcGIS等定量分析工具,对中国装备制造产业合作网络的创新主体结构,空间结构及其演变,创新合作的空间尺度的影响因素进行了分析.研究发现,民营企业,高校在中国装备制造产业创新网络中的地位不断上升,数量不断增加,且已经成为重要的创新源泉;市域空间合作成为发达地区城市产学研创新合作最重要的空间单元,国家空间是欠发达地区城市产学研创新合作的主要空间载体;理工科高校等科技资源的空间集聚态势是导致创新网络层级特征的主要因子,科技资源富集的行政中心如直辖市,省会城市等发达城市成为最重要的资源集聚地,创新源泉和创新合作对象.     

Evaluation of coseismic landslide hazard on the proposed Haast-Hollyford Highway,South Island,New Zealand

Coseismic landsliding presents a major hazard to infrastructure in mountains during large earthquakes. This is particularly true for road networks, as historically coseismic landsliding has resulted in road losses larger than those due to ground shaking. Assessing the exposure of current and planned highway links to coseismic landsliding for future earthquake scenarios is therefore vital for disaster risk reduction. This study presents a method to evaluate the exposure of critical infrastructure to landsliding from scenario earthquakes from an underlying quantitative landslide hazard assessment. The method is applied to a proposed new highway link in South Island, New Zealand, for a scenario Alpine Fault earthquake and compared to the current network. Exposure (the likelihood of a network being affected by one or more landslides) is evaluated from a regional-scale coseismic landslide hazard model and assessed on a relative basis from 0 to 1. The results show that the proposed Haast-Hollyford Highway (HHH) would be highly exposed to coseismic landsliding with at least 30–40?km likely to be badly affected (the Simonin Pass route being the worse affected of the two routes). In the current South Island State Highway network, the HHH would be the link most exposed to landsliding and would increase the total network exposure by 50–70% despite increasing the total road length by just 3%. The present work is intended to provide an effective method to assess coseismic landslide hazard of infrastructure in mountains with seismic hazard, and potentially identify mitigation options and critical network segments.     

VGI and crowdsourced data credibility analysis using spam email detection techniques

Volunteered geographic information (VGI) can be considered a subset of crowdsourced data (CSD) and its popularity has recently increased in a number of application areas. Disaster management is one of its key application areas in which the benefits of VGI and CSD are potentially very high. However, quality issues such as credibility, reliability and relevance are limiting many of the advantages of utilising CSD. Credibility issues arise as CSD come from a variety of heterogeneous sources including both professionals and untrained citizens. VGI and CSD are also highly unstructured and the quality and metadata are often undocumented. In the 2011 Australian floods, the general public and disaster management administrators used the Ushahidi Crowd-mapping platform to extensively communicate flood-related information including hazards, evacuations, emergency services, road closures and property damage. This study assessed the credibility of the Australian Broadcasting Corporation’s Ushahidi CrowdMap dataset using a Naïve Bayesian network approach based on models commonly used in spam email detection systems. The results of the study reveal that the spam email detection approach is potentially useful for CSD credibility detection with an accuracy of over 90% using a forced classification methodology.     

Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks

In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.     

汕头市PM2.5的气象要素影响分析及预报研究

利用2014—2017年汕头市PM_2.5的日浓度资料、以及汕头市国家基准气象观测站的同期地面气象资料,重点分析了汕头市PM_2.5浓度的变化特征以及风、混合层厚度、降水等气象条件对PM_2.5浓度的影响,同时探讨了污染物浓度变化的成因。在此基础上,根据汕头市的气候特点,采用BP （Back-Propagation）人工神经网络方法针对汛期和非汛期分别建立了PM_2.5质量浓度预报模型。结果表明：与多数内陆城市不同,汕头市PM_2.5浓度日变化为单峰型,这与汕头地处沿海受海陆风影响有关;PM_2.5浓度日峰值出现在08时左右,除早高峰污染物排放增加的因素外,与早晨时段的低风速环境有关;PM_2.5日均浓度随着风速的增大呈现减小趋势,PM_2.5日均浓度与08时混合层厚度显著相关（相关系数为-0.143）;汕头市非汛期PM_2.5浓度比汛期高,这与汕头市的亚热带季风气候特征有关,汛期各量级降水（暴雨以上除外）对PM_2.5的清除效果无明显差别,而非汛期降水对PM_2.5浓度有明显清除作用;BP人工神经网络模型的预报效果表明,汛期和非汛期的PM_2.5级别命中率TS分别为100%和90.3%,准确指数分别为87.7%和89.9%,总体预报效果良好。不同时期预报模型出现正误差的数量和程度均大于负误差,汛期预报模型在有强降水发生时误差较大,而非汛期预报模型在有冷空气入侵时误差较大。     

具有随机扰动和混合时滞的两层异质网络的同步研究

在现实生活中,很多复杂的系统不是由单个网络来表示,而是由一组相互依赖的网络系统来表示的.本文研究了具有随机扰动和混合时滞的两层异质网络的对应节点的同步控制问题.基于随机微分时滞方程的LaSalle不变原理和Lyapunov稳定性理论,采用牵制控制方法,对部分节点实施控制,给出了实现同步的充分条件.为了降低反馈控制的增益,结合自适应控制的方法,进一步弱化了两层异质网络实现同步的条件.最后,通过数值仿真,验证了理论结果的有效性.     

基于循环神经网络的单站能见度短临预报试验

由于能见度具有局地性和复杂的非线性变化特征,一直是精细化预报的难点。人工神经网络对复杂变化过程的模拟能力较高,为解决这一难题提供了可能性。本文采用循环神经网络,利用福州气象观测站地面观测数据,建立了福州单站能见度短临预报模型,并就预报能力进行了评估。随机检验结果表明,在1 h、3 h、6 h时效上,循环神经网络的预报与观测的变化趋势一致性较好;均方根误差比基于实况的预报分别减小15.75%、31.66%、41.26%,说明具备较好的预报能力;平均绝对值误差比传统BP神经网络分别减小12.90%、24.45%、 38.99%,表明循环神经网络对能见度预报具有优势,为能见度的精细化短临预报提供了新途径。     

MODELLING UNKNOWN STRUCTURAL SYSTEMS THROUGH THE USE OF NEURAL NETWORKS

This paper explores the potential of using neural networks to identify the internal forces of typical systems encountered in the field of earthquake engineering and structural dynamics. After formulating the identification task as a neural network learning procedure, the method is applied to a representative chain-like system under deterministic and stochastic excitations. The neural network based identification method provides very good results for general classes of multi-degree-of-freedom structural systems. The range of validity of the approach is demonstrated, and some application issues are discussed for (a) partially known multi-degree-of-freedom systems and (b) completely unknown systems.