Identification of physical processes inherent in artificial neural network rainfall runoff models

The emergence of artificial neural network (ANN) technology has provided many promising results in the field of hydrology and water resources simulation. However, one of the major criticisms of ANN hydrologic models is that they do not consider/explain the underlying physical processes in a watershed, resulting in them being labelled as black‐box models. This paper discusses a research study conducted in order to examine whether or not the physical processes in a watershed are inherent in a trained ANN rainfall‐runoff model. The investigation is based on analysing definite statistical measures of strength of relationship between the disintegrated hidden neuron responses of an ANN model and its input variables, as well as various deterministic components of a conceptual rainfall‐runoff model. The approach is illustrated by presenting a case study for the Kentucky River watershed. The results suggest that the distributed structure of the ANN is able to capture certain physical behaviour of the rainfall‐runoff process. The results demonstrate that the hidden neurons in the ANN rainfall‐runoff model approximate various components of the hydrologic system, such as infiltration, base flow, and delayed and quick surface flow, etc., and represent the rising limb and different portions of the falling limb of a flow hydrograph. Copyright © 2004 John Wiley & Sons, Ltd.     

Reliability assessment of serviceability performance of braced retaining walls using a neural network approach

In urban environments, one major concern with deep excavations in soft clay is the potentially large ground deformations in and around the excavation. Excessive movements can damage adjacent buildings and utilities. There are many uncertainties associated with the calculation of the ultimate or serviceability performance of a braced excavation system. These include the variabilities of the loadings, geotechnical soil properties, and engineering and geometrical properties of the wall. A risk‐based approach to serviceability performance failure is necessary to incorporate systematically the uncertainties associated with the various design parameters. This paper demonstrates the use of an integrated neural network–reliability method to assess the risk of serviceability failure through the calculation of the reliability index. By first performing a series of parametric studies using the finite element method and then approximating the non‐linear limit state surface (the boundary separating the safe and ‘failure’ domains) through a neural network model, the reliability index can be determined with the aid of a spreadsheet. Two illustrative examples are presented to show how the serviceability performance for braced excavation problems can be assessed using the reliability index. Copyright © 2005 John Wiley & Sons, Ltd.     

Application of back-propagation networks in debris flow prediction

Debris flows have caused serious loss of human lives and a lot of damage to properties in Taiwan over the past decades. Moreover, debris flows have brought massive mud causing water pollution in reservoirs and resulted in water shortage for daily life locally and affected agricultural irrigation and industrial usages seriously. A number of methods for prediction of debris flows have been studied. However, the successful prediction ratio of debris flows cannot always maintain a stable and reliable level. The objective of this study is to present a stable and reliable analytical model for occurrence predictions of debris flows. This study proposes an Artificial Neural Networks (ANN) model that was constructed by seven significant factors using back-propagation (BP) algorithm. These seven factors include (1) length of creek, (2) average slope, (3) effective watershed area, (4) shape coefficient, (5) median size of soil grain, (6) effective cumulative rainfall, and (7) effective rainfall intensity. A total of 178 potential cases of debris flows collected in eastern Taiwan were fed into the ANN model for training and testing. The average ratio of successful prediction reaching 93.82% demonstrates that the presented ANN model with seven significant factors can provide a stable and reliable result for the prediction of debris flows in hazard mitigation and guarding systems.     

Can we sustain sustainable agriculture? Learning from small-scale producer-suppliers in Canada and the UK

There has been particular interest in 'alternative' food over the last 10 years, with many policymakers and researchers throughout the Minority World following a growing number of consumers and producers in supporting organic farming and a host of 'alternative' food networks. To date, there has been a tendency for theory and policy to emerge somewhat divorced from the grounded practices and experiences of producer-suppliers themselves within these networks. Urging a shift from 'alternativity' to 'sustainability' as a more critical and valuable tool to analyse food networks, this paper draws upon in-depth ethnographic research with small-scale producer-supplier case studies in south Wales and southern Ontario. In so doing it explores often overlooked voices and stories within sustainable food discourses. Focusing on the value of farmer-led understandings and responses, the paper highlights important implications for policymakers and consumers and outlines future research on sustainable food networks.     

企业网络发育程度与区域创新能力研究

本文从分析企业网络的发育和完善程度出发，探讨影响网络创新能力的因素。文章指出，网络发育程度与创新能力(创新数量、创新发生的频率)是正相关的。从宏观上讲网络越密集、各种正式和非正式联系越有效、网络联系越稳定、网络自我更新能力越强、网络的开放性越强、网络越能根植于当地的良好的区域环境，越容易激发创新；从微观上讲，网络中行为主体的学习能力越强，其创新发生频率越高，创新能力越强。     

Generating fracture networks using iterated function systems

In order to model flow and transport in fractured rocks it is important to know the geometry of the fracture network. A stochastic approach is commonly used to generate a synthetic fracture network from the statistics measured at a natural fracture network. The approach presented herein is able to incorporate the structures found in a natural fracture network into the synthetic fracture network. These synthetic fracture networks are the images generated by Iterated Function Systems (IFS) as introduced by Barnsley (1988). The conditions these IFS have to fulfil to determine images resembling fracture networks and the effects of their parameters on the images are discussed. It is possible to define the parameters of the IFS in order to generate some properties of a fracture network. The image of an IFS consists of many single points and has to be suitably processed for further use.     

IGGOS as a potential partner in IGOS

This short note reviews our thinking on how IGGOS can best achieve a high status within the set of global monitoring programmes. If such a high status can be obtained, then the importance of geodetic networks and services will be recognized more widely, and their activities will consequently be better resourced in the long term. One particular aspect concerns how IGGOS can complement the roles of the various IGOS partners within global monitoring. The different ways in which IGGOS can contribute to IGOS are outlined.     

Assessing the Comparability of Ammonium,Nitrate and Sulfate Concentrations Measured by Three Air Quality Monitoring Networks

Airborne fine particulate matter across the United States is monitored by different networks, the three prevalent ones presently being the Clean Air Status and Trend Network (CASTNet), the Interagency Monitoring of PROtected Visual Environment Network (IMPROVE) and the Speciation and Trend Network (STN). If combined, these three networks provide speciated fine particulate data at several hundred locations throughout the United States. Yet, differences in sampling protocols and samples handling may not allow their joint use. With these concerns in mind, the objective of this study is to assess the spatial and temporal comparability of the sulfate, nitrate and ammonium concentrations reported by each of these networks. One of the major differences between networks is the sampling frequency they adopted. While CASTNet measures pollution levels on seven-day integrated samples, STN and IMPROVE data pertain to 24-hour samples collected every three days. STN and IMPROVE data therefore exhibit considerably more short-term variability than their CASTNet counterpart. We show that, despite their apparent incongruity, averaging the data with a window size of four to six weeks is sufficient to remove the effects of differences in sampling frequency and duration and allow meaningful comparison of the signals reported by the three networks of concern. After averaging, all the sulfate and, to a lesser degree, ammonium concentrations reported are fairly similar. Nitrate concentrations, on the other hand, are still divergent. We speculate that this divergence originates from the different types of filters used to collect particulate nitrate. Finally, using a rotated principal component technique (RPCA), we determined the number and the geographical organization of the significant temporal modes of variation (clusters) detected by each network for the three pollutants of interest. For sulfate and ammonium, the clusters’ geographical boundaries established for each network and the modes of variations within each cluster seem to correspond. RPCA erformed on nitrate concentrations revealed that, for the CASTNet and IMPROVE networks, the modes of variation do not correspond to unified geographical regions but are found more sporadically. For STN, the clustered areas are unified and easily delineable. We conclude that the possibility of jointly using the data collected by CASTNet, IMPROVE and STN has to be weighed pollutant by pollutant. While sulfate and ammonium data show some potential for joint use, at this point, combining the nitrate data from these monitoring networks may not be a judicious choice.     

全球生产网络与本土创新网络的战略耦合动态——以中国生物医药产业为例

构建显示性比较优势指数,分析"走出去"全球化下中国医药产业的国际竞争力;识别企业战略连接类型,分析"引进来"全球化下生物医药全球生产网络(GPN)与本土创新网络(IIN)间的战略耦合过程;运用超效率SBM模型,测度GPN-IIN战略耦合目标实现的达成效率,并从静、动态视角探究其时空变化的原因。发现:(1)中国医药产业通过转口、代加工进入北美市场的难度加大,东盟、金砖国家成为其重要的出口对象,与欧盟加强贸易有助于其形成高标准的自由贸易协定网络。(2) 2000—2006年,多数外商直接投资(FDI)企业形成"两头在外"的产业布局,在GPN中处于被俘虏地位,大多内资企业学习能力不足,处于IIN边缘。2007—2013年,部分FDI企业由GPN价值链末端向高端转移,部分内资企业由IIN边缘向核心转移,但转移过程中具有强松脚性。2014—2019年,GPN-IIN战略耦合克服上一阶段嵌入不足、松脚性等问题,两者间的关系通道日益增多和稳固。(3) GPN-IIN耦合绩效经历了"大分散、小集聚→简单结构孕育→局部结构构建→级联秩序分异"的演变,在此过程中技术进步对其促进效果最强,规模效率次之,纯技...