Modelling the spatial distribution of red grouper (Epinephelus morio) at Campeche Bank, México, with respect substrate

The red grouper (Epinephelus morio) has historically been one of the most important fisheries of the Campeche Bank area in the Gulf of México, where two fleets from México and one from Cuba participate. Current stocks have been estimated to be a third or less as abundant as in the 1970s; hence, the fishery has been declared to be over-exploited. The federal government of México has expressed the need to investigate the potential use of protected areas as a management tool for recovery of this species. Based on artificial neural network (ANN) modelling, we analysed the spatial distribution of red grouper with respect substrate, considering the demographic structure of the stock. We found a significant relationship between the type of substrate and the three stages of development (juveniles, pre-adults and adults). Juveniles are distributed in shallow waters close to the coast on coral substrates; pre-adults are also associated with coral substrates, but at an intermediate depth; adults are found in deeper waters on sandy substrates. We also identified seasonal reproductive aggregation patterns, always in relation to substrate types. Reproductive aggregation during the winter and early spring in the north-eastern continental shelf and the almost permanent (exception in autumn) concentration of juveniles in coastal waters around the central and eastern coast of Yucatan are of particular importance for management. These patterns represent seasons and areas of high fish vulnerability, which is the basic criterion for further analysis of protected areas.     

ANN OUTPUT UPDATING OF LUMPED CONCEPTUAL RAINFALL/RUNOFF FORECASTING MODELS1

ABSTRACT: Artificial neural networks (ANNs) are tested for the output updating of one‐day‐ahead and three‐day‐ahead streamflow forecasts derived from three lumped conceptual rainfall/runoff (R‐R) models: the GR4J, the IHAC, and the TOPMO. ANN output updating proved superior to a parameter updating scheme and to the ‘simple’ output updating scheme, which always replicates the last observed forecast error. In fact, ANN output updating was able to compensate for large differences in the initial performance of the three tested lumped conceptual R‐R models, which the other tested updating approaches were not able to achieve. This is done mainly by incorporating input vectors usually exploited for ANN R‐R modeling such as previous rainfall and streamflow observations, in addition to the previous observed error. For one‐day‐ahead forecasts, the performance of all three lumped conceptual R‐R models, used in conjunction with ANN output updating, was equivalent to that of the ANN R‐R model. For three‐day‐ahead forecasts, the performance of the ANN‐output‐updated conceptual models was even superior to that of the ANN R‐R model, revealing that the conceptual models are probably performing some tasks that the ANN R‐R model cannot map. However, further testing is needed to substantiate the last statement.     

人工神经网络在沿海区域环境复杂系统预测中的应用

针对复杂系统的非线性特征，分析了应用人工神经网络技术实现可持续发展复杂系统预测的可能性，并以上海市和崇明县为例建立沿海区域预测模型，取得了较好的预测结果，为可持续发展复杂系统的预测研究探索了一种新的可能方法。     

地震作用下土‐深埋地下结构相互作用的高效时程分析方法∗

基于黏弹性边界和将场地地震反应转化为等效荷载的有限元直接法是目前进行地震作用下土-结构相互作用分析的常用时程分析方法之一。当结构埋深较深时,整个土-结构系统的有限元模型自由度数目较多,尤其对于三维问题,计算效率低。提出一种高效分析方法,即一维场地反应分析仍然针对整个深厚土层,在后续的土-结构相互作用分析中将土-结构计算模型的自由表面向下移动、底边界面向上移动到接近结构的位置,通过缩减土-结构相互作用模型尺寸来提高计算效率。采用理论分析与数值算例,通过与采用整个深厚土层的传统土-结构相互作用分析结果对比,说明提出的高效分析方法能够满足精度要求,并且针对不同结构尺寸、结构埋深和围岩等级给出上、下人工边界位置的建议。     

川中丘陵地区人工桤柏混交林演替过程中有机碳储量变化——以四川省盐亭县为例

川中丘陵地区从20世纪70年代起开始大规模营造人工桤柏混交林,使该区土地利用发生明显变化。在估算人工桤柏混交林不同生长阶段生物量和NPP（净初级生产力）的基础上,探讨了人工桤柏混交林生长过程中年固定有机碳数量以及林地植被有机碳密度的动态变化,并将同期人工桤柏混交林林地植被与农田植被年固定有机碳数量和有机碳密度进行比较。结果表明,该区人工桤柏混交林林地植被早期年固定有机碳的数量比较小,需要到7～8 a树龄,其年固定有机碳数量才与同期耕地植被年固定有机碳数量相当。随着树龄的增加,人工桤柏混交林的植被有机碳密度上升较快,碳汇效应不断增强。3～4 a以上树龄的人工桤柏混交林植被有机碳密度大于同期农田植被的有机碳密度,成熟林（20 a树龄）林地植被有机碳密度是同期农田植被有机碳密度的5倍多。从改善生态环境和减少碳排放的角度看,该区林地合理利用的措施主要包括加强现有人工桤柏混交林的保护和管理,抓好林木的贮存式管理,积极研究和探索人工桤柏混交林改造和合理利用对策等     

武汉城市圈产业发展的空间优化

武汉城市圈是指以武汉市为中心,包括黄石、鄂州、黄冈、孝感、咸宁、仙桃、潜江和天门等周边8市共同组成的城市密集区。该区域具有悠久的产业发展传统,其历史轨迹可分为3个阶段：第一阶段（1840~1949）为产业发展起步时期,第二阶段（1949~1994）为产业结构强化时期,第三阶段（1994~）为产业体系调整时期;与此相适应,区域产业的部门结构和空间结构均呈现典型的集中特征,以2003年区域制造业的增加值为指标,武汉市的空间集中度为50.5％,前10类制造业的产业集中度为60.6％。据此,目前的武汉城市圈是一个松散的“经济联邦”,但存在区域整合的产业、空间和创新基础。以2001~2004年武汉城市圈9城市的统计资料为基础,以制造业分行业的年均增加值和增长率为指标,计算和分析其区域产业发展潜力,结果表明：以钢铁、汽车和电子及通讯设备制造业等为依托,构建区域集群网络,能够充分发挥武汉市的产业组织和创新扩散功能。武汉城市圈应进一步调整产业发展思路,坚持创新驱动路径,通过完善集群网络规划、强化区域空间关联和引导产业集聚发展等政策措施,有效推动具有区域竞争优势的特色产业发展。     

A unique intelligent approach for forecasting project completion time in oil refineries

This study presents a hybrid approach for accurate forecasting of project completion time with noisy and uncertain safety factors in oil refineries. The hybrid approach is based on artificial neural network (ANN), fuzzy mathematical programming (FMP) and conventional regression. Three indictors, namely, number of occupational injuries, number of employees and ratio of maximum useful hours over useful hour per month are considered as inputs. Also, project completion time is considered as the main output. To achieve the objective of this study, five sets of data with respect to oil refinery construction projects in various cities of Iran are collected and analyzed through statistical methods. It is shown that for the actual case of this study, ANN presents lowest mean absolute percentage error (MAPE). Also, analysis of variance (ANOVA) is used to verify and validate the results of this study. This is the first study that presents a hybrid approach for accurate estimation and forecasting of project completion time with complex, noisy and uncertain occupational factors.     

Foreignness as a constraint on learning: The impact of migrants on disaster resilience in small islands

Knowledge about natural hazard management has increased significantly since Gilbert White's seminal research in 1945, yet people are still badly affected by natural hazards. A key question remains in natural hazards research: why, when all the conditions for effective disaster risk reduction are in place, do some people not take action to reduce their risk of harm? Through a questionnaire-based study we investigated the motivating factors that led residents of the Cayman Islands to prepare for annual tropical cyclones (hurricanes). Factors that increase the likelihood of individuals preparing for hurricanes are: previous experience of major storms, having linking networks and ties, having a child under the age of 15 in the home, and residency status—expatriate residents are less likely to prepare. Factors that appear to prevent adaptive behaviour include: living close to or adjacent to the coast, recent migration to the islands, and living in rented accommodation. The findings of the survey confirm that even within societies that are well prepared for tropical cyclones, there are still sub-groups who do not engage with the preparedness process. In the case of the Cayman Islands, new migrants are the most vulnerable to tropical cyclones as they tend to fall into the demographic groups least likely to prepare for cyclones, live in locations with high levels of exposure to cyclone impacts, and interact mostly with other expatriates with no previous experience of cyclone impacts. As climate change promises to bring an increasing intensity of tropical cyclones, these findings have relevance for all islands which draw on migrant workers to support economic growth.     

Optimum parameters for fault detection and diagnosis system of batch reaction using multiple neural networks

Batch process usually differs from the continuous process because of its time-varying variables and the process parameters. An early detection and isolation of faults in the process will help to reduce the process upsets and keep it safe and reliable. This paper discusses on the application of multi-layer perceptron neural network in detecting various faults in batch chemical reactor based on an esterification process that involves the reaction of ethanol and acetic acid catalyzed by sulfuric acid. A multi-layer feed forward neural network with double hidden layers has been used in the neural network architecture. The detection was based on the different patterns generated between normal and faulty conditions. An optimum network configuration was found when the network produced the minimal error with respect to the training, testing and data validation.     

地表变形预测分析--发电厂典型例子研究

通过对地表变形观测数据的分析、拟合及训练,采用人工神经网络方法和数理方法对地表变形的规律及发展趋势进行预测,并与观测数据进行对比分析,得到了较好的结果,为控制地表变形的发展及工程处理提供了可靠依据.