Data-based modelling approach for variable density flow and solute transport simulation in a coastal aquifer

Data-based models, namely artificial neural network (ANN), support vector machine (SVM), genetic programming (GP) and extreme learning machine (ELM), were developed to approximate three-dimensional, density-dependent flow and transport processes in a coastal aquifer. A simulation model, SEAWAT, was used to generate data required for the training and testing of the data-based models. Statistical analysis of the simulation results obtained by the four models show that the data-based models could simulate the complex salt water intrusion process successfully. The selected models were also compared based on their computational ability, and the results show that the ELM is the fastest technique, taking just 0.5 s to simulate the dataset; however, the SVM is the most accurate, with a Nash-Sutcliffe efficiency (NSE) ≥ 0.95 and correlation coefficient R ≥ 0.92 for all the wells. The root mean square error (RMSE) for the SVM is also significantly less, ranging from 12.28 to 77.61 mg/L.     

"干中学"与产业集群核心能力的形成

本文构建了产业集群核心能力的分析框架,从理论上说明学习效应是产业集群发展的内生动力,产业集群的学习是一个“干中学”的过程.     

基于深度学习和时空特征融合的海洋渔船密度预测方法

为了从海量渔船轨迹数据中挖掘隐含的信息和知识,进而为渔业行政主管部门的决策提供科学依据,本研究以AIS渔船轨迹数据为研究对象,提出了一种基于深度学习和面向时空特征融合的海洋渔船密度预测方法：首先,利用渔船轨迹数据集对渔船行驶区域进行网格划分;其次,筛选出渔船高密度区域进行研究,避免数据稀疏性问题;再次,根据渔船轨迹数据的时空分析,构建三维时空融合矩阵;最后,通过卷积循环神经网络模型捕获渔船分布的时间和空间特征,并利用卷积神经网络的堆叠加强对空间特征的学习。实验通过东海海域渔船真实轨迹数据进行具体测试,结果表明渔船密度预测值与真实值非常接近,平均绝对误差为4×10-4,模型较好地拟合了渔船密度分布特征,有效地提高了渔船捕捞热点预测的准确性和鲁棒性。     

基于BP神经网络与数学形态学的彩色地质图面要素信息智能提取

地质图是一个区域地质研究的重要成果,也是前人留下的宝贵资料,更融合了地质专家的丰富知识。本研究的目的是通过新的思路将彩色地质图信息提取出来,使其结果能直接进行数据分析,并用于决策和分析。以机器学习为指导,在分析半结构化（栅格）地质图特征的基础上,根据图例信息,提出一种彩色地质图信息提取新思路,对彩色地质图进行分层信息提取,并结合数学形态学和多层前向反馈式神经网络,探索半结构化数据转换为结构数据的有效技术方法。利用图像信息提取技术将半结构化地质图转化为结构化数据,可用于成矿预测等研究。这一变化将改变传统地质数据的结构,地质研究的信息基础和来源将会增加,对于获取更多的数据源和信息源,进一步开展地质分析研究具有重要意义。     

The Challenges and Rewards of Introducing Field Trips Into a Large Introductory Geography Class

Fieldwork is an essential component of undergraduate geographic education, but with growing enrollment and limited resources few first-year instructors incorporate this activity in their courses. This article reports on the challenges of incorporating fieldwork into a large first-year course and the strategies adopted to respond to these challenges and the achieved learning benefits. Field trips were created to cater to approximately 120 students directly engaged in field activities, with each student submitting an individual written report. Through the field activities, students developed a better understanding of geography, a stronger class community, and a more positive relationship with instructional staff.     

Popular Culture,Geopolitics, and Identity

Abstract

This study aims to theoretically investigate the notion of critical thinking for a more just understanding of self and “others” in global geographical learning. It focuses on the kinds of injustice in the world which are driven by our relationships with “others.” By drawing on the literature of critical education, philosophy of education, and geography education, this study reveals how universal notions of criticality tend to easily undermine those perceived as global others and may highlight, in deficit mode, their perceived differences. Instead, the study presents the imperative of deconstructive thinking for a more just world. The article concludes by proposing a teaching strategy for alternative criticality which strives for justice in school geography.     

“一带一路”建设背景下重庆与东盟国家贸易格局演变和影响因素分析

“贸易畅通”是“一带一路”建设的重要内容,重庆作为中国西部地区内陆开放高地,贸易发展优势明显。运用贸易强度指数和HM指数,分析2001—2017年重庆与东盟国家贸易格局和贸易依赖程度,并分析影响重庆与东盟国家贸易格局的影响因素。结果表明：①重庆与东盟国家贸易联系紧密,增长速度快,贸易总额在“一带一路”沿线六大区域中始终保持领先地位;②马来西亚和泰国成为重庆与东盟国家中最重要的贸易伙伴,越南、新加坡、菲律宾和印度尼西亚紧随其后,而与缅甸、柬埔寨、老挝和文莱的贸易总额较少;③在进口方面,形成以马来西亚、泰国和越南为首的多元进口格局,泰国和越南进口伙伴地位上升。在出口方面,形成以马来西亚为首的多元出口新格局,越南出口地位下降;④在市场相互依赖程度方面,重庆出口对东盟国家特别是马来西亚和新加坡贸易市场的重要性程度上升,而对东盟国家市场依赖程度较小;⑤产业结构、贸易通道、文化交流和政策等是影响重庆与东盟国家贸易格局的重要影响因素。     

基于深度学习的区域生态安全时空模拟与预测

区域作为人类、自然、社会共同作用和互相影响的复杂系统,对区域进行生态量化建模与模拟仿真,是实现区域可持续发展战略的关键。传统机器学习方法对区域生态系统建模取得了一定的成果,但难以确定学习特征和实现时空模拟。深度学习不需事先确定训练特征,具有优异的特征学习能力,能够提高模型预测精度,因此利用深度学习进行建模具有显著优势。本文使用植被净初级生产力（NPP）、气溶胶光学厚度（AOD）和人口格网数据,充分利用深度学习的优点,采用最优深度神经网络时空模拟,得到了河南省2007-2014年3 km分辨率的生态赤字空间分布图和河南省2015-2020年的生态赤字时间预测结果并进行分析,为区域生态的科学管理和建设供科学依据和参考。     

多重水力断裂的分形扩张

应用复杂性理论对于赣南脉钨矿床的著名“五层楼”式形态垂直分带进行研究 ,获得如下结果。 (1 )赣南脉钨矿床的“五层楼”式形态垂直分带是“多重水力断裂分形扩张”的结果。脉钨矿床的控矿多重断裂是一种以水力断裂为主导的热致与流体驱动断裂构造。脉钨矿床的自组织临界性是多重分形扩张之源 ,而中观破裂尖端周围流体静力学应力场梯度最大区则是分形扩张的驱动力。多重水力断裂的发生和发展是一种分形扩张过程 ,其演化服从串级“崩塌间断平衡”的时空分形生长动力学 ,与地震的Omori余震律相类似。 (2 )脉钨矿床“三环一帽”式的成矿地球化学分带是一种多组分成矿溶液的渗滤、溶解沉淀波结构 ,是成矿反应扩散系统中化学波的时空同步化传播而形成的目标斑图 ,是近平衡地质介质内 ,通过外界的“短暂局部激发”、继之以构造、岩浆和成矿脉动作用等“局部中断”而形成的径向对称、嵌套球状、远离平衡的局域化耗散结构 ,即脉动型自孤子。 (3)赣南脉钨矿床是近平衡区域地质背景中远离平衡的局域化耗散结构。赣南钨矿集区是复合自孤子的群集体。它们是在构造、岩浆多期次脉动条件下 ,来自①矿源层部分熔融的“区域提纯”、②岩浆期后成矿热液输运反应和③含钨地层、岩石淋滤交代的成矿物质 ,通过岩浆和热液孤     

Wireless Mapping,GIS, and Learning about the Digital Divide: A Classroom Experience

Abstract

The purpose of this article is to describe a capstone course in undergraduate student geographical research in which GIS and other geospatial tools were used to teach undergraduate students basic geographical principles. The course uses the “cooperative learning” pedagogical approach to address one of a number of client-supplied research projects, chosen on the basis of logistical difficulty, time, student ability, and project importance. In the connection of primary data with existing data, students confronted a number of important research issues such as mapping ethics, database design and management, time management, group dynamics, and research limitations.