深度学习方法在作物遥感分类中的应用和挑战

[目的]准确估算作物的面积和分布对粮食安全至关重要。与传统的机器学习方法相比,深度学习具有多种优势,如端到端训练、可迁移性。为有效利用高时空数据进行作物识别提供了新的机遇。已有多种模型被应用于作物分类任务中,针对不同的分类任务,如何有效地选择模型,并对其进行训练和使用已成为关键问题。[方法]文章回顾了利用深度学习模型对作物分类的主要研究。N维卷积神经网络(N-D CNN)(N=1、2、3)和递归神经网络(RNN)已被有效用于作物分类任务。长短期记忆RNN(LSTM RNN)和门控循环单元RNN(GRU RNN)是RNN的变体,解决了随着时间序列增加RNN出现的梯度消失或爆炸问题。此外,还有研究使用CNN和RNN(我们称为RCNN)的混合模型对作物进行分类。该文首先阐述了使用深度学习方法进行作物制图的背景和意义,并介绍了CNN和RNN模型结构。然后回顾了一些典型的研究,包括模型的结构、遥感数据源、数据处理方法和分类精度。最后,总结了使用深度学习方法进行作物分类的挑战以及现有解决方案的局限性。[结果](1)1-D CNN可用于提取时间特征,或时间+光谱特征,分类效果良好;2-D CNN已被广泛应用于单时相数据的空间特征提取,分类精度依赖于数据源;3-D CNN应用较少,但具有很大的潜力,尤其是时间+空间维度的特征提取;(2)相同条件下(架构、数据源、研究区域、类别),LSTM RNN和GRU RNN分类效果通常高于普通RNN,而前两者的效果差距不大,但GRU RNN训练时间较短;(3)CNN+RNN混合模型(RCNN)用RNN比3-D CNN更适合提取时间特征。这主要是由于RNN建立了对序列数据的长期依赖,而3-D CNN卷积核是局部计算的。[结论]通过分析,认为深度学习技术是作物遥感分类的有效工具。此外,与其他模型相比,RCNN,3-D CNN和GUR RNN具有更大的潜力。     

川西北高原藏区农村贫困化分异机制探测

[目的]客观揭示农村贫困化地域分异机制,为科学推进川西北高原藏区精准扶贫创新途径、综合战略和认真贯彻落实中央治藏方略提供参考依据。[方法]应用地理探测器模型、GIS空间分析与地统计方法等方法,探测川西北高原藏区贫困村单位面积GDP分异的主导因素,揭示农村贫困化分异机制,提出不同贫困化地域类型的扶贫政策措施。[结果]影响川西北高原藏区农村贫困化分异的主导因素包括到主要交通道路距离、归一化植被指数(NDVI)、土地利用、年均温度和海拔高程等,各因素对贫困村经济发展分异的解释力分别为80. 76%、12. 82%、8. 82%、5. 45%和3. 96%;贫困村经济发展贫困化的分异机制存在明显差异,可归纳为交通区位约束型、自然环境约束型和经济区位约束型等三大类型;农村贫困化驱动机制下的贫困村精准扶贫政策措施亟需因地制宜、科学推进、讲求实效,有序推进精准扶贫战略。[结论]精准扶贫应分类指导、重点突破,尤其加强贫困村交通、水利、公共基础设施建设和特色农牧业产业培植,注重多种扶贫模式的综合集成。     

航班计划优化研究概述

从航班计划优化的不同时间阶段分析,可以将航班计划优化分为航班计划静态编排优化、基于航班延误预测的航班计划动态反馈优化和基于机场协同决策(A-CDM)的航班计划动态调整角度三类;进而从航班时刻、机型指派、航班频率等编制环节分析了航班计划静态编排优化;随后利用延误波及预测与数据挖掘预测的优化方法分析了基于航班延误预测的航班计划动态反馈优化的相关研究。最后,根据航班计划优化复杂性分析,给出了航班计划优化的发展趋势和未来研究方向。     

Challenges and Changes in Gendered Poverty: The Feminization,De-Feminization,and Re-Feminization of Poverty in Latin America

Despite reductions in poverty generally, recent trends in Latin American countries show processes of both de-feminization and re-feminization of poverty. A rise in the numbers of women to men living in income-poor households has occurred despite feminized anti-poverty programs, most notably conditional cash transfers (CCTs), which target resources to women. This paper shows that methodological differences in what, how, and who is the focus of measurement may influence patterns of poverty “feminization.” It also suggests that feminized policy interventions might in themselves be playing a role in the re-feminization of poverty, not least because of data and definitional limitations in the way female-headed households and, relatedly, women’s poverty are understood. The somewhat paradoxical interactions between the feminization of household headship, the feminization of poverty, and the feminization of anti-poverty programs present interesting challenges for redressing gender gaps in poverty within the 2030 Agenda for Sustainable Development.     

乌蒙山片区绿色减贫指数分析

[目的]通过分析2012年和2014年乌蒙山片区绿色减贫指数,评价该地区不同年份扶贫效果,这也为今后各项扶贫政策的实施提供理论参考。[方法]文章依据中国绿色减贫指数指标体系,从经济增长绿化度、资源利用与环境保护程度、社会发展能力和扶贫开发与减贫效果4个方面,以人均地区生产总值、单位地区生产总值能耗等27个因子作为评价指标,利用线性加权综合法分析2012年和2014年经济增长绿化度、资源利用与环境保护程度、社会发展能力和扶贫开发与减贫效果指标值,最终确定绿色减贫指数。同时,分析片区内各贫困县波动较大的第三产业增加值比重、单位耕地面积化肥施用量、城乡收入比和农村人均纯收入增长率等指标。[结果]2014年相比2012年,乌蒙山片区经济增长绿化度、资源利用与环境保护程度和扶贫开发与减贫效果指标值上升,社会发展能力指标值降低,绿色减贫指数提高了15.40%。各县第三产业比重均降低,但农村人均纯收入都有提高。四川省10个县单位耕地面积化肥施用量增加。四川省除叙永县和美姑县,贵州省除赤水市,片区内的各贫困县城乡收入比降低。[结论]2014年,乌蒙山区在落实国家扶贫规划上取得了较好的成效。但各县之间差距较大,在今后的扶贫攻坚中,需要从不同地区的实际情况出发,了解贫困类型和贫困程度,考察当地资源储备和环境现状,统筹区域发展。     

FDI and Welfare Dynamics in Africa

This article examines the welfare impact of foreign direct investment (FDI) in a panel of 20 African countries over the period 2000–2013. We explore the multifactor and nonmonetary measures of welfare and the nonlinear effect of FDI on welfare. We used the Driscoll and Kraay standard errors and augmented mean group (AMG) estimator by Eberhardt and Teal (2010) to account for cross‐sectional dependency, endogeneity, and heterogeneity within panel units. The results indicate that although FDI is welfare enhancing, the nonlinear terms report mixed findings. When a multifactor indicator is employed, the increase in the nonlinear term is lower than the linear part. However, there is strong evidence that FDI is ultimately welfare enhancing when a nonmonetary indicator is employed. From an international business perspective, the findings have unlocked the welfare effects of international business on African host economies. International businesses through FDI can enhance welfare in Africa countries. However, the optimal efficacy of FDI‐welfare impact differs across the various dimensions of welfare. © 2017 Wiley Periodicals, Inc.     

New development: China renews reform of central–local fiscal relations and provides for basic national public services

China’s reform on central–local fiscal reform has slowed down in recent years. The appointment of a new finance minister experienced in local government affairs is expected to renew the reform affirmed by the Chinese Communist Party (CCP) congress in late 2017. China has unprecedentedly identified a comprehensive list of 81 national basic public services as entitlements. Eighteen of them are subject to national and local standards, and co-financed by central and local governments. A new cost-sharing method for 10 of these services classifies sub-national jurisdictions into five tiers, in which the central government’s share declines from 80% to 10%. These measures, effective in 2019, aim at creating a ‘harmonious and moderately prosperous society’.     

Simplified Jackknife Variance Estimates for Fuzzy Measures of Multidimensional Poverty

In this paper, we present a practical methodology for variance estimation for multi‐dimensional measures of poverty and deprivation of households and individuals, derived from sample surveys with complex designs and fairly large sample sizes. The measures considered are based on fuzzy representation of individuals' propensity to deprivation in monetary and diverse non‐monetary dimensions. We believe this to be the first original contribution for estimating standard errors for such fuzzy poverty measures. The second objective is to describe and numerically illustrate computational procedures and difficulties in producing reliable and robust estimates of sampling error for such complex statistics. We attempt to identify some of these problems and provide solutions in the context of actual situations. A detailed application based on European Union Statistics on Income and Living Conditions data for 19 NUTS2 regions in Spain is provided.     

The development trinity: How regional integration impacts growth,inequality and poverty

Developing countries today have become more active participants in regional trade agreements. This raises questions about how the benefits of integration are distributed, and the extent to which lower‐income countries are able to capture development gains. Historically, such impacts have been difficult to identify with precision. This paper seeks to address this gap by empirically analysing the impact of regional integration on development, particularly the effects on growth and welfare. Using both bilateral and regional integration measures, we show that the ability to capture gains from integration varies across developing country regional groups, with developing Asia benefiting on par with developed countries. The findings in the paper indicate that trade and trade policy play an important role in reducing inequality and poverty in developing countries. It also shows that regionalism can function as a channel to make multilateralism a more adept way of addressing national challenges.     

基于遥测信号的测距技术及其发展趋势

基于遥测信号的测距技术可以有效解决深空测距下行链路同时传输遥测、测距信号时出现的遥测数据传输速率受限、频谱带宽增加等问题，应用前景广阔。介绍了基于遥测信号的测距技术发展历程，重点总结了其中的关键技术，包括上行测距码的选择、遥测帧的设计和传输、PN码相位估计算法，最后探讨了其发展趋势。基于遥测信号的测距技术适应未来深空测距的发展需求，是深空测距的重要发展方向之一。