交互式洪水预报系统及其在淮河流域中的应用

随着计算机技术的发展,图形用户界面在联机洪水作业预报中的应用越来越广泛,为实现专家交互式洪水预报提供了可能。本文简要描述了在美国天气局河流预报系统和交互式预报程序基础上建立起来的交互式洪水预报系统,介绍了淮河流域洪水的专家交互预报模式,指出了现有系统中存在的不足及其发展方向。     

一种交互式多目标决策方法及其应用

针对水资源系统优化规划的特点,提出了一种交互式多目标决策方法,给出了该方法的理论依据。实例表明,该方法能求解广义的多目标决策模型,提供给决策者的交互信息较丰富,求解简便,能高效地寻求非劣的满意解。     

The prospects of an adjustment policy based on collective learning in old industrial regions

This paper aims to discuss the possibilities of adopting a policy based on collective learning in old industrial regions. This is particularly interesting because old industrial regions are believed to have lost their learning capabilities, as indicated by notions of `technological' and `institutional' lock-in. Moreover, the success stories where positive effects of interactive learning have been observed (Silicon Valley, Baden-Württemberg) all share the lack of an industrial past.First, we specify how a theoretical framework based on interactive learning, which tries to explain the industrial decline of old agglomerations, may look like, and how such an approach differs from other approaches. Then, we set out a policy framework that aims to deal with the process of structural adjustment and which incorporates the ideas of interactive learning based on socio-cultural factors. In this respect, we distinguish between two possible routes of adjustment, which reveal a complex interplay between different types of agglomeration economies, innovations and restructuring processes. Finally, we devote attention to the problems such a policy based on the notion of the learning region may face, such as the problem of how to overcome a negative lock-in situation caused by localized path dependency.     

Regional innovation strategies in the knowledge-based economy

This paper aims to examine major regional innovation strategies for regional development in the knowledge-based economy in Korea. Innovation policy and Regional Innovation Systems (RIS) are becoming important issues in Korea in both national and regional perspectives. These issues have been evolving since the mid 1990s, especially since the financial crisis of 1997 in Korea. Five major policy issues for promoting innovation and regional competitiveness are examined in this paper. The major policy issues are: promoting region-specific clustering; building habitats for innovation and entrepreneurship; collective learning processes and innovation networks; building a stock of social capital; and promoting local and global networks. Several strategies are suggested for each of these policy issues. These major policy issues and related strategies for regional innovation and competitiveness can be regarded as common issues required for the successful development of RIS. Taking these basic policy issues into account, each region can develop their own region-specific RIS, with appropriate consideration of distinctive regional characteristics such as the level of development, industrial specialization, local labor market, local business climate, local financial system, etc.     

长白山天池火山双岩浆房岩浆作用与互动式喷发

广义的长白山火山在我国境内包括天池火山、望天鹅火山、图们江火山和龙岗火山,是我国最大的第四纪火山岩分布区。长白山各个火山区的火山活动具有此起彼伏的穿时性特征,天池火山之下地壳和地幔两个岩浆房具有上下呼应、互动式喷发之特点。一方面来自地幔的钾质粗面玄武岩浆直接喷出地表,在天池火山锥体内外形成诸多小火山渣锥;另一方面钾质粗面玄武岩浆持续补给地壳岩浆房,发生岩浆分离结晶作用和混合作用,形成双峰式火山岩特征并触发千年大喷发。西太平洋板块俯冲-东北亚大陆弧后引张是长白山天池火山喷发的动力学机制。     

地质领域机器学习、深度学习及实现语言

地质大数据正在以指数形式增长。只有发展智能数据处理方法才有可能追上大数据的超常增长。机器学习是人工智能的核心,是使计算机具有智能的根本途径。机器学习已成为地质大数据研究的前沿热点,它将让地质大数据插上翅膀,并因此改变地质。机器学习是一个源于数据的模型的训练过程,最终给出一个面向某种性能度量的决策。深度学习是机器学习研究中的一个重要子类,它通过构建具有很多隐层的机器学习模型和海量的训练数据,来学习更有用的特征,从而最终提升分类或预测的准确性。卷积神经网络算法是最为常用的一种深度学习算法之一,它广泛用于图像识别和语音分析等。Python语言在科学领域的地位占据着越来越重要。其下的Scikit-Learn是一个机器学习相关的库,提供有数据预处理、分类、回归、聚类、预测、模型分析等算法。Keras是一个基于Theano/Tensorflow的深度学习库,可以应用来搭建简洁的人工神经网络。     

中国地质工作转型升级中的资金投入特征

通过对当前地质工作转型升级时期的资金投入分析,梳理了财政投入和社会资金的现状特征和问题,进而提出了对策建议。研究结果显示,中国的地质工作正处于转型升级期,在资金投入上主要表现出资金投下滑总体趋势放缓、矿产勘查资金供需矛盾突出、新旧动能转换引领投资分化、科技和信息化投入仍需提升、投入空间格局正发生转变五大特征。研究认为,为进一步优化资金投入以适应新的发展形势,应该以中长期战略引领投资布局,强化两级财政的协同配合,多措并举吸引社会资本注入,完善财政投入评估调整机制。     

基于岩石图像深度学习的岩性自动识别与分类方法

岩石岩性的识别与分类对于地质分析极为重要,采用机器学习的方法建立识别模型进行自动分类是一条新的途径。基于Inception-v3深度卷积神经网络模型,建立了岩石图像集分析的深度学习迁移模型,运用迁移学习方法实现了岩石岩性的自动识别与分类。采用此方法对所采集的173张花岗岩图像、152张千枚岩图像和246张角砾岩图像进行了学习和识别分类研究,通过训练学习建立岩石图像深度学习迁移模型,并分别采用训练集和测试集中的岩石图像对模型进行了检验分析。对于训练集中的岩石图像,每组岩石分别用3张图像测试,三种岩石的岩性分类均正确,且分类概率值均达到90%以上,显示了模型良好的鲁棒性;对于测试集中的岩石图像,每组岩石分别采用9张图像进行识别分析,三种岩石的岩性分类均正确,并且千枚岩组图像分类概率均高于90%,但是花岗岩组2张图像和角砾岩组的1张图像分类概率值不足70%,概率值较其他岩石图像低,推测其原因是训练集中相同模式的岩石图像较少,导致模型的泛化能力减小。为了提高识别精确度,对准确率较低的岩石图像进行截取,分别取其中的3张图像加入训练集进行再训练,增加与测试图像具有相同模式的训练样本;在新的模型中,对3张图像进行二次检验,测试概率值均达到85%以上,说明在数据足够的状况下模型具有良好的学习能力。与传统的机器学习方法相比,所提出的岩石图像深度学习方法具有以下优点:第一,模型通过搜索图像像素点提取物体特征,不需要手动提取待分类物体特征;第二,对于图像像素大小,成像距离及光照要求低;第三,采用适当的训练集可获得较好的识别分类效果,并具有良好鲁棒性和泛化能力。     

机器学习在地下水环境背景值与污染风险评价的应用和展望

地下水资源在世界各国水资源中占有举足轻重的地位,对人类生存发展、维系生态系统健康发挥着重要作用。现阶段地下水污染日益严重,地下水环境背景值研究和污染风险评价对地下水污染防治工作具有重要意义。由于地下水污染影响因素复杂,地下水化学组分空间分布的非均质性、地下水样品采集的小样本问题与大尺度区域的高计算代价,都对传统的污染风险评价方法构成了极大挑战。机器学习作为人工智能的核心,已成为水文地质领域研究的前沿热点,通过智能高效的数据处理和挖掘,在地下水化学组分的分布、变化以及赋存机制等方向已得到探索和尝试。本文全面介绍了近年来在地下水污染研究方面应用的机器学习方法,涵盖了以聚类为主的非监督学习算法,以回归为主的监督学习算法,以提升算法效率为目标的混合算法,以及以神经网络为核心的深度结构算法,展示了不同类型算法在地下水污染研究方面的成果,详细归纳了各种算法的机理,对算法的技术优劣及适用方向进行了探讨;最后对机器学习在地下水污染方面的应用发展趋势进行了展望,建议探索高效集成学习模型,以弥补单一算法的不足,同时发展面向小样本的深度学习建模技术,提高地下水污染评价精度,拓展和丰富新方法新技术在地下水污染研究方面的应用。     

Ecological modernisation and policy learning in Hong Kong

Whilst ecological modernisation theory emphasizes the potential for modern societies to recognize and respond to their environmental impacts by finding new ways of governing environment-economy relations, concepts of policy learning focus on the scope for new forms of environmental policy to be generated within and transferred between different contexts. Within this paper we explore the conceptual and practical linkages between the two areas of debate - a hitherto neglected area in the literature - and we set this discussion in the context of environmental policy-making in Hong Kong. We suggest that the practical relevance of the concepts of ecological modernisation and policy learning depends upon the presence of a reflexive society with rational, responsive institutions. While many theorists assume that such institutions exist, our analysis of policies for water and air quality management in Hong Kong highlights the need for theories to consider the embeddedness of existing institutions and the significance of the capacities for, and the barriers to, change more fully. We find that capacities for some forms of ecological modernisation and policy learning do exist in Hong Kong. However, we argue that the nature of these capacities often limits the potential for change to those local environmental problems that can be addressed through more technically and economically viable forms of policy intervention and that can be easily accommodated within existing political and economic structures. We also conclude that the capacities for ecological modernisation and policy learning that are needed if Hong Kong is to tackle the effects of the trans-boundary environmental problems that it is increasingly encountering have yet to emerge.     

Power and privilege in alternative civic practices: Examining imaginaries of change and embedded rationalities in community economies

Community economies can be considered as examples of the diverse economies growing outside common capitalist logics of private accumulation and profit, seeking to bypass or reconfigure dominant global trends of societal and economic organization. Yet, these communities seem to fit quite well under a neoliberal program in which responsibilities are shifting downwards, favoring multi-level governance over State intervention and accountability. This binary character makes imperative an open and critical discussion on the development of community initiatives, including on the motivations and visions of citizens practicing alternative ethical consumption. This article explores the neoliberal rationalities embraced by community members within the imaginaries of change they frame and examines how these rationalities contribute to (re)producing neoliberal conditions and forms of governance. Our analysis builds on semi-structured interviews conducted among the members of 11 initiatives in 5 EU countries and on participant observation. We argue here that communities articulate an “alternative imaginary” of change that appears imprinted by core neoliberal rationalities around questions of individual responsibility, the role of the State, and civic participation and equity. It is an imaginary related to the construction of CBEs to by-pass existing socio-political and economic configurations. This imaginary more often than not responds to neoliberal promises of individual freedom and autonomy and seems to undermine CBEs' more radical possibilities at the same time obscuring more diverse voices of transformation.     

Environmental learning and the social construction of an exurban landscape in Fremont County, Colorado

Across the rural American West, the restructuring of rural capitalism has transformed production landscapes into those increasingly structured by the development and consumption of natural and cultural amenities. This project used principles from symbolic interactionism, ethnographic methods, and the analytical framework of regional political ecology to understand the role of environmental learning in negotiating the new management regime associated with amenity-based capitalism in rural Fremont County, Colorado. The study found that most amenity residents participate regularly in social learning about the environment through a variety of interpersonal and organizational behaviors. In addition, they are responding collectively to environmental risks and opportunities associated with wildfire, noxious weeds and invasive grass species, prospective uranium mining, and restoration of cultural-landscape features. Ultimately, the practices of environmental learning concern how private properties and assets will be managed relative to the social construction of the environment as an amenity for personal consumption. Conservation and management prospects in this and other rural areas in the postindustrial world can be enhanced by understanding the microsociology of exurban geographies and by engaging the social forms and processes related to this distinctive landscape construction.     

贵州省水工环地质工作需求分析

本文简要介绍了当今世界地质工作的发展趋势,强调了资源与环境并重的环境型社会对水工环地质的更高要求。结合贵州省情和环境现状,从八个方面对我省水工环地质工作旺盛的需求进行分析,并提出了今后的工作建议。     

黑河流域下游自然资源与社会经济耦合协调响应机制研究——以阿拉善盟额济纳旗为例

为研究近40 a黑河流域下游自然资源经济系统耦合协调过程和规律,以黑河流域下游阿拉善盟额济纳旗为研究对象,根据《额济纳旗统计年鉴》(1990—2015年)自然资源和社会经济相关数据,建立指标体系,进行综合发展水平研究,通过耦合协调度模型对研究区自然资源和社会经济耦合协调度进行分析,并对2020—2030年两者的耦合协调度进行预测。结果表明: 额济纳旗自然资源综合发展水平从1990年的0.160 0提高到2015年的0.811 5,增长趋向明显; 社会经济综合发展水平从1990年的0.115 0提高到2015年的0.713 8,也呈不断上升的趋势; 二者的综合发展水平曲线变化整体相似。自然资源与社会经济耦合协调程度呈上升趋势,由1990年的“重度失调经济损益型”历经“拮抗”“发展”“磨合”阶段转变为2015年的“高度协调发展同步型”。通过灰色系统理论GM(1,1)模型,预测未来10 a两者耦合协调度将进一步提高。     

基于深度学习和高分遥感影像的青藏高原东部融冻泥流阶地提取研究

融冻泥流阶地是一种典型的斜坡冷生型冰缘地貌,在青藏高原东部发现大量古融冻泥流阶地,其空间分布对于重建该区古多年冻土分布和古气候环境具有重要意义。融冻泥流阶地纹理复杂、几何形态不一、表面覆盖多样化,导致融冻泥流阶地遥感解译和自动提取困难,然而,深度学习方法能获取上下文多尺度语义信息,提高特征表达的能力,为融冻泥流阶地的大范围提取提供了重要手段。因此,本文提出了一种基于DeepLab V3+深度学习模型和高分辨率光学遥感影像的融冻泥流阶地自动提取方法,并在四川甘孜州新都桥周边地区开展了实验研究。结果表明：与人工解译结果对比,本方法提取结果的综合精度达到0.68以上,并经野外调查验证了其有效性;在该区共识别了9 203条融冻泥流阶地,主要分布在新都桥镇附近的山谷两侧;泥流阶地主要朝西北方向,坡度集中分布在20°~25°,海拔高程大部分位于3 650~3 750 m间,主要地表覆盖类型是草地。     

典型喀斯特城市水资源与社会经济发展耦合度评价——以贵阳市为例

运用系统科学和可持续发展理论,结合喀斯特发育典型的贵阳市区域特征,构建评价指标体系及水资源与社会经济发展耦合模型,运用模糊集对模型计算水资源系统和社会经济系统综合指数。结果表明:2002—2010年贵阳市水资源系统综合发展程度相对较低,与社会经济系统发展水平差距较大,水资源与社会经济发展耦合度分别为0.5、0.49、0.42、0.46、0.42、0.34、0.41、0.48,整体处于颉颃阶段。今后应对城市河段和部分工矿企业比较发达的区域实行高污染企业转移或疏散,降低高耗水、高污染排放产业比重,提高水资源利用效率;提高市民节水意识,推广节水型小区建设;加大对石漠化治理力度,提高植被覆盖率,提高生态蓄水能力;加大水利工程、集雨工程建设力度,提高客水资源利用率,调整国民经济布局,使之与水资源时空分布相匹配等,以提高水资源与社会经济发展的协调能力,促进整个贵阳市的可持续发展。      

Gully erosion spatial modelling: Role of machine learning algorithms in selection of the best controlling factors and modelling process

This investigation assessed the efficacy of 10 widely used machine learning algorithms (MLA) comprising the least absolute shrinkage and selection operator (LASSO), generalized linear model (GLM), stepwise generalized linear model (SGLM), elastic net (ENET), partial least square (PLS), ridge regression, support vector machine (SVM), classification and regression trees (CART), bagged CART, and random forest (RF) for gully erosion susceptibility mapping (GESM) in Iran. The location of 462 previously existing gully erosion sites were mapped through widespread field investigations, of which 70% (323) and 30% (139) of observations were arbitrarily divided for algorithm calibration and validation. Twelve controlling factors for gully erosion, namely, soil texture, annual mean rainfall, digital elevation model (DEM), drainage density, slope, lithology, topographic wetness index (TWI), distance from rivers, aspect, distance from roads, plan curvature, and profile curvature were ranked in terms of their importance using each MLA. The MLA were compared using a training dataset for gully erosion and statistical measures such as RMSE (root mean square error), MAE (mean absolute error), and R-squared. Based on the comparisons among MLA, the RF algorithm exhibited the minimum RMSE and MAE and the maximum value of R-squared, and was therefore selected as the best model. The variable importance evaluation using the RF model revealed that distance from rivers had the highest significance in influencing the occurrence of gully erosion whereas plan curvature had the least importance. According to the GESM generated using RF, most of the study area is predicted to have a low (53.72%) or moderate (29.65%) susceptibility to gully erosion, whereas only a small area is identified to have a high (12.56%) or very high (4.07%) susceptibility. The outcome generated by RF model is validated using the ROC (Receiver Operating Characteristics) curve approach, which returned an area under the curve (AUC) of 0.985, proving the excellent forecasting ability of the model. The GESM prepared using the RF algorithm can aid decision-makers in targeting remedial actions for minimizing the damage caused by gully erosion.     

粤港澳大湾区水资源现状及其与社会经济协同演化趋势——与国际湾区对比研究

粤港澳大湾区（以下简称大湾区）水资源现状及其演化规律关系到该区社会经济的高质量发展。本文对大湾区"9市+2区"近10年的社会经济与水资源现状及其协同演化规律进行分析研究。结果显示：目前大湾区供水主要依赖地表水，水资源的分布与区域经济发展不协调，作为区域发展核心引擎的香港、澳门、深圳（极度缺水）以及广州（重度缺水）人均水资源量过低。广州、佛山、中山、东莞（>80%）以及深圳（>40%）水资源开发利用程度高，水资源供需压力大。通过归因分析得到大湾区的水资源利用现状与社会经济的协同规律：产业结构影响用水结构以及水资源开发利用程度，控制用水效率。区域内产业结构与发展趋势，及其与世界湾区的对比分析验证了产业结构理论中的"配第-克拉克定理"。随着大湾区经济持续的发展与产业结构优化，大湾区用水效率将提高，人均用水量会逐步降低。同时城市公共用水、生活用水需求量将持续上升，需确保大湾区供水设施，供水量及供水安全满足未来社会经济发展需求。