为识别及评估水利水电工程的社会稳定风险，建立了风险评估的模糊灰关联故障树模型，模型用三角模糊数来表示基本事件的模糊概率；计算顶上时间模糊概率和基本事件的模糊重要度；以基本事件模糊重要度作为参考列，以最小割集组成的特征矩阵作为比较列，通过计算关联系数进而求出最小割集所代表的故障模式与顶上事件之间的灰色关联度。以QP水库进行了实例计算，表明移民安置问题是该水库建设的主要风险因子，符合水库建设实际。该模型适用于处理复杂系统问题，可为水利水电工程的社会风险评估，及建立科学的预警机制提供参考。

In order to identify and evaluate the social stability risk of water conservancy and hydropower projects， a fuzzy grey correlation fault tree model for risk assessment is established. The model uses triangular fuzzy number to represent the fuzzy probability of the basic event； calculates the fuzzy probability of the top event and the fuzzy importance of the basic event； takes the fuzzy importance of the basic event as the reference column， takes the characteristic matrix composed of the minimum cut set as the comparison column， and calculates the grey correlation between the fault mode represented by the minimum cut set and the top event by calculating the correlation coefficient. A case study of Qianping reservoir shows that resettlement is the main risk factor of the reservoir construction， which is in line with the reality of reservoir construction. The model is suitable for dealing with complex system problems， and can provide reference for the social risk assessment of water conservancy and hydropower projects and the establishment of scientific early warning mechanism.

采用克里金插值法分析2014年江苏省PM_2.5浓度空间分布特征,运用灰色关联模型计算PM_2.5浓度与影响因素间关联度,分析主要影响指标因子与PM_2.5浓度空间分布的相互关系。结果显示：① 江苏省PM_2.5浓度具有沿海低、内陆高,南部高、北部低的空间分布特征;② PM_2.5污染来源指标层的权重值最大（w_i = 0.4691）,空气质量与气象要素指标层的权重稍大（w_i = 0.2866）,城市化与产业结构层的权重值最小（w_i = 0.2453）;③ 在27个指标因子中,与PM_2.5浓度关联度为中度的仅有公路客运量、房屋建筑施工面积、园林绿地面积、人口密度等4个指标因子,PM_2.5与其余指标因子均呈强度相关联,其中与PM₁₀、O₃、降雨量、公路货运总量、地区工业总产值和第二产业占地区生产总值比重等指标的关联度较高;④ PM_2.5污染源指标层与PM_2.5浓度关联度值较大的城市分别是南京、无锡、常州、南通、泰州市;城市化与产业结构指标层与PM_2.5浓度关联度值较大的城市分别是徐州、苏州、盐城、常州市;空气质量与气象要素指标层与PM_2.5浓度关联度值较大的城市分别是盐城、扬州、常州、南通市。综合分析可知,影响指标因子关联度值与PM_2.5浓度空间分布有较好相关性。研究表明,灰色关联模型可有效分析影响PM_2.5浓度的主要因素,能对PM_2.5浓度影响指标进行定量分析与评价。

In this paper, the Kriging interpolation method was introduced to analyze the spatial distribution characteristics of PM_2.5 in Jiangsu province in 2014, and then the evaluation index system for the PM_2.5 was constructed, which consists of three index layers and 27 indexes. The grey correlation analysis method was used to explore the correlation between PM_2.5 and its influencing factors. Finally, the relationship between the spatial distribution of PM_2.5 and the main influencing factors was analyzed. The conclusions can be drawn as follows: (1) The PM_2.5 in the coastal areas and the north is lower, while it is higher in the inland areas and the south. (2) The weight of PM_2.5 pollution sources index layer is the largest (w_i = 0.4691), the weight of the air quality index and meteorological elements layer is larger (w_i = 0.2866), and the weight value of urbanization and industrial structure index layer is the minimum (w_i = 0.2453). (3) In the 27 indexes, the volume of highway freight, housing construction area, garden green space area and population density have moderate correlation degrees. The other indexes have strong correlation degrees, among which, the correlation degree of the PM₁₀, O₃, total road freight volume and gross industrial output value are relatively high. (4) The synthetic correlation degree values between the PM_2.5 pollution sources index layer and PM_2.5 are much higher in cities of Nanjing, Wuxi, Changzhou, Nantong and Taizhou. The synthetic correlation degree values between urbanization and industrial structure index layer and PM_2.5 are much higher in cities of Xuzhou, Suzhou, Yancheng and Changzhou. The synthetic correlation degree values between the air quality index and meteorological elements layer and PM_2.5 are much higher in cities of Yancheng, Yangzhou, Changzhou and Nantong. Our results demonstrate that the grey correlation degrees of the evaluation indexes system are closely related with spatial distribution of PM_2.5 in Jiangsu province. Therefore, the grey correlation analysis model can be employed to analyze and evaluate the spatial distribution of PM_2.5.

碳强度影响因子数量众多,通过在众多因子中评估其重要性以识别出关键影响因子进而解析碳强度关键因子的变化规律,是中国2030年碳强度能否实现比2005年下降60%~65%目标的科学基础。传统的回归分析方法对于评估众多因子的重要性存在多重共线性等问题,而机器学习处理海量数据则具有较好的稳健性等优点。本文从能源结构、产业结构、技术进步和居民消费等方面选取了56个中国碳强度影响因子指标,采用随机森林算法基于信息熵评估了1980-2014年逐年各项因子的重要性,通过指标数量与信息熵的对应关系统一筛选出每年重要性最大的前22个指标作为相应年度关键影响因子,最终依据关键影响因子的变化趋势划分了3个阶段作了演进分析。结果发现：1980-1991年,碳强度的关键因子主要以高耗能产业规模及占比、化石能源占比和技术进步为主;1992-2007年,中国经济进入快车道增长时期,服务业占比和化石能源价格对碳强度的影响作用开始显现,居民传统消费的影响作用在增大;2008年全球金融危机后,中国进入经济结构深化调整时期,节能减排力度大大增强,新能源占比和居民新兴消费的影响作用迅速显现。为实现2030年碳强度下降60%~65%目标,优化能源结构和产业结构,促进技术进步,提倡绿色消费,强化政策调控是未来需要采取的主要措施。

As the Chinese government ratified the Paris Climate Agreement in 2016, the goal of reducing carbon dioxide emissions per unit of gross domestic product (carbon intensity) from 60% to 65% of 2005 levels must now be achieved by 2030. However, as numerous factors influence Chinese carbon intensity, it is key to assess their relative importance in order to determine which are most important. As traditional methods are inadequate for identifying key factors from a range acting simultaneously, machine learning is applied in this research. The random forest (RF) algorithm based on decision tree theory was proposed by Breiman (2001); this algorithm is one of the most appropriate because it is insensitive to multicollinearity, robust to missing and unbalanced data, and provides reasonable predictive results. We therefore identified the key factors influencing Chinese carbon intensity using the RF algorithm and analyzed their evolution between 1980 and 2014. The results of this analysis reveal that dominant factors include the scale and proportion of energy-intensive industries as well as fossil energy proportion and technical progress between 1980 and 1991. As the Chinese economy developed rapidly between 1992 and 2007, effects on carbon intensity were enhanced by service industry proportion and the fossil fuel price such that the influence of traditional residential consumption also increased. The Chinese economy then entered a period of deep structural adjustment subsequent to the 2008 global financial crisis; energy-saving emission reductions were greatly enhanced over this period and effects on carbon intensity were also rapidly boosted by the increasing availability of new energy and its residential consumption. Optimization of energy and industrial structures, promotion of technical progress, green consumption, and the reduction and management of emissions will be key to cutting future carbon intensity levels within China. These approaches will all help to achieve the 2030 goal of reducing carbon emission intensity from 60% to 65% of 2005 levels.