Short-term wind speed forecasting based on random forest model combining ensemble empirical mode decomposition and improved harmony search algorithm

ABSTRACT

Wind speed forecasting plays an important role in power grid dispatching management. This article proposes a short-term wind speed forecasting method based on random forest model combining ensemble empirical modal decomposition and improved harmony search algorithm. First, the initial wind speed data set is decomposed into several ensemble empirical mode functions by EEMD, then feature extraction of each sub-modal IMF is performed using fast Fourier transform to solve the cycle of each sub-modal IMF. Next, combining the high-performance parameter optimization ability of the improved harmony search algorithm, two optimal parameters of random forest model, number of decision trees, and number of split features are determined. Finally, the random forest model is used to forecast the processing results of each submodal IMF. The proposed model is applied to the simulation analysis of historical wind data of Chaoyang District, Liaoning Province from April 27, 2015 to May 22, 2015. To illustrate the suitability and superiority of the EEMD-RF-IHS model, three types of models are used for comparison: single models including ANN, SVM, RF; EMD combination models including EMD-ANN, EMD-SVM, EMD-RF; EEMD combination models including EEMD-ANN, EEMD-SVM, EEMD-RF. The analysis results of evaluation indicators show that the proposed model can effectively forecast short-term wind data with high stability and precision, providing a reference for forecasting application in other industry fields.     

Landscape consequences of aggregation rules for functional equivalence in compensatory mitigation programs

Mitigation and offset programs designed to compensate for ecosystem function losses due to development must balance losses from affected ecosystems with gains in restored ecosystems. Aggregation rules applied to ecosystem functions to assess site equivalence are based on implicit assumptions about the substitutability of functions among sites and can profoundly influence the distribution of restored ecosystem functions on the landscape. We investigated the consequences of rules applied to the aggregation of ecosystem functions for wetland offsets in the Beaverhill watershed in Alberta, Canada. We considered the fate of 3 ecosystem functions: hydrology, water purification, and biodiversity. We set up an affect‐and‐offset algorithm to simulate the effect of aggregation rules on ecosystem function for wetland offsets. Cobenefits and trade‐offs among functions and the constraints posed by the quantity and quality of restorable sites resulted in a redistribution of functions between affected and offset wetlands. Hydrology and water purification functions were positively correlated with one another and negatively correlated with biodiversity function. Weighted‐average rules did not replace functions in proportion to their weights. Rules prioritizing biodiversity function led to more monofunctional wetlands and landscapes. The minimum rule, for which the wetland score was equal to the worst performing function, promoted multifunctional wetlands and landscapes. The maximum rule, for which the wetland score was equal to the best performing function, promoted monofunctional wetlands and multifunctional landscapes. Because of implicit trade‐offs among ecosystem functions, no‐net‐loss objectives for multiple functions should be constructed within a landscape context. Based on our results, we suggest criteria for the design of aggregation rules for no net loss of ecosystem functions within a landscape context include the concepts of substitutability, cobenefits and trade‐offs, landscape constraints, heterogeneity, and the precautionary principle.     

大气中黑碳的健康效应及机制研究进展

虽然人类社会不断进步发展,但大量工业和自然排放也导致了严重的空气污染。大气颗粒物是大气污染物的主要成分之一,黑碳是其中的重要组成成分,被国际癌症研究机构(IARC)归类为2B类致癌物。黑碳可以吸附其他致癌物质,会对环境和人体健康产生不利影响,因此黑碳暴露对人类的危害得到越来越多的重视。空气中黑碳的水平与心血管、呼吸和神经系统疾病的发生都有关系;黑碳主要通过引起氧化应激和炎症反应,诱发基因突变等一系列损伤。虽然现今对于黑碳健康效应的研究已取得了一些进展,但研究多数处于起步阶段,且仅针对黑碳本身进行单独研究,未来还需要加强开展对黑碳和其他污染物联合毒性效应及机制的研究。本综述主要针对近年来已开展的研究进行了总结归纳。     

环境保护在学习实践科学发展观活动中的地位与作用——从环境哲学角度看学习实践科学发展观活动

环境保护是科学发展观的题中之意,科学发展观关于环境保护的论述,是党的环境保护理论的精髓。学习实践科学发展观活动,是一个哲学内涵非常丰富的课题,是十分难得的研究环境哲学的大好机遇。试点经验显示了环境保护在学习实践科学发展观活动中的重要作用。他们一方面在科学发展中通过转变发展方式,调整经济结构,解决环境难题;一方面坚持环境保护与经济发展并重,在保护环境中求发展,努力实现环境与经济“双赢”。其共性是,注重治本、注重生态、注重政策。深入学习实践科学发展观,关键在实践,要深入一线,深入调研,融人群众的实践,总结来自一线的新鲜经验。要适应新形势,了解新情况,解决新问题。在学习实践科学发展观活动中,不断提高落实科学发展观,在科学发展中,提高解决环境问题的能力,实现环境与发展、环境与经济的“双赢”。     

铅冶炼区土壤重金属总量和有效态含量的函数分析

采集铅冶炼企业周边3 000 m范围内220个表层土壤样品,测定了有毒有害元素铅、镉、砷和汞的总量和有效态含量,探讨了它们之间的关系。结果表明:研究区土壤受到汞、砷、铅、镉的污染依次明显严重,土壤重金属的总量和有效态含量的变异系数均大于100%,土壤镉、铅、汞、砷的生物有效性系数平均值分别为25.9%、17.2%、0.58%、0.11%。土壤铅、镉和砷的总量与其有效态含量呈显著正相关(P0.001),而汞的总量与其有效态含量的相关性不显著(P0.05)。土壤铅和镉的总量和有效态含量可以用直线函数和幂函数表达,函数反推的有效态值和对应统计值的变异系数不大于10%。     

常州市臭氧污染传输路径和潜在源区

利用NCEP全球再分析资料和HYSPLIT4模式,计算了2013—2015年常州市臭氧(O_3)超标日的气流后向轨迹。结合聚类分析方法和常州市PM2.5、PM10、SO2、NO2、O_3数据,分析了O_3超标日不同类型气团来源对各污染物浓度的影响,并利用引入权重因子后的潜在污染源贡献函数分析了影响常州市O_3超标的潜在污染源区分布特征。结果表明:常州市O_3超标期间易受到东南和西南方向气流影响,其中从东海和黄海途经浙江东北部、上海、江苏南部等地的东南气流占比达50%以上。自内陆途经黄山-湖州-宜兴到常州的气流对应的O_3平均质量浓度最高,为116μg/m3。自山东经枣庄-宿迁-淮安-泰州-苏州-无锡到常州的气流对应的O_3平均质量浓度最低,为78μg/m3,但该气流对应的SO2和NO2平均值为各聚类中的最高。影响常州市O_3的潜在污染源区主要在常州周边200 km以内的区域,且集中在从南京至上海的长江下游沿线区域和杭州湾区域;其中太湖湖区为重点污染源源区之一。O_3超标日影响常州NO2的潜在污染源区主要集中在江苏南部、浙江东北部和上海3个区域,太湖周边的常州、无锡、苏州和湖州等几个临近城市为潜在的重点污染源区。与影响常州O_3的WPSCF高值区相比,影响NO2的高值区分布范围更大、距离更远。影响常州O_3的潜在污染源区分布,与长江三角洲地区人为源大气污染物的高排放区域较为一致,说明长江三角洲地区的O_3污染与本区域的人为源大气污染物排放有着极为密切的关联。     

郑州市大气监测优化布点的研究

利用物元分析法，在大气污染普查基础上，以郑州市污染最严重的季节（冬季）的数据为准，构造大气环境监测的标准物元矩阵，求出关联函数值，进行了大气监测点的优选，并与用模糊聚类选出的点位相比较，来验证郑州市目前已有测子丫建立的合理性，并以此证明物元分析法是环境监测优化布点的一种可靠的方法。     

环境监测优化布点的物元分析模型

为了探索物元分析法在环境监测优化布点中应用的可能性，在确定了最佳和最次理想点基础上，建立了标准事物和节域事物的物元矩阵，并根据监测点对标准物元的关联函数值分布对采样点进行优化。实例表明物元分析法用于环境监测优化布点是可行的     

海水水质评价的倍斜率隶属函数聚类法

建立了宽域式倍斜率聚类的海水水质评价模式，其函数的右侧斜度为左侧斜率的２倍，勿求权重，直接聚类，海水水质评价实例说明，本文模糊综合评判法和灰色聚类法和更为合理，实用。     

海水水质评价的物元分析法

为了探索物元分析方法用于海水水质综合评价的可能性，通过计算海不水质对各评论评价等级的综合关联度，进行海水水质综合评价。用物元分析法对５个监测站位的海水水质进行评价，结果表明它用于海水水质综合评价是可行的。