基于Stacking集成学习的恒星/星系分类研究

机器学习在当今诸多领域已经取得了巨大的成功,但是机器学习的预测效果往往依赖于具体问题.集成学习通过综合多个基分类器来预测结果,因此,其适应各种场景的能力较强,分类准确率较高.基于斯隆数字巡天(Sloan Digital Sky Survey,SDSS)计划恒星/星系中最暗源星等集分类正确率低的问题,提出一种基于Stacking集成学习的恒星/星系分类算法.从SDSS-DR7(SDSS Data Release 7)中获取完整的测光数据集,并根据星等值划分为亮源星等集、暗源星等集和最暗源星等集.仅针对分类较为复杂且困难的最暗源星等集展开分类研究.首先,对最暗源星等集使用10折嵌套交叉验证,然后使用支持向量机(Support Vector Machine,SVM)、随机森林(Random Forest,RF)、XGBoost(eXtreme Gradient Boosting)等算法建立基分类器模型;使用梯度提升树(Gradient Boosting Decision Tree,GBDT)作为元分类器模型.最后,使用基于星系的分类正确率等指标,与功能树(Function Tree,FT)、SVM、RF、GBDT、XGBoost、堆叠降噪自编码(Stacked Denoising AutoEncoders,SDAE)、深度置信网络(Deep Belief Network,DBN)、深度感知决策树(Deep Perception Decision Tree,DPDT)等模型进行分类结果对比分析.实验结果表明,Stacking集成学习模型在最暗源星等集分类中要比FT算法的星系分类正确率提高了将近10%.同其他传统的机器学习算法、较强的提升算法、深度学习算法相比,Stacking集成学习模型也有较大的提升.     

An Automatic Method for Detecting Transients and Variable Sources in AST3 Survey Based on Image Subtraction and Random Forest

AST3-2 (the second Antarctic Survey Telescope) is located in Antarctic Dome A, the loftiest ice dome on the Antarctic Plateau. It produces a huge amount of observational data which require a more efficient data reduction program to be developed. Also the data transmission in Antarctica is much difficult, thus it is necessary to perform data reduction and detect variable and transient sources remotely and automatically in Antarctica, but this attempt is restricted by the unsatisfactory performance of the low power consumption computer in Antarctica. For realizing this purpose, to develop a new method based on the existing image subtraction method and random forest algorithm, taking the AST3-2 2016 dataset as the test sample, becomes an alternative choice. This method performs image subtraction on the dataset, then applies the principle component analysis to extract the features of residual images. Random forest is used as a machine learning classifier, and in the test a recall rate of 97% is resulted for the positive sample. Our work has verified the feasibility and accuracy of this method, and finally found out a batch of candidates for variable stars in the AST3-2 2016 dataset.     

Formation of Carbon-Enhanced Metal-Poor RR Lyrae Stars

Carbon-enhanced metal-poor (CEMP) stars are considered to be related to the first generation of stars, and responsible for the chemical evolution of the early Galaxy. More than half of them are in binaries, and could be explained by the binary evolution, but the formation channel of them is still not fully understood. Among the hundreds of CEMP stars, there are nine CEMP RR Lyrae stars identified, and at least seven of which are very likely not binaries. The usual binary star evolution channel is difficult to produce such a single star, particularly that of carbon enrichment. One way in which such a single star might be produced is the merger of a helium white dwarf with a Hertzsprung gap (HG) star. We use a stellar evolution program to calculate the models of the merger remnants, and find that the models can reproduce the observed distribution of these CEMP single RR Lyrae stars in terms of surface temperature, gravity, and carbon abundance. Hence, it is extremely possible that the helium white dwarf and HG star merger model is one of the formation channels of the metal-poor carbon-rich RR Lyrae stars.     

基于大数据的极端暴雨事件下城市道路交通及人群活动时空响应

随着全球气候变化加剧,极端降雨增多,暴雨内涝灾害频发,严重威胁城市的可持续发展。快速掌握暴雨给城市交通及人群的影响,有助于提高灾害应急管理水平和事件响应能力。利用实时动态的交通路况信息和手机定位请求数据,通过一种融合STL时序分解技术与极端学生化偏差统计检验的时间序列异常探测方法,监测和分析暴雨内涝灾害事件中,城市道路交通和人群活动的时空响应特征,并以2018年7月16日发生在北京的极端暴雨事件为例开展实证研究。研究结果显示,在降雨集中的早、晚高峰两个时段（8—9时、18—19时）,市区的拥堵道路数量超出往常水平最高可达150%,异常检测分析显示拥堵道路数量和交通拥堵指数均达到异常甚至极端水平。人群活动的异常响应分析结果显示,暴雨事件引起定位请求量异常升高、异常点增多,且异常点的空间分布与1 h前的降雨量分布存在较高相关性。以上结果不仅证明了大数据及异常检测方法对于快速洞察暴雨事件对城市交通及人群影响的有效性,也为城市暴雨内涝灾害的应急响应与管理提供了新的技术手段。     

Swelter in the city: Urban greenery and its effects on temperature in Guwahati,India

Changing urban landscape with multistoried high rises, roads and pavements is continuously reducing urban green space. These structures result in high surface temperature variation within cities. To explore the relationship between surface temperature and normalized difference vegetation index (NDVI), this study estimates two models—geographically weighted regression (GWR) and a fixed effect panel data model in relation to the Guwahati Metropolitan Area (GMA), a secondary city in north east India. The results indicate the superiority of GWR regression in presence of spatial dependence. Panel data analysis shows that the densely populated urban areas in the GMA with less than 10 per cent greenery are 1°C warmer than the sub-urban areas with 50 per cent greenery.     

Decumbent development: Urban sprawl in the Guwahati Metropolitan Area,India

Urban sprawl has become a global phenomenon as an outcome of growing population and rapid urbanization. Previous studies have addressed the rising incidence of uncontrollable urban development, particularly in peri-urban areas of cities, leading to chronic urban sprawl. The city of Guwahati, a million city in north east India, has expanded significantly in recent years. In this article, the links between population and growth of built-up areas were examined using geo-spatial techniques and remotely sensed datasets. The results indicate that the sprawl has accentuated in recent years. The intensity of land use remained uneven due to marked variations in the distribution of built-up areas, plausibly an outcome of unplanned urban growth. If current trends are anything to go by, future urban sprawl could pose serious threats to the vulnerable eco-sensitive and peri-urban areas of Guwahati. Secondary cities have unfortunately received scant attention in urban policy research, and Guwahati, epitomizes urban woes in a developing country.     

野外科学观测研究台站（网络）和科学数据中心建设发展

中国科学院地理科学与资源研究所成立80年来,十分重视野外台站（网络）和科学数据中心的建设,取得了辉煌成就。研究所建立了4个野外观测研究网络,引领了中国生态系统研究网络的建设与发展;成立了2个国家级科学数据中心,1个中国科学院数据中心,1个数据出版系统并于2016年加入了世界数据系统;拥有2个国家级野外观测研究站,1个中国科学院野外研究站,形成了独具特色的野外观测研究平台和数据共享服务平台。本文回顾了中国生态系统研究网络、国家生态系统观测研究网络、中国通量观测研究网络、中国物候观测网和禹城站、拉萨站、千烟洲站以及地球系统科学数据中心、生态科学数据中心、资源环境科学数据中心和全球变化科学研究数据出版系统的发展历程。地理资源所台站（网络）从无到有,不断发展壮大,引领了中国野外观测研究事业的发展,支撑了地理学、生态学等重要科学成果产出,科技支撑能力和示范能力大幅提升,有力支撑了华北平原、青藏高原以及南方山地丘陵区的生态文明建设;成为中国地球系统科学、野外台站、资源环境等学科和领域最大的科学数据汇聚中心,数据共享服务成效显著,在国内外具有广泛影响力。在未来发展中,地理资源所将充分发挥野外台站（网络）综合中心作用,强化生态系统、碳水通量、物候等观测研究网络的能力建设,稳步提升野外观测研究站条件保障能力和科学数据中心的数据汇聚能力、分析挖掘能力以及共享服务能力,持续推动和引领中国科学数据的共享,在科学研究和支撑国家需求等方面做出更大贡献。     

基于兴趣点（POI）大数据的东北城市空间结构分析

以东北三省36个城市为研究区,利用 400余万条兴趣点行业分类大数据,采用核密度估计、标准差椭圆、区位熵等方法分析城市空间结构及其行业构成机制。研究发现,东北城市要素显著集聚,城市内部空间结构呈现集中团块型、分散组合型、线型、放射型特征以及多元复合类型;第二产业和房地产业呈现郊区化特征,各行业发展方向与东北大区域的经济轴线一致,多数行业尚未形成专业化功能区;第二产业与房地产业的离心发展对集中团块型城市的塑造作用不强,但对分散组合型城市空间结构的贡献较大。线型城市通常兼具多中心特征,放射型城市各行业仍偏向于向心聚集。     

兰州盆地新石器时期遗址分布与地形的关系研究

研究遗址和地形等环境要素的关系有助于理解人地关系的作用机制。基于GIS空间分析和二元逻辑斯蒂模型分析了兰州盆地新石器时期马家窑和齐家文化遗址空间分布的特征、变化规律及影响因素,定量研究了地形等环境要素与遗址分布的关系。结果表明：新石器时期的马家窑文化、半山文化、马厂文化和齐家文化遗址均沿黄河分布,主要集中于河流阶地上坡度较小的区域。距河流的水平最近距离为318.6~17 721.7 m。新石器遗址特别是马厂遗址的空间集聚性明显。从马家窑类型、半山类型,发展到马厂类型,单一型遗址的占比逐渐由53.3%增多至92.6%。马厂类型的分布中心距离黄河最近。地形等环境要素显著影响遗址的空间分布,遗址出现概率主要受坡度、坡向和距黄河最近距离的影响,模型的解释程度可达65.0%。引入历史时期和现代聚落进行比较,历史时期聚落分布受到高程和坡度的影响,而现代聚落的分布主要受到高程、坡度和距河流距离的影响。聚落分布和影响因素的演变可能受到社会生产力发展的影响。     

毛乌素沙地东南缘全新世气候不稳定性

毛乌素沙地处于中国季风区的西北边缘,对气候变化敏感,是古气候演化和古环境变迁研究的理想场所。全新世气温回暖期,气候整体稳定但存在暖湿冷干的次级波动,不同类型沉积相组成的地层序列记录了全新世千年、百年尺度的气候不稳定性。对毛乌素沙地不同沉积序列的研究表明:(1)毛乌素沙地东南缘的沙漠/黄土边界带DLT、NB剖面粒度及Rb/Sr比值可作为气候变化的代用指标。>63 μm砂含量增加,Rb/Sr比值降低,揭示东亚冬季风增强,风成砂堆积,风沙活动加剧,气候干冷;反之,东亚夏季风增强,降水增多,风化成壤程度加大,气候暖湿。(2)毛乌素沙地东南缘沙漠/黄土边界带及低洼沟谷区年代概率密度函数的分析显示,全新世早期~8\^5 ka BP风成砂堆积,风沙活动加剧,气候表现为干冷;全新世中期8\^5 ka~3\^0 ka BP地势较高处古土壤广泛发育,地势低洼处发育湖沼相/泥炭层,但在6.0 ka BP左右存在气候转冷过程;全新世晚期3\^0 ka BP以来气候波动频繁。(3)毛乌素沙地气候变化与北大西洋冰筏冷事件、董哥洞石笋、季风边缘区湖泊、东部沙地等记录具有可对比性和相对一致性,反映出全新世千年和百年尺度上的气候变化主要受全球变化的影响,这对预测和模拟未来气候变化具有借鉴意义。