基于随机森林特征优选的冬小麦分类方法

本文基于多时相Landsat 8 OLI数据,进行综合光谱、植被指数的特征提取与特征选择的方法研究。通过分析光谱与植被指数特征时序变化,提取最佳时相光谱,构建小麦提取特征;采用基于重要性与Pearson相关性的随机森林特征选择算法优选特征。结果表明:利用优选特征分类时,总体精度为89.78%,小麦分类精度为98.33%;与优选前特征的分类结果相比,精度分别提高了2.96%、2.55%;基于重要性与Pearson相关性的随机森林特征选择提高了分类精度和分类器工作效率。     

基于人工鱼群算法和Pearson相关系数的裂缝属性识别

将人工鱼群算法和Pearson相关系数结合,引入到进行裂缝属性识别的横波分裂方法中。结果表明,本文使用的方法能快速准确地识别裂缝属性,相比于模型空间扫描、粒子群算法及遗传算法等识别方法,收敛速度增快了约3倍,稳定性上也有所提高。     

氢化物发生—原子荧光光谱法测定地质样品中的锑(Ⅲ)和锑(Ⅴ)

提出了一种氢化物发生—原子荧光光谱法测定地质样品(水系沉积物)中Sb(Ⅲ)和Sb(Ⅴ)的方法.选取4.8 mol/L HC1为提取剂,采用超声波辅助提取,以6 g/mL柠檬酸钠作为Sb(Ⅴ)的掩蔽剂,在0.24 mol/L的HC1介质中选择性测定Sb(Ⅲ),用差减法求得Sb(Ⅴ).Sb(Ⅲ)的方法检出限为0.075×10-6,Sb(Ⅴ)的方法检出限为0.097×10-6.对40 ng/mL的Sb(Ⅲ)和Sb(Ⅴ)分别连续测定11次,得到相对标准偏差分别为1.1％和0.64％.应用该方法对地质样品中的Sb(Ⅲ)和Sb(Ⅴ)进行分析测定,并与王水溶解值相比较,该方法测定的总Sb提取率在80％以上,Sb(Ⅲ)和Sb(Ⅴ)的加标回收率分别为83％ ～ 107％和98％ ～ 114％.     

Photooxidation of Methacrolein in Fe(Ⅲ)-Oxalate Aqueous System and Its Atmospheric Implication

Iron and oxalic acids are widely distributed in the atmosphere and easily form ferric oxalate complex (Fe(Ⅲ)-Ox). The tropospheric aqueous-phase could provide a medium to enable the photo-Fenton reaction with Fe(Ⅲ)-Ox under solar irradiation. Although the photolysis mechanisms of Fe(Ⅲ)-Ox have been investigated extensively, information about the oxidation of volatile organic compounds (VOC), specifically the potential for Secondary Organic Aerosol (SOA) formation in the Fe(Ⅲ)-Ox system, is lacking. In this study, a ubiquitous VOC methacrolein (MACR) is chosen as a model VOC, and the oxidation of MACR with Fe(Ⅲ)-Ox is investigated under typical atmospheric water conditions. The effects of oxalate concentration, Fe(Ⅲ) concentration, MACR concentration, and pH on the oxidation of MACR are studied in detail. Results show that the oxidation rate of MACR greatly accelerates in the presence of oxalate when compared with only Fe(Ⅲ). The oxidation rate of MACR also accelerates with increasing concentration of oxalate. The effect of Fe(Ⅲ) is found to be more complicated. The oxidation rate of MACR first increases and then decreases with increasing Fe(Ⅲ) concentration. The oxidation rate of MACR increases monotonically with decreasing pH in the common atmospheric water pH range or with decreasing MACR concentration. The production of ferrous and hydrogen peroxide, pH, and aqueous absorbance are monitored throughout the reaction process. The quenching experiments verify that ·OH and (O-·2) are both responsible for the oxidation of MACR. MACR is found to rapidly oxidize into small organic acids with higher boiling points and oligomers with higher molecular weight, which contributes to the yield of SOA. These results suggest that Fe(Ⅲ)-Ox plays an important role in atmospheric oxidation.     

柴达木盆地鄂博梁Ⅲ号中新统成岩作用及沉积环境

综合运用岩石学、矿物学和元素地球化学等方法,对柴达木盆地北缘构造带鄂博梁Ⅲ号构造中新统上干柴沟组碎屑岩的成岩作用、形成环境和物质来源等进行了系统研究。发现上干柴沟组碎屑岩中碎屑颗粒间主要以点-线接触关系为主,长粒矿物被定向排列,经历过较强的压实作用。其中黏土矿物含量较高,平均达到了35.03%,主要以伊利石,绿泥石及伊-蒙混层为主。碳酸盐胶结物类型主要以方解石为主,仅含有少量白云石。碳酸盐胶结物的碳氧同位素含量测定表明,碳同位素(δ13C)分布在-6.8‰~-4.0‰之间,平均为-5.0‰;氧同位素(δ18O)分布于-11.1‰~-5.4‰,平均为-8.7‰;根据碳氧同位素含量推算古盐度Z值分布于108.34~114.89,平均值为112.77;碳酸盐沉淀温度分布在43.36℃~77.84℃,平均值为62.30℃。结合对主量元素、微量元素及有机碳含量等地球化学元素的综合分析,认为鄂博梁Ⅲ号构造带中新统上干柴沟组目前所处的成岩阶段主要为早成岩阶段B期至中成岩阶段A期,在形成早期主要以干、冷的淡水-微咸水环境为主,晚期则以要对暖、湿的淡水环境为主。     

基于多时相Sentinel-2影像多特征优选的湿地信息提取

本文提出了一种随机森林(random forest,RF)模型和Pearson相关系数相结合的RF-Pearson模型特征优选方法。以多时相Sentinel-2影像为数据源,提取多时相多特征;利用RF-Pearson模型进行特征选择,筛选出特征重要性得分较高且相关性较小的特征作为优选特征,参与黄河三角洲湿地信息提取;最后将分类结果与多时相全特征和随机森林模型优选特征进行比较。实验表明:特征优选能够提高湿地信息的提取效果,基于RF-Pearson模型特征优选方法的分类精度最高,表明了特征优选方法的有效性以及特征优选在湿地分类方面的优势。     

Multi-hazard susceptibility mapping based on Convolutional Neural Networks

Multi-hazard susceptibility prediction is an important component of disasters risk management plan. An effective multi-hazard risk mitigation strategy includes assessing individual hazards as well as their interactions. However, with the rapid development of artificial intelligence technology, multi-hazard susceptibility prediction techniques based on machine learning has encountered a huge bottleneck. In order to effectively solve this problem, this study proposes a multi-hazard susceptibility mapping framework using the classical deep learning algorithm of Convolutional Neural Networks (CNN). First, we use historical flash flood, debris flow and landslide locations based on Google Earth images, extensive field surveys, topography, hydrology, and environmental data sets to train and validate the proposed CNN method. Next, the proposed CNN method is assessed in comparison to conventional logistic regression and k-nearest neighbor methods using several objective criteria, i.e., coefficient of determination, overall accuracy, mean absolute error and the root mean square error. Experimental results show that the CNN method outperforms the conventional machine learning algorithms in predicting probability of flash floods, debris flows and landslides. Finally, the susceptibility maps of the three hazards based on CNN are combined to create a multi-hazard susceptibility map. It can be observed from the map that 62.43% of the study area are prone to hazards, while 37.57% of the study area are harmless. In hazard-prone areas, 16.14%, 4.94% and 30.66% of the study area are susceptible to flash floods, debris flows and landslides, respectively. In terms of concurrent hazards, 0.28%, 7.11% and 3.13% of the study area are susceptible to the joint occurrence of flash floods and debris flow, debris flow and landslides, and flash floods and landslides, respectively, whereas, 0.18% of the study area is subject to all the three hazards. The results of this study can benefit engineers, disaster managers and local government officials involved in sustainable land management and disaster risk mitigation.     

1970-2020年年昌吉地区日照时数时空变化特征分析

基于昌吉地区10个气象站点1970-2020年的气象观测数据,运用气候倾向法、5年滑动平均趋势分析法、M-K检验法、Pearson相关分析法以及ArcGIS10.7环境下的反距离加权(IDW)插值法探究昌吉地区日照时数时空变化规律及影响因素。结果表明:昌吉地区日照时数多年平均值为2840.3h,空间分布特征为“东部多,中西部少；山区多,平原少”,并呈现显著减少趋势,其速率为-62.8h/10a；从季度上看,日照时数夏季最高,其次是春季和秋季,冬季最低；下降速率冬季最快,其次是秋季和夏季,春季变化幅度最小；日照时数年内变化呈现双峰型,最大值出现在5月、7月和8月,最小值出现在12月,1-12月日照时数均呈现减少趋势,1月减少最为明显,12月次之。昌吉地区年日照时数在1987年发生突变；在影响因子方面,日照时数与总云量、水气压、雾日数呈现显著负相关,与大风日数、扬沙日数呈现显著正相关,说明,总云量、水气压、雾日数的逐年增加和大风日数逐年减少是日照时数逐年减少的主要原因。