基于机器学习的稀疏样本下的土壤有机质估算方法

采用GRNN（Generalized Regression Neural Network）和RF（Random Forest）2种机器学习方法构建土壤有机质预测模型,以提高稀疏样本情况下的土壤有机质估算精度。依据北京市大兴区农用地2007年的土壤有机质采样数据,按MMSD准则（Minimization of the Mean of the Shortest Distances）抽稀为8种不同采样密度的样本（分别为2703、1352、676、339、169、85、43、22个样本）,分别采用GRNN、RF和Ordinary kriging对各采样密度下的未知采样点进行预测,采用交叉检验的方式验证各采样密度下未知样点的预测精度。随着采样点密度的下降,样点间的空间自相关性逐渐减弱,半变异函数的拟和精度变差,预测点结果误差增大,预测的置信度降低。当抽稀到43个和22个采样点时,样点间的空间自相关性接近歼灭,半变异函数的决定系数较低且残差较大。普通克里格受到采样点数量和采样密度、样点的空间结构的影响比较明显,其预测精度随采样点数量的下降而下降。在85个采样点及以下时,其预测值与观测值之间没有显著的相关性。GRNN和RF的预测精度受采样密度的影响不大,其预测精度在一个较小的范围内波动,其预测值围绕观测值在一定阈值空间内震荡波动,具有较好的相关性,在85个及以下的采样密度时,预测精度相对普通克里格有较大的提升。普通克里格法不适合在稀疏样本条件下空间插值计算,尤其是在空间自相关性比较弱的情况下。机器学习模型能充分学习土壤间环境信息、样点空间邻近效应信息,兼顾属性相似性和空间自相关,具有更好的稳定性和适应性,不容易受到采样点数量、构型和采样密度等因素的影响,即使在采样点空间自相关性很弱的情况下也能做出稳定预测精度。     

Probability Distribution of the Hull Motion and Mooring Line Tension of Two Floating Systems

The statistical and distribution characteristics of the responses of a floater and its mooring lines are essential in designing floating/mooring systems.In general,the dynamic responses of offshore structures obey a Gaussian distribution,assuming that the structural system,and sea loads are linear or weakly nonlinear.However,mooring systems and wave loads are considerably nonlinear,and the dynamic responses of hull/mooring systems are non-Gaussian.In this study,the dynamic responses of two types of floaters,semi-submersible and spar platforms,and their mooring lines are computed using coupled dynamic analysis in the time domain.Herein,the statistical characteristics and distributions of the hull motion and mooring line tension are discussed and compared.The statistical distributions of the dynamic responses have strong non-Gaussianity and are unreasonably fitted by a Gaussian distribution for the two floating and mooring systems.Then,the effects of water depth,wave parameters,and low-frequency and wave-frequency components on the non-Gaussianity of the hull motion,and mooring line tension are investigated and discussed.A comparison of the statistical distributions of the responses with various probability density functions,including the Gamma,Gaussian,General Extreme Value,Weibull,and Gaussian Mixture Model(GMM)distributions,shows that the GMM distribution is better than the others for characterizing the statistical distributions of the hull motion,and mooring line tension responses.Furthermore,the GMM distribution has the best accuracy of response prediction.     

The Characteristics of Storm Wave Behavior and Its Effect on Cage Culture Using the ADCIRC+SWAN Model in Houshui Bay,China

The current storm wave hazard assessment tends to rely on a statistical method using wave models and fewer historical data which do not consider the effects of tidal and storm surge.In this paper,the wave-current coupled model ADCIRC+SWAN was used to hindcast storm events in the last 30 years.We simulated storm wave on the basis of a large set of historical storms in the North-West Pacific Basin between 1985 and 2015 in Houshui Bay using the wave-current coupled model ADCIRC+SWAN to obtain the storm wave level maps.The results were used for the statistical analysis of the maximum significant wave heights in Houshui Bay and the behavior of wave associated with storm track.Comparisons made between observations and simulated results during typhoon Rammasun(2014)indicate agreement.In addition,results demonstrate that significant wave height in Houshui Bay is dominated by the storm wind velocity and the storm track.Two groups of synthetic storm tracks were designed to further investigate the worst case of typhoon scenarios.The storm wave analysis method developed for the Houshui Bay is significant in assisting government's decision-making in rational planning of deep sea net-cage culture.The method can be applied to other bays in the Hainan Island as well.     

Effects of a Dry-Mass Conserving Dynamical Core on the Simulation of Tropical Cyclones

The accurate forecasting of tropical cyclones(TCs) is a challenging task. The purpose of this study was to investigate the effects of a dry-mass conserving(DMC) hydrostatic global spectral dynamical core on TC simulation. Experiments were conducted with DMC and total(moist) mass conserving(TMC) dynamical cores. The TC forecast performance was first evaluated considering 20 TCs in the West Pacific region observed during the 2020 typhoon season. The impacts of the DMC dynamical core on forecasts o...     

黑河流域降水统计——动力降尺度问题研究

依据区域气候模式RIEMS2.0输出的3 km高分辨率数据和站点降水记录分析了中国西北黑河流域降水的动力降尺度和统计—动力降尺度问题,检验了多种因子组合下多元线性回归（MLR）和贝叶斯模式平均（BMA）降尺度模型,评估了降尺度降水的均方根误差、相关系数、方差百分率及“负降水”偏差率等方面的统计特征。结果表明,动力降尺度降水相关系数最高,误差也最大,降水方差达到观测值的1.5～2倍;除相关系数外,统计—动力降尺度模型的几个统计特征均最优,纯统计模型次之。检验表明,仅用700 hPa位势高度场、经向风和比湿等构建的统计降尺度模型估计的站点降水相关系数较低,均方根误差也较大。当在统计降尺度模型中引入模式降水因子后站点降水的估计得到明显改善,其中MLR类模型的降水相关系数和方差百分率均明显高于BMA类模型,均方根误差二者相当,但前者“负降水”出现频次明显大于后者,“负降水”偏差主要出现在降水稀少的冬半年及黑河中、下游干旱或极端干旱区,上游出现频率较低,其中MLR类模型“负降水”出现频次明显高于BMA类模型,后者仅出现在黑河中、下游地区。包含模式降水因子的统计—动力降尺度模型能减少“负降水”出现...     

Change detection of linear features in temporally spaced remotely sensed images using edge-based grid analysis

Automatic change detection of land cover features using high-resolution satellite images, is a challenging problem in the field of intelligent remote sensing data interpretation, and is becoming more and more effective for its applications viz. urban planning and monitoring, disaster assessment etc. In the present study, a change in detection approach based on the image morphology that analyses change in the local image grids is proposed. In this approach, edges from both the images are extracted and grid wise comparison is made by probabilistic thresholding and power spectral density analysis for identifying change area. One of the advantages of the proposed methodology is that the temporal images used in the change analysis need not be radiometrically corrected as analysis is based on edge extractions. The grid-based analysis further reduces the error, which might have been introduced by image mis-registration. The proposed methodology is validated by finding the temporal changes in the linear land cover features in parts of Kolkata city, India using three different image data-sets from LISS IV, Cartosat-1 and Google earth having varied spatial resolutions of 5.8 m, 2.5 m and about 1 m, respectively. The overall accuracy in identifying changes is found to be 64.82, 73.86 and 80.93% for LISS IV, Cartosat-1 and Google earth data-set, respectively.     

签到位置数据的密度峰值快速搜索与聚类方法

位置签到数据蕴含了城市居民活动变化。由于客户端位置候选问题,不同的签到行为以同一候选位置签到时会产生位置重复现象。针对现有密度聚类方法在签到数据聚类上存在的问题,以快速搜索和查找密度峰值聚类算法(CFSFDP)为基础,提出了签到位置数据的密度峰值快速搜索与聚类方法。首先,引入位置重复频率来表达签到位置重复,然后,对原始签到位置数据点统计位置重复频率并重新设计数据结构,以新的空间点要素为研究对象寻找密度峰值点;最后,构建了峰值点密度簇聚类算法,在点要素集聚类过程中考虑密度连通性来保证峰值密度簇的连续与完整。试验表明,所提出的聚类方法有效避免了重复度较高的离群位置对象选为峰值并聚类的情况,并具有良好的空间适应性。所提取的密度峰值点不仅可以用来表示热区的中心,还能够反映热区的集中趋势,进而可以帮助探索热区的动态变化情况。     

SAR图像河流分割的加权指数区域能量模型

传统主动轮廓模型很难实现精确的SAR图像河流分割。针对这一问题,本文提出了一种加权指数区域能量主动轮廓模型,以精确地提取SAR图像中的河流。该模型在Chan-Vese(CV)模型能量泛函中引入了指数区域能量,能更好地衡量分割图像和原始图像的差异程度,提高模型的分割准确性。此外,利用目标区域和背景区域内像素灰度的最大绝对差取代模型中常值区域能量权重,自适应地调节目标区域和背景区域的能量比重,加速曲线运动到目标区域的边缘,获得更高的分割效率。针对实际河流SAR图像进行了分割试验,结果表明:与传统主动轮廓模型相比,本文提出的模型能更快速、精确地分割SAR图像中的河流,在分割结果和分割效率两方面具有优势。     

A STUDY OF RAPID DECAY TYPHOONS IN OFFSHORE WATERS OF CHINA

On the basis of NCEP/NCAR reanalysis data and yearbooks of CMA tropical cyclones, statistical analysis is performed for 1949—2013 offshore typhoons subjected to rapid decay(RD). This analysis indicates that RD typhoons are small-probability events, making up about 2.2% of the total offshore typhoons during this period. The RD events experience a decadal variation, mostly in the 1960 s and 1970 s(maximal in the 1970 s), rapidly decrease in the 1980 s and 1990 s and quickly increase from 2000. Also, RD typhoons show remarkable seasonal differences: they arise mainly in April and July-December, with the prime stage being in October-November. The offshore RD typhoons occur mostly in the South China Sea(SCS) and to a lesser extent in the East China Sea(ECS); however, none are observed over the Huang Sea and Bo Sea.Composite analysis and dynamic diagnosis of the RD typhoon-related large-scale circulations are performed.Physical quantities of the composite analysis consist of 500-h Pa height and temperature fields, vapor transfer, vertical wind shear(VWS), density of core convection(DCC), and high-level jet and upper-air outflow of the typhoon. The results suggest that(1) at the 500-h Pa height field, the typhoon is ahead of a westerly trough and under the effects of its passing trough;(2) at the temperature field, the typhoon is ahead of a temperature trough, with an invading cold tongue present;(3) at the vapor transfer field, water transfer into the RD typhoon is cut off; and(4) at higher levels, the related jet weakens and the outbreak of convection becomes attenuated in the typhoon core. In addition, VWS bears a relation to the RD typhoon; in particular, strong VWS favors RD occurrence.The differences in RD events between the SCS and ECS show that for the RD, the VWS of the ECS environmental winds is markedly stronger in comparison with its SCS counterpart. The cold advection invading into the typhoons is more intense in the SCS than in the ECS, and the low-level vapor transfer and high-level outflow are weaker in the SCS RD typhoons.Data analysis shows that sea surface temperature(SST), VWS, and DCC can be employed as efficient factors to predict RD occurrence. With appropriate SST, VWS, and DCC, a warning of RD occurrence can be given 36, 30-36,and 30 h, respectively, in advance. These values suggest that atmospheric SST responses lag. Owing to this time lag,the prediction of RD typhoons is possible.     

结合毫米波雷达提取降水条件下风廓线雷达大气垂直速度的研究

风廓线雷达主要是利用大气湍流对电磁波的散射作用,在晴空条件下对大气风场等进行探测。在降水天气下,风廓线雷达能同时接收到大气湍流回波和雨滴的散射回波信号,其探测到的回波功率谱中降水信号谱和大气湍流信号谱叠加在一起,使得大气的运动被雨滴的运动信息所掩盖,给后续的大气风场反演带来误差。而毫米波云雷达在降水天气下仅能探测到云雨粒子的回波而无法探测到大气湍流回波,基于这一差异结合毫米波云雷达资料对风廓线雷达功率谱数据进行订正,剔除其中的降水回波信息,进而获取正确的大气运动垂直速度。通过一次典型弱降水天气过程的雷达资料对该方法进行了可行性验证,并将计算得出的大气垂直速度与传统双峰法提取的大气运动垂直速度及原始风廓线雷达垂直速度进行了对比分析,显示在弱降水天气下该方法能有效消除降水对风廓线雷达垂直速度测量的影响,提高弱降水天气下测速准确率,并且在湍流谱极其微弱的情况下该方法也能准确地获取到大气运动垂直速度信息。但是云雷达回波在降水时会有衰减,虽然是弱降水也会导致在高层距离库上的订正效果变差,故目前只适用于弱降水时低距库处的降水订正。