Prediction of snow water equivalent using artificial neural network and adaptive neuro-fuzzy inference system with two sampling schemes in semi-arid region of Iran

Direct measurement of snow water equivalent(SWE) in snow-dominated mountainous areas is difficult, thus its prediction is essential for water resources management in such areas. In addition, because of nonlinear trend of snow spatial distribution and the multiple influencing factors concerning the SWE spatial distribution, statistical models are not usually able to present acceptable results. Therefore, applicable methods that are able to predict nonlinear trends are necessary. In this research, to predict SWE, the Sohrevard Watershed located in northwest of Iran was selected as the case study. Database was collected, and the required maps were derived. Snow depth(SD) at 150 points with two sampling patterns including systematic random sampling and Latin hypercube sampling(LHS), and snow density at 18 points were randomly measured, and then SWE was calculated. SWE was predicted using artificial neural network (ANN), adaptive neuro-fuzzy inference system(ANFIS) and regression methods. The results showed that the performance of ANN and ANFIS models with two sampling patterns were observed better than the regression method. Moreover, based on most of the efficiency criteria, the efficiency of ANN, ANFIS and regression methods under LHS pattern were observed higher than the systematic random sampling pattern. However, there were no significant differences between the two methods of ANN and ANFIS in SWE prediction. Data of both two sampling patterns had the highest sensitivity to the elevation. In addition, the LHS and the systematic random sampling patterns had the least sensitivity to the profile curvature and plan curvature, respectively.     

CNOP-P-based parameter sensitivity for double-gyre variation in ROMS with simulated annealing algorithm

Reducing the error of sensitive parameters by studying the parameters sensitivity can reduce the uncertainty of the model, while simulating double-gyre variation in Regional Ocean Modeling System(ROMS). Conditional Nonlinear Optimal Perturbation related to Parameter(CNOP-P) is an effective method of studying the parameters sensitivity, which represents a type of parameter error with maximum nonlinear development at the prediction time. Intelligent algorithms have been widely applied to solving Conditional Nonlinear Optimal Perturbation(CNOP). In the paper, we proposed an improved simulated annealing(SA) algorithm to solve CNOP-P to get the optimal parameters error,studied the sensitivity of the single parameter and the combination of multiple parameters and verified the effect of reducing the error of sensitive parameters on reducing the uncertainty of model simulation. Specifically, we firstly found the non-period oscillation of kinetic energy time series of double gyre variation, then extracted two transition periods, which are respectively from high energy to low energy and from low energy to high energy. For every transition period, three parameters, respectively wind amplitude(WD), viscosity coefficient(VC)and linear bottom drag coefficient(RDRG), were studied by CNOP-P solved with SA algorithm. Finally,for sensitive parameters, their effect on model simulation is verified. Experiments results showed that the sensitivity order is WDVCRDRG, the effect of the combination of multiple sensitive parameters is greater than that of single parameter superposition and the reduction of error of sensitive parameters can effectively reduce model prediction error which confirmed the importance of sensitive parameters analysis.     

Optimal precursor of the transition from Kuroshio large meander to straight path

We used the conditional nonlinear optimal perturbation(CNOP) method to explore the optimal precursor of the transition from Kuroshio large meander(LM) to straight path within a barotropic inflowoutflow model,and found that large amplitudes of the optimal precursor are mainly located in the east of Kyushu,which implies that perturbations in the region are important for the transition from LM to straight path.Furthermore,we investigated the transition processes caused by the optimal precursor,and found that these processes could be divided into three stages.In the first stage,a cyclonic eddy is advected to the formation region of the Kuroshio large meander,which enhances the LM path and causes a cyclonic eddy to shed from the Kuroshio mainstream.This process causes the LM path to change into a small meander path.Subsequently,the small meander is maintained for a period because the vorticity advection is balanced by the beta effect in the second stage.In the third stage,the small meander weakens and the straight path ultimately forms.The positive vorticity advecting downstream is responsible for this process.The exploration of the optimal precursor will conduce to improve the prediction of the transition processes from LM path to straight path,and its spatial structure can be used to guide Kuroshio targeted observation studies.     

Impact of nonlinear processes on formation of the Kuroshio large meander path in a barotropic inflow-outflow model

Based on a barotropic inflow-outflow model,we examine the formation of the Kuroshio large meander(LM) using conditional nonlinear optimal perturbation(CNOP) method.Both linear and nonlinear evolutions of such perturbations obtained by this method are investigated.The results show that the nonlinear evolution can result in the Kuroshio transition from a straight to LM path,whereas the linear evolution cannot.This implies that nonlinearity plays an important role in the formation of the Kuroshio LM path.The nonlinearity exists as advection in the evolution equations of the perturbation derived from the barotropic inflow-outflow model,namely the nonlinear advection of the perturbation by the perturbation(NAPP).By examining the role of this nonlinearity,we find that the NAPP tends to move the cyclonic eddy induced by the CNOP-type perturbation westward.Together with the beta effect,this offsets part of the eastward advection caused by the interaction between the perturbation and the background flow.Hence,the eastward movement of the cyclonic eddy is significantly weakened,effectively causing the eddy to develop.The sufficient evolution of this cyclonic eddy leads to the formation of the Kuroshio LM.     

A Comparison Study of Sensitivity on PJ and NPS Models in China Seas

Evaporation duct is an ubiquitous natural phenomenon over the ocean and can be diagnosed by evaporation duct model. The model proposed by Paulus and Jeske and another model established by the American naval postgraduate school are the most widely used. They are called PJ model and NPS model, respectively. Two methods are used to investigate the global sensitivity of PJ model and NPS model in China Seas. The first method is based on meteorological and oceanographic observation data in China Seas. Considering the system random error caused by sensor measurement inaccuracies, the mean relative error and mean absolute error are used as criterion for sensitivity analysis. The second method, called Extended Fourier Amplitude Sensitivity Test(EFAST), takes into account the interaction between input parameters and is used for sensitivity analysis. The results show that NPS model is more sensitive to the random errors of sensors than PJ model. The mean relative errors of PJ model and NPS model are 11.43% and 14.81%, respectively. The results of global sensitivity parameter analysis indicate that wind speed is the key factor of PJ model, while all input parameter of NPS model have relatively large total sensitivity index. In addition, sensitivity analysis results confirm that wind speed is one of main driving factors for the formation of evaporation duct. These results are valuable for the selection of diagnosis models for evaporation duct, the evaluation of radio wave propagation in the marine atmospheric surface layer, and the prediction technique of evaporation duct based on numerical weather prediction(NWP) in China seas.     

确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用

编制科学的滑坡易发性分区图,可以有效降低灾害带来的损失。以云南省芒市为研究区,利用确定性系数模型（certainty factor,简称CF）方法计算各个因子的敏感值,作为随机森林（random forests,简称RF）的分类数据,选取合适的训练数据和最优化的模型参数进行模型预测,从而对研究区进行滑坡易发性评价分区。采用频率比方法将连续性因子离散化,从而通过确定性系数计算因子不同区间的滑坡易发性,同时利用CF先验模型,对研究区负样本进行选取。通过计算袋外误差得到最优化的RF参数,随后利用RF模型对研究区模型进行训练及预测。绘制ROC曲线和三维遥感影像对预测模型结果分别进行定量和定性评价,结果表明,所得到的模型精度为91%,优于随机抽样得到的结果。最后,采用平均基尼不纯度减少和平均准确度下降两种计算方法计算、评价了研究区各个因子的重要性。基于以上对研究区进行的滑坡易发性评价结果,可以为该区灾害风险评估和管理提供依据。      

Optimal precursors of double-gyre regime transitions with an adjoint-free method

In this paper,we find the optimal precursors which can cause double-gyre regime transitions based on conditional nonlinear optimal perturbation(CNOP)method with Regional Ocean Modeling System(ROMS).Firstly,we simulate the multiple-equilibria regimes of double-gyre circulation under different viscosity coefficient and obtain the bifurcation diagram,then choose two equilibrium states(called jet-up state and jet-down state)as reference states respectively,propose Principal Component Analysisbased Simulated Annealing(PCASA)algorithm to solve CNOP-type initial perturbations which can induce double-gyre regime transitions between jet-up state and j et-down state.PCASA algorithm is an adj oint-free method which searches optimal solution randomly in the whole solution space.In addition,we investigate CNOP-type initial perturbations how to evolve with time.The results show:(1)the CNOP-type perturbations present a two-cell structure,and gradually evolves into a three-cell structure at predictive time;(2)by superimpo sing CNOP-type perturbations on the j et-up state and integrating ROMS,double-gyre circulation transfers from jet-up state to jet-down state,and vice versa,and random initial perturbations don't cause the transitions,which means CNOP-type perturbations are the optimal precursors of double-gyre regime transitions;(3)by analyzing the transition process of double-gyre regime transitions,we find that CNOPtype initial perturbations obtain energy from the background state through both barotropic and baroclinic instabilities,and barotropic instability contributes more significantly to the fast-growth of the perturbations.The optimal precursors and the dynamic mechanism of double-gyre regime transitions revealed in this paper have an important significance to enhance the predictability of double-gyre circulation.     

结合网络文本的模糊层次分析法评价水环境敏感性

水环境监测数据在水环境敏感性评价中起关键作用,然而受地形、环境、站点布设等因素影响存在缺失或不足的问题。为此,本文选取福建省为实验区,以2017年4-6月该省重点平台采集的网络文本数据为数据源,从水环境网络文本敏感度、污染敏感度和保护敏感度3个方面分析遴选出13个评价因子,基于模糊层次分析法结合网络文本构建水环境敏感性评价模型,分类验证评估结果的合理性。结果表明：① 从网络文本敏感度看,该省东部-中北部地区高于西部-中南部地区,高敏感区分布集中在闽江下游地区;② 从污染敏感度看,该省南部地区高于北部地区,高敏感区主要分布在汀江中下游、晋江下游和龙江等区域;③ 从保护敏感度看,该省西北-中南地区高于东北-西南地区,高敏感区主要分布在闽江上游支流建溪、木兰溪、萩芦溪等区域。综合各敏感度因子分析后发现全省水环境敏感度整体从东南-西南-北部-中部-东北依次减小,东沿海经济发达区和河流入海口等区域呈现出高敏感性,与实际情况相符。本研究使得水环境敏感性评价结果更具合理性,对于预测或排查水环境高敏感污染风险区、重要保护区及公众关注区具有一定的实用意义。     

人工神经网络和决策树模型在滑坡易发性分析中的性能对比

机器学习模型广泛应用于区域性滑坡易发性分析。模型的选择关系到评价结果的可信度、准确率和稳定性。现有滑坡易发性分析模型对比研究侧重模型的预测精度。模型的稳定性和数据量敏感性对机器学习模型的性能评估同样非常重要。本文以福建省南平市蔡源流域为研究区,以四川省绵阳市北川县为验证区,从预测精度、稳定性和数据量敏感性3个方面深入对比BP（Back Propagation）人工神经网络模型和CART（Classification and Regression Tree）决策树模型在滑坡易发性分析中的效果,主要结论如下:① 在逐渐增加一定数量训练样本的过程中,BP人工神经网络模型预测精度的增长率更高。在蔡源流域内,当训练样本数量增加10 000时,BP人工神经网络模型的预测精度上升5.22%,CART决策树模型的预测精度上升2.11%。② BP人工神经网络的预测精度高于CART决策树模型,且较为稳定。在100组数据集上,BP人工神经网络模型验证集预测精度的均值和验证集滑坡样本预测精度的均值分别为81.60%和84.86%,高于CART决策树模型的72.97%和76.59%。与此同时,BP人工神经网络模型对应预测精度的标准差分别是0.32%和0.37%,小于CART决策树模型的0.35%和0.67%。③ BP人工神经网络模型分析的滑坡易发区相比CART决策树模型,更接近实际滑坡的空间分布。最后,北川县的验证实验也出现了相同的现象。     

���ڸĽ���ɫARMAģ�͵������Ӳ����Ԥ���о�

?????????????????????????λ???????????????????????????????????????????????????ARMA?????????????????????????????и??????????????????????????????????ARMA????????????????????????в???IGS????????????????????????????????????     

A numerical study on seasonal variations of the Taiwan Warm Current

Princeton Ocean Model (POM) is employed to investigate the Taiwan Warm Current (TWC) and its seasonal variations. Results show that the TWC exhibits pronounced seasonal variations in its sources, strength and flow patterns. In summer, the TWC flows northeast in straight way and reaches around 32°N; it comes mainly from the Taiwan Strait, while its lower part is from the shelf-intrusion of the Kuroshio subsurface water (KSSW). In winter, coming mainly from the shelf-intrusion of the Kuroshio northeast of Taiwan, the TWC flows northward in a winding way and reaches up around 30°N. The Kuroshio intrusion also has distinct seasonal patterns. The shelf-intrusion of KSSW by upwelling is almost the same in four seasons with a little difference in strength; it is a persistent source of the TWC. However, Kuroshio surface water (KSW) can not intrude onto the shelf in summer, while in winter the intrusion of KSW always occurs. Additional experiments were conducted to examine effects of winds and transport through     

北太平洋海表温度异常对我国汛期降水的影响

本文对我国汛期降水进行了旋转主分量分析,得到6个最基本的降水型,并利用北太平洋超前一年各季的海表温度与这6个降水型求相关,得到24张相关图。分析相关图的结果表明:黑潮海域的海表温度对我国东部绝大部分地区降水很敏感;影响我国江淮流域降水的海温区有几个,因而使得江淮流域旱涝情况特别复杂也难以预报;我国汛期降水和北太平洋海表温度的相关具有不同的时滞现象,绝大多数与冬半年的海温有密切联系,充分反映了海气相互作用具有十分复杂的机制。     

Holocene temperature records from the East China sea mud area southwest of the Cheju Island reconstructed by the U 37 K′ and TEX86 paleothermometers

As an important marginal sea under the influences of both the Changjiang River and the Kuroshio, the East China Sea (ECS) environment is sensitive to both continental and oceanic forcing. Paleoenvironmental records are essential for understanding the long-term environmental evolution of the ECS and adjacent areas. However, paleo-temperature records from the ECS shelf are currently very limited. In this study, the U ₃₇ ^K′ and TEX₈₆ paleothermometers were used to reconstruct surface and subsurface temperature changes of the mud area southwest of the Cheju Island (Site F10B) in the ECS during the Holocene. The results indicate that temperature changes of F10B during the early Holocene (11.6–6.2 kyr) are associated with global climate change. During the period of 6.2–2.5 kyr, the similar variability trends of smoothing average of ΔT (the difference between surface and subsurface temperature) of Site F10B and the strength of the Kuroshio suggest that the Kuroshio influence on the site started around 6.2 kyr when the Kuroshio entered the Yellow Sea and continued to 2.5 kyr. During the late Holocene (2.5–1.45 kyr), apparent decreases of U ₃₇ ^K′ sea surface temperature (SST) and ΔT imply that the direct influence of the Kuroshio was reduced while cold eddy induced by the Kuroshio gradually controlled hydrological conditions of this region around 2.5 kyr.     

基于径向基函数神经网络的地震液化侧移预测

在已有的地震液化侧移数据库中增加累积绝对速度（CAV₅）这一地震参数,以考虑震源机制对液化侧移的影响。然后采用径向基函数神经网络（RBFNN）方法建立地震液化侧移预测模型,并与其他模型进行对比分析。结果表明,本文模型预测精确度最高;CAV₅在液化侧移预测方面可以代替震级、震中距2项参数;所有参数中,震级、震中距、可液化土层厚度敏感性较高,对液化侧移影响程度较大。     

新疆阿克苏河流域降水空间变异特征分析

根据阿克苏河流域降水空间观测数据,其降水稀疏且分布不均匀的特点,选取不同模型对降水空间变化规律进行研究,其结果精确性差异很大。通常应用地统计理论研究降水空间变异性,一般只涉及单个变量,传统的多元回归分析虽然涉及多个变量的影响,但缺乏区域化的空间结构特征。揭示具有协同区域化特征的降水空间变异现象及建立其空间分布模型,既要考虑多元信息的空间位置关系,即同一变量在不同地理位置上的相关性,又要考虑多元信息由于空间重复性引起的协同关系,即同一地理位置上不同变量的相关性。本文用阿克苏河流域范围内的降水观测数据建立析取-协克立格模型,考虑高程变量对降水量空间分布的影响,定量地揭示降水区域化变量的空间变异规律,并将其结果用于降水量的空间最优插值。     

夜间灯光数据驱动的成渝城市群空间形成过程重建及分析

2016年4月发布的《成渝城市群发展规划》首次正式确定了成渝城市群的内涵和具体边界,重建成渝城市群的形成过程,有利于把握未来发展趋势,并合理优化与调整其发展过程。在重建技术方面,对DMSP/OLS夜间灯光数据传统的不变目标区域校正法加以改进,将成渝城市群2013年城市市区范围内的全部像元加入校正模型的拟合中,设计了统计数据的校正规则,再通过二分比较法较好地恢复了成渝城市群内各城市建成区的时序空间信息。提取面积与统计面积总体平均相对误差为-0.38%,利用高分辨率Google Earth图像验证的建成区提取准确率达到98.29%,相比其他研究结果,经方法改进后的提取结果精度高且稳定。在结果分析方面,基于提取结果展开对城市群建成区重心转移过程与城市聚合过程的深层次研究,剖析了城市群的内部格局与时空变化特征。分析表明,成渝城市群的聚合情况与《成渝城市群发展规划》高度吻合,城市群已进入快速发育阶段,随着区域差异的持续扩大,成都、重庆都市圈的核心地位逐渐形成,而重庆的发展态势稍好。     

Seasonal variation of the Taiwan Warm Current Water and its underlying mechanism

Based on the historical observed data and the modeling results,this paper investigated the seasonal variations in the Taiwan Warm Current Water(TWCW)using a cluster analysis method and examined the contributions of the Kuroshio onshore intrusion and the Taiwan Strait Warm Current(TSWC)to the TWCW on seasonal time scales.The TWCW has obviously seasonal variation in its horizontal distribution,T-S characteristics and volume.The volume of TWCW is maximum(13746 km~3)in winter and minimum(11397 km~3)in autumn.As to the contributions to the TWCW,the TSWC is greatest in summer and smallest in winter,while the Kuroshio onshore intrusion northeast of Taiwan Island is strongest in winter and weakest in summer.By comparison,the Kuroshio onshore intrusion make greater contributions to the Taiwan Warm Current Surface Water(TWCSW)than the TSWC for most of the year,except for in the summertime(from June to August),while the Kuroshio Subsurface Water(KSSW)dominate the Taiwan Warm Current Deep Water(TWCDW).The analysis results demonstrate that the local monsoon winds is the dominant factor controlling the seasonal variation in the TWCW volume via Ekman dynamics,while the surface heat fl ux can play a secondary role via the joint ef fect of baroclinicity and relief.     

随机动力模式中误差对气候预报的影响

本文采用时间平均的矩方程随机动力气候模式,对大尺度大气系统的演化情况进行了计算,其中考虑了初始条件的误差和外部非绝热加热的误差对系统稳定性的影响,并比较了它们的相对重要性。同时,此结果又与以随机试验得到的结果进行了比较,积分两个月的结论是:矩方法在本模式中可以近似代替随机试验,初始条件的误差对系统稳定性的影响较外部加热的误差的影响要大。     

优化背景值的非等间距线性时变参数GM(1,1)幂模型在变形监测中的应用

为弥补传统GM(1,1)幂模型背景值等权构造的缺陷,针对原始变形序列的非等距振荡特征构建背景值加权优化的非等间距线性时变参数GM(1,1)幂模型,并采用具有全局优化特性、收敛速度快的粒子群算法求解模型的幂指数和背景值权重。以2组矿区监测点累积沉降观测数据为例进行沉降分析与预测,结果表明,本文模型的平均绝对百分比误差分别为2.33%和4.70%,预测误差分别为2.10%和6.38%,计算结果均优于其他3种模型。工程应用表明,优化模型在小样本非等距振荡序列应用中具有优越性,适用于地表沉陷的短期预测与时变分析。     

��С������������ͨKriging���ıȽ�

?????????????????????????????????С???????ú????Kriging????????????????????????÷??????Kriging??????????????????????????μ??????????????????1??????????????????￡?????????????Kriging???????????????÷??????????????￡?????????????÷??????????????Kriging????????2????:???????????????У????Kriging??????????Ч?????????