����С��������LSSVM�Ļ��±���Ԥ��

??????????????,???????С????????LSSVM????????±???????????????С???任???????????з?????в???????????????????????????????к???????з??????LSSVM????????????????????????????????С????????LSSVM????±????????????????GM(1,1)??AR??????LSSVM??????     

基于小波分解与GA-LSSVM的GPS可降水量短临预报

针对GPS可降水量时间序列具有非线性、非平稳性的特征,研究一种基于小波分解（WD）、遗传算法（GA）和最小二乘支持向量机（LSSVM）的GPS可降水量短临预报方法。先采用小波分解将GPS可降水量时间序列分解成便于预报的低频分量和高频分量;然后利用遗传算法优化LSSVM参数,进而对各分量建立预报模型;再将各分量预报结果进行叠加重构得到最终预报结果。选取两组数据进行实验,并将预报结果分别与LSSVM和遗传小波神经网络（GA-WNN）预报结果进行对比。结果表明,该组合模型具有良好的泛化能力,可有效解决神经网络易陷于局部极小的问题,提高了全局预报精度。     

����EMD��GEP�Ļ��±���Ԥ��ģ��

??????????????????????????±???????????÷????????????????????t??????????????????з?????в????????????????????????????к???????з???????????????????????????????????????????÷???????????GM(1??1)??AR??LSSVM??????     

Local vs. cross station simulation of suspended sediment load in successive hydrometric stations: heuristic modeling approach

The present paper aims at modeling suspended sediment load (SSL) using heuristic data driven methodologies, e.g. Gene Expression Programming (GEP) and Support Vector Machine (SVM) in three successive hydrometric stations of Housatonic River in U.S. The simulations were carried out through local and cross-station data management scenarios to investigate the interrelations between the SSL values of upstream/downstream stations. The available scenarios were applied to predict SSL values using GEP to obtain the best models. Then, the best models were predicted by SVM approach and the obtained results were compared with those of GEP. The comparison of the results revealed that the SVM technique is more capable than the GEP for modeling the SSL through the both local and cross-station data management strategies. Besides, local application seems to be better than cross-station application for modeling SSL. Nevertheless, the cross-station application demonstrated to be a valid methodology for simulating SSL, which would be of interest for the stations with lack of observational data. Also, the prediction capability of conventional Sediment Rating Curve (SRC) method was compared with those of GEP and SVM techniques. The obtained results revealed the superiority of GEP and SVM-based models over the traditional SRC technique in the studied stations.     

A WD-GA-LSSVM model for rainfall-triggered landslide displacement prediction

This paper proposes a WD-GA-LSSVM model for predicting the displacement of a deepseated landslide triggered by seasonal rainfall,in which wavelet denoising(WD)is used in displacement time series of landslide to eliminate the GPS observation noise in the original data,and genetic algorithm(GA)is applied to obtain optimal parameters of least squares support vector machines(LSSVM)model.The model is first trained and then evaluated by using data from a gentle dipping(~2°-5°)landslide triggered by seasonal rainfall in the southwest of China.Performance comparisons of WD-GA-LSSVM model with Back Propagation Neural Network(BPNN)model and LSSVM are presented,individually.The results indicate that the adoption of WD-GA-LSSVM model significantly improves the robustness and accuracy of the displacement prediction and it provides a powerful technique for predicting the displacement of a rainfall-triggered landslide.     

一种基于小波分析的卫星钟差数据粗差处理方法

针对传统MAD方法在探测钟差粗差方面存在的不足,提出一种基于小波分析的钟差数据粗差探测与处理方法.该方法利用小波变换的多尺度分析能力,将含有粗差的数据分解为低频小波系数和各层的高频小波系数,并在不同时间尺度下进行粗差探测和消除.使用CODE提供的BDS精密钟差数据进行实验,分析不同小波函数及不同分解尺度对预处理效果的影...     

基于小波变换与RBF神经网络的GNSS水汽值预测研究

利用小波变换与RBF神经网络方法预测河北省GNSS水汽值。首先对GNSS测站水汽序列进行小波分解,然后利用RBF神经网络对小波分解的高频与低频信号进行预测,最后通过实验选择合适的高频与低频信号结果重构获得GNSS水汽值预测值。以实测GNSS水汽值为标准,基于小波变换与RBF神经网络预测的GNSS水汽值精度高于单一RBF神经网络预测精度,但预测结果的精度随着预测时长的增加而降低。     

����ARIMA��ANN���ģ�͵������Ӳ�Ԥ������

?????????????????????????????????????????????ARIMA??ANN??????????????????????????ARIMA????ANN???????????????б??????????????????????????????????????????????????????????????????????????????????IGS??????????????????????????????ARIMA????ANN??????????????ж?????????????????????????????????????????????????????????????????棬???????С??50%??     

基于机器学习的参考作物蒸散量估算研究

参考作物蒸散量（Reference Evapotranspiration, ET₀）的准确估算对区域水资源管理和分配、流域水量平衡以及气候变化等研究具有重要作用。新疆地处我国西北干旱地区,水资源供需矛盾尖锐,精确估算该地区的ET₀有助于其科学合理地调配水资源,缓解水资源供需压力。FAO推荐的Penman-Monteith法是计算ET₀的标准方法,但该方法需要多项气象因子,而新疆地区气象站点较少且分布不均,精确完备的气象数据在新疆大部分区域难以获取。因此,如何使用有限气象因子获取高精度的ET₀在新疆地区备受关注。本文基于中国气象数据网提供的新疆地区1980—2019年的地面气候资料日值数据集,在日和月尺度下,通过对最高气温T_max、最低气温T_min、平均气温T_avg、风速U₂、相对湿度RH和日照时数n共6项气象因子进行敏感性分析,形成不同的气象因子组合;然后使用SVM、RF、GBDT和ELM 4种机器学习算法,以FAO-56 PM计算值为标准值,对新疆地区的ET₀进行了拟合建模;最后,从拟合精度、稳定性和计算代价3个方面对模型进行评价。研究表明：① 在新疆地区,ET₀对RH、T_max和U₂敏感系数级别为高,平均敏感系数分别为-0.516、0.283和0.266;n为中等,平均敏感系数为0.124;T_min和T_avg为低,平均敏感系数分别为-0.016和-0.003;② 在日尺度,各算法在RH、T_max、U₂和n这4项气象因子为输入时精度较高（RMSE<0.5 mm/day,R²>0.95）,可对ET₀进行精确估算;在月尺度,各算法使用RH、T_max和U₂这3项参数便可对ET₀进行精确估算。SVM和GBDT这2种算法在日尺度和月尺度都有较好的适用性,可在相应尺度下使用较少气象因子替代FAO-56 PM公式对ET₀进行估算。     

利用小波变换方法分析跨断层形变异常

为了从跨断层形变观测资料中获取中强地震的前兆异常信息，运用二进小波变换方法和噪声与信号的定量识别方法，分析了不同尺度的小波变换的细节信号变化特征。研究结果表明：(1)不同尺度小波变换分解的细节信号显示出不同的时变特征。当尺度为1时。细节信号主要为噪声；尺度为2、4、5时，细节信号主要为非平稳信号；尺度为3时，细节信号主要为平稳周期信号；(2)每月观测一次的跨断层形变资料在尺度为3时的细节信号有较好的年周期特征；(3)当尺度为3时的细节信号变化超出2倍均方误差时，测点周围200km左右范围内发生中强地震的可能性很大。     

一种区域精密天顶对流层延迟组合预报模型

针对现有区域天顶对流层延迟(ZTD)模型属于函数或格网型,参数固定,且难以表达ZTD时空快速变化特性等问题,提出一种基于小波变换、傅里叶级数拟合、自回归(AR)、支持向量回归(SVR)的组合预报新模型构建方法。该模型在时域内对ZTD序列进行小波变换,分解出低频和高频序列。低频序列采用傅里叶级数拟合成时间函数,高频序列则由AR进行预报。在空间域内利用SVR建立位置参数向傅里叶级数参数的映射。在该模型中输入时间与位置信息即可获取ZTD预报值。利用94个GNSS基站2 a的ZTD数据进行建模,24个GNSS基站1 a的ZTD数据进行预测对比。结果表明,实测值与模型预报值之间的平均偏差为-2.02 mm,均方根误差为3.07 cm,优于大部分区域ZTD模型。在伪距单点定位测试中,该模型能够显著提高定位精度。实验表明,该组合模型具有较高的预报精度和可靠性,具有一定的应用价值。     

Development and application of a GIS-based artificial neural network system for water quality prediction: a case study at the Lake Champlain area

Journal of Oceanology and Limnology - Artificial Neural Network (ANN) models have been extensively applied in the prediction of water resource variables, and Geographical Information System (GIS)...     

库岸滑坡地下水位时间序列混沌特征识别与PSO-LSSVM模型预测

地下水位预测对滑坡稳定性分析具有重要意义,三峡库区库岸滑坡地下水位时间序列在季节性强降雨和周期性库水位涨落等诸多因素影响下呈现混沌特征。在对地下水位序列进行相空间重构的基础上,采用饱和关联维数法和最大Lyapunov指数法对其混沌特征进行验证。再用预测性能优秀的最小二乘支持向量机(LSSVM)模型对其进行预测,并用粒子群算法优化选取LSSVM模型的参数,以克服LSSVM模型参数选取困难的缺点。以三峡库区三舟溪滑坡前缘STK-1水文孔日平均地下水位序列为例进行了混沌分析,分别运用粒子群优化的LSSVM模型(PSO-LSSVM)和BP神经网络模型对STK-1水文孔地下水位进行了预测。结果表明库岸滑坡地下水位序列存在混沌特征,PSO-LSSVM模型预测结果的均方根误差为0.193m,拟合优度为0.815,说明预测效果较理想,且PSO-LSSVM模型预测精度高于BP网络模型,具有较强的实用性。      

小波分解改进电离层VTEC时间序列预报模型

介绍了小波分解法改进时间序列预报模型的原理。以IGS发布的2013年VTEC数据为例进行逐点建模,选用db4小波对5 112个格网点VTEC序列进行分解,并对各小波分量进行时间序列预报和重构,进而对VTEC进行预报。对一般方法和改进方法预报偏差的比例变化及全球范围内各格网点的预报值RMSE进行比较。结果表明,改进法预报的高精度点比例及其预报精度均优于一般方法。     

Potential distribution of a montane rodent(Cricetidae,Handleyomys chapmani) through time in Mexico: the importance of occurrence data

Ecological Niche Modeling uses the geographic coordinates of species presence records as the primary input to estimate potential geographic distributions. It is little known whether carrying out rigorous data pre-processing is necessary before building niche models to be transferred to different time period. Here we compared the current, past, and future potential distributions projected by niche models built from two different databases, an openaccess database and a database compiled ad hoc, for Handleyomys chapmani, a rodent closely associated with montane cloud forests in Mexico. The models predicted different spatial patterns of climatic suitability for the three periods examined. Based on our current knowledge of cloud forest species in Mexico, the distributions predicted by the model built from the ad hoc database are more ecologically realistic than those obtained from the open-access database. The models built using the open-access database were particularly inaccurate at the limits of the geographic range, predicting larger, more diffuse distributions for the three periods. We conclude that pre-processing occurrence data is crucial for mountain species, as the number of localities and even minor inaccuracies in the geographic coordinates can translate into very different climatic conditions due to abrupt altitudinal changes. Finally, the predicted shifts in the potential distribution of H. chapmani over time indicate that this species is highly susceptible to climate change.     

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.     

Comparison of artificial neural networks,geographically weighted regression and Cokriging methods for predicting the spatial distribution of soil macronutrients (N,P, and K)

Soil macronutrients(i.e. nitrogen(N), phosphorus(P), and potassium(K)) are important soils components and knowing the spatial distribution of these parameters are necessary at precision agriculture. The purpose of this study was to evaluate the feasibility of different methods such as artificial neural networks(ANN) and two geostatistical methods(geographically weighted regression(GWR) and cokriging(CK)) to estimate N, P and K contents. For this purpose, soil samples were taken from topsoil(0–30 cm) at 106 points and analyzed for their chemical and physical parameters. These data were divided into calibration(n = 84) and validation(n = 22). Chemical and physical variables including clay, p H and organic carbon(OC) were used as auxiliary soil variables to estimate the N, P and K contents. Results showed that the ANN model(with coefficient of determination R~2 = 0.922 and root mean square error RMSE = 0.0079%) was more accurate compared to the CK model(with R~2 = 0.612 and RMSE = 0.0094%), and the GWR model(with R~2 = 0.872 and RMSE = 0.0089%) to estimate the N variable. The ANN model estimated the P with the RMSE of 3.630 ppm, which was respectively 28.93% and 20.00% less than the RMSE of 4.680 ppm and 4.357 ppm from the CK and GWR models. The estimated K by CK, GWR and ANN models have the RMSE of 76.794 ppm, 75.790 ppm and 52.484 ppm. Results indicated that the performance of the CK model for estimation of macro nutrients(N, P and K) was slightly lower than the GWR model. Also, the accuracy of the ANN model was higher than CK and GWR models, which proved to be more effective and reliable methods for estimating macro nutrients.     

不同组合方法对GPS高程拟合的影响

针对平面拟合、二次曲面拟合和GA-BP神经网络3种模型的各自特点和适用范围,为综合各模型优点、提高高程拟合的精度与可靠性,对比分析了不同非线性组合和线性组合方法,即RBF神经网络组合、加权最小二乘支持向量机（WLSSVM）组合和最优加权组合、最优非负变权组合等对GPS高程拟合精度的影响。理论分析和算例结果表明,不同组合方法对GPS高程拟合精度的影响不同,WLSSVM组合和最优非负变权组合的拟合效果较好,可靠性较强|最优非负变权组合能较好地控制残差极值,有效减小误差区间,且转换精度较高。     

A Spatiotemporal Interactive Processing Bias Correction Method for Operational Ocean Wave Forecasts

Numerical models and correct predictions are important for marine forecasting,but the forecasting results are often unable to satisfy the requirements of operational wave forecasting.Because bias between the predictions of numerical models and the actual sea state has been observed,predictions can only be released after correction by forecasters.This paper proposes a spati-otemporal interactive processing bias correction method to correct numerical prediction fields applied to the production and release of operational ocean wave forecasting products.The proposed method combines the advantages of numerical models and Forecast Discussion;specifically,it integrates subjective and objective information to achieve interactive spatiotemporal correc-tions for numerical prediction.The method corrects the single-time numerical prediction field in space by spatial interpolation and sub-zone numerical analyses using numerical model grid data in combination with real-time observations and the artificial judg-ment of forecasters to achieve numerical prediction accuracy.The difference between the original numerical prediction field and the spatial correction field is interpolated to an adjacent time series by successive correction analysis,thereby achieving highly efficient correction for multi-time forecasting fields.In this paper,the significant wave height forecasts from the European Centre for Medium-Range Weather Forecasts are used as background field for forecasting correction and analysis.Results indicate that the proposed method has good application potential for the bias correction of numerical predictions under different sea states.The method takes into account spatial correlations for the numerical prediction field and the time series development of the numerical model to correct numerical predictions efficiently.     

基于LSTM神经网络的青藏高原月降水量预测

青藏高原的降水量预测不仅为该地区水资源合理规划利用提供依据,同时对中国及周边国家气候变化研究有着重要的意义。论文利用1990—2016年青藏高原降水量数据,采用长短期记忆神经网络（LSTM）对青藏高原月降水量进行预测,主要包括：① 使用青藏高原86个测站1990—2013年的月降水资料,预测各个测站2014—2016年的月降水量,并与传统的RNN、NAR、SSA和ARIMA预测模型相比,平均决定系数R²分别提高了0.07、0.15、0.13和0.36,均方根误差（RMSE）和平均绝对误差（MAE）表现更低;② 分析了降水量预测精度的空间分布特征,将各模型的R²在青藏高原地区内插值,分析R²的空间分布特征,发现所有模型降雨稀少的干旱地区和降雨多的湿润地区R²较低,在气候稳定、降水规律性明显的地区R²较高,且LSTM模型R²≥0.6的空间范围远大于传统模型;③ 分析了不同预测长度对各模型预测精度的影响,发现所有模型会随着预测长度增加而预测精度降低,但在不同的预测长度下LSTM预测的RMSE值都低于其他模型。