ARTIFICIAL NEURAL NETWORK CORRECTION OF ROUGH ERRORS OF OBSERVATIONS

In the context of tower measured radiation datasets.following the correction principle meetinga diagnostic equation in data quality control and in terms of a technique for model construction ondata and ANN(artificial neural network)retrieval for BP correction of radiation measurementswith rough errors available,a BP model is presented.Evidence suggests that the developed modelworks well and is superior to a convenient multivariate linear regression model,indicating its wideapplications.     

TIMESERIES PREDICTION MODEL CONSISTING OF ARTIFICIAL NEURAL NETWORK AND GENETIC ALGORITHM*

The paper introduces the basic concept and flow diagram of genetic algorithm(GA) and the merits and demerits of artificial neural network(ANN) as a timeseries prediction model and thereupon developed is a new model with ANN and GA in combination. Eventually, calculations are presented with the results and model examined.     

TIMESERIES PREDICTION MODEL CONSISTING OF ARTIFICIAL NEURAL NETWORK AND GENETIC ALGORITHM

The paper introduces the basic concept and flow diagram of genetic algorithm (GA) and themerits and demerits of artificial neural network (ANN) as a timeseries prediction model andthereupon developed is a new model with ANN and GA in combination. Eventually, calculationsare presented with the results and model examined.     

人工神经网络与遗传算法结合的时间序列预测模式

介绍了遗传算法的基本概念和流程，阐述了人工神经网络作为时间序列预测模式的可行性和不足之处，并提出了人工网络与遗传算法相结合的时间序列预测模式，最后给出了该算法的计算结果，并对结果和模式作了讨论。     

NEURAL NETWORK BP MODEL APPROXIMATION AND PREDICTION OF COMPLICATED WEATHER SYSTEMS*

An artificial neural network BP model and its revised algorithm are used to approximate quite successfully a Lorenz chaotic dynamic system and the mapping relation is established between the indices of Southern Oscillation and equatorial zonal wind and lagged equatorial eastern Pacific sea surface temperature(SST) in the context of NCEP/NCAR data,and thereby a model is prepared.The constructed net model shows fairly high fit precision and feasible prediction accuracy,thus making itself of some usefulness to the prognosis of intricate weather systems.     

STUDY ON MIXED MODEL OF NEURAL NETWORK FOR FARMLAND FLOOD/DROUGHT PREDICTION*

The paper concerns a flood/drought prediction model involving the continuation of time series of a predictand and the physical factors influencing the change of predictand.Attempt is made to construct the model by the neural network scheme for the nonlinear mapping relation based on multi-input and single output.The model is found of steadily higher predictive accuracy by testing the output from one and multiple stepwise predictions against observations and comparing the results to those from a traditional statistical model.     

热带气旋路径人工神经元预报方法对比试验研究

分别对具有动量项BP、LM、RBF人工神经网络建立36、48、60、72小时的热带气旋路径预测模型,各用100个独立样本进行预测检验,分析了网络"学习好,预报差"的原因,解决这一问题的关键是选择合适的网络结构参数、相应的学习算法和合适的预报因子,并总结了合理应用人工神经网络建立预测模型的经验.针对人工神经网络模型不具有自动选取因子的功能,给实际应用造成困难,提出了基于RBF的逐步选取因子的算法,并进行了对比试验,表明该方法具有较高的实用价值.     

运用天气雷达识别强对流天气的人工神经网络方法

选取对强对流天气反应较好的雷达回波参数和天气因子作为输入信息单元，应用Ｂ－Ｐ神经网络方法可对强对流天气和雷雨天气非常理想又迅捷地识别出来。     

CLIMATIC CHARACTERISTICS OF NET RADIATION IN THE EARTH-ATMOSPHERE SYSTEM OVER CHINA*

Investigated are effects of the total cloudiness and other factors on earth-atmosphere net radiation(EANR) and analyzed is its relation to other components and ground surface net radiation in the context of ERBE and ISCCP.Evidence suggests that planetary scale albedo and earth-atmosphere short wave absorption radiation have maximum effect on the net radiation under study,with the influence of cloud and latitude displayed predominantly through the two factors;OLR has relatively weak effect;the earth-atmosphere net radiation is well correlated with surface net radiation.Analysis is also performed of the geographic distribution of the earth-atmosphere net radiation throughout China,and the annual curve of the net radiation on a local basis is marked by high(low) value in summer(winter) with the impact of factors.including total cloudiness responsible largely for the shift of the months with maximum.     

一种改进的BP算法及在降水预报中的应用

传统BP（back propagation）算法在实际应用中具有网络结构参数和学习训练参数难以确定、泛化能力差、训练学习易陷入局部极小点等问题。该文在传统BP算法的基础上,提出一种改进算法,在训练过程中能自动确定各种参数,并避免陷入局部极小点,提高网络的泛化能力。利用2003—2005年5—9月中国国家气象中心T213的数值预报产品,通过动力诊断得出反映降水的物理量,然后从中挑选出与降水关系较好的25个因子,连同中国国家气象中心T213模式、日本气象厅业务模式和德国气象局业务模式相应的降水量预报结果作为预报因子。采用改进的BP算法建立江淮流域68个站24 h降水 (08:00—08:00,北京时）3个等级（降水量≥0.1 mm,降水量≥10 mm,降水量≥25 mm）的预报模型。通过对2006—2007年5—9月68个站试报结果表明：改进BP算法对降水预报的TS评分大大高于传统BP算法,也高于几种模式的降水预报结果,同时,改进算法使降水预报的平均空报率、漏报率明显降低。     

STUDY ON SST IN THE NORTHWESTERN PACIFIC OCEAN WITH SATELLITE OBSERVATIONS*

On the basis of extracting the clear brightness temperature in GMS-4 infrared data,the tests have been carried out by using three methods for SST retrieval in the northwestern Pacific Ocean in August 1993.Considering error amplification is the inherent feature in the single channel physical method,two statistical methods are developed.One is a single channel method.Its precision is 1.186℃,which is superior to that of other similar methods.The other is a multi-channel method using both TOVS and GMS-4 data.Its precision is 1.061℃,which is matched with that of other current multi-channel statistical methods(0.5-1.36℃).The retrieval SST distributions obtained by the two methods are in good agreement with conventional observations.     

CLIMATIC CHARACTERISTICS OF ATMOSPHERIC NET RADIATION OVER CHINA*

In terms of ERBE and ISCCP data.and measured/calculated surface net radiation,computation is performed of the climatic characteristics of ANR(atmospheric net radiation) across China alongside with the discussion and relations to other two kinds of radiation and contributing factors.Evidence suggests a high linear correlation of ANR with atmosphere-absorbed shortwave radiation.whereby can be established a general expression for ANR,which decreases more sharply as a function of altitude and increases slightly with latitude in summer,and changes uniformly in winter.Eventually,a comparison is made of the findings presented in this paper and literatures regarding the ANR pattern and magnitudes,indicating their great difference.     

TBB-REVEALED ANNUAL CYCLE FEATURES OF TROPICAL LFO*

In the context of 1980-1992 JMA(Japan Meteorological Agency) GMS TBB gridded dataset,study is undertaken of annual cycle features of FFT-derived window power spectrum averaged over the record length,with localized space/time characteristics of low-frequency oscillation(LFO) in the tropical atmosphere investigated alongside possible causes.It turns out that the LFO takes on surprisingly noticeable annual cycle features marked by a wider variable range of the LFO periods over northern tropics than the southern counterpart and equatorial vicinity.In addition,on the whole,the signals are more intense in the Northern Hemisphere during summer/autumn and at equatorial/southern latitudes when northern winter/spring occur as well.Also,not all these features are identical for different segments at the same latitudes,displaying signatures on a local basis,and the spatial/temporal locality can be qualitatively interpreted in terms of nonlinear interaction between tropical waves,and modulation of diabatic heating on the LFO periods.     

THE CALCULATION AND ANALYSIS OF SLOPE NET RADIATION IN CHINA*

By using the climatological calculating method for each component of slope surface net radiation proposed by the authors,calculations and analyses are done of the distribution features of slope net radiation in China with emphasis on the discussion of variations of slope net radiation in typical stations and sites with slope direction,slope,latitude and season.The distribution features of net radiation on the north and south slopes are,for the first time,mapped and discussed,revealing the great difference on the national basis,and thus acquiringa new interesting result that the negative-value area of winter net radiation on the north slope(20°)can reach Yunnan and Guizhou Provinces and middle and upper reaches of the Changjiang River.     

CLIMATIC CHARACTERISTICS OF EARTH-ATMOSPHERE OUTGOING LONGWAVE RADIATION OVER CHINA*

ERBE and ISCCP data are used to investigate the cloud forcing and latitude and atmospheric temperature effects on outgoing longwave radiation(OLR) in the earth-atmosphere system,and the similarity of OLR field to 500 hPa and surface effective radiation fields.Also,discussion is taken up of the OLR distribution on a nationwide basis,indicating that the winter(summer) OLR pattern is roughly a zonal type(asymmetrical saddle) with the annual pattern analogous to the January one.In the end the yearly OLR variation features are addressed on a regional basis.     

STUDY ON CANONICAL AUTOREGRESSION PREDICTION OF METEOROLOGICAL ELEMENT FIELDS*

Through extension of canonical correlation to the analysis of meteorological element fields (MEF), a concept from combination of canonical autocorrelation with canonical autoregression (CAR) is developed for short-term climatic prediction of MEFs with a formulated scheme. Experimental results suggest that the scheme is of encouraging usefulness to a weak persistence MEF,i.e., rainfall field and, in particular, to a strong persistance one like a SST field.     

人工神经网络方法在夏季降水预报中的应用

在夏季雨型预报中引进了人工神经网络方法。首先,根据雨型与前期（冬季）环流和海温的关系,从前期冬季资料场中找预报因子;然后,用人工神经网络方法对我国夏季的雨型进行模拟预报,以前４０年资料做训练样本,让网络在一定的学习规则下进行学习,最后得到一种分类预报模型。经对１９９２～１９９６年夏季雨型做独立试报,结果与实况基本相符。     

STUDY ON THE QUASI-FOUR YEAR OSCILLATION OF AIR-SEA INTERACTION*

Complex Singular Value Decomposition(CSVD)analysis technique was applied to study the Quasi Four year Oscillation(QFO)of air sea interaction and its coupled pattern evolution during different phases.Results show that:(1)CSVD method can better reveal phase relation between two physical fields:(2)Not only northerly anomalies from Northern Hemisphere but also southerly anomalies from Southern Hemisphere contribute to EI Nino.They converge in western equatorial Pacific,leading to outburst of strong equatorial westerly anomalies,and result in strong El Nino event onset:(3)An abnormal subtropical anticyclone circulation appears over northwestern Pacific while El Nino developing.It favors transitions from the warm SST(EINino)to the cold SST(La Nina),just as the tropical westerly anomalies produced by abnormal cyclone during a decaying La Nina.which encourage the development of El Nino:(4)The westerly anomalies in equatorial Pacific are mainly induced by eastward abnormal subtropical cyclone pairs,which are located in north and south Pacific respectively,and are not the eastward westerly anomalies from equatorial Indian Ocean.     

AN ERROR ANALYSIS ON THE SIMULATED DATA OF TOVS HIRS BY RTTOV5 MODEL*

The sounding data of meteorological satellites provide not only the real time weather information about the distribution of both cloud and rainfall,but also some others about the movement and state of atmosphere.They are important variables and parameters for NWP model used to simulate and predict atmospheric state.In order to introduce remote sensing information from satellites into NWP model,there is an efficient way of establishing an RT model by use of the atmosphere radiation sounding data of meteorological satellites to get the variables and parameters valuable to NWP model.In this paper,we set up profiles of air temperature and water vapor from the surface to upper (0.1 hPa) using the radiosounding data and the surface data from May to August 1998 atmosphere East Asia.A TOVS RT model (RTTOV5) is provided to compute the value of radiation value of HIRS channels in NOAA14.Then the radiation values of 19 HIRS channels are gotten.After matching these data computed by the RT model and the corresponding values coming from satellite sounding in time,the statistic distribution of bias between tile model output and the satellite sounding at each sounding channel can be gotten.At the same time.the distribution of RMS to every TOVS HIRS channel,the standard biases to different scanning angle to each channel are also obtained.     

FOUR-DIMENSIONAL DATA QUALITY CONTROL THROUGH THE ADJOINT APPROACH*

Using the variational four-dimensional (4-D) data assimilation technique (the adjoint method), we defined the error/mean-error ratios (EMER) of observational data. The plausibility of marking the gross error using the EMER is investigated theoretically under some assumptions.Idealized numerical experiments are carried out using the simple Lorenz model to test the quality control scheme.