The Meteorological Prediction Model of Lemon Production in Anyue County Based on Correlation

Using the meteorological data during 1971- 2013 and lemon growth and yield data during 2003- 2013 in Anyue,the suitability problem of lemon growth and correlation problem between meteorological factors and lemon growth in Anyue area were studied. According to relevance between the selected meteorological factors and yield of lemon,meteorological prediction model of lemon yield was established in Anyue,and the prediction accuracy was higher. The research had certain guiding significance for management work of lemon production in Anyue area.

Artificial Intelligence Based Meteorological Parameter Forecasting for Optimizing Response of Nuclear Emergency Decision Support System

This paper presents a novel artificial intelligence (AI) based approach to predict crucial meteorological parameters such as temperature,pressure,and wind speed,typically calculated from computationally intensive weather research and forecasting (WRF) model.Accurate meteorological data is indispensable for simulating the release of radioactive effluents,especially in dispersion modeling for nuclear emergency decision support systems.Simulation of meteorological conditions during nuclear emergencies using the conventional WRF model is very complex and time-consuming.Therefore,a new artificial neural network (ANN) based technique was proposed as a viable alternative for meteorological prediction.A multi-input multi-output neural network was trained using historical site-specific meteorological data to forecast the meteorological parameters.Comprehensive evaluation of this technique was conducted to test its performance in forecasting various parameters including atmospheric pressure,temperature,and wind speed components in both East-West and North-South directions.The performance of developed network was evaluated on an unknown dataset,and acquired results are within the acceptable range for all meteorological parameters.Results show that ANNs possess the capability to forecast meteorological parameters,such as temperature and pressure,at multiple spatial locations within a grid with high accuracy,utilizing input data from a single station.However,accuracy is slightly compromised when predicting wind speed components.Root mean square error (RMSE) was utilized to report the accuracy of predicted results,with values of 1.453℃for temperature,77 Pa for predicted pressure,1.058 m/s for the wind speed of U-component and 0.959 m/s for the wind speed of V-component.In conclusion,this approach offers a precise,efficient,and wellinformed method for administrative decision-making during nuclear emergencies.

PROGRESS IN THE STUDY OF RETROSPECTIVE NUMERICAL SCHEME AND THE CLIMATE PREDICTION

The retrospective numerical scheme(RNS)is a numerical computation scheme de- signed for multiple past value problems of the initial value in mathematics and considering the self- memory property of the system in physics.This paper briefly presents the historical background of RNS,elaborates the relation of the scheme with other difference schemes and other meteorological prediction methods,and introduces the application of RNS to the regional climatic self-memory model, simplified climate model,barotropic model,spectral model,and mesoscale model.At last,the paper sums up and points out the application perspective of the scheme and the direction for the future study.

A Study on Influence of Predictor Multicollinearity on Performance of the Stepwise Regression Prediction Equation

The prediction accuracy of the traditional stepwise regression prediction equation（SRPE）is affected by the multicollinearity among its predictors.This paper introduces the condition number analysis into the prediction modeling to minimize the multicollinearity in the SRPE.In the condition number prediction modeling,the condition number is used to select the combination of predictors with the lowest multicollinearity from the possible combinations of a number of candidate predictors（variables）,and the selected combination is then used to construct the condition number regression prediction equation（CNRPE）.This novel prediction modeling is performed in typhoon track prediction,which is a difficult task among meteorological disaster predictions.Six pairs of typhoon track latitude/longitude SRPEs and CNRPEs for July,August,and September are built by employing the traditional and the novel prediction modeling approaches,respectively,and by using a large number of identical modeling samples.The comparative analysis indicates that under the condition of the same candidate predictors（variables）and predictands（dependent variables）,although the fitting accuracy of the novel prediction models used for the historical samples of South China Sea（SCS）typhoon tracks is slightly lower than that of the traditional prediction models,the prediction accuracy for the independent samples is obviously improved,with the averaged prediction error of the novel models for July,August,and September being 153.9 kin,which is 75.3 km smaller than that of the traditional models（a reduction of 33%）.This is because the novel prediction modeling effectively minimizes the multicollinearity by computation and analysis of the condition number.It is shown further that when F=1.0,2.0,and 3.0,the average prediction errors of the traditional SRPEs are obviously larger than those of the CNRPEs.Moreover,extremely large and unreasonable prediction errors occur at some individual points of the typhoon track predicted by the SRPEs due to the multicollinearity existing in the combination of predictors.