A Dynamic Forecasting System with Applications in Production Logistics

Production logistics involve the co-ordination of ac tivities such as production and materials control (PMC), inventory management, p roduct life cycle management, etc. Those activities demand for an accurate forec asting model. However, the conventional methods of making sell and buy decision based on human forecast or conventional moving average and exponential smoothing methods is no longer be sufficient to meet the future need. Furthermore, the un derlying statistics of the market information change from time to time due to a number of reasons such as change of global economic environment, government poli cies and business risks. This demands for highly adaptive forecasting model which is robust enough to response and adapt well to the fast changes in the dat a characteristics, in other words, the trajectory of the "dynamic characteristic s" of the data. In this paper, an adaptive time-series modelling method was proposed for short -term dynamic forecasting. The method employs an autoregressive (AR) time-seri es model to carry out the forecasting process. A modified least mean square (MLM S) adaptive filter algorithm was established for adjusting the AR model coeffici ents so as to minimise the sum of squared of forecasting errors. A prototype dyn amic forecasting system was built based on the adaptive time-series modelling m ethod. Basically, the dynamic forecasting system can be divided into two phases, i.e. the Learning Phase and the Application Phase. The learning procedures star t with the determination of upper limit of the adaptation gain based on the conv ergence in the mean square criterion. Hence, the optimum ELMS filter parameters are determined using an iteration algorithm which changes each filter parameter i.e. the order, the adaptation gain andthe values initial coefficient vector on e by one inside a predetermined iteration range. The set of parameters which giv es the minimum value for sum of squared errors within the iteration range is sel ected as the optimum set of filter parameters. In the Application Phase, the sys tem is operated under a real-time environment. The sampled data is processed by the optimised ELMS filter and the forecasted data are calculated based on the a daptive time-series model. The error of forecasting is continuously monitored w ithin the predefined tolerance. When the system detects excessive forecasting er ror, a feedback alarm signal was issued for system re-calibration. Experimental results indicated that the convergence rate and sum of squared erro rs during initial adaptation could be significantly improved using the MLMS algorithm. The performance of the system was verified through a series of experi ments conducted on the forecast of materials demand and costing in productio n logistics. Satisfactory results were achieved with the forecast errors confini ng within in most instances. Further applications of the system can be found i n sales demand forecast, inventory management as well as collaborative planning, forecast and replenishment (CPFR) in logistics engineering.

Superiority of a Convolutional Neural Network Model over Dynamical Models in Predicting Central Pacific ENSO

The application of deep learning is fast developing in climate prediction,in which El Ni?o–Southern Oscillation(ENSO),as the most dominant disaster-causing climate event,is a key target.Previous studies have shown that deep learning methods possess a certain level of superiority in predicting ENSO indices.The present study develops a deep learning model for predicting the spatial pattern of sea surface temperature anomalies(SSTAs)in the equatorial Pacific by training a convolutional neural network(CNN)model with historical simulations from CMIP6 models.Compared with dynamical models,the CNN model has higher skill in predicting the SSTAs in the equatorial western-central Pacific,but not in the eastern Pacific.The CNN model can successfully capture the small-scale precursors in the initial SSTAs for the development of central Pacific ENSO to distinguish the spatial mode up to a lead time of seven months.A fusion model combining the predictions of the CNN model and the dynamical models achieves higher skill than each of them for both central and eastern Pacific ENSO.

Development of a global high-resolution marine dynamic environmental forecasting system

A project entitled‘Development of a Global High-resolution Marine Dynamic Environmental Forecasting System’has been funded by‘The Program on Marine Environmental Safety Guarantee’of The National Key Research and Development Program of China.This project will accomplish its objectives through basic theoretical research,model development and expansion,and system establishment and application,with a focus on four key issues separated into nine tasks.A series of research achievements have already been obtained,including datasets,observations,theories,and model results.

Application of Bayesian Dynamic Forecast in Anomaly Detection

A macroscopical anomaly detection method based on intrusion statistic and Bayesian dynamic forecast is presented. A large number of alert data that cannot be dealt with in time are always aggregated in control centers of large-scale intrusion detection systems. In order to improve the efficiency and veracity of intrusion analysis, the intrusion intensity values are picked from alert data and Bayesian dynamic forecast method is used to detect anomaly. The experiments show that the new method is effective on detecting macroscopical anomaly in large-scale intrusion detection systems.

Experimental Dynamical Forecast of an MJO Event Observed during TOGA-COARE Period

With a hybrid atmosphere-ocean coupled model we carried out an experimental forecast of a well documented Madden-Julian Oscillation (MJO) event that was observed during the period of Tropical Ocean Global Atmosphere Coupled Ocean-Atmosphere Response Experiment (TOGA-COARE). The observed event, originated in the western Indian Ocean around 6 January 1993, moved eastward with a phase speed of about 6.2 m s 1 and reached the dateline around February 1. The hybrid coupled model reasonably forecasts the MJO initiation in the western Indian Ocean, but the predicted MJO event propagates too slow (～ 4.4 m s 1 ). Results from previous observational studies using unprecedented humidity profiles obtained by NASA Aqua/AIRS satellite suggested that two potential physical processes may be responsible for this model caveat. After improving the cumulus parameterization scheme based on the observations, the model is able to forecast the same event one month ahead. Further sensitivity experiment confirms that the speed-up of model MJO propagation is primarily due to the improved convective scheme. Further, air-sea coupling plays an important role in maintaining the intensity of the predicted MJO. The results here suggest that MJO prediction skill is sensitive to model cumulus parameterization and air-sea coupling.

Parallelism and Optimization of Numerical Ocean Forecasting Model

According to the characteristics of Chinese marginal seas, the Marginal Sea Model of China(MSMC) has been developed independently in China. Because the model requires long simulation time, as a routine forecasting model, the parallelism of MSMC becomes necessary to be introduced to improve the performance of it. However, some methods used in MSMC, such as Successive Over Relaxation(SOR) algorithm, are not suitable for parallelism. In this paper, methods are developedto solve the parallel problem of the SOR algorithm following the steps as below. First, based on a 3D computing grid system, an automatic data partition method is implemented to dynamically divide the computing grid according to computing resources. Next, based on the characteristics of the numerical forecasting model, a parallel method is designed to solve the parallel problem of the SOR algorithm. Lastly, a communication optimization method is provided to avoid the cost of communication. In the communication optimization method, the non-blocking communication of Message Passing Interface(MPI) is used to implement the parallelism of MSMC with complex physical equations, and the process of communication is overlapped with the computations for improving the performance of parallel MSMC. The experiments show that the parallel MSMC runs 97.2 times faster than the serial MSMC, and root mean square error between the parallel MSMC and the serial MSMC is less than 0.01 for a 30-day simulation(172800 time steps), which meets the requirements of timeliness and accuracy for numerical ocean forecasting products.

STUDY OF THE EFFECTS OF REDUCING SYSTEMATIC ERRORS ON MONTHLY REGIONAL CLIMATE DYNAMICAL FORECAST

A nested-model system is constructed by embedding the regional climate model RegCM3 into a general circulation model for monthly-scale regional climate forecast over East China. The systematic errors are formulated for the region on the basis of 10-yr (1991-2000) results of the nested-model system, and of the datasets of the Climate Prediction Center (CPC) Merged Analysis of Precipitation (CMAP) and the temperature analysis of the National Meteorological Center (NMC), U.S.A., which are then used for correcting the original forecast by the system for the period 2001-2005. After the assessment of the original and corrected forecasts for monthly precipitation and surface air temperature, it is found that the corrected forecast is apparently better than the original, suggesting that the approach can be applied for improving monthly-scale regional climate dynamical forecast.

Tidal Level Response to Sea-Level Rise in the Yangtze Estuary

The rise of tidal level in tidal reaches induced by sea-level rise has a large impact on flood control and water supply for the regions around the estuary. This paper focuses on the variations of tidal level response along the tidal reaches in the Yangtze Estuary, as well as the impacts of upstream discharge on tidal level response, due to the sea-level rise of the East China Sea. Based on the Topex/Poseidon altimeter data obtained during the period 1993-2005, a stochastic dynamic analysis was performed and a forecast model was run to predict the sea-level rise of the East China Sea. Two- dimensional hydrodynamic numerical models downscaling from the East China Sea to estuarine areas were implemented to analyze the rise of tidal level along the tidal reaches. In response to the sea-level rise, the tidal wave characteristics change slightly in nearshore areas outside the estuaries, involving the tidal range and the duration of flood and ebb tide. The results show that the rise of tidal level in the tidal reaches due to the sea-level rise has upstream decreasing trends. The step between the stations of Zhangjiagang and Shiyiwei divides the tidal reaches into two parts, in which the tidal level response declines slightly. The rise of tidal level is 1-2.5 mm/a in the upper part, and 4-6 mm/a in the lower part. The stations of Jiangyin and Yanglin, as an example of the upper part and the lower part respectively, are extracted to analyze the impacts of upstream discharge on tidal level response to the sea-level rise. The relation between the rise of tidal level and the upstream discharge can be fitted well with a quadratic fimction in the upper part. However, the relation is too complicated to be fitted in the lower part because of the tide dominance. For comparison purposes, hourly tidal level observations at the stations of Xuliujing and Yanglin during the period 1993-2009 are adopted. In order to uniform the influence of upstream discharge on tidal level for a certain day each year, the hourly tidal level observations are corrected by the correlation between the increment of tidal level and the increment of daily mean upstream discharge. The rise of annual mean tidal level is evaluated. The resulting rise of tidal level at the stations of Xuliujing and Yanglin is 3.0 mm/a and 6.6 mm/a respectively, close to the rise of 5 mm/a according to the proposed relation between the rise of tidal level and the upstream discharge.

Study on Refined Forecast Method of Daily Maximum Temperature in Wugang City from July to September

[Objective] The aim was to study the refined forecast method of daily highest temperature in Wugang City from July to September. IM[ethod] By dint of ECMWF mode product and T231 in 2009 and 2010 and daily maximum temperature in the station in corresponding period, multi-factors similar forecast method to select forecast sample, multivariate regression multi-mode integration MOS method, after dynamic corrected mode error and regression error, dynamic forecast equation was concluded to formulate the daily maximum temperature forecast in 24 -120 h in Wugang City from July to September. [ Result] Through selection, error correction, the daily maximum temperature equation in Wugang City from July to September was concluded. Through multiple random sampling, F test was made to pass test with significant test of 0.1. [ Conclusionl The method integrated domestic and foreign forecast mode, made full use of useful information of many modes, absorbed each others advantages, con- sidered local regional environment, lessen mode and regression error, and improved forecast accuracy.

DOWNSCALING FORECAST OF MONTHLY PRECIPITATION OVER GUANGXI BASED ON BP NEURAL NETWORK MODEL

Variables fields such as enstrophy, meridional-wind and zonal-wind variables are derived from monthly 500 hPa geopotential height anomalous fields. In this work, we select original predictors from monthly 500-hPa geopotential height anomalous fields and their variables in June of 1958 - 2001, and determine comprehensive predictors by conducting empirical orthogonal function (EOF) respectively with the original predictors. A downscaling forecast model based on the back propagation (BP) neural network is built by use of the comprehensive predictors to predict the monthly precipitation in June over Guangxi with the monthly dynamic extended range forecast products. For comparison, we also build another BP neural network model with the same predictands by using the former comprehensive predictors selected from 500-hPa geopotential height anomalous fields in May to December of 1957 - 2000 and January to April of 1958 - 2001. The two models are tested and results show that the precision of superposition of the downscaling model is better than that of the one based on former comprehensive predictors, but the prediction accuracy of the downscaling model depends on the output of monthly dynamic extended range forecast.

Dynamically integrated regression model for online auction data

We propose a dynamically integrated regression model to predict the price of online auctions,including the final price.Different from existing models,the proposed method uses not only the historical price but also the information from bidding time.Consequently,the prediction accuracy is improved compared with the existing methods.An estimation method based on B-spline approximation is proposed for the estimation and the inference of parameters and nonparametric functions in this model.The minimax rate of convergence for the prediction risk and large-sample results including the consistency and the asymptotic normality are established.Simulation studies verify the finite sample performance and the appealing prediction accuracy and robustness.Finally,when we apply our method to a 7-day auction of iPhone 6s during December 2015 and March 2016,the proposed method predicts the ending price with a much smaller error than the existing models.

Dynamic downscaling of near-surface air temperature at the basin scale using WRF-a case study in the Heihe River Basin, China

The spatial resolution of general circulation models （GCMs） is too coarse to represent regional climate variations at the regional, basin, and local scales required for many environmental modeling and impact assessments. Weather research and forecasting model （WRF） is a nextgeneration, fully compressible, Euler non-hydrostatic mesoscale forecast model with a runtime hydrostatic option. This model is useful for downscaling weather and climate at the scales from one kilometer to thousands of kilometers, and is useful for deriving meteorological parameters required for hydrological simulation too. The objective of this paper is to validate WRF simulating 5 km/ 1 h air temperatures by daily observed data of China Meteorological Administration （CMA） stations, and by hourly in-situ data of the Watershed Allied Telemetry Experimental Research Project. The daily validation shows that the WRF simulation has good agreement with the observed data; the R2 between the WRF simulation and each station is more than 0.93; the absolute of meanbias error （MBE） for each station is less than 2℃; and the MBEs of Ejina, Mazongshan and Alxa stations are near zero, with R2 is more than 0.98, which can be taken as an unbiased estimation. The hourly validation shows that the WRF simulation can capture the basic trend of observed data, the MBE of each site is approximately 2℃, the R2 of each site is more than 0.80, with the highest at 0.95, and the computed and observed surface air temperature series show a significantly similar trend.

COMPARATIVE EXPERIMENTS OF DYNAMICAL FORECAST AND STATISTICAL FORECAST

After analyzing the advantages and disadvantages of dynamical system and statistical system. some simple models with the equations of Lorenz system and auto-regresslon model have been respectively set up,and comparative experiments conducted.The result of the research demonstrates that in chaotic parametric domain,the accuracy of statistical forecast is higher than that of dynamical forecast,while in non-chaotic parametric domain,dynamical forecast is more accurate than statistical forecast.

The dynamic forecast method of convective vorticity vector

In this paper we introduce the convective vorticity vector and its application in the forecast and diagnosis of rainstorm.Convective vorticity vector is a parameter of vector field,different from scalar field,it contains more important information of physical quantities,so it could not be replaced.Considering the irresistible importance of vector field we will introduce the theory of vector field and its dynamic forecast method.With the convective vorticity vector and its vertical component's tendency equation,diagnostic analysis on the heavy-rainfall event caused by landfall typhoon“Morakot”in the year 2009 is conducted.The result shows that,the abnormal values of convective vorticity vector always changes with the development of the observed precipitation region,and their horizontal distribution is quite similar.Analysis reveals a certain correspondence between the convective vorticity vector and the observed 6-h accumulated surface rainfall,they are significantly related.The convective vorticity vector is capable of describing the typical vertical structure of dynamical and thermodynamic fields of precipitation system,so it is closely related to the occurrence and development of precipitation system and could have certain relation with the surface rainfall regions.

Numerical study of the effects of Planetary Boundary Layer structure on the pollutant dispersion within built-up areas

The effects of different Planetary Boundary Layer（PBL） structures on pollutant dispersion processes within two idealized street canyon configurations and a realistic urban area were numerically examined by a Computational Fluid Dynamics（CFD） model. The boundary conditions of different PBL structures/conditions were provided by simulations of the Weather Researching and Forecasting model. The simulated results of the idealized 2D and 3D street canyon experiments showed that the increment of PBL instability favored the downward transport of momentum from the upper flow above the roof to the pedestrian level within the street canyon. As a result, the flow and turbulent fields within the street canyon under the more unstable PBL condition are stronger. Therefore, more pollutants within the street canyon would be removed by the stronger advection and turbulent diffusion processes under the unstable PBL condition. On the contrary, more pollutants would be concentrated in the street canyon under the stable PBL condition. In addition, the simulations of the realistic building cluster experiments showed that the density of buildings was a crucial factor determining the dynamic effects of the PBL structure on the flow patterns. The momentum field within a denser building configuration was mostly transported from the upper flow, and was more sensitive to the PBL structures than that of the sparser building configuration. Finally, it was recommended to use the Mellor-Yamada-Nakanishi-Niino（MYNN） PBL scheme, which can explicitly output the needed turbulent variables, to provide the boundary conditions to the CFD simulation.