How Do Deep Learning Forecasting Models Perform for Surface Variables in the South China Sea Compared to Operational Oceanography Forecasting Systems?

It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.

Regional Storm Surge Forecast Method Based on a Neural Network and the Coupled ADCIRC-SWAN Model

Timely and accurate forecasting of storm surges can effectively prevent typhoon storm surges from causing large economic losses and casualties in coastal areas.At present,numerical model forecasting consumes too many resources and takes too long to compute,while neural network forecasting lacks regional data to train regional forecasting models.In this study,we used the DUAL wind model to build typhoon wind fields,and constructed a typhoon database of 75 processes in the northern South China Sea using the coupled Advanced Circulation-Simulating Waves Nearshore(ADCIRC-SWAN)model.Then,a neural network with a Res-U-Net structure was trained using the typhoon database to forecast the typhoon processes in the validation dataset,and an excellent storm surge forecasting effect was achieved in the Pearl River Estuary region.The storm surge forecasting effect of stronger typhoons was improved by adding a branch structure and transfer learning.

Enhancing Deep Learning Soil Moisture Forecasting Models by Integrating Physics-based Models

Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient representation of land-surface processes.In addition to PB models,deep learning(DL)models have been widely used in SM predictions recently.However,few pure DL models have notably high success rates due to lacking physical information.Thus,we developed hybrid models to effectively integrate the outputs of PB models into DL models to improve SM predictions.To this end,we first developed a hybrid model based on the attention mechanism to take advantage of PB models at each forecast time scale(attention model).We further built an ensemble model that combined the advantages of different hybrid schemes(ensemble model).We utilized SM forecasts from the Global Forecast System to enhance the convolutional long short-term memory(ConvLSTM)model for 1–16 days of SM predictions.The performances of the proposed hybrid models were investigated and compared with two existing hybrid models.The results showed that the attention model could leverage benefits of PB models and achieved the best predictability of drought events among the different hybrid models.Moreover,the ensemble model performed best among all hybrid models at all forecast time scales and different soil conditions.It is highlighted that the ensemble model outperformed the pure DL model over 79.5%of in situ stations for 16-day predictions.These findings suggest that our proposed hybrid models can adequately exploit the benefits of PB model outputs to aid DL models in making SM predictions.

Comparison among the UECM Model, and the Composite Model in Forecasting Malaysian Imports

For more than a century, forecasting models have been crucial in a variety of fields. Models can offer the most accurate forecasting outcomes if error terms are normally distributed. Finding a good statistical model for time series predicting imports in Malaysia is the main target of this study. The decision made during this study mostly addresses the unrestricted error correction model (UECM), and composite model (Combined regression—ARIMA). The imports of Malaysia from the first quarter of 1991 to the third quarter of 2022 are employed in this study’s quarterly time series data. The forecasting outcomes of the current study demonstrated that the composite model offered more probabilistic data, which improved forecasting the volume of Malaysia’s imports. The composite model, and the UECM model in this study are linear models based on responses to Malaysia’s imports. Future studies might compare the performance of linear and nonlinear models in forecasting.

A Hybrid Model Evaluation Based on PCA Regression Schemes Applied to Seasonal Precipitation Forecast

Possible changes in the structure and seasonal variability of the subtropical ridge may lead to changes in the rainfall’s variability modes over Caribbean region. This generates additional difficulties around water resource planning, therefore, obtaining seasonal prediction models that allow these variations to be characterized in detail, it’s a concern, specially for island states. This research proposes the construction of statistical-dynamic models based on PCA regression methods. It is used as predictand the monthly precipitation accumulated, while the predictors (6) are extracted from the ECMWF-SEAS5 ensemble mean forecasts with a lag of one month with respect to the target month. In the construction of the models, two sequential training schemes are evaluated, obtaining that only the shorter preserves the seasonal characteristics of the predictand. The evaluation metrics used, where cell-point and dichotomous methodologies are combined, suggest that the predictors related to sea surface temperatures do not adequately represent the seasonal variability of the predictand, however, others such as the temperature at 850 hPa and the Outgoing Longwave Radiation are represented with a good approximation regardless of the model chosen. In this sense, the models built with the nearest neighbor methodology were the most efficient. Using the individual models with the best results, an ensemble is built that allows improving the individual skill of the models selected as members by correcting the underestimation of precipitation in the dynamic model during the wet season, although problems of overestimation persist for thresholds lower than 50 mm.

Short-Term Wind Speed Forecasts over the Pearl River Estuary:Numerical Model Evaluation and Deterministic Post-Processing

The Pearl River Estuary(PRE)is one of China’s busiest shipping hubs and fishery production centers,as well as a region with abundant island tourism and wind energy resources,which calls for accurate short-term wind forecasts.First,this study evaluated three operational numerical models,i.e.,ECMWF-EC,NCEP-GFS,and CMA-GD,for their ability to predict short-term wind speed over the PRE against in-situ observations during 2018-2021.Overall,ECMWF-EC out-performs other models with an average RMSE of 2.24 m s^(-1)and R of 0.57,but the NCEP-GFS performs better in the case of strong winds.Then,various bias correction and multi-model ensemble(MME)methods are used to perform the deterministic post-processing using a local and lead-specific scheme.Two-factor model output statistics(MOS2)is the optimal bias correction method for reducing(increasing)the overall RMSE(R)to 1.62(0.70)m s^(-1),demonstrating the benefits of considering both initial and lead-specific information.Intercomparison of MME results reveals that Multiple linear regression(MLR)presents superior skills,followed by random forest(RF),but it is slightly inferior to MOS2,particularly for the first few forecasting hours.Furthermore,the incorporation of additional features in MLR reduces the overall RMSE to 1.53 m s^(-1)and increases R to 0.74.Similarly,RF presents comparable results,and both outperform MOS2 in terms of correcting their deficiencies at the first few lead hours and limiting the error growth rate.Despite the satisfactory skill of deterministic post-processing techniques,they are unable to achieve a balanced performance between mean and extreme statistics.This highlights the necessity for further development of probabilistic forecasts.

Predictability Study of Weather and Climate Events Related to Artificial Intelligence Models

Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather and climate phenomena.In the past few decades,dynamical numerical models have been the primary tools for predictability studies,achieving significant progress.Nowadays,with the advances in artificial intelligence(AI)techniques and accumulations of vast meteorological data,modeling weather and climate events using modern data-driven approaches is becoming trendy,where FourCastNet,Pangu-Weather,and GraphCast are successful pioneers.In this perspective article,we suggest AI models should not be limited to forecasting but be expanded to predictability studies,leveraging AI's advantages of high efficiency and self-contained optimization modules.To this end,we first remark that AI models should possess high simulation capability with fine spatiotemporal resolution for two kinds of predictability studies.AI models with high simulation capabilities comparable to numerical models can be considered to provide solutions to partial differential equations in a data-driven way.Then,we highlight several specific predictability issues with well-determined nonlinear optimization formulizations,which can be well-studied using AI models,holding significant scientific value.In addition,we advocate for the incorporation of AI models into the synergistic cycle of the cognition–observation–model paradigm.Comprehensive predictability studies have the potential to transform“big data”to“big and better data”and shift the focus from“AI for forecasts”to“AI for science”,ultimately advancing the development of the atmospheric and oceanic sciences.

Synoptic Verification of Precipitation Forecast of Three NWP Models from May to August of 2008 in Liaoning Province

In order to evaluate the precipitation forecast performance of mesoscale numerical model in Northeast China,mesoscale model in Liaoning Province and T213 model,and improve the ability to use their forecast products for forecasters,the synoptic verifications of their 12 h accumulated precipitation forecasts of 3 numerical modes from May to August in 2008 were made on the basis of different systems impacting weather in Liaoning Province.The time limitations were 24,36,48 and 60 h.The verified contents included 6 aspects such as intensity and position of precipitation center,intensity,location,scope and moving velocity of precipitation main body.The results showed that the three models had good forecasting capability for precipitation in Liaoning Province,but the cupacity of each model was obviously different.

TIME SERIES NEURAL NETWORK MODEL FOR HYDROLOGIC FORECASTING

Time series analysis plays an important role in hydrologic forecasting,while the key to this analysis is to establish a proper model.This paper presents a time series neural network model with back propagation procedure for hydrologic forecasting.Free from the disadvantages of previous models,the model can be parallel to operate information flexibly and rapidly.It excels in the ability of nonlinear mapping and can learn and adjust by itself,which gives the model a possibility to describe the complex nonlinear hydrologic process.By using directly a training process based on a set of previous data, the model can forecast the time series of stream flow.Moreover,two practical examples were used to test the performance of the time series neural network model.Results confirm that the model is efficient and feasible.

River channel flood forecasting method of coupling wavelet neural network with autoregressive model

Based on analyzing the limitations of the commonly used back-propagation neural network （BPNN）, a wavelet neural network （WNN） is adopted as the nonlinear river channel flood forecasting method replacing the BPNN. The WNN has the characteristics of fast convergence and improved capability of nonlinear approximation. For the purpose of adapting the timevarying characteristics of flood routing, the WNN is coupled with an AR real-time correction model. The AR model is utilized to calculate the forecast error. The coefficients of the AR real-time correction model are dynamically updated by an adaptive fading factor recursive least square（RLS） method. The application of the flood forecasting method in the cross section of Xijiang River at Gaoyao shows its effectiveness.

Application of discrete choice model in trip mode structure forecast:a case study of Bengbu

In order to find the main factors that influence the urban traffic structure,a relational model between the travelers＇ characteristics and the trip mode choice is built.The data of urban residents＇ characteristics are obtained from statistical data,while the trip mode split data is collected through a trip survey in Bengbu.In addition,the discrete choice model is adopted to build the functional relationship between the mode choice and the travelers＇ personal characteristics,as well as family characteristics and trip characteristics.The model shows that the relationship between the mode split and the personal,as well as family and trip characteristics is stable and changes little as the time changes.Deduced by the discrete model,the mode split result is relatively accurate and can be feasibly used for trip mode structure forecasts.Furthermore,the proposed model can also contribute to find the key influencing factors on trip mode choice,and restructure or optimize the urban trip mode structure.

The Application of ARIMA Model in Forecasting of PDSI in Henan Province

[Objective] The aim was to establish drought forecasting model with high precision. [Method] With an ARIMA regression model, the research performed Palmer Drought mode（PDSI） time series modeling analysis of Henan Province based on PDSI time series and DPS（Data Processing Software） in order to build drought forecasting model. [Result] It is feasible to perform drought forecasting with appropriate parameters. [Conclusion] ARIMA model is practical and more precise in PDSI-based drought analysis and forecasting.

Short Term Load Forecasting Using Subset Threshold Auto Regressive Model

The subset threshold auto regressive (SSTAR) model, which is capable of reproducing the limit cycle behavior of nonlinear time series, is introduced. The algorithm for fitting the sampled data with SSTAR model is proposed and applied to model and forecast power load. Numerical example verifies that desirable accuracy of short term load forecasting can be achieved by using the SSTAR model.

The Water-Bearing Numerical Model and Its Operational Forecasting Experiments PartII: The Operational Forecasting Experiments

おhe water-bearing numerical model is undergone all round examinations during the operational forecasting experiments from 1994 to 1996. A lot of difficult problems arising from the model′s water-bearing are successfully resolved in these experiments through developing and using a series of technical measures. The operational forecasting running of the water-bearing numerical model is realized stably and reliably, and satisfactory forecasts are obtained.

A GCM-Based Forecasting Model for the Landfall of Tropical Cyclones in China

A statistical dynamic model for forecasting Chinese landfall of tropical cyclones （CLTCs） was developed based on the empirical relationship between the observed CLTC variability and the hindcast atmospheric circulations from the Pusan National University coupled general circulation model （PNU-CGCM）.In the last 31 years,CLTCs have shown strong year-to-year variability,with a maximum frequency in 1994 and a minimum frequency in 1987.Such features were well forecasted by the model.A cross-validation test showed that the correlation between the observed index and the forecasted CLTC index was high,with a coefficient of 0.71.The relative error percentage （16.3%） and root-mean-square error （1.07） were low.Therefore the coupled model performs well in terms of forecasting CLTCs;the model has potential for dynamic forecasting of landfall of tropical cyclones.

Interval grey number sequence prediction by using non-homogenous exponential discrete grey forecasting model

This paper aims to study a new grey prediction approach and its solution for forecasting the main system variable whose accurate value could not be collected while the potential value set could be defined. Based on the traditional nonhomogenous discrete grey forecasting model（NDGM）, the interval grey number and its algebra operations are redefined and combined with the NDGM model to construct a new interval grey number sequence prediction approach. The solving principle of the model is analyzed, the new accuracy evaluation indices, i.e. mean absolute percentage error of mean value sequence（MAPEM） and mean percent of interval sequence simulating value set covered（MPSVSC）, are defined and, the procedure of the interval grey number sequence based the NDGM（IG-NDGM） is given out. Finally, a numerical case is used to test the modelling accuracy of the proposed model. Results show that the proposed approach could solve the interval grey number sequence prediction problem and it is much better than the traditional DGM（1,1） model and GM（1,1） model.

Forecasting Method of Stock Market Volatility in Time Series Data Based on Mixed Model of ARIMA and XGBoost

Stock price forecasting is an important issue and interesting topic in financial markets.Because reasonable and accurate forecasts have the potential to generate high economic benefits,many researchers have been involved in the study of stock price forecasts.In this paper,the DWT-ARIMAGSXGB hybrid model is proposed.Firstly,the discrete wavelet transform is used to split the data set into approximation and error parts.Then the ARIMA(0,1,1),ARIMA(1,1,0),ARIMA(2,1,1)and ARIMA(3,1,0)models respectively process approximate partial data and the improved xgboost model(GSXGB)handles error partial data.Finally,the prediction results are combined using wavelet reconstruction.According to the experimental comparison of 10 stock data sets,it is found that the errors of DWT-ARIMA-GSXGB model are less than the four prediction models of ARIMA,XGBoost,GSXGB and DWT-ARIMA-XGBoost.The simulation results show that the DWT-ARIMA-GSXGB stock price prediction model has good approximation ability and generalization ability,and can fit the stock index opening price well.And the proposed model is considered to greatly improve the predictive performance of a single ARIMA model or a single XGBoost model in predicting stock prices.

Forecasting China’s natural gas consumption based on a combination model

Ensuring a sufficient energy supply is essential to a country. Natural gas constitutes a vital part in energy supply and therefore forecasting natural gas consumption reliably and accurately is an essential part of a country＇s energy policy. Over the years, studies have shown that a combinative model gives better projected results compared to a single model. In this study, we used Polynomial Curve and Moving Average Combination Projection （PCMACP） model to estimate the future natural gas consumption in China from 2009 to 2015. The new proposed PCMACP model shows more reliable and accurate results： its Mean Absolute Percentage Error （MAPE） is less than those of any previous models within the investigated range. According to the PCMACP model, the average annual growth rate will increase for the next 7 years and the amount of natural gas consumption will reach 171600 million cubic meters in 2015 in China.

Development of a fine-resolution atmosphere-wave-ocean coupled forecasting model for the South China Sea and its adjacent seas

A 72-h fine-resolution atmosphere-wave-ocean coupled forecasting system was developed for the South China Sea and its adjacent seas. The forecasting model domain covers from from 15°S to 45°N in latitude and 99°E to135°E in longitude including the Bohai Sea, the Yellow Sea, the East China Sea, the South China Sea and the Indonesian seas. To get precise initial conditions for the coupled forecasting model, the forecasting system conducts a 24-h hindcast simulation with data assimilation before forecasting. The Ensemble Adjustment Kalman Filter(EAKF) data assimilation method was adopted for the wave model MASNUM with assimilating Jason-2 significant wave height(SWH) data. The EAKF data assimilation method was also introduced to the ROMS model with assimilating sea surface temperature(SST), mean absolute dynamic topography(MADT) and Argo profiles data. To improve simulation of the structure of temperature and salinity, the vertical mixing scheme of the ocean model was improved by considering the surface wave induced vertical mixing and internal wave induced vertical mixing. The wave and current models were integrated from January 2014 to October 2015 driven by the ECMWF reanalysis 6 hourly mean dataset with data assimilation. Then the coupled atmosphere-wave-ocean forecasting system was carried out 14 months operational running since November 2015. The forecasting outputs include atmospheric forecast products, wave forecast products and ocean forecast products. A series of observation data are used to evaluate the coupled forecasting results, including the wind, SHW, ocean temperature and velocity.The forecasting results are in good agreement with observation data. The prediction practice for more than one year indicates that the coupled forecasting system performs stably and predict relatively accurate, which can support the shipping safety, the fisheries and the oil exploitation.

Comparison of performance of statistical models in forecasting monthly streamflow of Kizil River,China

This paper presents the application of autoregressive integrated moving average （ARIMA）, seasonal ARIMA （SARIMA）, and Jordan-Elman artificial neural networks （ANN） models in forecasting the monthly streamflow of the Kizil River in Xinjiang, China. Two different types of monthly streamflow data （original and deseasonalized data） were used to develop time series and Jordan-Elman ANN models using previous flow conditions as predictors. The one-month-ahead forecasting performances of all models for the testing period （1998-2005） were compared using the average monthly flow data from the Kalabeili gaging station on the Kizil River. The Jordan-Elman ANN models, using previous flow conditions as inputs, resulted in no significant improvement over time series models in one-month-ahead forecasting. The results suggest that the simple time series models （ARIMA and SARIMA） can be used in one-month-ahead streamflow forecasting at the study site with a simple and explicit model structure and a model performance similar to the Jordan-Elman ANN models.