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...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.展开更多
Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific ...Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific basis for governance and prevention efforts.In this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of data.Graph generative network(GGN)is used to process time-series meteorological data with complex structures.The graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the model.In addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval prediction.With the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale data.The PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.展开更多
Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational...Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational techniques,and experience.This made providing meteorological services for this event particularly challenging.The China Meteorological Administration(CMA)Earth System Modeling and Prediction Centre,achieved breakthroughs in research on short-and medium-term deterministic and ensemble numerical predictions.Several key technologies crucial for precise winter weather services during the Winter Olympics were developed.A comprehensive framework,known as the Operational System for High-Precision Weather Forecasting for the Winter Olympics,was established.Some of these advancements represent the highest level of capabilities currently available in China.The meteorological service provided to the Beijing 2022 Games also exceeded previous Winter Olympic Games in both variety and quality.This included achievements such as the“100-meter level,minute level”downscaled spatiotemporal resolution and forecasts spanning 1 to 15 days.Around 30 new technologies and over 60 kinds of products that align with the requirements of the Winter Olympics Organizing Committee were developed,and many of these techniques have since been integrated into the CMA’s operational national forecasting systems.These accomplishments were facilitated by a dedicated weather forecasting and research initiative,in conjunction with the preexisting real-time operational forecasting systems of the CMA.This program represents one of the five subprograms of the WMO’s high-impact weather forecasting demonstration project(SMART2022),and continues to play an important role in their Regional Association(RA)II Research Development Project(Hangzhou RDP).Therefore,the research accomplishments and meteorological service experiences from this program will be carried forward into forthcoming highimpact weather forecasting activities.This article provides an overview and assessment of this program and the operational national forecasting systems.展开更多
A dual-resolution（DR） version of a regional ensemble Kalman filter（EnKF）-3D ensemble variational（3DEnVar） coupled hybrid data assimilation system is implemented as a prototype for the operational Rapid Refresh f...A dual-resolution（DR） version of a regional ensemble Kalman filter（EnKF）-3D ensemble variational（3DEnVar） coupled hybrid data assimilation system is implemented as a prototype for the operational Rapid Refresh forecasting system. The DR 3DEnVar system combines a high-resolution（HR） deterministic background forecast with lower-resolution（LR） EnKF ensemble perturbations used for flow-dependent background error covariance to produce a HR analysis. The computational cost is substantially reduced by running the ensemble forecasts and EnKF analyses at LR. The DR 3DEnVar system is tested with 3-h cycles over a 9-day period using a 40/13-km grid spacing combination. The HR forecasts from the DR hybrid analyses are compared with forecasts launched from HR Gridpoint Statistical Interpolation（GSI） 3D variational（3DVar）analyses, and single LR hybrid analyses interpolated to the HR grid. With the DR 3DEnVar system, a 90% weight for the ensemble covariance yields the lowest forecast errors and the DR hybrid system clearly outperforms the HR GSI 3DVar.Humidity and wind forecasts are also better than those launched from interpolated LR hybrid analyses, but the temperature forecasts are slightly worse. The humidity forecasts are improved most. For precipitation forecasts, the DR 3DEnVar always outperforms HR GSI 3DVar. It also outperforms the LR 3DEnVar, except for the initial forecast period and lower thresholds.展开更多
In order to satisfy the increasing demand for the marine forecasting capacity,the Bohai Sea,the Yellow Sea and the East China Sea Operational Oceanography Forecasting System(BYEOFS)has been upgraded and improved to Ve...In order to satisfy the increasing demand for the marine forecasting capacity,the Bohai Sea,the Yellow Sea and the East China Sea Operational Oceanography Forecasting System(BYEOFS)has been upgraded and improved to Version 2.0.Based on the Regional Ocean Modeling System(ROMS),a series of comparative experiments were conducted during the improvement process,including correcting topography,changing sea surface atmospheric forcing mode,adjusting open boundary conditions,and considering atmospheric pressure correction.(1)After the topography correction,the volume transport and meridional velocity maximum of Yellow Sea Warm Current increase obviously and the unreasonable bending of its axis around 36.1°N,123.5°E disappears.(2)After the change of sea surface forcing mode,an effective negative feedback mechanism is formed between predicted sea surface temperature(SST)by the ocean model and sea surface radiation fluxes fields.The simulation errors of SST decreased significantly,and the annual average of root-mean-square error(RMSE)decreased by about 18%.(3)The change of the eastern lateral boundary condition of baroclinic velocity from mixed Radiation-Nudging to Clamped makes the unreasonable westward current in Tsushima Strait disappear.(4)The adding of mean sea level pressure correction option which forms the mean sea level gradient from the Bohai Sea and the Yellow Sea to the western Pacific in winter and autumn is helpful to increasing the fluctuation of SLA and outflow of the Yellow Sea when the cold high air pressure system controls the Yellow Sea area.展开更多
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 D...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.展开更多
Based on the domestic and foreign related research methods, the life meteorological index forecasting system of Wuhu City was compiled using database and network as well as computer language. The system realized the a...Based on the domestic and foreign related research methods, the life meteorological index forecasting system of Wuhu City was compiled using database and network as well as computer language. The system realized the automation process for the generation of life index forecasting products from local situation of Wuhu City and forecasting data, which could get the latest service products dispensing with manual intervention. The development of the system not only made the operation process of the life meteorological index of Wuhu City more time-saving and efficient, but also made the results more scientific and rigorous.展开更多
An air pollution forecast system,ARIA Regional,was implemented in 2007–2008 at the Beijing Municipality Environmental Monitoring Center,providing daily forecast of main pollutant concentrations.The chemistry-transpor...An air pollution forecast system,ARIA Regional,was implemented in 2007–2008 at the Beijing Municipality Environmental Monitoring Center,providing daily forecast of main pollutant concentrations.The chemistry-transport model CHIMERE was coupled with the dust emission model MB95 for restituting dust storm events in springtime so as to improve forecast results.Dust storm events were sporadic but could be extremely intense and then control air quality indexes close to the source areas but also far in the Beijing area.A dust episode having occurred at the end of May 2008 was analyzed in this article,and its impact of particulate matter on the Chinese air pollution index （API） was evaluated.Following our estimation,about 23 Tg of dust were emitted from source areas in Mongolia and in the Inner Mongolia of China,transporting towards southeast.This episode of dust storm influenced a large part of North China and East China,and also South Korea.The model result was then evaluated using satellite observations and in situ data.The simulated daily concentrations of total suspended particulate at 6：00 UTC had a similar spatial pattern with respect to OMI satellite aerosol index.Temporal evolution of dust plume was evaluated by comparing dust aerosol optical depth （AOD） calculated from the simulations with AOD derived from MODIS satellite products.Finally,the comparison of reported Chinese API in Beijing with API calculated from the simulation including dust emissions had showed the significant improvement of the model results taking into accountmineral dust correctly.展开更多
In this study,an operational forecasting system of sea dike risk in the southern Zhejiang Province,South China was developed based on a coupled storm-surge and wave model.This forecasting system is important because o...In this study,an operational forecasting system of sea dike risk in the southern Zhejiang Province,South China was developed based on a coupled storm-surge and wave model.This forecasting system is important because of the high cost of storm-surge damage and the need for rapid emergency planning.A comparison with astronomical tides in 2016 and the validation of storm surges and high water marks of 20 typhoons verified that the forecast system has a good simulation ability.The system can forecast relatively realistic water levels and wave heights as shown under the parametric atmospheric forces simulated in a case study;the sea dikes in credible high risk were mainly located in the estuaries,rivers,and around the islands in the southern Zhejiang.Therefore,the forecast system is applicable in the southern Zhejiang with a support to the effective prevention from typhoon storm-surge damage.展开更多
An operational ocean circulation-surface wave coupled forecasting system for the seas off China and adjacent areas（OCFS-C） is developed based on parallelized circulation and wave models. It has been in operation sin...An operational ocean circulation-surface wave coupled forecasting system for the seas off China and adjacent areas（OCFS-C） is developed based on parallelized circulation and wave models. It has been in operation since November 1, 2007. In this paper we comprehensively present the simulation and verification of the system, whose distinguishing feature is that the wave-induced mixing is coupled in the circulation model. In particular, with nested technique the resolution in the China＇s seas has been updated to（1/24）° from the global model with（1/2）°resolution. Besides, daily remote sensing sea surface temperature（SST） data have been assimilated into the model to generate a hot restart field for OCFS-C. Moreover, inter-comparisons between forecasting and independent observational data are performed to evaluate the effectiveness of OCFS-C in upper-ocean quantities predictions, including SST, mixed layer depth（MLD） and subsurface temperature. Except in conventional statistical metrics, non-dimensional skill scores（SS） is also used to evaluate forecast skill. Observations from buoys and Argo profiles are used for lead time and real time validations, which give a large SS value（more than 0.90）. Besides, prediction skill for the seasonal variation of SST is confirmed. Comparisons of subsurface temperatures with Argo profiles data indicate that OCFS-C has low skill in predicting subsurface temperatures between 100 m and 150 m. Nevertheless, inter-comparisons of MLD reveal that the MLD from model is shallower than that from Argo profiles by about 12 m, i.e., OCFS-C is successful and steady in MLD predictions. Validation of 1-d, 2-d and 3-d forecasting SST shows that our operational ocean circulation-surface wave coupled forecasting model has reasonable accuracy in the upper ocean.展开更多
The floods in river Mahanadi delta are due to either dam release of Hirakud or due to contribution of intercepted catchment between Hirakud dam and delta. It is seen from post-Hirakud periods (1958) that out of 19 flo...The floods in river Mahanadi delta are due to either dam release of Hirakud or due to contribution of intercepted catchment between Hirakud dam and delta. It is seen from post-Hirakud periods (1958) that out of 19 floods 14 are due to intercepted catchment contribution. The existing flood forecasting systems are mostly for upstream catchment, forecasting the inflow to reservoir, whereas the downstream catchment is devoid of a sound flood forecasting system. Therefore, in this study an attempt has been made to develop a workable forecasting system for downstream catchment. Instead of taking the flow time series concurrent flood peaks of 12 years of base and forecasting stations with its corresponding travel time are considered for analysis. Both statistical method and ANN based approach are considered for finding the peak to reach at delta head with its corresponding travel time. The travel time has been finalized adopting clustering techniques, there by differentiating high, medium and low peaks. The method is simple and it does not take into consideration the rainfall and other factors in the intercepted catchment. A comparison between both methods are tested and it is found that the ANN methods are better beyond the calibration range over statistical method and the efficiency of either methods reduces as the prediction reach is extended. However, it is able to give the peak discharge at delta head before 24 hour to 37 hour for high to low peaks.展开更多
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 as...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.展开更多
Meteo-hydrological forecasting models are an effective way to generate high-resolution gridded rainfall data for water source research and flood forecast.The quality of rainfall data in terms of both intensity and dis...Meteo-hydrological forecasting models are an effective way to generate high-resolution gridded rainfall data for water source research and flood forecast.The quality of rainfall data in terms of both intensity and distribution is very important for establishing a reliable meteo-hydrological forecasting model.To improve the accuracy of rainfall data,the successive correction method is introduced to correct the bias of rainfall,and a meteo-hydrological forecasting model based on WRF and WRF-Hydro is applied for streamflow forecast over the Zhanghe River catchment in China.The performance of WRF rainfall is compared with the China Meteorological Administration Multi-source Precipitation Analysis System(CMPAS),and the simulated streamflow from the model is further studied.It shows that the corrected WRF rainfall is more similar to the CMPAS in both temporal and spatial distribution than the original WRF rainfall.By contrast,the statistical metrics of the corrected WRF rainfall are better.When the corrected WRF rainfall is used to drive the WRF-Hydro model,the simulated streamflow of most events is significantly improved in both hydrographs and volume than that of using the original WRF rainfall.Among the studied events,the largest improvement of the NSE is from-0.68 to 0.67.It proves that correcting the bias of WRF rainfall with the successive correction method can greatly improve the performance of streamflow forecast.In general,the WRF/WRF-Hydro meteo-hydrological forecasting model based on the successive correction method has the potential to provide better streamflow forecast in the Zhanghe River catchment.展开更多
Effective technology for wind direction forecasting can be realized using the recent advances in machine learning.Consequently,the stability and safety of power systems are expected to be significantly improved.Howeve...Effective technology for wind direction forecasting can be realized using the recent advances in machine learning.Consequently,the stability and safety of power systems are expected to be significantly improved.However,the unstable and unpredictable qualities of the wind predict the wind direction a challenging problem.This paper proposes a practical forecasting approach based on the weighted ensemble of machine learning models.This weighted ensemble is optimized using a whale optimization algorithm guided by particle swarm optimization(PSO-Guided WOA).The proposed optimized weighted ensemble predicts the wind direction given a set of input features.The conducted experiments employed the wind power forecasting dataset,freely available on Kaggle and developed to predict the regular power generation at seven wind farms over forty-eight hours.The recorded results of the conducted experiments emphasize the effectiveness of the proposed ensemble in achieving accurate predictions of the wind direction.In addition,a comparison is established between the proposed optimized ensemble and other competing optimized ensembles to prove its superiority.Moreover,statistical analysis using one-way analysis of variance(ANOVA)and Wilcoxon’s rank-sum are provided based on the recorded results to confirm the excellent accuracy achieved by the proposed optimized weighted ensemble.展开更多
Recently the importance of intellectual property has been increased. There has been various ways of research on analy- sis of companies, forecast of technology and so on through patents and many investments of money a...Recently the importance of intellectual property has been increased. There has been various ways of research on analy- sis of companies, forecast of technology and so on through patents and many investments of money and time. Unlike traditional method of patent analysis such as company analysis, forecasting technologies, this research is to suggest the ways to forecast registration and rejection of patents which help minimize the efforts to register patents. To do so, in- formation such as inventors, applicants, application date, and IPC codes were extracted to be used as input variables for analyzing Bayesian network. Especially, among various forms of Bayesian network, we used Tree Augmented NBN (TAN) to forecast registration and rejection of patent. This is because, TAN was assumed to have dependence between variables. As a result of this Bayesian network, it was shown that there are nearly more than 80% of accuracy to fore- cast registration and rejection of patents. Therefore, we expect the minimization of time and cost of registration by forecasting registration and rejection of R&D patent through this research.展开更多
Transport system is a time-varying, huge and complex system. In order to have the traffic management department make pre-appropriate traffic management measures to adjust the traffic management control program, and re...Transport system is a time-varying, huge and complex system. In order to have the traffic management department make pre-appropriate traffic management measures to adjust the traffic management control program, and release travel information to travelers, to provide optimal path options to ensure that the transport system operates efficiently and safely, we have to monitor the changing of the state of road traffic and to accurately evaluate the state of the traffic, then to predict the future state of traffic. This paper represents the construction of the road traffic flow simulation including the logical structure and the physical structure, and introduces the system functions of forecasting system in Beijing.展开更多
[Objectives]To assess the effectiveness of the intelligent small insect monitoring and forecasting system developed by Zhejiang Top Cloud-Agri Technology Co.,Ltd.in monitoring,providing early warnings,and identifying ...[Objectives]To assess the effectiveness of the intelligent small insect monitoring and forecasting system developed by Zhejiang Top Cloud-Agri Technology Co.,Ltd.in monitoring,providing early warnings,and identifying rice planthoppers.[Methods]In 2024,an experiment involving the automatic identification and counting of rice planthoppers was conducted using the intelligent small insect monitoring and forecasting system in the rice production demonstration area of Qingxichang Sub-district,Xiushan Autonomous County,Chongqing City.The results obtained were subsequently compared and analyzed against those derived from manual identification.[Results]The intelligent small insect monitoring and forecasting system achieved recognition accuracy rates of 95.14%,94.25%,and 97.78% for Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus,respectively,resulting in an average accuracy rate of 95.72%.The outcomes derived from automatic recognition closely corresponded with those obtained through manual identification.[Conclusions]This research provides a reference for the optimization of the intelligent small insect monitoring and forecasting system.展开更多
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 weat...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.展开更多
To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance,this paper proposes a seasonal short-termload combination predi...To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance,this paper proposes a seasonal short-termload combination prediction model based on modal decomposition and a feature-fusion multi-algorithm hybrid neural network model.Specifically,the characteristics of load components are analyzed for different seasons,and the corresponding models are established.First,the improved complete ensemble empirical modal decomposition with adaptive noise(ICEEMDAN)method is employed to decompose the system load for all four seasons,and the new sequence is obtained through reconstruction based on the refined composite multiscale fuzzy entropy of each decomposition component.Second,the correlation between different decomposition components and different features is measured through the max-relevance and min-redundancy method to filter out the subset of features with strong correlation and low redundancy.Finally,different components of the load in different seasons are predicted separately using a bidirectional long-short-term memory network model based on a Bayesian optimization algorithm,with a prediction resolution of 15 min,and the predicted values are accumulated to obtain the final results.According to the experimental findings,the proposed method can successfully balance prediction accuracy and prediction time while offering a higher level of prediction accuracy than the current prediction methods.The results demonstrate that the proposedmethod can effectively address the load power variation induced by seasonal differences in different regions.展开更多
Commodity markets,such as crude oil and precious metals,play a strategic role in the economic development of nations,with crude oil prices influencing geopolitical relations and the global economy.Moreover,gold and si...Commodity markets,such as crude oil and precious metals,play a strategic role in the economic development of nations,with crude oil prices influencing geopolitical relations and the global economy.Moreover,gold and silver are argued to hedge the stock and cryptocurrency markets during market downsides.Therefore,accurate forecasting of crude oil and precious metals prices is critical.Nevertheless,due to the nonlinear nature,substantial fluctuations,and irregular cycles of crude oil and precious metals,predicting their prices is a challenging task.Our study contributes to the commodity market price forecasting literature by implementing and comparing advanced deep-learning models.We address this gap by including silver alongside gold in our analysis,offering a more comprehensive understanding of the precious metal markets.This research expands existing knowledge and provides valuable insights into predicting commodity prices.In this study,we implemented 16 deep-and machine-learning models to forecast the daily price of the West Texas Intermediate(WTI),Brent,gold,and silver markets.The employed deep-learning models are long short-term memory(LSTM),BiLSTM,gated recurrent unit(GRU),bidirectional gated recurrent units(BiGRU),T2V-BiLSTM,T2V-BiGRU,convolutional neural networks(CNN),CNN-BiLSTM,CNN-BiGRU,temporal convolutional network(TCN),TCN-BiLSTM,and TCN-BiGRU.We compared the forecasting performance of deep-learning models with the baseline random forest,LightGBM,support vector regression,and k-nearest neighborhood models using mean absolute error(MAE),mean absolute percentage error,and root mean squared error as evaluation criteria.By considering different sliding window lengths,we examine the forecasting performance of our models.Our results reveal that the TCN model outperforms the others for WTI,Brent,and silver,achieving the lowest MAE values of 1.444,1.295,and 0.346,respectively.The BiGRU model performs best for gold,with an MAE of 15.188 using a 30-day input sequence.Furthermore,LightGBM exhibits comparable performance to TCN and is the best-performing machine-learning model overall.These findings are critical for investors,policymakers,mining companies,and governmental agencies to effectively anticipate market trends,mitigate risk,manage uncertainty,and make timely decisions and strategies regarding crude oil,gold,and silver markets.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42375062 and 42275158)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab)the Natural Science Foundation of Gansu Province(Grant No.22JR5RF1080)。
文摘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.
基金Project(2020YFC2008605)supported by the National Key Research and Development Project of ChinaProject(52072412)supported by the National Natural Science Foundation of ChinaProject(2021JJ30359)supported by the Natural Science Foundation of Hunan Province,China。
文摘Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific basis for governance and prevention efforts.In this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of data.Graph generative network(GGN)is used to process time-series meteorological data with complex structures.The graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the model.In addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval prediction.With the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale data.The PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.
基金This work was jointly supported by the National Natural Science Foundation of China(Grant Nos.41975137,42175012,and 41475097)the National Key Research and Development Program(Grant No.2018YFF0300103).
文摘Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational techniques,and experience.This made providing meteorological services for this event particularly challenging.The China Meteorological Administration(CMA)Earth System Modeling and Prediction Centre,achieved breakthroughs in research on short-and medium-term deterministic and ensemble numerical predictions.Several key technologies crucial for precise winter weather services during the Winter Olympics were developed.A comprehensive framework,known as the Operational System for High-Precision Weather Forecasting for the Winter Olympics,was established.Some of these advancements represent the highest level of capabilities currently available in China.The meteorological service provided to the Beijing 2022 Games also exceeded previous Winter Olympic Games in both variety and quality.This included achievements such as the“100-meter level,minute level”downscaled spatiotemporal resolution and forecasts spanning 1 to 15 days.Around 30 new technologies and over 60 kinds of products that align with the requirements of the Winter Olympics Organizing Committee were developed,and many of these techniques have since been integrated into the CMA’s operational national forecasting systems.These accomplishments were facilitated by a dedicated weather forecasting and research initiative,in conjunction with the preexisting real-time operational forecasting systems of the CMA.This program represents one of the five subprograms of the WMO’s high-impact weather forecasting demonstration project(SMART2022),and continues to play an important role in their Regional Association(RA)II Research Development Project(Hangzhou RDP).Therefore,the research accomplishments and meteorological service experiences from this program will be carried forward into forthcoming highimpact weather forecasting activities.This article provides an overview and assessment of this program and the operational national forecasting systems.
基金supported by the National Natural Science Foundation of China (Grant Nos.41730965,41775099 and 2017YFC1502104)PAPD (the Priority Academic Program Development of Jiangsu Higher Education Institutions)
文摘A dual-resolution（DR） version of a regional ensemble Kalman filter（EnKF）-3D ensemble variational（3DEnVar） coupled hybrid data assimilation system is implemented as a prototype for the operational Rapid Refresh forecasting system. The DR 3DEnVar system combines a high-resolution（HR） deterministic background forecast with lower-resolution（LR） EnKF ensemble perturbations used for flow-dependent background error covariance to produce a HR analysis. The computational cost is substantially reduced by running the ensemble forecasts and EnKF analyses at LR. The DR 3DEnVar system is tested with 3-h cycles over a 9-day period using a 40/13-km grid spacing combination. The HR forecasts from the DR hybrid analyses are compared with forecasts launched from HR Gridpoint Statistical Interpolation（GSI） 3D variational（3DVar）analyses, and single LR hybrid analyses interpolated to the HR grid. With the DR 3DEnVar system, a 90% weight for the ensemble covariance yields the lowest forecast errors and the DR hybrid system clearly outperforms the HR GSI 3DVar.Humidity and wind forecasts are also better than those launched from interpolated LR hybrid analyses, but the temperature forecasts are slightly worse. The humidity forecasts are improved most. For precipitation forecasts, the DR 3DEnVar always outperforms HR GSI 3DVar. It also outperforms the LR 3DEnVar, except for the initial forecast period and lower thresholds.
基金The National Key Research and Development Program of China under contract No.2017YFA0604203the National Natural Science Foundation of China under contract Nos 42176029 and 41806003。
文摘In order to satisfy the increasing demand for the marine forecasting capacity,the Bohai Sea,the Yellow Sea and the East China Sea Operational Oceanography Forecasting System(BYEOFS)has been upgraded and improved to Version 2.0.Based on the Regional Ocean Modeling System(ROMS),a series of comparative experiments were conducted during the improvement process,including correcting topography,changing sea surface atmospheric forcing mode,adjusting open boundary conditions,and considering atmospheric pressure correction.(1)After the topography correction,the volume transport and meridional velocity maximum of Yellow Sea Warm Current increase obviously and the unreasonable bending of its axis around 36.1°N,123.5°E disappears.(2)After the change of sea surface forcing mode,an effective negative feedback mechanism is formed between predicted sea surface temperature(SST)by the ocean model and sea surface radiation fluxes fields.The simulation errors of SST decreased significantly,and the annual average of root-mean-square error(RMSE)decreased by about 18%.(3)The change of the eastern lateral boundary condition of baroclinic velocity from mixed Radiation-Nudging to Clamped makes the unreasonable westward current in Tsushima Strait disappear.(4)The adding of mean sea level pressure correction option which forms the mean sea level gradient from the Bohai Sea and the Yellow Sea to the western Pacific in winter and autumn is helpful to increasing the fluctuation of SLA and outflow of the Yellow Sea when the cold high air pressure system controls the Yellow Sea area.
基金funded by "The Program on Marine Environmental Safety Guarantee" of "The National Key Research and Development Program of China"[grant number2016YFC1401409]
文摘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.
文摘Based on the domestic and foreign related research methods, the life meteorological index forecasting system of Wuhu City was compiled using database and network as well as computer language. The system realized the automation process for the generation of life index forecasting products from local situation of Wuhu City and forecasting data, which could get the latest service products dispensing with manual intervention. The development of the system not only made the operation process of the life meteorological index of Wuhu City more time-saving and efficient, but also made the results more scientific and rigorous.
基金French Ministry of Economy and Finance is acknowledged for their financial support in the framework of the FASEP projectsupported by French ANRT CIFRE grant attributed to ARIA Technologies and LISA laboratories
文摘An air pollution forecast system,ARIA Regional,was implemented in 2007–2008 at the Beijing Municipality Environmental Monitoring Center,providing daily forecast of main pollutant concentrations.The chemistry-transport model CHIMERE was coupled with the dust emission model MB95 for restituting dust storm events in springtime so as to improve forecast results.Dust storm events were sporadic but could be extremely intense and then control air quality indexes close to the source areas but also far in the Beijing area.A dust episode having occurred at the end of May 2008 was analyzed in this article,and its impact of particulate matter on the Chinese air pollution index （API） was evaluated.Following our estimation,about 23 Tg of dust were emitted from source areas in Mongolia and in the Inner Mongolia of China,transporting towards southeast.This episode of dust storm influenced a large part of North China and East China,and also South Korea.The model result was then evaluated using satellite observations and in situ data.The simulated daily concentrations of total suspended particulate at 6：00 UTC had a similar spatial pattern with respect to OMI satellite aerosol index.Temporal evolution of dust plume was evaluated by comparing dust aerosol optical depth （AOD） calculated from the simulations with AOD derived from MODIS satellite products.Finally,the comparison of reported Chinese API in Beijing with API calculated from the simulation including dust emissions had showed the significant improvement of the model results taking into accountmineral dust correctly.
基金Supported by the National Key Research and Development Program of China(No.2016YFC1402000)
文摘In this study,an operational forecasting system of sea dike risk in the southern Zhejiang Province,South China was developed based on a coupled storm-surge and wave model.This forecasting system is important because of the high cost of storm-surge damage and the need for rapid emergency planning.A comparison with astronomical tides in 2016 and the validation of storm surges and high water marks of 20 typhoons verified that the forecast system has a good simulation ability.The system can forecast relatively realistic water levels and wave heights as shown under the parametric atmospheric forces simulated in a case study;the sea dikes in credible high risk were mainly located in the estuaries,rivers,and around the islands in the southern Zhejiang.Therefore,the forecast system is applicable in the southern Zhejiang with a support to the effective prevention from typhoon storm-surge damage.
基金China-Korea Cooperation Project on the development of oceanic monitoring and prediction system on nuclear safetythe Project of the National Programme on Global Change and Air-sea Interaction under contract No.GASI-03-IPOVAI-05
文摘An operational ocean circulation-surface wave coupled forecasting system for the seas off China and adjacent areas（OCFS-C） is developed based on parallelized circulation and wave models. It has been in operation since November 1, 2007. In this paper we comprehensively present the simulation and verification of the system, whose distinguishing feature is that the wave-induced mixing is coupled in the circulation model. In particular, with nested technique the resolution in the China＇s seas has been updated to（1/24）° from the global model with（1/2）°resolution. Besides, daily remote sensing sea surface temperature（SST） data have been assimilated into the model to generate a hot restart field for OCFS-C. Moreover, inter-comparisons between forecasting and independent observational data are performed to evaluate the effectiveness of OCFS-C in upper-ocean quantities predictions, including SST, mixed layer depth（MLD） and subsurface temperature. Except in conventional statistical metrics, non-dimensional skill scores（SS） is also used to evaluate forecast skill. Observations from buoys and Argo profiles are used for lead time and real time validations, which give a large SS value（more than 0.90）. Besides, prediction skill for the seasonal variation of SST is confirmed. Comparisons of subsurface temperatures with Argo profiles data indicate that OCFS-C has low skill in predicting subsurface temperatures between 100 m and 150 m. Nevertheless, inter-comparisons of MLD reveal that the MLD from model is shallower than that from Argo profiles by about 12 m, i.e., OCFS-C is successful and steady in MLD predictions. Validation of 1-d, 2-d and 3-d forecasting SST shows that our operational ocean circulation-surface wave coupled forecasting model has reasonable accuracy in the upper ocean.
文摘The floods in river Mahanadi delta are due to either dam release of Hirakud or due to contribution of intercepted catchment between Hirakud dam and delta. It is seen from post-Hirakud periods (1958) that out of 19 floods 14 are due to intercepted catchment contribution. The existing flood forecasting systems are mostly for upstream catchment, forecasting the inflow to reservoir, whereas the downstream catchment is devoid of a sound flood forecasting system. Therefore, in this study an attempt has been made to develop a workable forecasting system for downstream catchment. Instead of taking the flow time series concurrent flood peaks of 12 years of base and forecasting stations with its corresponding travel time are considered for analysis. Both statistical method and ANN based approach are considered for finding the peak to reach at delta head with its corresponding travel time. The travel time has been finalized adopting clustering techniques, there by differentiating high, medium and low peaks. The method is simple and it does not take into consideration the rainfall and other factors in the intercepted catchment. A comparison between both methods are tested and it is found that the ANN methods are better beyond the calibration range over statistical method and the efficiency of either methods reduces as the prediction reach is extended. However, it is able to give the peak discharge at delta head before 24 hour to 37 hour for high to low peaks.
文摘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.
基金Program of Key Laboratory of Meteorological Disaster(KLME202209)National Key R&D Program of China(2017YFC1502102)。
文摘Meteo-hydrological forecasting models are an effective way to generate high-resolution gridded rainfall data for water source research and flood forecast.The quality of rainfall data in terms of both intensity and distribution is very important for establishing a reliable meteo-hydrological forecasting model.To improve the accuracy of rainfall data,the successive correction method is introduced to correct the bias of rainfall,and a meteo-hydrological forecasting model based on WRF and WRF-Hydro is applied for streamflow forecast over the Zhanghe River catchment in China.The performance of WRF rainfall is compared with the China Meteorological Administration Multi-source Precipitation Analysis System(CMPAS),and the simulated streamflow from the model is further studied.It shows that the corrected WRF rainfall is more similar to the CMPAS in both temporal and spatial distribution than the original WRF rainfall.By contrast,the statistical metrics of the corrected WRF rainfall are better.When the corrected WRF rainfall is used to drive the WRF-Hydro model,the simulated streamflow of most events is significantly improved in both hydrographs and volume than that of using the original WRF rainfall.Among the studied events,the largest improvement of the NSE is from-0.68 to 0.67.It proves that correcting the bias of WRF rainfall with the successive correction method can greatly improve the performance of streamflow forecast.In general,the WRF/WRF-Hydro meteo-hydrological forecasting model based on the successive correction method has the potential to provide better streamflow forecast in the Zhanghe River catchment.
文摘Effective technology for wind direction forecasting can be realized using the recent advances in machine learning.Consequently,the stability and safety of power systems are expected to be significantly improved.However,the unstable and unpredictable qualities of the wind predict the wind direction a challenging problem.This paper proposes a practical forecasting approach based on the weighted ensemble of machine learning models.This weighted ensemble is optimized using a whale optimization algorithm guided by particle swarm optimization(PSO-Guided WOA).The proposed optimized weighted ensemble predicts the wind direction given a set of input features.The conducted experiments employed the wind power forecasting dataset,freely available on Kaggle and developed to predict the regular power generation at seven wind farms over forty-eight hours.The recorded results of the conducted experiments emphasize the effectiveness of the proposed ensemble in achieving accurate predictions of the wind direction.In addition,a comparison is established between the proposed optimized ensemble and other competing optimized ensembles to prove its superiority.Moreover,statistical analysis using one-way analysis of variance(ANOVA)and Wilcoxon’s rank-sum are provided based on the recorded results to confirm the excellent accuracy achieved by the proposed optimized weighted ensemble.
文摘Recently the importance of intellectual property has been increased. There has been various ways of research on analy- sis of companies, forecast of technology and so on through patents and many investments of money and time. Unlike traditional method of patent analysis such as company analysis, forecasting technologies, this research is to suggest the ways to forecast registration and rejection of patents which help minimize the efforts to register patents. To do so, in- formation such as inventors, applicants, application date, and IPC codes were extracted to be used as input variables for analyzing Bayesian network. Especially, among various forms of Bayesian network, we used Tree Augmented NBN (TAN) to forecast registration and rejection of patent. This is because, TAN was assumed to have dependence between variables. As a result of this Bayesian network, it was shown that there are nearly more than 80% of accuracy to fore- cast registration and rejection of patents. Therefore, we expect the minimization of time and cost of registration by forecasting registration and rejection of R&D patent through this research.
基金Key Projects in Science & Technology Pillar Program in 2007 in Beijing (No.D07020601400705)
文摘Transport system is a time-varying, huge and complex system. In order to have the traffic management department make pre-appropriate traffic management measures to adjust the traffic management control program, and release travel information to travelers, to provide optimal path options to ensure that the transport system operates efficiently and safely, we have to monitor the changing of the state of road traffic and to accurately evaluate the state of the traffic, then to predict the future state of traffic. This paper represents the construction of the road traffic flow simulation including the logical structure and the physical structure, and introduces the system functions of forecasting system in Beijing.
文摘[Objectives]To assess the effectiveness of the intelligent small insect monitoring and forecasting system developed by Zhejiang Top Cloud-Agri Technology Co.,Ltd.in monitoring,providing early warnings,and identifying rice planthoppers.[Methods]In 2024,an experiment involving the automatic identification and counting of rice planthoppers was conducted using the intelligent small insect monitoring and forecasting system in the rice production demonstration area of Qingxichang Sub-district,Xiushan Autonomous County,Chongqing City.The results obtained were subsequently compared and analyzed against those derived from manual identification.[Results]The intelligent small insect monitoring and forecasting system achieved recognition accuracy rates of 95.14%,94.25%,and 97.78% for Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus,respectively,resulting in an average accuracy rate of 95.72%.The outcomes derived from automatic recognition closely corresponded with those obtained through manual identification.[Conclusions]This research provides a reference for the optimization of the intelligent small insect monitoring and forecasting system.
文摘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.
文摘To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance,this paper proposes a seasonal short-termload combination prediction model based on modal decomposition and a feature-fusion multi-algorithm hybrid neural network model.Specifically,the characteristics of load components are analyzed for different seasons,and the corresponding models are established.First,the improved complete ensemble empirical modal decomposition with adaptive noise(ICEEMDAN)method is employed to decompose the system load for all four seasons,and the new sequence is obtained through reconstruction based on the refined composite multiscale fuzzy entropy of each decomposition component.Second,the correlation between different decomposition components and different features is measured through the max-relevance and min-redundancy method to filter out the subset of features with strong correlation and low redundancy.Finally,different components of the load in different seasons are predicted separately using a bidirectional long-short-term memory network model based on a Bayesian optimization algorithm,with a prediction resolution of 15 min,and the predicted values are accumulated to obtain the final results.According to the experimental findings,the proposed method can successfully balance prediction accuracy and prediction time while offering a higher level of prediction accuracy than the current prediction methods.The results demonstrate that the proposedmethod can effectively address the load power variation induced by seasonal differences in different regions.
文摘Commodity markets,such as crude oil and precious metals,play a strategic role in the economic development of nations,with crude oil prices influencing geopolitical relations and the global economy.Moreover,gold and silver are argued to hedge the stock and cryptocurrency markets during market downsides.Therefore,accurate forecasting of crude oil and precious metals prices is critical.Nevertheless,due to the nonlinear nature,substantial fluctuations,and irregular cycles of crude oil and precious metals,predicting their prices is a challenging task.Our study contributes to the commodity market price forecasting literature by implementing and comparing advanced deep-learning models.We address this gap by including silver alongside gold in our analysis,offering a more comprehensive understanding of the precious metal markets.This research expands existing knowledge and provides valuable insights into predicting commodity prices.In this study,we implemented 16 deep-and machine-learning models to forecast the daily price of the West Texas Intermediate(WTI),Brent,gold,and silver markets.The employed deep-learning models are long short-term memory(LSTM),BiLSTM,gated recurrent unit(GRU),bidirectional gated recurrent units(BiGRU),T2V-BiLSTM,T2V-BiGRU,convolutional neural networks(CNN),CNN-BiLSTM,CNN-BiGRU,temporal convolutional network(TCN),TCN-BiLSTM,and TCN-BiGRU.We compared the forecasting performance of deep-learning models with the baseline random forest,LightGBM,support vector regression,and k-nearest neighborhood models using mean absolute error(MAE),mean absolute percentage error,and root mean squared error as evaluation criteria.By considering different sliding window lengths,we examine the forecasting performance of our models.Our results reveal that the TCN model outperforms the others for WTI,Brent,and silver,achieving the lowest MAE values of 1.444,1.295,and 0.346,respectively.The BiGRU model performs best for gold,with an MAE of 15.188 using a 30-day input sequence.Furthermore,LightGBM exhibits comparable performance to TCN and is the best-performing machine-learning model overall.These findings are critical for investors,policymakers,mining companies,and governmental agencies to effectively anticipate market trends,mitigate risk,manage uncertainty,and make timely decisions and strategies regarding crude oil,gold,and silver markets.
