Weather forecasting is crucial for agriculture,transportation,and industry.Deep Learning(DL)has greatly improved the prediction accuracy.Among them,Graph Neural Networks(GNNs)excel at processing weather data by establ...Weather forecasting is crucial for agriculture,transportation,and industry.Deep Learning(DL)has greatly improved the prediction accuracy.Among them,Graph Neural Networks(GNNs)excel at processing weather data by establishing connections between regions.This allows them to understand complex patterns that traditional methods might miss.As a result,achieving more accurate predictions becomes possible.The paper reviews the role of GNNs in short-to medium-range weather forecasting.The methods are classified into three categories based on dataset differences.The paper also further identifies five promising research frontiers.These areas aim to boost forecasting precision and enhance computational efficiency.They offer valuable insights for future weather forecasting systems.展开更多
In this paper, the authors develop the earlier work of Chen Jiabin et al. (1986). In order to reduce spectral truncation errors, the reference atmosphere has been introduced in ECMWF model, and the spectrally-represen...In this paper, the authors develop the earlier work of Chen Jiabin et al. (1986). In order to reduce spectral truncation errors, the reference atmosphere has been introduced in ECMWF model, and the spectrally-represented variables, temperature, geopotential height and orography, are replaced by their deviations from the reference atmosphere. Two modified semi- implicit schemes have been proposed to alleviate the computational instability due to the introduction of reference atmosphere. Concerning the deviation of surface geopotential height from reference atmosphere, an exact computational formulation has been used instead of the approximate one in the earlier work. To re duce aliasing errors in the computations of the deviation of the surface geopotential height, a spectral fit has been used slightly to modify the original Gaussian grid-point values of orography.A series of experiments has been performed in order to assess the impact of the reference atmosphere on ECMWF medium- range forecasts at the resolution T21, T42 and T63. The results we have obtained reveal that the reference atmosphere introduced in ECMWF spectral model is generally beneficial to the mean statistical scores of 1000-200 hPa height 10-day forecasts over the globe. In the Southern Hemisphere, it is a clear improvement for T21, T42 and T63 throughout the 10-day forecast period. In the Northern Hemisphere, the impact of the reference atmos phere on anomaly correlation is positive for resolution T21, a very slightly damaging at T42 and almost neutral at T63 in the range of day 1 to day 4. Beyond the day 4 there is a clear improvement at all resolutions.展开更多
This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administratio...This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administration.The analysis reveals systematic improvements in both track and intensity forecasts over the decade,with distinct error characteristics observed across various forecast parameters.Track forecast errors have steadily decreased,particularly for longer lead times,while error magnitudes have increased with longer forecast lead times.Intensity forecasts show similar progressive enhancements,with maximum sustained wind speed errors decreasing by 0.26 m/s per year for 120 h forecasts.The study also identifies several key patterns in forecast performance:typhoon-grade or stronger TCs exhibit smaller track errors than week or weaker systems;intensity forecasts systematically overestimate weaker TCs while underestimating stronger systems;and spatial error distributions show greater track inaccuracies near landmasses and regional intensity biases.These findings highlight both the significant advances in TC forecasting capability achieved through improved modeling and observational systems,and the remaining challenges in predicting TC changes and landfall behavior,providing valuable benchmarks for future forecast system development.展开更多
Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep...Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.展开更多
Engineering multiscale structural hierarchies in glassy alloys enable a broad spectrum of potential applications.Metallic glasses were born in hierarchical structures from atomic-to-nanometer scales.However,the frozen...Engineering multiscale structural hierarchies in glassy alloys enable a broad spectrum of potential applications.Metallic glasses were born in hierarchical structures from atomic-to-nanometer scales.However,the frozen-in structures in traditional metallic glasses prepared by rapid quenching techniques are challenging to tailor.Here,we show that a PdNiPbulk nanostructured glass of polyamorphous interfacial structures was prepared by inert-gas condensation with a laser evaporation source,and its multiscale structures could be engineered.In-situ scattering experiment results reveal polyamorphous phase transitions occurred in the interfacial regions,which are accompanied by the evolution of medium-range order and the nanoscale heterogeneous structures during the condensation process of glassy nanoparticles under high pressure and the following heating process.Moreover,changes in the cluster connectivity resulting from repacking of the local ordering induced by pressure and temperature could be observed.The thermophysical and mechanical properties,including boson peaks,hardness,and elasticity modulus,could be changed as a function of heat-treatment parameters.Our findings would shed light on the synthesis of bulk nanostructured glassy alloys with tailorable thermodynamic and dynamical behavior as well as mechanical properties based on the understanding of metastability for polyamorphous interfacial phases.展开更多
Fe-based metallic glasses are promising functional materials for advanced magnetism and sensor fields.Tailoring magnetic performance in amorphous materials requires a thorough knowledge of the correlation between stru...Fe-based metallic glasses are promising functional materials for advanced magnetism and sensor fields.Tailoring magnetic performance in amorphous materials requires a thorough knowledge of the correlation between structural disorder and magnetic order,which remains ambiguous.Two practical difficulties remain:the first is directly observing subtle magnetic structural changes on multiple scales,and the second is precisely regulating the various amorphous states.Here we propose a novel approach to tailor the amorphous structure through the liquid-liquid phase transition.In-situ synchrotron diffraction has unraveled a medium-range ordering process dominated by edge-sharing cluster connectivity during the liquid-liquid phase transition.Moreover,nanodomains with topological order have been found to exist in composition with liquid-liquid phase transition,manifesting as hexagonal patterns in small-angle neutron scattering profiles.The liquid-liquid phase transition can induce the nanodomains to be more locally ordered,generating stronger exchange interactions due to the reduced Fe–Fe bond length and the enhanced structural order,leading to the increment of saturation magnetization.Furthermore,the increased local heterogeneity at the medium-range scale enhances the magnetic anisotropy,promoting the permeability response under applied stress and leading to a better stress-impedance effect.These experimental results pave the way to tailor the magnetic structure and performance through the liquid-liquid phase transition.展开更多
Developing ductile bulk metallic glasses(BMGs)can benefit from an in-depth understanding of the structure-property relation during plastic deformation.However,endowing BMGs with tensile ductility in BMGs needs to reve...Developing ductile bulk metallic glasses(BMGs)can benefit from an in-depth understanding of the structure-property relation during plastic deformation.However,endowing BMGs with tensile ductility in BMGs needs to reveal the response of critical structure units during deformation.Here,we report the experimental results of an in-situ synchrotron high-energy X-ray study of a Zr-based BMG under uniaxial tension after preprocessing by canning compression of the three-dimensional compressive stress state.It is revealed that the canning-compressed BMG(CC-BMG)sample has better tensile ductility and higher ultimate strength than the as-cast sample,which possesses heterogeneous and loosely packed local struc-tures on medium-range scales.The experimental results revealed two stages of plastic deformation in the CC-BMGs compared with one stage of plastic deformation in the as-cast BMG.Moreover,the shift in the first sharp diffraction peak along the tension direction for the canning-compressed sample is substan-tially more pronounced than that of the as-cast sample.Furthermore,the real-space analysis illustrates a competition mechanism between the 2-atom and 3-atom connection modes on medium-range order during the plastic deformation of the CC-BMG.Additionally,the ordering on the medium-range scale de-creases in the first plastic deformation stage but increases in the second plastic deformation stage.There-fore,a structural crossover phenomenon occurs in the CC-BMG during plastic deformation.Our results demonstrate a structure-property correlation for the CC-BMGs of heterogeneous medium-range ordered structures,which may be beneficial for endowing BMGs with ductility based on medium-range order engineering techniques.展开更多
A method of multi-spectral analysis is used to study the spectral characteristics of surface and upper-level meteorological elements over the Great Wall Station (62°12'S, 58°57'W), Antarctica and the...A method of multi-spectral analysis is used to study the spectral characteristics of surface and upper-level meteorological elements over the Great Wall Station (62°12'S, 58°57'W), Antarctica and their phasecorrelation, propagation of mean oscillation at 500hPa level in the Southern Hemisphere and their corresponding synoptic sense. the results are summed up as follows: 1. Over the sub-Antatctic zone, as in the Northern Hemisphere there generally exist quasi-weekly oscillation and quasi-biweekly oscillation. In different seasons the oscillations of meteorological elements are different: in winter season quasi-biweekly oscillation is dominant, while in summer season quasi-weekly oscillation is dominant. 2. From the Earth's surface to the lower stratosphere there is a distinct quasi-weekly oscillation at each isobaric surface, but the most intense oscillation appears at 200-300hPa, and the oscillations of height and temperature are propagated downward. 3. Both in winter and summer seasons the quasi-biweekly oscillation are propagated from west to east, and the mean velocity of its propagation is about 7-17 longtitude / day. 4. The quasi-biweekly oscillation and the quasi-weekly oscillation over the sub - Antarctic zone are closely related to the activity and intensity variation of polar vortex at 500hPa, while at 1000hPa they reflect an interaction between the circumpolar depression and the sub-tropical high. The quasi-biweekly oscillation may be a reflection of inherent oscillation of the polar vortex, where as the quasi-weekly oscillation is a result of forced oscillation by external disturbance.A large number of calculations and analysis made reveals the features of medium-range oscillation over the sub-Antarctic zone. The results are of significance for understanding the behaviour of synoptic dynamics and making the weather forecast.This work is supported by National Committee for Antarctic Research.展开更多
By the use of space-time spectral analysis and band-pass filter, some of the features of the medium-range oscillations in the summer tropical easterlies (10 S-20 N) at 200 hPa are investigated based on a two-year (198...By the use of space-time spectral analysis and band-pass filter, some of the features of the medium-range oscillations in the summer tropical easterlies (10 S-20 N) at 200 hPa are investigated based on a two-year (1980 and 1982) wind (u, v) data set for the period from May to September. Space-time power spectral analysis shows that the total energy of the westward moving waves was the largest and that of the standing waves and eastward mov ing waves was relatively small in the 200 hPa easterlies: the total energy of the eastward moving waves was m minimum at 10° N. Three kinds of the medium-range oscillations with about 50 day, 25 day and quasi-biweekly periods were found in the easterlies, which all show a remarkable interannual variations and latitudinal differences in these two years. The wave energy of zonal wind is mainly associated with the planetary waves (1-3). which all may make important contributions to the 50 day and 25 day oscillations in different years or different latitudes, The quasi-biweekly oscillation is mainly related to the synoptic waves (4-6). In equatorial region, the 50 day oscillation was dominant with a eastward phase propagation in 1982 while the dominant oscillation in 1980 was of 25 day period with a westward phase propagations in 1980. Both of them are of the mode of zonal wavenumber 1. Strong westward 50 day oscillation was found in 10° N-20° N in these two years. Regular propagations of the meridional wind 50 cay oscillation were also found in the easterlies.The 50 day and 25 day oscillation of zonal wind all demonstrate southward phase propagation over the region of the South Asia monsoon and northward phase propagation near international date line, where are the climatic mean position of the tropical upper-tropospheric easterly jet and the tropical upper tropospheric trough (TUTT). respectively.展开更多
In this paper, we use a spectral model for the medium-range numerical weather forecast to discuss the impact of the diurnal variation of solar radiation on the medium-range weather processes. Under the tests of two ty...In this paper, we use a spectral model for the medium-range numerical weather forecast to discuss the impact of the diurnal variation of solar radiation on the medium-range weather processes. Under the tests of two typical winter and summer cases, we find that the influences of the diurnal variation of solar radiation on summer weather are really important, especially on its rainfall, surface heat transport and 500 hPa height field. On winter weather, however, the influences are very weak.展开更多
In this paper, using the daily grid data (2.5 × 2.5) of the ECMWF / WMO, we have computed respectively the three-dimensional wave activity flux in the stages of pre-onset, prevailing and post ending of Meiyu from...In this paper, using the daily grid data (2.5 × 2.5) of the ECMWF / WMO, we have computed respectively the three-dimensional wave activity flux in the stages of pre-onset, prevailing and post ending of Meiyu from 1 to 31 July 1982. The potential vorticity field is taken as the physical quantity relating the wave activity flux to the variation of the subtropical high over the Western Pacific. It is found that the three-dimensional wave activity flux is a powerful means for diagnosis of the variation of the subtropical high over the Western Pacific: The region of the subtropical high is just the confluence area of wave energy, whose changes in intensity and range decide the variation of the subtropical high. The confluence of wave energy comes from the monsoon flow in low latitudes, the Meiyu rain belts in middle latitudes and the heating fields on the eastern side of the Qinghai-Xizang Plateau. The relation between these sources and the subtropical high displays the self-adjusting mechanism among members of East-Asia summer monsoon.展开更多
Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,th...Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.展开更多
Vector winds play a crucial role in weather and climate,as well as the effective utilization of wind energy resources.However,limited research has been conducted on treating the wind field as a vector field in the eva...Vector winds play a crucial role in weather and climate,as well as the effective utilization of wind energy resources.However,limited research has been conducted on treating the wind field as a vector field in the evaluation of numerical weather prediction models.In this study,the authors treat vector winds as a whole by employing a vector field evaluation method,and evaluate the mesoscale model of the China Meteorological Administration(CMA-MESO)and ECMWF forecast,with reference to ERA5 reanalysis,in terms of multiple aspects of vector winds over eastern China in 2022.The results show that the ECMWF forecast is superior to CMA-MESO in predicting the spatial distribution and intensity of 10-m vector winds.Both models overestimate the wind speed in East China,and CMA-MESO overestimates the wind speed to a greater extent.The forecasting skill of the vector wind field in both models decreases with increasing lead time.The forecasting skill of CMA-MESO fluctuates more and decreases faster than that of the ECMWF forecast.There is a significant negative correlation between the model vector wind forecasting skill and terrain height.This study provides a scientific evaluation of the local application of vector wind forecasts of the CMA-MESO model and ECMWF forecast.展开更多
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 ...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.展开更多
Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficie...Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficiency and how they process solar radiation.This study evaluates the effectiveness of deep learning models in predicting PV power generation for three panel technologies:Hybrid-Si,Mono-Si,and Poly-Si,across three forecasting horizons:1-step,12-step,and 24-step.Among the tested models,the Convolutional Neural Network—Long Short-Term Memory(CNN-LSTM)architecture exhibited superior performance,particularly for the 24-step horizon,achieving R^(2)=0.9793 and MAE 0.0162 for the Poly-Si array,followed by Mono-Si(R^(2)=0.9768)and Hybrid-Si arrays(R^(2)=0.9769).These findings demonstrate that the CNN-LSTM model can provide accurate and reliable PV power predictions for all studied technologies.By identifying the most suitable predictive model for each panel technology,this study contributes to optimizing PV power forecasting and improving energy management strategies.展开更多
A remarkable marine heatwave,known as the“Blob”,occurred in the Northeast Pacific Ocean from late 2013 to early 2016,which displayed strong warm anomalies extending from the surface to a depth of 300 m.This study em...A remarkable marine heatwave,known as the“Blob”,occurred in the Northeast Pacific Ocean from late 2013 to early 2016,which displayed strong warm anomalies extending from the surface to a depth of 300 m.This study employed two assimilation schemes based on the global Climate Forecast System of Nanjing University of Information Science(NUIST-CFS 1.0)to investigate the impact of ocean data assimilation on the seasonal prediction of this extreme marine heatwave.The sea surface temperature(SST)nudging scheme assimilates SST only,while the deterministic ensemble Kalman filter(EnKF)scheme assimilates observations from the surface to the deep ocean.The latter notably improves the forecasting skill for subsurface temperature anomalies,especially at the depth of 100-300 m(the lower layer),outperforming the SST nudging scheme.It excels in predicting both horizontal and vertical heat transport in the lower layer,contributing to improved forecasts of the lower-layer warming during the Blob.These improvements stem from the assimilation of subsurface observational data,which are important in predicting the upper-ocean conditions.The results suggest that assimilating ocean data with the EnKF scheme significantly enhances the accuracy in predicting subsurface temperature anomalies during the Blob and offers better understanding of its underlying mechanisms.展开更多
Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predict...Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predictability,deep learning has yet to be sufficiently explored for complex deformation patterns associated with landslides and is inherently opaque.Herein,we developed a holistic landslide deformation forecasting method that considers spatiotemporal correlations of landslide deformation by integrating domain knowledge into interpretable deep learning.By spatially capturing the interconnections between multiple deformations from different observation points,our method contributes to the understanding and forecasting of landslide systematic behavior.By integrating specific domain knowledge relevant to each observation point and merging internal properties with external variables,the local heterogeneity is considered in our method,identifying deformation temporal patterns in different landslide zones.Case studies involving reservoir-induced landslides and creeping landslides demonstrated that our approach(1)enhances the accuracy of landslide deformation forecasting,(2)identifies significant contributing factors and their influence on spatiotemporal deformation characteristics,and(3)demonstrates how identifying these factors and patterns facilitates landslide forecasting.Our research offers a promising and pragmatic pathway toward a deeper understanding and forecasting of complex landslide behaviors.展开更多
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
Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devi...Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.展开更多
Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradi...Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.展开更多
基金supported by Key Laboratory of Smart Earth(KF2023ZD03-05)CMA Innovative and Development Program(CXFZ.20231035)+2 种基金National Key R&D Program of China(No.2021ZD0111902)National Natural Science Foundation of China(Nos.62472014,U21B2038)the Scientific and Technological Project of China Meteorological Administration(CMAJBGS202505).
文摘Weather forecasting is crucial for agriculture,transportation,and industry.Deep Learning(DL)has greatly improved the prediction accuracy.Among them,Graph Neural Networks(GNNs)excel at processing weather data by establishing connections between regions.This allows them to understand complex patterns that traditional methods might miss.As a result,achieving more accurate predictions becomes possible.The paper reviews the role of GNNs in short-to medium-range weather forecasting.The methods are classified into three categories based on dataset differences.The paper also further identifies five promising research frontiers.These areas aim to boost forecasting precision and enhance computational efficiency.They offer valuable insights for future weather forecasting systems.
文摘In this paper, the authors develop the earlier work of Chen Jiabin et al. (1986). In order to reduce spectral truncation errors, the reference atmosphere has been introduced in ECMWF model, and the spectrally-represented variables, temperature, geopotential height and orography, are replaced by their deviations from the reference atmosphere. Two modified semi- implicit schemes have been proposed to alleviate the computational instability due to the introduction of reference atmosphere. Concerning the deviation of surface geopotential height from reference atmosphere, an exact computational formulation has been used instead of the approximate one in the earlier work. To re duce aliasing errors in the computations of the deviation of the surface geopotential height, a spectral fit has been used slightly to modify the original Gaussian grid-point values of orography.A series of experiments has been performed in order to assess the impact of the reference atmosphere on ECMWF medium- range forecasts at the resolution T21, T42 and T63. The results we have obtained reveal that the reference atmosphere introduced in ECMWF spectral model is generally beneficial to the mean statistical scores of 1000-200 hPa height 10-day forecasts over the globe. In the Southern Hemisphere, it is a clear improvement for T21, T42 and T63 throughout the 10-day forecast period. In the Northern Hemisphere, the impact of the reference atmos phere on anomaly correlation is positive for resolution T21, a very slightly damaging at T42 and almost neutral at T63 in the range of day 1 to day 4. Beyond the day 4 there is a clear improvement at all resolutions.
基金supported by the National Key R&D Program of China [grant number 2023YFC3008004]。
文摘This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administration.The analysis reveals systematic improvements in both track and intensity forecasts over the decade,with distinct error characteristics observed across various forecast parameters.Track forecast errors have steadily decreased,particularly for longer lead times,while error magnitudes have increased with longer forecast lead times.Intensity forecasts show similar progressive enhancements,with maximum sustained wind speed errors decreasing by 0.26 m/s per year for 120 h forecasts.The study also identifies several key patterns in forecast performance:typhoon-grade or stronger TCs exhibit smaller track errors than week or weaker systems;intensity forecasts systematically overestimate weaker TCs while underestimating stronger systems;and spatial error distributions show greater track inaccuracies near landmasses and regional intensity biases.These findings highlight both the significant advances in TC forecasting capability achieved through improved modeling and observational systems,and the remaining challenges in predicting TC changes and landfall behavior,providing valuable benchmarks for future forecast system development.
基金supported by the National Natural Science Foundation of China[grant number 62376217]the Young Elite Scientists Sponsorship Program by CAST[grant number 2023QNRC001]the Joint Research Project for Meteorological Capacity Improvement[grant number 24NLTSZ003]。
文摘Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.
基金financially supported by the National Key R&D Program of China(No.2021YFB3802800)the National Natural Science Foundation of China(No.51871120)+8 种基金the Natural Science Foundation of Jiangsu Province(No.BK20200019)the Fundamental Research Funds for the Central Universities(Nos.309190111073092001000430919011404)supports by Guangdong-Hong Kong-Macao Joint Laboratory for Neutron Scattering Science and Technology and Shenzhen Science and Technology Innovation Commission(No.JCYJ202000109105618137)support from Qing Lan project and the distinguished professor project of Jiangsu provincesupport by the Shenzhen Science and Technology Innovation Committee(No.JCYJ20170413140446951)the Ministry of Science and Technology of China(No.2016YFA0401501)supported by the US DOE Office of Science,Office of Basic Energy Sciences。
文摘Engineering multiscale structural hierarchies in glassy alloys enable a broad spectrum of potential applications.Metallic glasses were born in hierarchical structures from atomic-to-nanometer scales.However,the frozen-in structures in traditional metallic glasses prepared by rapid quenching techniques are challenging to tailor.Here,we show that a PdNiPbulk nanostructured glass of polyamorphous interfacial structures was prepared by inert-gas condensation with a laser evaporation source,and its multiscale structures could be engineered.In-situ scattering experiment results reveal polyamorphous phase transitions occurred in the interfacial regions,which are accompanied by the evolution of medium-range order and the nanoscale heterogeneous structures during the condensation process of glassy nanoparticles under high pressure and the following heating process.Moreover,changes in the cluster connectivity resulting from repacking of the local ordering induced by pressure and temperature could be observed.The thermophysical and mechanical properties,including boson peaks,hardness,and elasticity modulus,could be changed as a function of heat-treatment parameters.Our findings would shed light on the synthesis of bulk nanostructured glassy alloys with tailorable thermodynamic and dynamical behavior as well as mechanical properties based on the understanding of metastability for polyamorphous interfacial phases.
基金financially supported by the National Key R&D Program of China(No.2021YFB3802800)the Natural Science Foundation of Jiangsu Province(No.BK20200019)+6 种基金the National Natural Science Foundation of China(Nos.52222104,12261160364,51871120,and 51520105001)support from the Guangdong-Hong Kong-Macao Joint Laboratory for Neutron Scattering Science and Technologysupport of the Shenzhen Science and Technology Innovation Committee(No.JCYJ20170413140446951)partial support by the Research Grants Council of the Hong Kong Special Administrative Region,Project N_CityU173/22support of the National Natural Science Foundation of China(No.12275154)the Guangdong Basic and Applied Basic Research Foundation(No.2021B1515140028)supported by the US DOE Office of Science,Office of Basic Energy Sciences.
文摘Fe-based metallic glasses are promising functional materials for advanced magnetism and sensor fields.Tailoring magnetic performance in amorphous materials requires a thorough knowledge of the correlation between structural disorder and magnetic order,which remains ambiguous.Two practical difficulties remain:the first is directly observing subtle magnetic structural changes on multiple scales,and the second is precisely regulating the various amorphous states.Here we propose a novel approach to tailor the amorphous structure through the liquid-liquid phase transition.In-situ synchrotron diffraction has unraveled a medium-range ordering process dominated by edge-sharing cluster connectivity during the liquid-liquid phase transition.Moreover,nanodomains with topological order have been found to exist in composition with liquid-liquid phase transition,manifesting as hexagonal patterns in small-angle neutron scattering profiles.The liquid-liquid phase transition can induce the nanodomains to be more locally ordered,generating stronger exchange interactions due to the reduced Fe–Fe bond length and the enhanced structural order,leading to the increment of saturation magnetization.Furthermore,the increased local heterogeneity at the medium-range scale enhances the magnetic anisotropy,promoting the permeability response under applied stress and leading to a better stress-impedance effect.These experimental results pave the way to tailor the magnetic structure and performance through the liquid-liquid phase transition.
基金the National Key R&D Program of China(No.2021YFB3802800)the National Natural Sci-ence Foundation of China(Nos.52222104,12261160364,51871120 and 51520105001)+3 种基金the Natural Science Foundation of Jiangsu Province(No.BK20200019)Si Lan acknowledges the support by Guangdong-Hong Kong-Macao Joint Laboratory for Neutron Scat-tering Science and Technology and Shenzhen Science and Technol-ogy Innovation Commission(No.JCYJ20200109105618137)the resources of the China Spallation Neutron Source located in Dongguan,China,and the Advanced Photon Source,a US Department of Energy(DOE)Office of Science User Facility op-erated for the DOE Office of Science by Argonne National Labora-tory under Contract No.DE-AC02-06CH11357the US DOE Office of Science,Office of Basic Energy Sciences.The neutron scattering experiments carried out at the Spallation Neutron Source were sponsored by the Scientific User Facilities Di-vision,Office of Basic Energy Sciences,U.S.Department of Energy,under Contract No.DE-AC05-00OR22725 with Oak Ridge National Laboratory.
文摘Developing ductile bulk metallic glasses(BMGs)can benefit from an in-depth understanding of the structure-property relation during plastic deformation.However,endowing BMGs with tensile ductility in BMGs needs to reveal the response of critical structure units during deformation.Here,we report the experimental results of an in-situ synchrotron high-energy X-ray study of a Zr-based BMG under uniaxial tension after preprocessing by canning compression of the three-dimensional compressive stress state.It is revealed that the canning-compressed BMG(CC-BMG)sample has better tensile ductility and higher ultimate strength than the as-cast sample,which possesses heterogeneous and loosely packed local struc-tures on medium-range scales.The experimental results revealed two stages of plastic deformation in the CC-BMGs compared with one stage of plastic deformation in the as-cast BMG.Moreover,the shift in the first sharp diffraction peak along the tension direction for the canning-compressed sample is substan-tially more pronounced than that of the as-cast sample.Furthermore,the real-space analysis illustrates a competition mechanism between the 2-atom and 3-atom connection modes on medium-range order during the plastic deformation of the CC-BMG.Additionally,the ordering on the medium-range scale de-creases in the first plastic deformation stage but increases in the second plastic deformation stage.There-fore,a structural crossover phenomenon occurs in the CC-BMG during plastic deformation.Our results demonstrate a structure-property correlation for the CC-BMGs of heterogeneous medium-range ordered structures,which may be beneficial for endowing BMGs with ductility based on medium-range order engineering techniques.
文摘A method of multi-spectral analysis is used to study the spectral characteristics of surface and upper-level meteorological elements over the Great Wall Station (62°12'S, 58°57'W), Antarctica and their phasecorrelation, propagation of mean oscillation at 500hPa level in the Southern Hemisphere and their corresponding synoptic sense. the results are summed up as follows: 1. Over the sub-Antatctic zone, as in the Northern Hemisphere there generally exist quasi-weekly oscillation and quasi-biweekly oscillation. In different seasons the oscillations of meteorological elements are different: in winter season quasi-biweekly oscillation is dominant, while in summer season quasi-weekly oscillation is dominant. 2. From the Earth's surface to the lower stratosphere there is a distinct quasi-weekly oscillation at each isobaric surface, but the most intense oscillation appears at 200-300hPa, and the oscillations of height and temperature are propagated downward. 3. Both in winter and summer seasons the quasi-biweekly oscillation are propagated from west to east, and the mean velocity of its propagation is about 7-17 longtitude / day. 4. The quasi-biweekly oscillation and the quasi-weekly oscillation over the sub - Antarctic zone are closely related to the activity and intensity variation of polar vortex at 500hPa, while at 1000hPa they reflect an interaction between the circumpolar depression and the sub-tropical high. The quasi-biweekly oscillation may be a reflection of inherent oscillation of the polar vortex, where as the quasi-weekly oscillation is a result of forced oscillation by external disturbance.A large number of calculations and analysis made reveals the features of medium-range oscillation over the sub-Antarctic zone. The results are of significance for understanding the behaviour of synoptic dynamics and making the weather forecast.This work is supported by National Committee for Antarctic Research.
文摘By the use of space-time spectral analysis and band-pass filter, some of the features of the medium-range oscillations in the summer tropical easterlies (10 S-20 N) at 200 hPa are investigated based on a two-year (1980 and 1982) wind (u, v) data set for the period from May to September. Space-time power spectral analysis shows that the total energy of the westward moving waves was the largest and that of the standing waves and eastward mov ing waves was relatively small in the 200 hPa easterlies: the total energy of the eastward moving waves was m minimum at 10° N. Three kinds of the medium-range oscillations with about 50 day, 25 day and quasi-biweekly periods were found in the easterlies, which all show a remarkable interannual variations and latitudinal differences in these two years. The wave energy of zonal wind is mainly associated with the planetary waves (1-3). which all may make important contributions to the 50 day and 25 day oscillations in different years or different latitudes, The quasi-biweekly oscillation is mainly related to the synoptic waves (4-6). In equatorial region, the 50 day oscillation was dominant with a eastward phase propagation in 1982 while the dominant oscillation in 1980 was of 25 day period with a westward phase propagations in 1980. Both of them are of the mode of zonal wavenumber 1. Strong westward 50 day oscillation was found in 10° N-20° N in these two years. Regular propagations of the meridional wind 50 cay oscillation were also found in the easterlies.The 50 day and 25 day oscillation of zonal wind all demonstrate southward phase propagation over the region of the South Asia monsoon and northward phase propagation near international date line, where are the climatic mean position of the tropical upper-tropospheric easterly jet and the tropical upper tropospheric trough (TUTT). respectively.
文摘In this paper, we use a spectral model for the medium-range numerical weather forecast to discuss the impact of the diurnal variation of solar radiation on the medium-range weather processes. Under the tests of two typical winter and summer cases, we find that the influences of the diurnal variation of solar radiation on summer weather are really important, especially on its rainfall, surface heat transport and 500 hPa height field. On winter weather, however, the influences are very weak.
文摘In this paper, using the daily grid data (2.5 × 2.5) of the ECMWF / WMO, we have computed respectively the three-dimensional wave activity flux in the stages of pre-onset, prevailing and post ending of Meiyu from 1 to 31 July 1982. The potential vorticity field is taken as the physical quantity relating the wave activity flux to the variation of the subtropical high over the Western Pacific. It is found that the three-dimensional wave activity flux is a powerful means for diagnosis of the variation of the subtropical high over the Western Pacific: The region of the subtropical high is just the confluence area of wave energy, whose changes in intensity and range decide the variation of the subtropical high. The confluence of wave energy comes from the monsoon flow in low latitudes, the Meiyu rain belts in middle latitudes and the heating fields on the eastern side of the Qinghai-Xizang Plateau. The relation between these sources and the subtropical high displays the self-adjusting mechanism among members of East-Asia summer monsoon.
基金supported by Yunnan Provincial Basic Research Project(202401AT070344,202301AT070443)National Natural Science Foundation of China(62263014,52207105)+1 种基金Yunnan Lancang-Mekong International Electric Power Technology Joint Laboratory(202203AP140001)Major Science and Technology Projects in Yunnan Province(202402AG050006).
文摘Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.
基金primarily supported by the National Key R&D Program of China[grant number 2021YFC3000904]the Jiangsu Provincial Key Technology R&D Program[grant number BE2022851]National Natural Science Foundation of China[grant number 42405035]。
文摘Vector winds play a crucial role in weather and climate,as well as the effective utilization of wind energy resources.However,limited research has been conducted on treating the wind field as a vector field in the evaluation of numerical weather prediction models.In this study,the authors treat vector winds as a whole by employing a vector field evaluation method,and evaluate the mesoscale model of the China Meteorological Administration(CMA-MESO)and ECMWF forecast,with reference to ERA5 reanalysis,in terms of multiple aspects of vector winds over eastern China in 2022.The results show that the ECMWF forecast is superior to CMA-MESO in predicting the spatial distribution and intensity of 10-m vector winds.Both models overestimate the wind speed in East China,and CMA-MESO overestimates the wind speed to a greater extent.The forecasting skill of the vector wind field in both models decreases with increasing lead time.The forecasting skill of CMA-MESO fluctuates more and decreases faster than that of the ECMWF forecast.There is a significant negative correlation between the model vector wind forecasting skill and terrain height.This study provides a scientific evaluation of the local application of vector wind forecasts of the CMA-MESO model and ECMWF forecast.
基金supported by the National Natural Science Foundation of China(Grant No.42076214)Natural Science Foundation of Shandong Province(Grant No.ZR2024QD057).
文摘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.
文摘Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficiency and how they process solar radiation.This study evaluates the effectiveness of deep learning models in predicting PV power generation for three panel technologies:Hybrid-Si,Mono-Si,and Poly-Si,across three forecasting horizons:1-step,12-step,and 24-step.Among the tested models,the Convolutional Neural Network—Long Short-Term Memory(CNN-LSTM)architecture exhibited superior performance,particularly for the 24-step horizon,achieving R^(2)=0.9793 and MAE 0.0162 for the Poly-Si array,followed by Mono-Si(R^(2)=0.9768)and Hybrid-Si arrays(R^(2)=0.9769).These findings demonstrate that the CNN-LSTM model can provide accurate and reliable PV power predictions for all studied technologies.By identifying the most suitable predictive model for each panel technology,this study contributes to optimizing PV power forecasting and improving energy management strategies.
基金supported by the National Natural Science Foundation of China [grant number 42030605]the National Key R&D Program of China [grant number 2020YFA0608004]。
文摘A remarkable marine heatwave,known as the“Blob”,occurred in the Northeast Pacific Ocean from late 2013 to early 2016,which displayed strong warm anomalies extending from the surface to a depth of 300 m.This study employed two assimilation schemes based on the global Climate Forecast System of Nanjing University of Information Science(NUIST-CFS 1.0)to investigate the impact of ocean data assimilation on the seasonal prediction of this extreme marine heatwave.The sea surface temperature(SST)nudging scheme assimilates SST only,while the deterministic ensemble Kalman filter(EnKF)scheme assimilates observations from the surface to the deep ocean.The latter notably improves the forecasting skill for subsurface temperature anomalies,especially at the depth of 100-300 m(the lower layer),outperforming the SST nudging scheme.It excels in predicting both horizontal and vertical heat transport in the lower layer,contributing to improved forecasts of the lower-layer warming during the Blob.These improvements stem from the assimilation of subsurface observational data,which are important in predicting the upper-ocean conditions.The results suggest that assimilating ocean data with the EnKF scheme significantly enhances the accuracy in predicting subsurface temperature anomalies during the Blob and offers better understanding of its underlying mechanisms.
基金supported by the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20230685)the National Science Foundation of China(Grant No.42277161).
文摘Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predictability,deep learning has yet to be sufficiently explored for complex deformation patterns associated with landslides and is inherently opaque.Herein,we developed a holistic landslide deformation forecasting method that considers spatiotemporal correlations of landslide deformation by integrating domain knowledge into interpretable deep learning.By spatially capturing the interconnections between multiple deformations from different observation points,our method contributes to the understanding and forecasting of landslide systematic behavior.By integrating specific domain knowledge relevant to each observation point and merging internal properties with external variables,the local heterogeneity is considered in our method,identifying deformation temporal patterns in different landslide zones.Case studies involving reservoir-induced landslides and creeping landslides demonstrated that our approach(1)enhances the accuracy of landslide deformation forecasting,(2)identifies significant contributing factors and their influence on spatiotemporal deformation characteristics,and(3)demonstrates how identifying these factors and patterns facilitates landslide forecasting.Our research offers a promising and pragmatic pathway toward a deeper understanding and forecasting of complex landslide behaviors.
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.
文摘Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.
基金the Young Investigator Group“Artificial Intelligence for Probabilistic Weather Forecasting”funded by the Vector Stiftungfunding from the Federal Ministry of Education and Research(BMBF)and the Baden-Württemberg Ministry of Science as part of the Excellence Strategy of the German Federal and State Governments。
文摘Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.
