Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning ...Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning methods,accurate and reliable price forecasts can be achieved.This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting(XGBoost).We benchmark XGBoost against four alternatives—Support Vector Machines(SVM),Long Short-Term Memory(LSTM),Random Forest(RF),and Gradient Boosting(GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul(EXIST).All models were trained on an identical chronological 80/20 train–test split,with hyperparameters tuned via 5-fold cross-validation on the training set.XGBoost achieved the best performance(Mean Absolute Error(MAE)=144.8 TRY/MWh,Root Mean Square Error(RMSE)=201.8 TRY/MWh,coefficient of determination(R^(2))=0.923)while training in 94 s.To enhance interpretability and identify key drivers,we employed Shapley Additive Explanations(SHAP),which highlighted a strong association between higher prices and increased natural-gas-based generation.The results provide a clear performance benchmark and practical guidance for selecting forecasting approaches in day-ahead electricity markets.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
Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefor...Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.展开更多
The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the th...The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the threshold for fluidelastic instability and affect heat transfer efficiency.This paper presents a mathematical model incorporating the squeeze film force between the tube and the support structure.We aim to clarify the mechanisms underlying fluidelastic instability in tube bundle systems exposed to two-phase flow.Using a self-developed computer program,we performed numerical calculations to examine the influence of the squeeze film on the threshold of fluidelastic instability in the tube bundle system.Furthermore,we analyzed how the thickness and length of the squeeze film affect both the underlying mechanisms and the critical velocity of fluidelastic instability.展开更多
Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristic...Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristics complicate the gas-water two-phase flow process in porous media following hydrate decomposition, posing challenges for efficient development. This study examines the transport response of clayey-silt reservoir samples from the Shenhu area using gas-water two-phase flow experiments and CT scanning to explore changes in pore structure, gas-water distribution, and relative permeability under varying flow conditions. The results indicate that pore heterogeneity significantly influences flow characteristics. Gas preferentially displaces water in larger pores, forming fracture-like pores, which serve as preferential flow channels for gas migration. The preferential flow channels enhance gas-phase permeability up to 19 times that of the water phase when fluid pressures exceed total stresses. However,small pores retain liquid, leading to a high residual water saturation of 0.561. CT imaging reveals that these hydro-fractures improve gas permeability but also confine gas flow to specific channels. Pore network analysis shows that gas injection expands the pore-throat network, enhancing connectivity and forming fracture-like pores. Residual water remains trapped in smaller pores and throats, while structural changes, including new fractures, improve gas flow pathways and overall connectivity. Relative permeability curves demonstrate a narrow gas-water cocurrent-flow zone, a right-shifted iso-permeability point and high reservoir capillary pressure, indicating a strong "water-blocking" effect. The findings suggest that optimizing reservoir stimulation techniques to enhance fracture formation, reduce residual water saturation, and improve gas flow capacity is critical for efficient hydrate reservoir development.展开更多
This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the...This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the excitation frequency aligns with the natural frequency of the pipe,significantly increasing the degree of operational risk.The governing equation of motion based on the Euler-Bernoulli beam is derived for the relative deflection with stationary simply supported ends,with the effects of the external excitations represented by source terms distributed along the pipe length.The fourth-order partial differential equation is solved via the generalized integral transform technique(GITT),with the solution successfully verified via comparison with results in the literature.A comprehensive analysis of the vibration phenomena and changes in the motion state of the pipe is conducted for three classes of external excitation conditions:same frequency and amplitude(SFSA),same frequency but different amplitudes(SFDA),and different frequencies and amplitudes(DFDA).The numerical results show that with increasing gas volume fraction,the position corresponding to the maximum vibration displacement shifts upward.Compared with conditions without external excitation,the vibration displacement of the pipe conveying two-phase flow under external excitation increases significantly.The frequency of external excitation has a significant effect on the dynamic behavior of a pipe conveying two-phase flow.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
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
As financial markets grow increasingly complex and volatile,timeseriesbased stock price forecasting has become a critical research focus in the field of finance.Traditional forecasting methods face significant limitat...As financial markets grow increasingly complex and volatile,timeseriesbased stock price forecasting has become a critical research focus in the field of finance.Traditional forecasting methods face significant limitations in handling nonlinear and high-dimensional data,while neural networks(NNs)have demonstrated great potential due to their powerful feature extraction and pattern recognition capabilities.Although several existing surveys discuss the applications of NNs in stock forecasting,they often lack a detailed examination of models that use time-series data as input and fail to cover the latest research developments.In response,this paper reviews relevant literature from 2015 to 2025 and classifies timeseriesbased stock forecasting methods into four categories:NNs,recurrent NNs(RNNs),convolutional NNs(CNNs),Transformers and other models.We analyze their performance under different market conditions,highlight strengths and limitations,and identify recent trends in model design.Our findings show that hybrid architectures and attention-based models consistently achieve superior forecasting stability and adaptability across volatile market scenarios.This survey offers a systematic reference for researchers and practitioners and outlines promising future research directions.展开更多
Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital t...Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital twin(DT)technologies to enhance decision-making and efficiency in food production.A data-driven DT was implemented in an Italian company for Raspberry production planning,based on a daily demand forecasting tool powered by a dynamic extreme gradient boosting(XGBoost)algorithm.The model achieved a mean absolute percentage error(MAPE)of 16.37%with 1.69 average of absolute extra working hours(AEW)and a tracking signal(TS)range of[−1.9,+4.3].展开更多
The significance of accurately forecasting natural gas prices is far-reaching and significant,not only for the stable operation of the energy market,but also as a key element in promoting sustainable development and a...The significance of accurately forecasting natural gas prices is far-reaching and significant,not only for the stable operation of the energy market,but also as a key element in promoting sustainable development and addressing environmental challenges.However,natural gas prices are affected by multiple source factors,presenting complex,unstable nonlinear characteristics hindering the improvement of the prediction accuracy of existing models.To address this issue,this study proposes an innovative multivariate combined forecasting model for natural gas prices.Initially,the study meticulously identifies and introduces 16 variables impacting natural gas prices across five crucial dimensions:the production,marketing,commodities,political and economic indicators of the United States and temperature.Subsequently,this study employs the least absolute shrinkage and selection operator,grey relation analysis,and random forest for dimensionality reduction,effectively screening out the most influential key variables to serve as input features for the subsequent learning model.Building upon this foundation,a suite of machine learning models is constructed to ensure precise natural gas price prediction.To further elevate the predictive performance,an intelligent algorithm for parameter optimization is incorporated,addressing potential limitations of individual models.To thoroughly assess the prediction accuracy of the proposed model,this study conducts three experiments using monthly natural gas trading prices.These experiments incorporate 19 benchmark models for comparative analysis,utilizing five evaluation metrics to quantify forecasting effectiveness.Furthermore,this study conducts in-depth validation of the proposed model's effectiveness through hypothesis testing,discussions on the improvement ratio of forecasting performance,and case studies on other energy prices.The empirical results demonstrate that the multivariate combined forecasting method developed in this study surpasses other comparative models in forecasting accuracy.It offers new perspectives and methodologies for natural gas price forecasting while also providing valuable insights for other energy price forecasting studies.展开更多
The China Meteorological Administration(CMA)said that in the last five years,China has made big improvements in its weather services.This includes better weather forecasts and ways to protect people from disasters.
The dynamics of vapor−liquid−solid(V−L−S)flow boiling in fluidized bed evaporators exhibit inherent complexity and chaotic behavior,hindering accurate prediction of pressure drop signals.To address this challenge,this...The dynamics of vapor−liquid−solid(V−L−S)flow boiling in fluidized bed evaporators exhibit inherent complexity and chaotic behavior,hindering accurate prediction of pressure drop signals.To address this challenge,this study proposes an innovative hybrid approach that integrates wavelet neural network(WNN)with chaos analysis.By leveraging the Cross-Correlation(C−C)method,the minimum embedding dimension for phase space reconstruction is systematically calculated and then adopted as the input node configuration for the WNN.Simulation results demonstrate the remarkable effectiveness of this integrated method in predicting pressure drop signals,advancing our understanding of the intricate dynamic phenomena occurring with V−L−S fluidized bed evaporators.Moreover,this study offers a novel perspective on applying advanced data-driven techniques to handle the complexities of multi-phase flow systems and highlights the potential for improved operational prediction and control in industrial settings.展开更多
Cleat serves as the primary flow pathway for coalbed methane(CBM)and water.However,few studies consider the impact of local contact on two-phase flow within cleats.A visual generalized model of endogenous cleats was c...Cleat serves as the primary flow pathway for coalbed methane(CBM)and water.However,few studies consider the impact of local contact on two-phase flow within cleats.A visual generalized model of endogenous cleats was constructed based on microfluidics.A microscopic and mesoscopic observation technique was proposed to simultaneously capture gas-liquid interface morphology of pores and throat and the two-phase flow characteristics in entire cleat system.The local contact characteristics of cleats reduced absolute permeability,which resulted in a sharp increase in the starting pressure.The reduced gas flow capacity narrowed the co-infiltration area and decreased water saturation at the isotonic point in a hydrophilic environment.The increased local contact area of cleats weakened gas phase flow capacity and narrowed the co-infiltration area.Jumping events occurred in methane-water flow due to altered porosity caused by local contact in cleats.The distribution of residual phases changed the jumping direction on the micro-scale as well as the dominant channel on the mesoscale.Besides,jumping events caused additional energy dissipation,which was ignored in traditional two-phase flow models.This might contribute to the overestimation of relative permeability.The work provides new methods and insights for investigating unsaturated flow in complex porous media.展开更多
Financial time series have been analyzed with a wide variety of models and approaches,some of which can forecast with great accuracy.However,most of these models,especially the machine learning ones,cannot show additi...Financial time series have been analyzed with a wide variety of models and approaches,some of which can forecast with great accuracy.However,most of these models,especially the machine learning ones,cannot show additional information for the decision maker or the financial analyst.The notion of causality is a concept that provides a more complete understanding of a problem beyond improved forecasts.In this study,we propose integrating the treatment/control concept of causality into a forecasting framework to better predict financial time series.Our results show that the proposed methodology outperforms classic econometric approaches such as ARIMA and Random Walk,as well as machine learning approaches without the proposed methodology.This improvement is statistically significant,as indicated by the Model Confidence Set test in the complete test set and quarterly analysis.展开更多
In this study, the three-dimensional non-premixed two-phase kerosene/air rotating detonation engines with different isolator configurations and throat area ratios are simulated by the Eulerian-Lagrangian method. The e...In this study, the three-dimensional non-premixed two-phase kerosene/air rotating detonation engines with different isolator configurations and throat area ratios are simulated by the Eulerian-Lagrangian method. The effects of the divergence, straight, and convergence isolators on the rotating detonation wave dynamics and the upstream oblique shock wave propagation mechanism are analyzed. The differences in the rotating detonation wave behaviors between ground and flight operations are clarified.The results indicate that the propagation regimes of the upstream oblique shock wave depend on the isolator configurations and operation conditions. With a divergence isolator, the airflow is accelerated throughout the isolator and divergence section, leading to a maximum Mach number(~1.8) before the normal shock. The total pressure loss reaches the largest, and the detonation pressure drops. The upstream oblique shock wave can be suppressed within the divergence section with the divergence isolator.However, for the straight and convergence isolators, the airflow in the isolator with a larger ψ_(1)(0.3 and0.4) can suffer from the disturbance of the upstream oblique shock wave. The critical incident angle is around 39° at ground operation conditions. The upstream oblique shock wave tends to be suppressed when the engine operates under flight operation conditions. The critical pressure ratio β_(cr0) is found to be able to help in distinguishing the propagation regimes of the upstream oblique shock wave. Slightly below or above the β_(cr0) can obtain different marginal propagation results. The high-speed airflow in the divergence section affects the fuel droplet penetration distance, which deteriorates the reactant mixing and the detonation area. Significant detonation velocity deficits are observed and the maximum velocity deficit reaches 26%. The results indicate the engine channel design should adopt different isolator configurations based on the purpose of total pressure loss or disturbance suppression. This study can provide useful guidance for the channel design of a more complete two-phase rotating detonation engine.展开更多
Two-phase partitioning bioreactors(TPPBs)have been widely used because they overcome the mass-transfer limitation of hydrophobic volatile organic compounds(VOCs)in waste gas biological treatments.Understanding the mec...Two-phase partitioning bioreactors(TPPBs)have been widely used because they overcome the mass-transfer limitation of hydrophobic volatile organic compounds(VOCs)in waste gas biological treatments.Understanding the mechanisms of mass-transfer enhancement in TPPBs would enable efficient predictions for further industrial applications.In this study,influences of gradually increasing silicone oil ratio on the TPPB was explored,and a 94.35%reduction of the n-hexane partition coefficient was observed with 0.1 vol.%silicone,which increased to 80.7%along with a 40-fold removal efficiency enhancement in the stabilised removal period.The elimination capacity increased from 1.47 to 148.35 g/(m^(3)·h),i.e.a 101-fold increase compared with that of the single-phase reactors,when 10 vol.%(3 Critical Micelle Concentration)silicone oil was added.The significantly promoted partition coefficient was the main reason for the mass transfer enhancement,which covered the negative influences of the decreased total mass-transfer coefficient with increasing silicone oil volume ratio.The gradually rising stirring rate was benefit to the n-hexane removal,which became negative when the dominant resistance shifted from mass transfer to biodegradation.Moreover,a mass-transfer-reaction kinetic model of the TPPB was constructed based on the balance of n-hexane concentration,dissolved oxygen and biomass.Similar to the mechanism,the partition factor was predicted sensitive to the removal performance,and another five sensitive parameters were found simultaneously.This forecasting method enables the optimisation of TPPB performance and provides theoretical support for hydrophobic VOCs degradation.展开更多
文摘Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning methods,accurate and reliable price forecasts can be achieved.This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting(XGBoost).We benchmark XGBoost against four alternatives—Support Vector Machines(SVM),Long Short-Term Memory(LSTM),Random Forest(RF),and Gradient Boosting(GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul(EXIST).All models were trained on an identical chronological 80/20 train–test split,with hyperparameters tuned via 5-fold cross-validation on the training set.XGBoost achieved the best performance(Mean Absolute Error(MAE)=144.8 TRY/MWh,Root Mean Square Error(RMSE)=201.8 TRY/MWh,coefficient of determination(R^(2))=0.923)while training in 94 s.To enhance interpretability and identify key drivers,we employed Shapley Additive Explanations(SHAP),which highlighted a strong association between higher prices and increased natural-gas-based generation.The results provide a clear performance benchmark and practical guidance for selecting forecasting approaches in day-ahead electricity markets.
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financial support by the National Natural Science Foundation of China (Nos.52471293 and 12372270)the National Youth Science Foundation of China (Nos.52101322 and 52108375)+3 种基金the Program for Intergovernmental International S&T Cooperation Projects of Shanghai Municipality, China (Nos.24510711100 and 22160710200)The Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (No.SL2022PT101)funded by the Open Fund of the State Key Laboratory of Coastal and Offshore Engineering of Dalian University of Technology (No.LP2415)National Key R&D Program of China (No.2023YFC2811600)
文摘Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.
基金financially supported by the National Natural Science Foundation of China(Grant No.12072336).
文摘The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the threshold for fluidelastic instability and affect heat transfer efficiency.This paper presents a mathematical model incorporating the squeeze film force between the tube and the support structure.We aim to clarify the mechanisms underlying fluidelastic instability in tube bundle systems exposed to two-phase flow.Using a self-developed computer program,we performed numerical calculations to examine the influence of the squeeze film on the threshold of fluidelastic instability in the tube bundle system.Furthermore,we analyzed how the thickness and length of the squeeze film affect both the underlying mechanisms and the critical velocity of fluidelastic instability.
基金the National Natural Science Foundation of China (Nos. 42302143, 42172159)China Geological Survey Project (No. DD20211350)support from the G. Albert Shoemaker endowment
文摘Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristics complicate the gas-water two-phase flow process in porous media following hydrate decomposition, posing challenges for efficient development. This study examines the transport response of clayey-silt reservoir samples from the Shenhu area using gas-water two-phase flow experiments and CT scanning to explore changes in pore structure, gas-water distribution, and relative permeability under varying flow conditions. The results indicate that pore heterogeneity significantly influences flow characteristics. Gas preferentially displaces water in larger pores, forming fracture-like pores, which serve as preferential flow channels for gas migration. The preferential flow channels enhance gas-phase permeability up to 19 times that of the water phase when fluid pressures exceed total stresses. However,small pores retain liquid, leading to a high residual water saturation of 0.561. CT imaging reveals that these hydro-fractures improve gas permeability but also confine gas flow to specific channels. Pore network analysis shows that gas injection expands the pore-throat network, enhancing connectivity and forming fracture-like pores. Residual water remains trapped in smaller pores and throats, while structural changes, including new fractures, improve gas flow pathways and overall connectivity. Relative permeability curves demonstrate a narrow gas-water cocurrent-flow zone, a right-shifted iso-permeability point and high reservoir capillary pressure, indicating a strong "water-blocking" effect. The findings suggest that optimizing reservoir stimulation techniques to enhance fracture formation, reduce residual water saturation, and improve gas flow capacity is critical for efficient hydrate reservoir development.
基金financially supported by the Key Research and Development Program of Shandong Province(Grant Nos.2022CXGC020405,2023CXGC010415 and 2025TSGCCZZB0238)the National Natural Science Foundation of China(Grant No.52171288)the financial support from CNPq,FAPERJ,ANP,Embrapii,and China National Petroleum Corporation(CNPC).
文摘This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the excitation frequency aligns with the natural frequency of the pipe,significantly increasing the degree of operational risk.The governing equation of motion based on the Euler-Bernoulli beam is derived for the relative deflection with stationary simply supported ends,with the effects of the external excitations represented by source terms distributed along the pipe length.The fourth-order partial differential equation is solved via the generalized integral transform technique(GITT),with the solution successfully verified via comparison with results in the literature.A comprehensive analysis of the vibration phenomena and changes in the motion state of the pipe is conducted for three classes of external excitation conditions:same frequency and amplitude(SFSA),same frequency but different amplitudes(SFDA),and different frequencies and amplitudes(DFDA).The numerical results show that with increasing gas volume fraction,the position corresponding to the maximum vibration displacement shifts upward.Compared with conditions without external excitation,the vibration displacement of the pipe conveying two-phase flow under external excitation increases significantly.The frequency of external excitation has a significant effect on the dynamic behavior of a pipe conveying two-phase flow.
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 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.
文摘As financial markets grow increasingly complex and volatile,timeseriesbased stock price forecasting has become a critical research focus in the field of finance.Traditional forecasting methods face significant limitations in handling nonlinear and high-dimensional data,while neural networks(NNs)have demonstrated great potential due to their powerful feature extraction and pattern recognition capabilities.Although several existing surveys discuss the applications of NNs in stock forecasting,they often lack a detailed examination of models that use time-series data as input and fail to cover the latest research developments.In response,this paper reviews relevant literature from 2015 to 2025 and classifies timeseriesbased stock forecasting methods into four categories:NNs,recurrent NNs(RNNs),convolutional NNs(CNNs),Transformers and other models.We analyze their performance under different market conditions,highlight strengths and limitations,and identify recent trends in model design.Our findings show that hybrid architectures and attention-based models consistently achieve superior forecasting stability and adaptability across volatile market scenarios.This survey offers a systematic reference for researchers and practitioners and outlines promising future research directions.
基金supported by European Union’s Horizon Europe Research and Innovation Programme(101092043)project AGILEHAND(Smart Grading,Handling and Packaging Solutions for Soft and Deformable Products in Agile and Reconfigurable Lines).
文摘Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital twin(DT)technologies to enhance decision-making and efficiency in food production.A data-driven DT was implemented in an Italian company for Raspberry production planning,based on a daily demand forecasting tool powered by a dynamic extreme gradient boosting(XGBoost)algorithm.The model achieved a mean absolute percentage error(MAPE)of 16.37%with 1.69 average of absolute extra working hours(AEW)and a tracking signal(TS)range of[−1.9,+4.3].
基金supported by the funding from the Humanities and Social Science Fund of Ministry of Education of China(No.22YJCZH028)National Natural Science Foundation of China(Grant No.72303001)+3 种基金Fundamental Research Funds for the Central Universities(No.JUSRP124043)Anhui Provincial Excellent Young Scientists Fund for Universities(No.2024AH030001)Anhui Education Department Excellent Young Teachers Fund(No.YQYB2024021)Basic Research Program of Jiangsu(No.BK20251593)。
文摘The significance of accurately forecasting natural gas prices is far-reaching and significant,not only for the stable operation of the energy market,but also as a key element in promoting sustainable development and addressing environmental challenges.However,natural gas prices are affected by multiple source factors,presenting complex,unstable nonlinear characteristics hindering the improvement of the prediction accuracy of existing models.To address this issue,this study proposes an innovative multivariate combined forecasting model for natural gas prices.Initially,the study meticulously identifies and introduces 16 variables impacting natural gas prices across five crucial dimensions:the production,marketing,commodities,political and economic indicators of the United States and temperature.Subsequently,this study employs the least absolute shrinkage and selection operator,grey relation analysis,and random forest for dimensionality reduction,effectively screening out the most influential key variables to serve as input features for the subsequent learning model.Building upon this foundation,a suite of machine learning models is constructed to ensure precise natural gas price prediction.To further elevate the predictive performance,an intelligent algorithm for parameter optimization is incorporated,addressing potential limitations of individual models.To thoroughly assess the prediction accuracy of the proposed model,this study conducts three experiments using monthly natural gas trading prices.These experiments incorporate 19 benchmark models for comparative analysis,utilizing five evaluation metrics to quantify forecasting effectiveness.Furthermore,this study conducts in-depth validation of the proposed model's effectiveness through hypothesis testing,discussions on the improvement ratio of forecasting performance,and case studies on other energy prices.The empirical results demonstrate that the multivariate combined forecasting method developed in this study surpasses other comparative models in forecasting accuracy.It offers new perspectives and methodologies for natural gas price forecasting while also providing valuable insights for other energy price forecasting studies.
文摘The China Meteorological Administration(CMA)said that in the last five years,China has made big improvements in its weather services.This includes better weather forecasts and ways to protect people from disasters.
基金supported by the open foundation of State Key Laboratory of Chemical Engineering(SKL-ChE-22B01)the Natural Science Foundation of China(22008169).
文摘The dynamics of vapor−liquid−solid(V−L−S)flow boiling in fluidized bed evaporators exhibit inherent complexity and chaotic behavior,hindering accurate prediction of pressure drop signals.To address this challenge,this study proposes an innovative hybrid approach that integrates wavelet neural network(WNN)with chaos analysis.By leveraging the Cross-Correlation(C−C)method,the minimum embedding dimension for phase space reconstruction is systematically calculated and then adopted as the input node configuration for the WNN.Simulation results demonstrate the remarkable effectiveness of this integrated method in predicting pressure drop signals,advancing our understanding of the intricate dynamic phenomena occurring with V−L−S fluidized bed evaporators.Moreover,this study offers a novel perspective on applying advanced data-driven techniques to handle the complexities of multi-phase flow systems and highlights the potential for improved operational prediction and control in industrial settings.
基金the financial support from the National Natural Science Foundation of China (No.42102127)the Postdoctoral Research Foundation of China (No.2024 M751860)。
文摘Cleat serves as the primary flow pathway for coalbed methane(CBM)and water.However,few studies consider the impact of local contact on two-phase flow within cleats.A visual generalized model of endogenous cleats was constructed based on microfluidics.A microscopic and mesoscopic observation technique was proposed to simultaneously capture gas-liquid interface morphology of pores and throat and the two-phase flow characteristics in entire cleat system.The local contact characteristics of cleats reduced absolute permeability,which resulted in a sharp increase in the starting pressure.The reduced gas flow capacity narrowed the co-infiltration area and decreased water saturation at the isotonic point in a hydrophilic environment.The increased local contact area of cleats weakened gas phase flow capacity and narrowed the co-infiltration area.Jumping events occurred in methane-water flow due to altered porosity caused by local contact in cleats.The distribution of residual phases changed the jumping direction on the micro-scale as well as the dominant channel on the mesoscale.Besides,jumping events caused additional energy dissipation,which was ignored in traditional two-phase flow models.This might contribute to the overestimation of relative permeability.The work provides new methods and insights for investigating unsaturated flow in complex porous media.
基金ANID for supporting the Fondecyt project 1200555.
文摘Financial time series have been analyzed with a wide variety of models and approaches,some of which can forecast with great accuracy.However,most of these models,especially the machine learning ones,cannot show additional information for the decision maker or the financial analyst.The notion of causality is a concept that provides a more complete understanding of a problem beyond improved forecasts.In this study,we propose integrating the treatment/control concept of causality into a forecasting framework to better predict financial time series.Our results show that the proposed methodology outperforms classic econometric approaches such as ARIMA and Random Walk,as well as machine learning approaches without the proposed methodology.This improvement is statistically significant,as indicated by the Model Confidence Set test in the complete test set and quarterly analysis.
基金supported by the National Natural Science Foundation of China (Grant No. 12202204)the Natural Science Foundation of Jiangsu Province (Grant No. BK20220953)+1 种基金the Fundamental Research Funds for the Central Universitiesthe Science and Technology Association's Young Talent Nurturing Program of Jiangsu Province (Grant No. JSTJ-2024-004)
文摘In this study, the three-dimensional non-premixed two-phase kerosene/air rotating detonation engines with different isolator configurations and throat area ratios are simulated by the Eulerian-Lagrangian method. The effects of the divergence, straight, and convergence isolators on the rotating detonation wave dynamics and the upstream oblique shock wave propagation mechanism are analyzed. The differences in the rotating detonation wave behaviors between ground and flight operations are clarified.The results indicate that the propagation regimes of the upstream oblique shock wave depend on the isolator configurations and operation conditions. With a divergence isolator, the airflow is accelerated throughout the isolator and divergence section, leading to a maximum Mach number(~1.8) before the normal shock. The total pressure loss reaches the largest, and the detonation pressure drops. The upstream oblique shock wave can be suppressed within the divergence section with the divergence isolator.However, for the straight and convergence isolators, the airflow in the isolator with a larger ψ_(1)(0.3 and0.4) can suffer from the disturbance of the upstream oblique shock wave. The critical incident angle is around 39° at ground operation conditions. The upstream oblique shock wave tends to be suppressed when the engine operates under flight operation conditions. The critical pressure ratio β_(cr0) is found to be able to help in distinguishing the propagation regimes of the upstream oblique shock wave. Slightly below or above the β_(cr0) can obtain different marginal propagation results. The high-speed airflow in the divergence section affects the fuel droplet penetration distance, which deteriorates the reactant mixing and the detonation area. Significant detonation velocity deficits are observed and the maximum velocity deficit reaches 26%. The results indicate the engine channel design should adopt different isolator configurations based on the purpose of total pressure loss or disturbance suppression. This study can provide useful guidance for the channel design of a more complete two-phase rotating detonation engine.
基金supported by the National Key Research and Development Program of China(No.2022YFC3702000)the National Natural Science Foundation of China(No.52070169)the Project of Bureau of Science and Technology of Zhoushan,China(No.2022C41013).
文摘Two-phase partitioning bioreactors(TPPBs)have been widely used because they overcome the mass-transfer limitation of hydrophobic volatile organic compounds(VOCs)in waste gas biological treatments.Understanding the mechanisms of mass-transfer enhancement in TPPBs would enable efficient predictions for further industrial applications.In this study,influences of gradually increasing silicone oil ratio on the TPPB was explored,and a 94.35%reduction of the n-hexane partition coefficient was observed with 0.1 vol.%silicone,which increased to 80.7%along with a 40-fold removal efficiency enhancement in the stabilised removal period.The elimination capacity increased from 1.47 to 148.35 g/(m^(3)·h),i.e.a 101-fold increase compared with that of the single-phase reactors,when 10 vol.%(3 Critical Micelle Concentration)silicone oil was added.The significantly promoted partition coefficient was the main reason for the mass transfer enhancement,which covered the negative influences of the decreased total mass-transfer coefficient with increasing silicone oil volume ratio.The gradually rising stirring rate was benefit to the n-hexane removal,which became negative when the dominant resistance shifted from mass transfer to biodegradation.Moreover,a mass-transfer-reaction kinetic model of the TPPB was constructed based on the balance of n-hexane concentration,dissolved oxygen and biomass.Similar to the mechanism,the partition factor was predicted sensitive to the removal performance,and another five sensitive parameters were found simultaneously.This forecasting method enables the optimisation of TPPB performance and provides theoretical support for hydrophobic VOCs degradation.
