Oil spill prediction is critical for reducing the detrimental impact of oil spills on marine ecosystems,and the wind strong-ly influences the performance of oil spill models.However,the wind drift factor is assumed to...Oil spill prediction is critical for reducing the detrimental impact of oil spills on marine ecosystems,and the wind strong-ly influences the performance of oil spill models.However,the wind drift factor is assumed to be constant or parameterized by linear regression and other methods in existing studies,which may limit the accuracy of the oil spill simulation.A parameterization method for wind drift factor(PMOWDF)based on deep learning,which can effectively extract the time-varying characteristics on a regional scale,is proposed in this paper.The method was adopted to forecast the oil spill in the East China Sea.The discrepancies between predicted positions and actual measurement locations of the drifters are obtained using seasonal statistical analysis.Results reveal that PMOWDF can improve the accuracy of oil spill simulation compared with the traditional method.Furthermore,the parameteriza-tion method is validated with satellite observations of the Sanchi oil spill in 2018.展开更多
Exploration practices show that the Silurian hydrocarbon accumulation in the Tazhong Uplift is extremely complicated.Our research indicates that the oil and gas accumulation is controlled by favorable facies and low f...Exploration practices show that the Silurian hydrocarbon accumulation in the Tazhong Uplift is extremely complicated.Our research indicates that the oil and gas accumulation is controlled by favorable facies and low fluid potential.At the macro level,hydrocarbon distribution in this uplift is controlled by structural zones and sedimentary systems.At the micro level,oil occurrences are dominated by lithofacies and petrophysical facies.The control of facies is embodied in high porosity and permeability controlling hydrocarbon accumulation.Besides,the macro oil and gas distribution in the uplift is also influenced by the relatively low fluid potential at local highs,where most successful wells are located.These wells are also closely related to the adjacent fractures.Therefore,the Silurian hydrocarbon accumulation mechanism in the Tazhong Uplift can be described as follows.Induced by structures,the deep and overpressured fluids migrated through faults into the sand bodies with relatively low potential and high porosity and permeability.The released overpressure expelled the oil and gas into the normal-pressured zones,and the hydrocarbon was preserved by the overlying caprock of poorly compacted Carboniferous and Permian mudstones.Such a mechanism reflects favorable facies and low potential controlling hydrocarbon accumulation.Based on the statistical analysis of the reservoirs and commercial wells in the uplift,a relationship between oil-bearing property in traps and the facies-potential index was established,and a prediction of two favorable targets was made.展开更多
Crude oil price prediction is a challenging task in oil producing countries.Its price is among the most complex and tough to model because fluctuations of price of crude oil are highly irregular,nonlinear and varies d...Crude oil price prediction is a challenging task in oil producing countries.Its price is among the most complex and tough to model because fluctuations of price of crude oil are highly irregular,nonlinear and varies dynamically with high uncertainty.This paper proposed a hybrid model for crude oil price prediction that uses the complex network analysis and long short-term memory(LSTM)of the deep learning algorithms.The complex network analysis tool called the visibility graph is used to map the dataset on a network and K-core centrality was employed to extract the non-linearity features of crude oil and reconstruct the dataset.The complex network analysis is carried out in order to preprocess the original data to extract the non-linearity features and to reconstruct the data.Thereafter,LSTM was employed to model the reconstructed data.To verify the result,we compared the empirical results with other research in the literature.The experiments show that the proposed model has higher accuracy,and is more robust and reliable.展开更多
Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production,starting from the upstream and downstream.This content can be used to monitor the progress of the oil palm fr...Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production,starting from the upstream and downstream.This content can be used to monitor the progress of the oil palm fresh fruit bunch(FFB)and be applied to identify product profitability.Based on the near-infrared(NIR)signals,this study proposes an empirical mode decomposition(EMD)technique to decompose signals and predict the oil content of palm fruit.First,350 palm fruits with Tenera varieties(Elaeis guineensis Jacq.var.tenera),at various ages of maturity,were harvested from the Cikabayan Oil Palm Plantation(IPB University,Indonesia).Second,each sample was sent directly to the laboratory for NIR signal measurements and oil content extraction.Then,the EMD analysis and arti-ficial neural network(ANN)were employed to correlate the NIR signals and oil content.Finally,a robust EMD-ANN model is generated by optimizing the lowest possible errors.Based on performance evaluation,the proposed technique can predict oil content with a coefficient of determination(R2)of 0.933±0.015 and a root mean squared error(RMSE)of 1.446±0.208.These results demonstrate that the model has a good predictive capacity and has the potential to predict the oil content of palm fruits directly,without neither solvents nor reagents,which makes it environmentally friendly.Therefore,the proposed technique has a promising potential to be applied in the oil palm industry.Measurements like this will lead to the effective and efficient management of oil palm production.展开更多
The transparent open box(TOB)learning network algorithm offers an alternative approach to the lack of transparency provided by most machine-learning algorithms.It provides the exact calculations and relationships amon...The transparent open box(TOB)learning network algorithm offers an alternative approach to the lack of transparency provided by most machine-learning algorithms.It provides the exact calculations and relationships among the underlying input variables of the datasets to which it is applied.It also has the capability to achieve credible and auditable levels of prediction accuracy to complex,non-linear datasets,typical of those encountered in the oil and gas sector,highlighting the potential for underfitting and overfitting.The algorithm is applied here to predict bubble-point pressure from a published PVT dataset of 166 data records involving four easy-tomeasure variables(reservoir temperature,gas-oil ratio,oil gravity,gas density relative to air)with uneven,and in parts,sparse data coverage.The TOB network demonstrates high-prediction accuracy for this complex system,although it predictions applied to the full dataset are outperformed by an artificial neural network(ANN).However,the performance of the TOB algorithm reveals the risk of overfitting in the sparse areas of the dataset and achieves a prediction performance that matches the ANN algorithm where the underlying data population is adequate.The high levels of transparency and its inhibitions to overfitting enable the TOB learning network to provide complementary information about the underlying dataset to that provided by traditional machine learning algorithms.This makes them suitable for application in parallel with neural-network algorithms,to overcome their black-box tendencies,and for benchmarking the prediction performance of other machine learning algorithms.展开更多
基金funded by the Social Science Foundation of Shandong(No.20CXWJ08).
文摘Oil spill prediction is critical for reducing the detrimental impact of oil spills on marine ecosystems,and the wind strong-ly influences the performance of oil spill models.However,the wind drift factor is assumed to be constant or parameterized by linear regression and other methods in existing studies,which may limit the accuracy of the oil spill simulation.A parameterization method for wind drift factor(PMOWDF)based on deep learning,which can effectively extract the time-varying characteristics on a regional scale,is proposed in this paper.The method was adopted to forecast the oil spill in the East China Sea.The discrepancies between predicted positions and actual measurement locations of the drifters are obtained using seasonal statistical analysis.Results reveal that PMOWDF can improve the accuracy of oil spill simulation compared with the traditional method.Furthermore,the parameteriza-tion method is validated with satellite observations of the Sanchi oil spill in 2018.
基金funded by National Natural Science Foundation Programs of China(Grant No.40802029 and No. 41072100)973 Program(Grant No.2006CB209108)
文摘Exploration practices show that the Silurian hydrocarbon accumulation in the Tazhong Uplift is extremely complicated.Our research indicates that the oil and gas accumulation is controlled by favorable facies and low fluid potential.At the macro level,hydrocarbon distribution in this uplift is controlled by structural zones and sedimentary systems.At the micro level,oil occurrences are dominated by lithofacies and petrophysical facies.The control of facies is embodied in high porosity and permeability controlling hydrocarbon accumulation.Besides,the macro oil and gas distribution in the uplift is also influenced by the relatively low fluid potential at local highs,where most successful wells are located.These wells are also closely related to the adjacent fractures.Therefore,the Silurian hydrocarbon accumulation mechanism in the Tazhong Uplift can be described as follows.Induced by structures,the deep and overpressured fluids migrated through faults into the sand bodies with relatively low potential and high porosity and permeability.The released overpressure expelled the oil and gas into the normal-pressured zones,and the hydrocarbon was preserved by the overlying caprock of poorly compacted Carboniferous and Permian mudstones.Such a mechanism reflects favorable facies and low potential controlling hydrocarbon accumulation.Based on the statistical analysis of the reservoirs and commercial wells in the uplift,a relationship between oil-bearing property in traps and the facies-potential index was established,and a prediction of two favorable targets was made.
文摘Crude oil price prediction is a challenging task in oil producing countries.Its price is among the most complex and tough to model because fluctuations of price of crude oil are highly irregular,nonlinear and varies dynamically with high uncertainty.This paper proposed a hybrid model for crude oil price prediction that uses the complex network analysis and long short-term memory(LSTM)of the deep learning algorithms.The complex network analysis tool called the visibility graph is used to map the dataset on a network and K-core centrality was employed to extract the non-linearity features of crude oil and reconstruct the dataset.The complex network analysis is carried out in order to preprocess the original data to extract the non-linearity features and to reconstruct the data.Thereafter,LSTM was employed to model the reconstructed data.To verify the result,we compared the empirical results with other research in the literature.The experiments show that the proposed model has higher accuracy,and is more robust and reliable.
基金the Research and Community Services Institution,IPB University(project no.10225/IT3.S3/KS/2020)。
文摘Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production,starting from the upstream and downstream.This content can be used to monitor the progress of the oil palm fresh fruit bunch(FFB)and be applied to identify product profitability.Based on the near-infrared(NIR)signals,this study proposes an empirical mode decomposition(EMD)technique to decompose signals and predict the oil content of palm fruit.First,350 palm fruits with Tenera varieties(Elaeis guineensis Jacq.var.tenera),at various ages of maturity,were harvested from the Cikabayan Oil Palm Plantation(IPB University,Indonesia).Second,each sample was sent directly to the laboratory for NIR signal measurements and oil content extraction.Then,the EMD analysis and arti-ficial neural network(ANN)were employed to correlate the NIR signals and oil content.Finally,a robust EMD-ANN model is generated by optimizing the lowest possible errors.Based on performance evaluation,the proposed technique can predict oil content with a coefficient of determination(R2)of 0.933±0.015 and a root mean squared error(RMSE)of 1.446±0.208.These results demonstrate that the model has a good predictive capacity and has the potential to predict the oil content of palm fruits directly,without neither solvents nor reagents,which makes it environmentally friendly.Therefore,the proposed technique has a promising potential to be applied in the oil palm industry.Measurements like this will lead to the effective and efficient management of oil palm production.
文摘The transparent open box(TOB)learning network algorithm offers an alternative approach to the lack of transparency provided by most machine-learning algorithms.It provides the exact calculations and relationships among the underlying input variables of the datasets to which it is applied.It also has the capability to achieve credible and auditable levels of prediction accuracy to complex,non-linear datasets,typical of those encountered in the oil and gas sector,highlighting the potential for underfitting and overfitting.The algorithm is applied here to predict bubble-point pressure from a published PVT dataset of 166 data records involving four easy-tomeasure variables(reservoir temperature,gas-oil ratio,oil gravity,gas density relative to air)with uneven,and in parts,sparse data coverage.The TOB network demonstrates high-prediction accuracy for this complex system,although it predictions applied to the full dataset are outperformed by an artificial neural network(ANN).However,the performance of the TOB algorithm reveals the risk of overfitting in the sparse areas of the dataset and achieves a prediction performance that matches the ANN algorithm where the underlying data population is adequate.The high levels of transparency and its inhibitions to overfitting enable the TOB learning network to provide complementary information about the underlying dataset to that provided by traditional machine learning algorithms.This makes them suitable for application in parallel with neural-network algorithms,to overcome their black-box tendencies,and for benchmarking the prediction performance of other machine learning algorithms.