Data- and Model-Driven Crude Oil Supply Risk Assessment of China Considering Maritime Transportation Factors

Combining physics-based and data-driven modeling in well construction: Hybrid fluid dynamics modeling

ENA-based evaluation of energy supply security: Comparison between the Chinese crude oil and natural gas supply systems

Clarifying new urban mobility services based on a threefold business model framework

Comparison of physical-based, data-driven and hybrid modeling approaches for evapotranspiration estimation

Dynamical models used in climate prediction often have systematic errors that can bias the predictions. In this study, we utilized machine learning to address this issue. Machine learning was applied to learn the error corrected by data assimilation and thus build a data-driven model to emulate the dynamical model error. A hybrid model was constructed by combining the dynamical and data-driven models. We tested the hybrid model using synthetic observations generated by a simplified high-resolution coupled ocean-atmosphere model (MAOOAM, De Cruz et al., 2016) and compared its performance to that of a low-resolution version of the same model used as a standalone dynamical model.To evaluate the forecast skill of the hybrid model, we produced ensemble predictions based on initial conditions determined through data assimilation. The results show that the hybrid model significantly improves the forecast skill for both atmospheric and oceanic variables compared to the dynamical model alone. To explore what affects short-term forecast skills and long-term forecast skills, we built two other hybrid models by correcting errors either only atmospheric or only oceanic variables. For short-term atmospheric forecasts, the results show that correcting only oceanic errors has no effect on atmosphere variables forecasts but correcting only atmospheric variables shows similar forecast skill to correcting both atmospheric and oceanic errors. For the long-term forecast of oceanic variables, correcting the oceanic error can improve the forecast skill, but correcting both atmospheric and oceanic errors can obtain the best forecast skill. The results indicate that for the long-term forecast of oceanic variables, bias correction of both oceanic and atmospheric components can have a significant effect.

Data-driven vehicle modeling of longitudinal dynamics based on a multibody model and deep neural networks

The article gives an insight into the general course of action of the Serbian state aimed at the diversification of hydrocarbon sources with an emphasis on the supply of crude oil. Furthermore, a case with primary goal related to the increase of energy system stability is presented in the light of its secondary psycho-informational influence. Interactions with the Russian leadership are analysed, mainly along the lines of the Serbian position regarding the territorial integrity of Ukraine and the possible accession to the sanction’s regime against the Russian Federation. The methodology of the study is based on a structuralist approach consisting of synchronic interpretation of separate phenomena directed towards the derivation of gross constituent units of relations. The results extrapolate that the practical steps aimed at guaranteeing the energy security of the country show lack of interest to move away from Russian supply of natural gas and crude oil which is in turn intrinsically related to the future general geopolitical stance of official Belgrade. Active diplomacy in the region is concentrated along the Vienna-Budapest axis. The significance of the results arises from the fact that the represented gross constituent units of relations expose a firm course that is diverging from the EU CFSP

Microfluidic platforms serve as powerful tools for pore-scale transport studies, generating datasets ideal for data-driven modeling. While conventional physics-driven models dominate flow characterization, their simplified two-dimensional (2D) implementations introduce substantial bias despite computational efficiency. Conversely, pure data-driven approaches face generalization limitations. To address both challenges, we developed a hybrid framework embedding physical transport mechanisms into neural networks. Through microfluidic experiments comparing four modeling approaches (pure data-driven, hybrid, 2D physics-based, and 2D depth-averaged models), we demonstrated that the hybrid model achieved consistent predictive accuracy across temporal scales. It outperformed traditional 2D physics-based models, which exhibited significant prediction bias. The model generalized well at different flow rates, as evidenced by the accurate reconstruction of the concentration field. Both hybrid and data-driven models performed comparably in short-term forecasting with sufficient data, but the hybrid framework uniquely maintained long-term prediction reliability. Quantitative analysis revealed monotonic accuracy improvements with increased experimental data in hybrid model bias correction. This work establishes the first experimental validation of hybrid modeling for pore-scale solute transport in microfluidic systems, bridging microscale observations with deep learning for enhanced porous media transport prediction.

Manufacturing, an industry set in the physical world, is undergoing its digital transformation, also known as the fourth industrial revolution. Sensors, connectivity, and platforms provide unprecedented access to quantify the quality and diversity of manufacturing data. Progress in data-driven modeling is exponential across all industries. This leads to the question of how physics-based and data-driven modeling can be utilized in a hybrid modeling approach to advance our understanding of processes, materials, and systems in manufacturing. In this review, we focus on discrete manufacturing based on the understanding that hybrid modeling is more mature in process manufacturing. This paper aims to provide an overview of projects where hybrid modeling was used in manufacturing and introduce various ways of composing hybrid models. We provide examples highlighting the implementation of models, structure and expand on metrics to test and validate hybrid models, discuss challenges, and future research directions of hybrid modeling in manufacturing.

The Petroleum Supply Annual (PSA) contains information on the supply and disposition of crude oil and petroleum products. The publication reflects data that were collected from the petroleum industry during 1996 through annual and monthly surveys. The PSA is divided into two volumes. This first volume contains three sections: Summary Statistics, Detailed Statistics, and Refinery Capacity; each with final annual data. The summary statistics section show 16 years of data depicting the balance between supply, disposition and ending stocks for various commodities including crude oil, motor gasoline, distillate fuel oil, residual fuel oil, jet fuel propane/propylene, and liquefied petroleum gases. The detailed statistics section provide 1996 detailed statistics on supply and disposition, refinery operations, imports and exports, stocks, and transportation of crude oil and petroleum products. The refinery capacity contain listings of refineries and associated crude oil distillation and downstream capacities by State, as of January 1, 1997, as well as summaries of corporate refinery capacities and refinery storage capacities. In addition, refinery receipts of crude oil by method of transportation for 1996 are provided. Also included are fuels consumed at refineries, and lists of shutdowns, sales, reactivations, and mergers during 1995 and 1996. 16 figs., 59 tabs.

PurposeThe agriculture industry has a considerable impact on Malaysia’s economy, as seen by its contribution of roughly 8.2% of gross domestic product in 2018 and its potential to absorb 11.09% of Malaysian labor in the same year. This study aims to simulate rising output in a system model of sustainable and profitable crude palm oil (CPO) supply chain management (SCM) and to formulate policy solutions to build sustainable and profitable SCM of Malaysian CPO.Design/methodology/approachThis research included both primary and secondary data. This study used the dynamic system model to simulate palm oil land expansion, replanting policies and environmentally friendly growing techniques.FindingsThis study’s findings suggest that the dynamic system model of Malaysia’s CPO’s sustainable and profitable SCM is valid when its structure and performance are tested. The fifth scenario provides the best results, with the most significant net benefit value compared to the other scenarios.Originality/valueThe ideal policy alternative is replanting sustainable agricultural practices without burning technologies during new land clearing to achieve the best net advantages.

Heavy (viscous) crude oils have become an increasingly important source of hydrocarbons in many parts of the world. Transport of these viscous crudes from the source to the refinery can be a problem. In a number of producing areas, a pipeline is in place, but the line was designed for lighter (less viscous) crudes. Pipeline transport can be effected by heating, dilution with lighter fractions, or thermal viscosity breaking. All of these techniques are expensive and are not practical in many situations. Techniques are needed to reduce the pumping costs without significantly increasing the handling costs at: either end of the pipeline. High oil content oil-in-water emulsions have been shown to be a viable alternative to the techniques mentioned above. Dramatic decreases in viscosity can be achieved while transporting a fluid which has an oil content of 70% or greater. A knowledge of the rheological behavior of these emulsions, under both laboratory and field conditions, is important. In this study, four different viscous crude oils were used. The viscosities ranged between 2000 and 500,000 (estimated) centipoise (2.0 to 500 Pa·s). The emulsions ranged from 60 to 72.5% oil in tap water stabilized with an emulsion stabilizer. Rheological measurements were carried out with a tube flow viscometer equipped with three tube sizes and a concentric cylinder viscometer (Rheometrics Pressure Rheometer). The data obtained showed that the shear stress-shear rate behavior of the emulsions are highly dependent on oil droplet size. For a given oil concentration, the non-Newtonian character and the apparent viscosity increased with decreasing droplet size. The majority of the emulsions showed shear thinning behavior at low shear rates (below 50 s−1) and Newtonian behavior at shear rates above 1000 s−1. These data show that the power law model is insufficient for the whole range of shear rates. A three parameter model needs to be considered. Results show that oil droplet size is the dominant factor in the behavior of emulsions. The influence of mixing intensity and duration while preparing the emulsion and emulsifier concentration on the resulting droplet size were investigated. Pipe flow data were collected for scale-up studies. Data were collected in both the laminar and turbulent flow regimes. This study reveals that careful laboratory testing and scale-up is needed prior to the designing of pipeline systems for the transport of heavy crude oils as emulsions.

Study regionVarahi River originating from the Western Ghats of India. Study focusWe developed a hybrid model that integrates process-based hydrological model (PHM) and data-driven (DD) techniques to generate streamflow simulations precisely. The hybrid modeling framework is practical as it respects hydrological processes through the PHM while considering the advantage of the DD model's ability to simulate the complex relationship between residuals and input variables. Further, we have proposed an optimization-based nudging scheme for post-processing the hybrid model simulated streamflow to overcome the limitations in PHM and DD. New hydrological insights for the regionWe formulated two approaches for simulating streamflow ensembles using DD and PHM models. In approach− 1, DD models are initially used to ensemble meteorological variables and then use the ensembles in a PHM to simulate streamflows. In approach− 2, PHM is forced with different sets of meteorological variables to simulate multiple streamflow sets and then use DD models to ensemble the PHM-derived streamflows. Random forest exhibited better performance for ensembling precipitation, temperature, and streamflow datasets compared to the other five DD algorithms in the study. Streamflows generated using approach− 2 showed reliable estimates when compared against observed streamflow values. However, post-processing the hybrid streamflows using an optimization-based nudging scheme outperformed the streamflows generated in approach− 1 and approach− 2 with better model fit statistics (R2 and NSE of 0.69 and 0.66). The output from the nudging scheme was further utilized for streamflow predictions under the combined impact of land use/cover (LULC) and climate change (CC) under the Representative Concentration Pathway 4.5 scenario. It depicted a decrease in monthly and seasonal stream flows with − 22.65 %, − 31.77 %, − 11.81 % for winter, summer, and monsoon seasons, respectively. These results suggest that water availability will decline, and water scarcity will increase in the study region. These variations in streamflow might negatively impact agriculture and natural ecosystems and even lead to water restrictions in the region.

Hydraulic-thermal coupling dynamic models based on mechanism and data-driven methods of the heating networks in integrated energy systems

Due to the numerous and widespread oil fields worldwide, the main components of the produced crude oil vary significantly. However, after years of research and analysis by researchers, it is believed that four main fractions in crude oil have the greatest impact on its low-temperature fluidity, namely saturated hydrocarbons, aromatic hydrocarbons, resins, and asphaltenes. During the transportation of crude oil, surfactants have always played an important role. This article elucidates the mechanism of surfactants in crude oil transportation, summarizing the recent years’ application and development progress of various surfactants in the transportation of heavy crude oil and waxy crude oil. This analysis indicates that using a single surfactant alone has a certain effect on reducing the pour point and viscosity of crude oil, but the effect is limited. To improve the pour point and viscosity reduction effects of surfactants, it is necessary to modify the surfactants. Research shows that introducing an appropriate amount of polar groups into surfactants can significantly reduce the viscosity of heavy crude oil. Based on the carbon number distribution of paraffin in waxy crude oil, introducing side chains of appropriate length into the surfactant can greatly enhance its pour point reduction effect.