Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the g...Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.展开更多
Gap acceptance theory is broadly used for evaluating unsignalized intersections in developed coun tries. Intersections with no specific priority to any move ment, known as uncontrolled intersections, are common in Ind...Gap acceptance theory is broadly used for evaluating unsignalized intersections in developed coun tries. Intersections with no specific priority to any move ment, known as uncontrolled intersections, are common in India. Limited priority is observed at a few intersections, where priorities are perceived by drivers based on geom etry, traffic volume, and speed on the approaches of intersection. Analyzing such intersections is complex because the overall traffic behavior is the result of drivers, vehicles, and traffic flow characteristics. Fuzzy theory has been widely used to analyze similar situations. This paper describes the application of adaptive neurofuzzy interface system （ANFIS） to the modeling of gap acceptance behavior of rightturning vehicles at limited priority Tintersections （in India, vehicles are driven on the left side of a road）. Field data are collected using video cameras at four Tintersections having limited priority. The data extracted include gap/lag, subject vehicle type, conflicting vehicle type, and driver＇s decision （accepted/rejected）. ANFIS models are developed by using 80 % of the extracted data （total data observations for major road right turning vehicles are 722 and 1,066 for minor road right turning vehicles） and remaining are used for model vali dation. Four different combinations of input variables are considered for major and minor road right turnings sepa rately. Correct prediction by ANFIS models ranges from 75.17 % to 82.16 % for major road right turning and 87.20 % to 88.62 % for minor road right turning. Themodels developed in this paper can be used in the dynamic estimation of gap acceptance in traffic simulation models.展开更多
基金funded by the National Natural Science Foundation of China(General Program:No.52074314,No.U19B6003-05)National Key Research and Development Program of China(2019YFA0708303-05)。
文摘Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.
基金partially funded by Department of Science and Technology (DST), Govt. of Indiaproject SR/ FTP/ETA-61/2010
文摘Gap acceptance theory is broadly used for evaluating unsignalized intersections in developed coun tries. Intersections with no specific priority to any move ment, known as uncontrolled intersections, are common in India. Limited priority is observed at a few intersections, where priorities are perceived by drivers based on geom etry, traffic volume, and speed on the approaches of intersection. Analyzing such intersections is complex because the overall traffic behavior is the result of drivers, vehicles, and traffic flow characteristics. Fuzzy theory has been widely used to analyze similar situations. This paper describes the application of adaptive neurofuzzy interface system （ANFIS） to the modeling of gap acceptance behavior of rightturning vehicles at limited priority Tintersections （in India, vehicles are driven on the left side of a road）. Field data are collected using video cameras at four Tintersections having limited priority. The data extracted include gap/lag, subject vehicle type, conflicting vehicle type, and driver＇s decision （accepted/rejected）. ANFIS models are developed by using 80 % of the extracted data （total data observations for major road right turning vehicles are 722 and 1,066 for minor road right turning vehicles） and remaining are used for model vali dation. Four different combinations of input variables are considered for major and minor road right turnings sepa rately. Correct prediction by ANFIS models ranges from 75.17 % to 82.16 % for major road right turning and 87.20 % to 88.62 % for minor road right turning. Themodels developed in this paper can be used in the dynamic estimation of gap acceptance in traffic simulation models.
