A forecasting method of oil well production based on multivariate time series(MTS)and vector autoregressive(VAR)machine learning model for waterflooding reservoir is proposed,and an example application is carried out....A forecasting method of oil well production based on multivariate time series(MTS)and vector autoregressive(VAR)machine learning model for waterflooding reservoir is proposed,and an example application is carried out.This method first uses MTS analysis to optimize injection and production data on the basis of well pattern analysis.The oil production of different production wells and water injection of injection wells in the well group are regarded as mutually related time series.Then a VAR model is established to mine the linear relationship from MTS data and forecast the oil well production by model fitting.The analysis of history production data of waterflooding reservoirs shows that,compared with history matching results of numerical reservoir simulation,the production forecasting results from the machine learning model are more accurate,and uncertainty analysis can improve the safety of forecasting results.Furthermore,impulse response analysis can evaluate the oil production contribution of the injection well,which can provide theoretical guidance for adjustment of waterflooding development plan.展开更多
The Natural Forest Protection Program(NFPP)is one of the key ecological forestry programs in China.It not only facilitates the improvement of forest ecological quality in NFPP areas,but also plays a significant role i...The Natural Forest Protection Program(NFPP)is one of the key ecological forestry programs in China.It not only facilitates the improvement of forest ecological quality in NFPP areas,but also plays a significant role in increasing the carbon storage of forest ecosystems.The program covers 17 provinces,autonomous regions,and municipalities with correspondingly diverse forest resources and environments,ecological features,engineering measures and forest management regimes,all of which affect regional carbon storage.In this study,volume of timber harvest,tending area,pest-infested forest,firedamaged forest,reforestation,and average annual precipitation,and temperature were evaluated as factors that influence carbon storage.We developed a vector autoregression model for these seven indicators and we studied the dominant factors of carbon storage in the areas covered by NFPP.Timber harvest was the dominant factorinfluencing carbon storage in the Yellow and Yangtze River basins.Reforestation contributed most to carbon storage in the state-owned forest region in Xinjiang.In state-owned forest regions of Heilongjiang and Jilin Provinces,the dominant factors were forest fires and forest cultivation,respectively.For the enhancement of carbon sequestration capacity,a longer rotation period and a smaller timber harvest are recommended for the Yellow and Yangtze River basins.Trees should be planted in stateowned forests in Xinjiang.Forest fires should be prevented in state-owned forests in Heilongjiang,and greater forest tending efforts should be made in the state-owned forests in Jilin.展开更多
基金Huo Yingdong Education Foundation Young Teachers Fund for Higher Education Institutions(171043)Sichuan Outstanding Young Science and Technology Talent Project(2019JDJQ0036)。
文摘A forecasting method of oil well production based on multivariate time series(MTS)and vector autoregressive(VAR)machine learning model for waterflooding reservoir is proposed,and an example application is carried out.This method first uses MTS analysis to optimize injection and production data on the basis of well pattern analysis.The oil production of different production wells and water injection of injection wells in the well group are regarded as mutually related time series.Then a VAR model is established to mine the linear relationship from MTS data and forecast the oil well production by model fitting.The analysis of history production data of waterflooding reservoirs shows that,compared with history matching results of numerical reservoir simulation,the production forecasting results from the machine learning model are more accurate,and uncertainty analysis can improve the safety of forecasting results.Furthermore,impulse response analysis can evaluate the oil production contribution of the injection well,which can provide theoretical guidance for adjustment of waterflooding development plan.
基金funded by Special Research Project of Institute of Applied Ecology,CAS(No.Y5YZX151YD)Key Laboratory of Forest Ecology and Management,Institute of Applied Ecology,CAS(No.LFEM2016-05)
文摘The Natural Forest Protection Program(NFPP)is one of the key ecological forestry programs in China.It not only facilitates the improvement of forest ecological quality in NFPP areas,but also plays a significant role in increasing the carbon storage of forest ecosystems.The program covers 17 provinces,autonomous regions,and municipalities with correspondingly diverse forest resources and environments,ecological features,engineering measures and forest management regimes,all of which affect regional carbon storage.In this study,volume of timber harvest,tending area,pest-infested forest,firedamaged forest,reforestation,and average annual precipitation,and temperature were evaluated as factors that influence carbon storage.We developed a vector autoregression model for these seven indicators and we studied the dominant factors of carbon storage in the areas covered by NFPP.Timber harvest was the dominant factorinfluencing carbon storage in the Yellow and Yangtze River basins.Reforestation contributed most to carbon storage in the state-owned forest region in Xinjiang.In state-owned forest regions of Heilongjiang and Jilin Provinces,the dominant factors were forest fires and forest cultivation,respectively.For the enhancement of carbon sequestration capacity,a longer rotation period and a smaller timber harvest are recommended for the Yellow and Yangtze River basins.Trees should be planted in stateowned forests in Xinjiang.Forest fires should be prevented in state-owned forests in Heilongjiang,and greater forest tending efforts should be made in the state-owned forests in Jilin.
