Physics-constrained sequence learning with attention mechanism for multi-horizon production forecasting
Authors:
- Ji ChangJCJi Chang
- Dongwei ZhangDZDongwei Zhang
- Yuling LiYLYuling Li
- Wenjun LvWLWenjun Lv
- Yitian XiaoYXYitian Xiao
- 9 October 2023
- journal article
- research article
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 231
Abstract
No abstract availableKeywords
Funding Information
- SINOPEC Petroleum Exploration and Production Research Institute (42050104)
- National Natural Science Foundation of China
- University of Science and Technology of China (62033012, 62273319)
This publication has 29 references indexed in Scilit:
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- Day-ahead high-resolution forecasting of natural gas demand and supply in Germany with a hybrid modelApplied Energy, 2020
- Significant Error Reduction in Machine-Learning Decline Curve Analysis for Unconventional Reservoirs2020
- Deep learning and process understanding for data-driven Earth system scienceNature, 2019
- Time series forecasting of petroleum production using deep LSTM recurrent networksNeurocomputing, 2019
- Multilayer Neural Network with Multi-Valued Neurons in time series forecasting of oil productionNeurocomputing, 2016
- A New Analytical Method for Analyzing Linear Flow in Tight/Shale Gas Reservoirs: Constant-Flowing-Pressure Boundary ConditionSPE Reservoir Evaluation & Engineering, 2012
- Rate-Decline Analysis for Fracture-Dominated Shale ReservoirsSPE Reservoir Evaluation & Engineering, 2011
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- Analysis of Decline CurvesTransactions of the AIME, 1945