TY - GEN
T1 - MISSING WELL-LOG PREDICTION USING LSTM IN THE BUNTER SANDSTONE FORMATION OF THE UK SOUTHERN NORTH SEA
AU - Li, Z.
AU - Huuse, M.
N1 - Publisher Copyright:
© 83rd EAGE Conference and Exhibition 2022. All rights reserved.
PY - 2022
Y1 - 2022
N2 - The Triassic Bunter Sandstone Formation (BSF) in the UK sector of the Southern North Sea (SNS) is thought to have a significant potential for CO2 storage. However, most of the wells in that area missed density logs (RHOB) which are required for seismic-well tie and calculating the rock porosity of the BSF. This study proposed using long and short-term memory (LSTM) neural network to predict the RHOB by GR and DT logs. Compared with the commonly used back-propagation (BP) neural network, the LSTM can receive the sequence data as the input and learn the trend among the data within the sequence, which determines it has a higher prediction accuracy in practice.
AB - The Triassic Bunter Sandstone Formation (BSF) in the UK sector of the Southern North Sea (SNS) is thought to have a significant potential for CO2 storage. However, most of the wells in that area missed density logs (RHOB) which are required for seismic-well tie and calculating the rock porosity of the BSF. This study proposed using long and short-term memory (LSTM) neural network to predict the RHOB by GR and DT logs. Compared with the commonly used back-propagation (BP) neural network, the LSTM can receive the sequence data as the input and learn the trend among the data within the sequence, which determines it has a higher prediction accuracy in practice.
UR - http://www.scopus.com/inward/record.url?scp=85142612773&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85142612773
T3 - 83rd EAGE Conference and Exhibition 2022
SP - 3501
EP - 3505
BT - 83rd EAGE Conference and Exhibition 2022
PB - EAGE Publishing BV
T2 - 83rd EAGE Conference and Exhibition 2022
Y2 - 6 June 2022 through 9 June 2022
ER -
