Petrophysical properties estimation is vital in reservoir characterisation domain to identify the prospect locations of presence of petroleum. Geophysical sensing with seismic survey and well logging provide such information of subsurface without completely digging over the reservoir. Machine learning models are popular in this domain to estimate the petrophysical properties from seismic signals and well logging. However, the performance is affected when the available labelled data are limited to model a reservoir. Transfer learning has a significant contribution in handling the limited labelled data issue in many application domains. But its applicability is almost unexplored in this domain as it is necessary to first identify the relevant model to transfer. In this paper, we propose a novel transfer learning approach for the estimation of petrophysical properties in a real-world reservoir dataset having inadequate labelled data samples. The proposed solution transfers the contextual knowledge of reservoir facies classes to the predictive model of petrophysical properties. Both the tasks share the common domain information and provided the improved generalisation performance considering the out-of-fold prediction in blind wells. Moreover, the analysis of results depicts better convergence and accuracy compared to its considered baselines. [ABSTRACT FROM AUTHOR]

Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)