Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Acta Geophysica

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: petrophysical characteristics

Sortuj według:

Ogranicz wyniki do:

Identifying the potash reservoirs from seismic data by using convolution neural network, constrained by the waveform characteristics of potash reservoirs

Zhu Lei, Zhang Fanchang, Xu Xunyong, Xu Wanglin

Acta Geophysica

2023

Vol. 71, no. 6

2699--2714

Exploration of potash resources under complex geological condition is particularly important. However, it is difficult to establish characteristic equations for direct prediction, since there is no direct relation between potash content (PC) and seismic response. To solve this problem, this paper proposed a potash reservoir prediction method by a specially designed convolution neural network (CNN) structure to train the special waveform and petrophysical characteristics of potash reservoirs. Considering that the potash reservoirs and petrophysical characteristics are not a one-to-one mapping, the prediction procedure is divided into two parts. First, a CNN is constructed for potash reservoir prediction, according to the spatial waveform characteristics of potash reservoirs. The mapping between potash reservoirs and waveform characteristics is used to obtain the potash reservoir probability data by the soft-max function. Then, another CNN for PC prediction is built based on the petrophysical characteristics of potash reservoirs. Meanwhile, according to the Hadamard criterion, the petrophysical characteristics of potash reservoir are constrained by the waveform characteristics. The two CNN models are used to directly predict the PC synergistically. Consequently, the bidirectional mapping problem can be alleviated and a loss function of the PC prediction CNN constrained with the waveform is obtained. Finally, by tuning the PC prediction CNN through the loss function, PC prediction is performed. The correlation between the predicted and true PC values can reach more than 80%.

Improved recognition of rock formation on the basis of well logging and laboratory experiments results using factor analysis

Puskarczyk Edyta, Jarzyna Jadwiga A., Wawrzyniak-Guz Kamila, Krakowska Paulina I., Zych Marcin

Acta Geophysica

2019

Vol. 67, no. 6

1809--1822

Several data sets from the Silurian and Ordovician formations from three wells on the shore of Baltic Basin in Northern Poland prepared on the basis of well logging data and results of their comprehensive interpretation were used in factor analysis. The goal of statistical analysis was structure recognition of data and proper selection of parameters to limit the number of variables in study. The top priority of research was recognition of specific features of claystone/mudstone formations predisposing them to be potential shale gas deposits. The identified data scheme based on data from one well, was then applied to: 1) well 2 and well 3 separately, 2) combined data from three wells, 3) depth intervals treated as sweet spots, i.e., formations of high hydrocarbon potential. Numbers of samples from well logging were proportional to number of laboratory data from individual formations. The extended data set comprising all available log samples in explored formations was also prepared. Outcomes from standard (Triple Combo—natural gamma log, resistivity log, neutron log and bulk density log and Quad Combo—with addition of sonic log and spectral gamma log) and sophisticated (GEM™—Elemental Analysis Tool, Wave Sonic and Nuclear Magnetic Resonance—NMR) logs were the basis for data sets. Finally, laboratory data set of huge amount of variables from elemental, mineralogical, geochemical and petrophysical laboratory experiments was built and verified in FA to select the most informative components. Conclusions on the data set size, number of factors and type of variables were drawn.