Complex lithology prediction using mean impact value, particle swarm optimization, and probabilistic neural network tech
- PDF / 4,684,519 Bytes
- 26 Pages / 595.276 x 790.866 pts Page_size
- 60 Downloads / 278 Views
RESEARCH ARTICLE - APPLIED GEOPHYSICS
Complex lithology prediction using mean impact value, particle swarm optimization, and probabilistic neural network techniques Yufeng Gu1 · Zhongmin Zhang2 · Demin Zhang2 · Yixuan Zhu2 · Zhidong Bao3 · Daoyong Zhang1 Received: 22 June 2020 / Accepted: 22 October 2020 © Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences 2020
Abstract Lithology prediction is a fundamental problem because the outcome of lithology prediction is the critical underlying data for some basic geological work, e.g., establishing stratigraphic framework or analyzing distribution of sedimentary facies. As the geological formation generally consists of many different lithologies, the lithology prediction is always viewed as a tough work by geologists. Probabilistic neural network (PNN) shows high efficiency when solving pattern recognition problem since learning data do not need to do any pre-training of learning data and calculation results are universally reliable, and then, this model could be considered as an effective solution. However, there are two factors that seriously limit the PNN’s performance: One is existence of the interference variables of learning samples, and the other is selection of the window length of probability density distribution. In view of adverse impact of those two factors, two techniques, mean impact value (MIV) and particle swarm optimization (PSO), are introduced to improve the PNN’s calculation capability. Thus, a new prediction method referred as MIV–PSO–PNN is proposed in this paper. The proposed method is validated by three well-designed experiments, and the corresponding experiment data are recorded by two cored wells of the LULA oilfield. For the three experiments, prediction accuracies of the results provided by the proposed method are 81.67%, 73.34% and 88.34%, respectively, all of which are higher than those provided by other comparative approaches including backpropagation (BP), PNN, and MIV-PNN. The experiment results strongly demonstrate that the proposed method is capable to predict complex lithology. Keywords Lacustrine carbonate formation · Complex lithology prediction · Backpropagation · Probabilistic neural network · Mean impact value · Particle swarm optimization List of symbols p(𝐲|𝐗i ) The probability density value of 𝐲 for the cluster 𝐗i n The number of variables, or the number of samples in Eq. (2), or the number of output units in Eq. (6) 𝐱ik kth sample of 𝐗i l The dimension of sample, or the number of hidden units in Eq. (6) and this number is an integer 𝜎 The smooth factor, also named as “spread” * Yufeng Gu [email protected] 1
Strategic Research Center of Oil and Gas Resources, Ministry of Natural Resources, Beijing, China
2
Sinopec Exploration & Production Research Institute, Beijing, China
3
College of Geosciences, China University of Petroleum (Beijing), Beijing, China
𝐁fn The test data m The number of learning samples, or the number of input units in Eq. (6) f The number of test samples 𝐃f
Data Loading...
