An automatic fitting method for a variogram based on deep learning
ZHAO Li-Fang1,2(), YU Si-Yu1,2(), LI Shao-Hua1,2
1. Key Laboratory of Exploration Technologies for Oil and Gas Resources, Ministry of Education, Yangtze University, Wuhan 430100, China 2. School of Geosciences, Yangtze University, Wuhan 430100, China
A variogram serves as a crucial tool for quantifying spatial correlations. However, existing variogram fitting methods often yield unstable results. This study proposed an automatic variogram fitting method based on deep learning, aiming to enhance the precision and stability of automatic fitting. The fitting of the experimental variogram is essentially a nonlinear optimization problem, which involves optimizing the matching between the experimental and theoretical variograms. The proposed method generated substantial training datasets using several sets of theoretical variograms with varying parameter values for training and learning in deep neural networks. The trained model was then used for the automatic fitting of the experimental variogram. Multiple sets of experimental results demonstrate that based on the robust fitting capability of deep neural networks, the proposed method manifested superior fitting stability and computational efficiency compared to the least squares method, providing a novel approach for automatic variogram fitting in geostatistics.
赵丽芳, 喻思羽, 李少华. 基于深度学习的变差函数自动拟合方法研究[J]. 物探与化探, 2024, 48(5): 1359-1367.
ZHAO Li-Fang, YU Si-Yu, LI Shao-Hua. An automatic fitting method for a variogram based on deep learning. Geophysical and Geochemical Exploration, 2024, 48(5): 1359-1367.
Li Z W, Li Q, Wu C R. Comprehensive identification technology of effective reservoirs in sedimentary basins[M]. Chengdu: Sichuan Science and Technology Press, 2002.
[2]
Mardia K V, Marshall R J. Maximum likelihood estimation of models for residual covariance in spatial regression[J]. Biometrika, 1984, 71(1):135-146.
Li S H, Zhang C M, Ma Y Z. Improvement of automatic fit of variation functions in linear programming[J]. Journal of Oil and Gas Technology, 2001, 23(S1):36-37,5.
Xie Y, Li Q, Chen J, et al. Research on variogram fitting method and its application based on the improved quantum particle swarm algorithm[J]. Journal of Chengdu University of Technology:Science and Technology Edition, 2018, 45(3):379-385.
Cheng H J, Yang Y, Sun Y P. Based on the variogram of the random particle swarm optimization method[J]. Science Technology and Engineering, 2012, 12(31):8373-8378.
Wang Y F, Liu G J, Liu X J, et al. Neural network-based blood pressure detection algorithms for pulse wave signals[J]. Chinese Journal of Medical Physics, 2022, 39(8):998-1002.
[8]
Yu X, Yu Z D, Ramalingam S. Learning strict identity mappings in deep residual networks[C]// Salt Lake City: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2018: 4432-4440.
[9]
Yang L, Zhong B R, Xu X H, et al. Application of a semivariogram based on a deep neural network to Ordinary Kriging interpolation of elevation data[J]. PLOS One, 2022, 17(4):e0266942.
Mei Y, Yang Y, Li H. Study of spatio-temporal theory model and its influence on the sptio-temporal prediction accuracy[J]. Science of Surveying and Mapping, 2017, 42(6):1-5,35.
[12]
Soltani-Mohammadi S, Safa M. A simulated annealing based optimization algorithm for automatic variogram model fitting[J]. Archives of Mining Sciences, 2016, 61(3):635-649.
[13]
张磊. 煤矿井下煤质预测及工作面三维可视化研究与实现[D]. 西安: 西安科技大学, 2017.
[13]
Zhang L. Research and implementation of coal quality prediction and three-dimensional visualization of working face in underground coal mine[D]. Xi’an: Xi’an University of Science and Technology, 2017.
[14]
Matheron G. Principles of geostatistics[J]. Economic Geology, 1963, 58(8):1246-1266.
[15]
Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.
doi: 10.1162/neco.2006.18.7.1527
pmid: 16764513
Liu M Y, Wu L J, Liang H, et al. A kind of high-precision LSTM-FC atmospheric contaminant concentrations forecasting model[J]. Computer Science, 2021, 48(S1):184-189.
He T, Zhou N, Wu X Y. Thickness prediction of reservoir effective sand body by deep fully connected neural network[J]. Journal of Jilin University:Earth Science Edition, 2023, 53(4):1262-1274.
[18]
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.
[19]
Amari S I. Backpropagation and stochastic gradient descent method[J]. Neurocomputing, 1993, 5(4-5):185-196.
[20]
Kingma D P, Ba J. Adam:A method for stochastic optimization[C]// Proceedings of the 3rd International Conference on Learning Representations(ICLR 2015), 2015.
Xiao K Y. The study of variogram model fitting by interactive computer-aided program[J]. Journal of Jilin University:Earth Science Edition, 1994, 24(2):218-221,233.
[22]
Wackernagel H, Oliveira V D, Kedem B. Multivariate geostatistics[J]. SIAM Review, 1997, 39(2):340-340.
[23]
Webster R, Oliver M A. Geostatistics for environmental scientists[M]. London: John Wiley Sons, 2007.
[24]
Minasny B, McBratney A B. The Matérn function as a general model for soil variograms[J]. Geoderma, 2005, 128(3-4):192-207.
[25]
李长胜, 刘刚. 线性插值算法研究[J]. 机床与液压, 2002, 30(1):107-108.
[25]
Li C S, Liu G. Research on linear interpolation algorithm[J]. Machine Tool & Hydraulics, 2002, 30(1):107-108.
