Search

How to reconstruct a credible three-dimensional (3D) geological model from very limited survey data, e.g. boreholes, outcrop, and two-dimensional (2D) images, is challenging in the field of 3D geological modeling. Against the limitations of the huge computational consumption and complex parameterization of geostatistics-based stochastic simulation methods, we propose an automatic reconstruction method of 3D geological models based on deep convolutional generative adversarial network (DCGAN). In this work, 2D geological sections are used as conditioning data to generate 3D geological models automatically. Various realizations can be reproduced under a same DCGAN model established through deep network training. A U-Net structure is used to enhance the fitting effect of the DCGAN model. In addition, joint loss functions are exploited to increase the similarity between 3D realizations and reference models. Three synthetic datasets were used to verify the capability of the method presented in this paper. Experimental results show that the proposed 3D automatic reconstruction method based on DCGAN can capture the features, trends and spatial patterns of geological structures well. The output models obey the used conditioning data. The complex heterogeneous structures are reconstructed more accurately and quickly by using the proposed method. [ABSTRACT FROM AUTHOR]

Image colorization technique is used to colorize the gray-level image or single-channel image, which is a very significant and challenging task in image processing, especially the colorization of remote sensing images. This paper proposes a new method for coloring remote sensing images based on deep convolution generation adversarial network. The adopted generator model is a symmetrical structure using the principle of auto-encoder, and a multi-scale convolutional module is specially designed to introduce into the generator model. Thus, the proposed generator can enable the whole model to retain more image features in the process of up-sampling and down-sampling. Meanwhile, the discriminator uses residual neural network 18 that can compete with the generator, so that the generator and discriminator can effectively optimize each other. In the proposed method, the color space transformation technique is first utilized to convert remote sensing images from RGB to YUV. Then, the Y channel (a gray-level image) is used as the input of the neural network model to predict UV channels. Finally, the predicted UV channels are concatenated with the original Y channel as a whole YUV that is then transformed into RGB space to get the final color image. Experiments are conducted to test the performance of different image colorization methods, and the results show that the proposed method has good performance in both visual quality and objective indexes on the colorization of remote sensing image. [ABSTRACT FROM AUTHOR]