Over the last decades, seismic random noise attenuation has been dominated by transform-based denoising methods over the last decades. However, these methods usually need to estimate the noise level and select an optimal transformation in advance, and they may generate some artifacts in the denoising result (e.g., nonsmooth edges and pseudo-Gibbs phenomena). To overcome these disadvantages, we trained a deep convolutional neural network (CNN) with residual learning for seismic data denoising. We used synthetic seismic data for network training rather than seismic images, and we adopted a method to preprocess the seismic data before it was inputted in the network to help network training. We demonstrate the performance of the deep CNN in seismic random noise attenuation based on the synthetic seismic data. Results of numerical experiments show that our network adaptively and effectively suppresses noise of different levels and exhibits a competitive performance in comparison with the traditional transform-based methods.

Aggregation of nanosized materials in composite lithium-ion-battery electrodes can be a significant factor influencing electrochemical behavior. In this study, aggregation was controlled in magnetite, Fe₃O₄, composite electrodes via oleic acid capping and subsequent dispersion in a carbon black matrix. A heat treatment process was effective in the removal of the oleic acid capping agent while preserving a high degree of Fe₃O₄ dispersion. Electrochemical testing showed that Fe₃O₄ dispersion is initially beneficial in delivering a higher functional capacity, in agreement with continuum model simulations. However, increased capacity fade upon extended cycling was observed for the dispersed Fe₃O₄ composites relative to the aggregated Fe₃O₄ composites. X-ray absorption spectroscopy measurements of electrodes post cycling indicated that the dispersed Fe₃O₄ electrodes are more oxidized in the discharged state, consistent with reduced reversibility compared with the aggregated sample. Higher charge-transfer resistance for the dispersed sample after cycling suggests increased surface-film formation on the dispersed, high-surface-area nanocrystalline Fe₃O₄ compared to the aggregated materials. This study provides insight into the specific effects of aggregation on electrochemistry through a multiscale view of mechanisms for magnetite composite electrodes.

For seismic random noise attenuation, deep learning has attracted much attention and achieved promising performance. However, compared with conventional methods, the denoising performance of supervised learning-based methods heavily depends on massive training samples with high-quality labeled data, which makes their generalization capabilities limited. Even though deep neural networks (DNNs) usually outperform the conventional denoising methods, their performance is not guaranteed since neural networks still lack good mathematical interpretability at present. To alleviate the dependency on labeled data and explore insights into the denoising system, we proposed an unsupervised denoising method based on model-based deep learning, which combined domain knowledge and a data-driven method. We designed a network based on the modified iterative soft threshold algorithm (ISTA), which omitted the soft threshold to alleviate uncertainties introduced by empirically selected thresholds. In this network, we set the dictionary and code as trainable parameters. A loss function with a smooth penalty was designed to ensure that the network training can be implemented in an unsupervised manner. In the proposed method, we set the denoised result by $f-x$ deconvolution as the input for our network, and the further denoised data can be obtained after each epoch of the training, which means that our method does not need the testing procedure. Experiments on synthetic and field seismic data demonstrate that our method exhibits competitive performance compared to the conventional, supervised, and unsupervised methods, including $f-x$ deconvolution, curvelet, the Denoising Convolutional Neural Network (DnCNN), and the integration of neural network and Block-matching and 3-D filtering method (NN + BM3D).

The efficiency of solving geophysical inverse problem largely relies on the efficiency of solving the corresponding forward problem. As for electromagnetic (EM) data forward modeling in frequency domain, the conventional numerical methods, e.g. finite difference method (FDM), discretize the governing equations resulting a large linear system which is usually expensive to solve. Meanwhile, for inversion iteration we normally do not need to solve the forward problem in high precision. Thus a rapid surrogate modeling approach which uses the neural network is promising for replacing the forward modeling module in the inversion scheme. Here we proposed an algorithm which uses the neural operator to solve the EM data modeling problem in the frequency domain. To develop a surrogate model for EM data forward problem, we introduce an extended Fourier neural operator (EFNO) that enables the calculation at least 100 times faster than the conventional FDM solver while maintaining good precision. Moreover, by adding a sub-network the proposed neural operator has good generalization which has the capacity of predicting solution at any site locations and frequencies. Due to the discretization-invariance of Fourier neural operator, the neural operator trained on coarse grids can easily transfer to fine grids with only retraining part of parameters, resulting in a super-resolution prediction capability. We test our proposed method with 2-D and 3-D magnetotelluric (MT) data modeling problems, demonstrating that the EFNO has great potentials for severing as a general rapid surrogate forward solver in EM data inversion scheme.

Deep learning techniques have been widely used for semantic change detection (SCD) of remote sensing images (RSIs) and have shown encouraging performance. In this paper, we propose a novel neural network by embedding the difference enhancement (DE) module into the adjacent layers of ResNet for SCD of RSIs (DESNet), which can pay more attention to the changes of bi-temporal RSIs. Furthermore, we deploy the module of multi-scale parallel sampling spatial-spectral non-local (SSN) after feature extraction, which can effectively improve the robustness to large-scale changes and the integrity of the changed objects by fusing global features that sampled from the multi-scale feature space. The experimental tests demonstrate that our DESNet can achieve state-of-the-art accuracy on the SECOND dataset and the LandSat-SCD dataset.

The non-linear conjugate gradient (NLCG) algorithm is one of the popular linearized methods used to solve the frequency domain electromagnetic (EM) geophysical inverse problem. During the NLCG iterations, the model gradient guides the searching direction while the line-search algorithm determines the step length of each iteration. Normally, the line search requires solving the corresponding forward problem a few times. Since line search is usually computationally inefficient, we introduce the adaptive gradient descent (AGD) algorithm to accelerate solving the frequency domain EM inverse problem within the linearized framework. The AGD algorithm is a variant of the classical gradient descent method and has been well developed and widely used in deep learning. Rather than the time-consuming line search, its core idea is to algebraically manipulate the cumulative gradients and updates of the model from previous iterations to estimate the model parameter variables at the current iteration. For the inversion of magnetotelluric (MT) data, we here designed and implemented a framework by using the AGD algorithm combined with the cool-down scheme to tune the regularization parameter. To improve the convergence performance of the AGD algorithm (specifying to Adam and RMSProp), we proposed a tolerance strategy which has been tested numerically. To optimize the global learning rate, we carried out some comparative trials in the proposed inversion framework. The inverted results of synthetic and real-world data showed that both AGD algorithms (Adam and RMSProp) can recover comparable results and save more than a third of CPU time compared to the NLCG algorithm.