Due to the strong capability of building complex nonlinear mapping without involving linearization theory and high prediction efficiency; the deep learning (DL) technique applied to solve geophysical inverse problems has been a subject of growing interest. Currently, most DL-based inversion approaches are fully data-driven (namely standard deep learning), the performance of which largely depends on the training sample sets. However, due to the heavy burden of time and computational resources, it can be challenging to supply such a massive and exhaustive training dataset for generic realistic exploration scenarios and to perform network training. In this work, based on the recent advances in physics-based networks, the physical laws of magnetotelluric (MT) wave propagation is incorporated into a purely data-driven DL approach (PlainDNN) and thus builds a physics-driven DL MT inversion scheme (PhyDNN). In this scheme, the forward operator modeling MT wave propagation is integrated into the network training loop, in the form of minimizing a hybrid loss objective function composed of the data-driven model misfit and physics-based data misfit, to guide the network training. Consequently, the proposed PhyDNN method will take the advantage of the fully data-driven DL and conventional physics-based deterministic methods, allowing it to deal with complex realistic exploration scenarios. Quantitative and qualitative analysis results demonstrate that the PhyDNN can honor the physical laws of the MT inverse problem, and with other conditions unchanged, the PhyDNN outperforms the PlainDNN and the classical deterministic Occam inversion method. When processing field data, the PhyDNN method yields considerably impressive inversion results compared to the Occam method, and the corresponding simulated MT responses agree well with the real measurements, which confirms the effectiveness and applicability of the PhyDNN method.
Despite demonstrating exceptional inversion production for synthetic data, the application of deep learning (DL) inversion methods to invert realistic magnetotelluric (MT) measurements, which are inevitably contaminated by noise in acquisition, poses a significant challenge. Hence, to facilitate DL inversion for realistic MT measurements, this work explores developing a noise-robust MT DL inversion method by generating targeted noisy training datasets and constructing a physics-informed neural network. Different from most previous works that only considered the noise of one fixed distribution and level, we propose three noise injection strategies and compare their combinations to mitigate the adverse effect of measurement noise on MT DL inversion results: (1) add synthetic relative noise obeying Gaussian distribution; (2) propose a multiwindow Savitzky–Golay (MWSG) filtering scheme to extract potential and possible noise from the target field data and then introduce them into training data; (3) create an augmented training dataset based on the former two strategies. Moreover, we employ the powerful Swin Transformer as the backbone network to construct a U-shaped DL model (SwinTUNet), based on which a physics-informed SwinTUNet (PISwinTUNet) is implemented to further enhance its generalization ability. In synthetic examples, the proposed noise injection strategies demonstrate impressive inversion effects, regardless of whether they are contaminated by familiar or unfamiliar noise. In a field example, the combination of three strategies drives PISwinTUNet to produce considerably faithful reconstructions for subsurface resistivity structures and outperform the classical deterministic Occam inversions. The experimental results show that the proposed noise-robust DL inversion method based on the noise injection strategies and physics-informed DL architecture holds great promise in processing MT field data.
Methane (CH4), the primary constituent of natural gas, is a colorless, odorless, combustible gas prevalent in petroleum and natural gas transmission pipelines as well as coal mines. However, conventional n-type semiconductor sensors face significant challenges in real-time CH4 leak monitoring within these environments due to severe signal drift induced by synergistic interference from high humidity and volatile organic compounds (VOCs). To address this, we synthesized La0.9Fe0.8Co0.2O3 nanomaterials via a facile one-pot hydrothermal method. A dual-site synergistic modulation strategy, involving the co-introduction of self-induced defects and Co dopants, endows the sensor with exceptional sensitivity toward CH4 at markedly lowered operating temperatures. At the optimal temperature of 125 °C, the tailored sensor exhibited a remarkable sensitivity of 17.55 toward 100 ppm CH4, representing an order-of-magnitude improvement over pristine LaFeO3. Furthermore, the device demonstrated excellent dynamic performance, with a rapid response time of 9.9 s and a recovery time of 7.2 s, enabling reliable detection across diverse environmental matrices. Notably, the sensor maintained a stable response value of approximately 15 even under extreme humidity (95% relative humidity) and exhibited outstanding repeatability. The exceptional performance originates predominantly from A-site-induced lattice strain coupled with the proliferation of active sites triggered by B-site substitution. The insights gained and the established mechanism herein enable the advancement of advanced methane sensing technologies geared towards industrial safety applications.