Search

The conventional reservoir automatic history matching method requires multiple computationally time-consuming reservoir numerical simulations. Deep learning agent models can perform alternative reservoir numerical simulation calculations with approximate accuracy and greater computational efficiency. In the reservoir automatic history matching method based on the deep learning agent model， the reservoir uncertainty parameters adjusted by the reservoir automatic history matching method are usually used as the input parameters of the deep learning agent model. Existing deep learning agent models are often single input-output neural network model architectures. They do not consider that reservoir automatic history matching methods require the adjustment of multiple reservoir uncertainty parameters. Multiple deep learning agent models need to be trained to predict water saturation field distribution and pressure field distribution in reservoirs. For solving this problem， a reservoir automatic history matching method based on a dual input-output convolutional neural network agent model was proposed to simultaneously predict the water saturation field distribution and pressure field distribution in a reservoir by using a dual input-output convolutional neural network， with the reservoir permeability field distribution and phase permeability parameters as input. The production was calculated with the help of the Peaceman equation. It was coupled to the ensemble smoother with multiple data assimilation （ES-MDA） methods to invert the reservoir permeability field distribution and phase permeability parameters to achieve a more efficient reservoir automatic history matching solution. The results of the study show that the prediction accuracy of the reservoir water saturation field distribution and pressure field distribution is above 93% at the specified time step based on the dual input-output convolutional neural network agent model. Compared with the traditional reservoir automatic history matching method， the proposed reservoir automatic history matching method based on a dual input-output convolutional neural network agent model avoids the time-consuming computation of multiple calls to the reservoir numerical simulator and improves the efficiency of the matching.

Permafrost is degrading globally, particularly those with low thermal stability on the Qinghai‒Tibet Plateau, owing to climate change. However, the inadequacy of direct research on permafrost degradation based on in-situ monitoring limits the prediction of permafrost degradation and engineering practices. This study explored the processes and modes of permafrost degradation into talik by analyzing ground temperature data from five points in the hinterland of the Qinghai‒Tibet Plateau from 2006 to 2021. The results showed that the degradation of the warm permafrost layer with a geothermal gradient of zero occurred simultaneously in the top and bottom directions. The rate of permafrost degradation from the top down and bottom up increase during the degradation process, but the increase of the former is more drastic after the formation of thawed interlayer. Additionally, the construction of the Qinghai‒Tibet Railway changed the degradation modes of the permafrost in adjacent natural sites through horizontal heat transfer, particularly after through talik formation under the embankment. The findings suggest that taking countermeasures before or immediately after forming thawed interlayer is more effective. When evaluating the thermal impact of projects in warm permafrost regions, special attention should be given to the horizontal heat transfer process that may result from the formation of a through talik.

Immune checkpoint inhibitors (ICIs) have been increasingly used in combination for cancer treatment but are associated with myocarditis. Here, we report that tumor-bearing mice exhibited response to treatment with combinatorial anti-programmed cell death 1 and anti-cytotoxic T lymphocyte antigen-4 antibodies but also presented with cardiovascular toxicities observed clinically with ICI therapy, including myocarditis and arrhythmia. Female mice were preferentially affected with myocarditis compared to male mice, consistent with a previously described genetic model of ICI myocarditis and emerging clinical data. Mechanistically, myocardial tissue from ICI-treated mice, the genetic mouse model, and human heart tissue from affected patients with ICI myocarditis all exhibited down-regulation of MANF (mesencephalic astrocyte-derived neurotrophic factor) and HSPA5 (heat shock 70-kDa protein 5) in the heart; this down-regulation was particularly notable in female mice. ICI myocarditis was amplified by heart-specific genetic deletion of mouse Manf and was attenuated by administration of recombinant MANF protein, suggesting a causal role. Ironically, both MANF and HSPA5 were transcriptionally induced by liganded estrogen receptor β and inhibited by androgen receptor. However, ICI treatment reduced serum estradiol concentration to a greater extent in female compared to male mice. Treatment with an estrogen receptor β-specific agonist and androgen depletion therapy attenuated ICI-associated cardiac effects. Together, our data suggest that ICI treatment inhibits estradiol-dependent expression of MANF/HSPA5 in the heart, curtailing the cardiomyocyte response to immune injury. This endocrine-cardiac-immune pathway offers new insights into the mechanisms of sex differences in cardiac disease and may offer treatment strategies for ICI myocarditis.