An adaptive physics-informed deep learning method for pore pressure prediction using seismic data

Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.

A Novel Method of Heart Failure Prediction Based on DPCNN-XGBOOST Model

The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients.Existing methods depend on the judgment of doctors,the results are affected by many factors such as doctors’knowledge and experience.The accuracy is difficult to guarantee and has a serious lag.In this paper,a mixture prediction model is proposed for perioperative adverse events of heart failure,which combined with the advantages of the Deep Pyramid Convolutional Neural Networks(DPCNN)and Extreme Gradient Boosting(XGBOOST).The DPCNN was used to automatically extract features from patient’s diagnostic texts,and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients,then the XGBOOST algorithm was used to construct the prediction model of heart failure.An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018.The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3%and 31%compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.

Facial Expression Recognition Based on the Fusion of Infrared and Visible Image

Facial expression recognition is a research hot spot in the fields of computer vision and pattern recognition.However,the existing facial expression recognition models are mainly concentrated in the visible light environment.They have insufficient generalization ability and low recognition accuracy,and are vulnerable to environmental changes such as illumination and distance.In order to solve these problems,we combine the advantages of the infrared and visible images captured simultaneously by array equipment our developed with two infrared and two visible lens,so that the fused image not only has the texture information of visible image,but also has the contrast information of infrared image.On the other hand,we improved the WGAN by adding SSIM and LBP loss functions to ensure the structural similarity between the fused image and infrared image,and also the texture similarity between the fused image and visible image respectively.Finally,a facial expression recognition model Pyconv-SE18 with pyramid convolution and attention mechanism module is designed to extract the important feature information of facial expression in multiple scales.We add cosine distance loss function to reduce the feature difference within the class.Experiment results show that the robustness of expression recognition algorithm to illumination is improved based on the fused images.The accuracy of this model on FER2013 and CK+public data sets are 69.3%and 94.6%,respectively.

Power Grid Fault Diagnosis Based on Deep Pyramid Convolutional Neural Network

Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.

Automatic Segmentation Method for Cone-Beam Computed Tomography Image of the Bone Graft Region within Maxillary Sinus Based on the Atrous Spatial Pyramid Convolution Network

Sinus floor elevation with a lateral window approach requires bone graft(BG)to ensure sufficient bone mass,and it is necessary to measure and analyse the BG region for follow-up of postoperative patients.However,the BG region from cone-beam computed tomography(CBCT)images is connected to the margin of the maxillary sinus,and its boundary is blurred.Common segmentation methods are usually performed manually by experienced doctors,and are complicated by challenges such as low efficiency and low precision.In this study,an auto-segmentation approach was applied to the BG region within the maxillary sinus based on an atrous spatial pyramid convolution(ASPC)network.The ASPC module was adopted using residual connections to compose multiple atrous convolutions,which could extract more features on multiple scales.Subsequently,a segmentation network of the BG region with multiple ASPC modules was established,which effectively improved the segmentation performance.Although the training data were insufficient,our networks still achieved good auto-segmentation results,with a dice coefficient(Dice)of 87.13%,an Intersection over Union(Iou)of 78.01%,and a sensitivity of 95.02%.Compared with other methods,our method achieved a better segmentation effect,and effectively reduced the misjudgement of segmentation.Our method can thus be used to implement automatic segmentation of the BG region and improve doctors’work efficiency,which is of great importance for developing preliminary studies on the measurement of postoperative BG within the maxillary sinus.

基于双支路特征融合的MRI颅脑肿瘤图像分割研究

针对磁共振成像(magnetic resonance imaging, MRI)颅脑肿瘤区域误识别与分割网络空间信息丢失问题,提出一种基于双支路特征融合的MRI脑肿瘤图像分割方法。首先通过主支路的重构VGG与注意力模型(re-parameterization visual geometry group and attention model, RVAM)提取网络的上下文信息,然后使用可变形卷积与金字塔池化模型(deformable convolution and pyramid pooling model, DCPM)在副支路获取丰富的空间信息,之后使用特征融合模块对两支路的特征信息进行融合。最后引入注意力模型,在上采样过程中加强分割目标在解码时的权重。提出的方法在Kaggle_3m数据集和BraTS2019数据集上进行了实验验证,实验结果表明该方法具有良好的脑肿瘤分割性能,其中在Kaggle_3m上,Dice相似系数、杰卡德系数分别达到了91.45%和85.19%。