Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

Pharmacological Investigation on the Qi-Invigorating Action of Schisandrin B: Effects on Mitochondrial ATP Generation in Multiple Tissues and Innate/Adaptive Immunity in Mice

Schisandrae Fructus, containing schisandrin B (Sch B) as its main active component, is recognized in traditional Chinese medicine (TCM) for its Qi-invigorating properties in the five visceral organs. Our laboratory has shown that the Qi-invigorating action of Chinese tonifying herbs is linked to increased mitochondrial ATP generation and an enhancement in mitochondrial glutathione redox status. To explore whether Sch B can exert Qi-invigorating actions across various tissues, we investigated the effects of Sch B treatment on mitochondrial ATP generation and glutathione redox status in multiple mouse tissues ex vivo. In line with TCM theory, which posits that Zheng Qi generation relies on the Qi function of the visceral organs, we also examined Sch B’s impact on natural killer cell activity and antigen-induced splenocyte proliferation, both serving as indirect measures of Zheng Qi. Our findings revealed that Sch B treatment consistently enhanced mitochondrial ATP generation and improved mitochondrial glutathione redox status in mouse tissues. This boost in mitochondrial function was associated with stimulated innate and adaptive immune responses, marked by increased natural killer cell activity and antigen-induced T/B cell proliferation, potentially through the increased generation of Zheng Qi.

Adaptive Kernel Firefly Algorithm Based Feature Selection and Q-Learner Machine Learning Models in Cloud

CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferring information.A dynamic strategy,DevMLOps(Development Machine Learning Operations)used in automatic selections and tunings of MLTs result in significant performance differences.But,the scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.RFEs(Recursive Feature Eliminations)are computationally very expensive in its operations as it traverses through each feature without considering correlations between them.This problem can be overcome by the use of Wrappers as they select better features by accounting for test and train datasets.The aim of this paper is to use DevQLMLOps for automated tuning and selections based on orchestrations and messaging between containers.The proposed AKFA(Adaptive Kernel Firefly Algorithm)is for selecting features for CNM(Cloud Network Monitoring)operations.AKFA methodology is demonstrated using CNSD(Cloud Network Security Dataset)with satisfactory results in the performance metrics like precision,recall,F-measure and accuracy used.

Adaptive Cloud Intrusion Detection System Based on Pruned Exact Linear Time Technique

Cloud computing environments,characterized by dynamic scaling,distributed architectures,and complex work-loads,are increasingly targeted by malicious actors.These threats encompass unauthorized access,data breaches,denial-of-service attacks,and evolving malware variants.Traditional security solutions often struggle with the dynamic nature of cloud environments,highlighting the need for robust Adaptive Cloud Intrusion Detection Systems(CIDS).Existing adaptive CIDS solutions,while offering improved detection capabilities,often face limitations such as reliance on approximations for change point detection,hindering their precision in identifying anomalies.This can lead to missed attacks or an abundance of false alarms,impacting overall security effectiveness.To address these challenges,we propose ACIDS(Adaptive Cloud Intrusion Detection System)-PELT.This novel Adaptive CIDS framework leverages the Pruned Exact Linear Time(PELT)algorithm and a Support Vector Machine(SVM)for enhanced accuracy and efficiency.ACIDS-PELT comprises four key components:(1)Feature Selection:Utilizing a hybrid harmony search algorithm and the symmetrical uncertainty filter(HSO-SU)to identify the most relevant features that effectively differentiate between normal and anomalous network traffic in the cloud environment.(2)Surveillance:Employing the PELT algorithm to detect change points within the network traffic data,enabling the identification of anomalies and potential security threats with improved precision compared to existing approaches.(3)Training Set:Labeled network traffic data forms the training set used to train the SVM classifier to distinguish between normal and anomalous behaviour patterns.(4)Testing Set:The testing set evaluates ACIDS-PELT’s performance by measuring its accuracy,precision,and recall in detecting security threats within the cloud environment.We evaluate the performance of ACIDS-PELT using the NSL-KDD benchmark dataset.The results demonstrate that ACIDS-PELT outperforms existing cloud intrusion detection techniques in terms of accuracy,precision,and recall.This superiority stems from ACIDS-PELT’s ability to overcome limitations associated with approximation and imprecision in change point detection while offering a more accurate and precise approach to detecting security threats in dynamic cloud environments.

Tomato detection method using domain adaptive learning for dense planting environments

This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.

Robust Space-Time Adaptive Track-Before-Detect Algorithm Based on Persymmetry and Symmetric Spectrum

Underwater monopulse space-time adaptive track-before-detect method,which combines space-time adaptive detector(STAD)and the track-before-detect algorithm based on dynamic programming(DP-TBD),denoted as STAD-DP-TBD,can effectively detect low-speed weak targets.However,due to the complexity and variability of the underwater environment,it is difficult to obtain sufficient secondary data,resulting in a serious decline in the detection and tracking performance,and leading to poor robustness of the algorithm.In this paper,based on the adaptive matched filter(AMF)test and the RAO test,underwater monopulse AMF-DP-TBD algorithm and RAO-DP-TBD algorithm which incorporate persymmetry and symmetric spectrum,denoted as PSAMF-DP-TBD and PS-RAO-DP-TBD,are proposed and compared with the AMF-DP-TBD algorithm and RAO-DP-TBD algorithm based on persymmetry array,denoted as P-AMF-DP-TBD and P-RAO-DP-TBD.The simulation results show that the four methods can work normally with sufficient secondary data and slightly insufficient secondary data,but when the secondary data is severely insufficient,the P-AMF-DP-TBD and P-RAO-DP-TBD algorithms has failed while the PSAMF-DP-TBD and PS-RAO-DP-TBD algorithms still have good detection and tracking capabilities.

An Adaptive Control Strategy for Energy Storage Interface Converter Based on Analogous Virtual Synchronous Generator

In the DC microgrid,the lack of inertia and damping in power electronic converters results in poor stability of DC bus voltage and low inertia of the DC microgrid during fluctuations in load and photovoltaic power.To address this issue,the application of a virtual synchronous generator(VSG)in grid-connected inverters control is referenced and proposes a control strategy called the analogous virtual synchronous generator(AVSG)control strategy for the interface DC/DC converter of the battery in the microgrid.Besides,a flexible parameter adaptive control method is introduced to further enhance the inertial behavior of the AVSG control.Firstly,a theoretical analysis is conducted on the various components of the DC microgrid,the structure of analogous virtual synchronous generator,and the control structure’s main parameters related to the DC microgrid’s inertial behavior.Secondly,the voltage change rate tracking coefficient is introduced to adjust the change of the virtual capacitance and damping coefficient flexibility,which further strengthens the inertia trend of the DC microgrid.Additionally,a small-signal modeling approach is used to analyze the approximate range of the AVSG’s main parameters ensuring system stability.Finally,conduct a simulation analysis by building the model of the DC microgrid system with photovoltaic(PV)and battery energy storage(BES)in MATLAB/Simulink.Simulation results from different scenarios have verified that the AVSG control introduces fixed inertia and damping into the droop control of the battery,resulting in a certain level of inertia enhancement.Furthermore,the additional adaptive control strategy built upon the AVSG control provides better and flexible inertial support for the DC microgrid,further enhances the stability of the DC bus voltage,and has a more positive impact on the battery performance.

Unveiling the dynamic role of innate and adaptive immune cells in COPD pathogenesis induced by cigarette smoke

Chronic obstructive pulmonary disease(COPD)is a multifaceted syndrome characterized by a dysregulated inflammatory cascade within the respiratory system,primarily triggered by exposure to harmful particles and gases,notably from cigarette smoke.This inflammatory response is orchestrated by innate immune cells like macrophages and epithelial cells,which recognize danger signals released from damaged cells.Prolonged inflammation prompts an adaptive immune reaction mediated by dendritic cells,culminating in the formation of lymphoid follicles and involving a complex interplay of T and B cells,as well as cytotoxic activity.Additionally,both viral and bacterial infections exacerbate COPD by further igniting inflammatory pathways,perpetuating the chronic inflammatory state.This comprehensive review encapsulates the intricate interplay between innate and adaptive immunity in COPD,with a particular focus on the role of cigarette smoke in its pathogenesis and potential therapeutic targets.

Estimation of Generalized Pareto under an Adaptive Type-II Progressive Censoring

In this paper, based on a new type of censoring scheme called an adaptive type-II progressive censoring scheme introduce by Ng et al. [1], Naval Research Logistics is considered. Based on this type of censoring the maximum likelihood estimation (MLE), Bayes estimation, and parametric bootstrap method are used for estimating the unknown parameters. Also, we propose to apply Markov chain Monte Carlo (MCMC) technique to carry out a Bayesian estimation procedure and in turn calculate the credible intervals. Point estimation and confidence intervals based on maximum likelihood and bootstrap method are also proposed. The approximate Bayes estimators obtained under the assumptions of non-informative priors, are compared with the maximum likelihood estimators. Numerical examples using real data set are presented to illustrate the methods of inference developed here. Finally, the maximum likelihood, bootstrap and the different Bayes estimates are compared via a Monte Carlo simulation study.

Adaptive Control Based on Neural Networks for an Uncertain 2-DOF Helicopter System With Input Deadzone and Output Constraints

In this paper, a study of control for an uncertain2-degree of freedom(DOF) helicopter system is given. The2-DOF helicopter is subject to input deadzone and output constraints. In order to cope with system uncertainties and input deadzone, the neural network technique is introduced because of its capability in approximation. In order to update the weights of the neural network, an adaptive control method is utilized to improve the system adaptability. Furthermore, the integral barrier Lyapunov function(IBLF) is adopt in control design to guarantee the condition of output constraints and boundedness of the corresponding tracking errors. The Lyapunov direct method is applied in the control design to analyze system stability and convergence. Finally, numerical simulations are conducted to prove the feasibility and effectiveness of the proposed control based on the model of Quanser's 2-DOF helicopter.

Wide-Area Delay-Dependent Adaptive Supervisory Control of Multi-machine Power System Based on Improve Free Weighting Matrix Approach

The paper demonstrates the possibility to enhance the damping of inter-area oscillations using Wide Area Measurement (WAM) based adaptive supervisory controller (ASC) which considers the wide-area signal transmission delays. The paper uses an LMI-based iterative nonlinear optimization algorithm to establish a method of designing state-feedback controllers for power systems with a time-varying delay. This method is based on the delay-dependent stabilization conditions obtained by the improved free weighting matrix (IFWM) approach. In the stabilization conditions, the upper bound of feedback signal’s transmission delays is taken into consideration. Combining theoriesof state feedback control and state observer, the ASC is designed and time-delay output feedback robust controller is realized for power system. The ASC uses the input information from Phase Measurement Units (PMUs) in the system and dispatches supplementary control signals to the available local controllers. The design of the ASC is explained in detail and its performance validated by time domain simulations on a New England test power system (NETPS).

Ground-layer Adaptive Optics for the 2.5 m Wide-field and High-resolution Solar Telescope

The 2.5 m wide-field and high-resolution solar telescope(WeHoST)is currently under developing for solar observations.WeHoST aims to achieve high-resolution observations over a super-wide field of view(FOV)of5′×5′,and a desired resolution of 0.3″.To meet the scientific requirements of WeHoST,the ground-layer adaptive optics(GLAO)with a specially designed wave front sensing system is as the primary consideration.We introduce the GLAO configuration,particularly the wave front sensing scheme.Utilizing analytic method,we simulate the performance of both classical AO and GLAO systems,optimize the wave front sensing system,and evaluate GLAO performance in terms of PSF uniformity and correction improvement across whole FOV.The results indicate that,the classical AO will achieve diffraction-limited resolution;the suggested GLAO configuration will uniformly improve the seeing across the full 5′×5′FOV,reducing the FWHM across the axis FOV to less than0.3″(λ≥705 nm,r0≥11 cm),which is more than two times improvement.The specially designed wave front sensor schedule offers new potential for WeHoST’s GLAO,particularly the multi-FOV GLAO and the flexibility to select the detected area.These capabilities will significantly enhance the scientific output of the telescope.

Improving Video Watermarking through Galois Field GF(2^(4)) Multiplication Tables with Diverse Irreducible Polynomials and Adaptive Techniques

Video watermarking plays a crucial role in protecting intellectual property rights and ensuring content authenticity.This study delves into the integration of Galois Field(GF)multiplication tables,especially GF(2^(4)),and their interaction with distinct irreducible polynomials.The primary aim is to enhance watermarking techniques for achieving imperceptibility,robustness,and efficient execution time.The research employs scene selection and adaptive thresholding techniques to streamline the watermarking process.Scene selection is used strategically to embed watermarks in the most vital frames of the video,while adaptive thresholding methods ensure that the watermarking process adheres to imperceptibility criteria,maintaining the video's visual quality.Concurrently,careful consideration is given to execution time,crucial in real-world scenarios,to balance efficiency and efficacy.The Peak Signal-to-Noise Ratio(PSNR)serves as a pivotal metric to gauge the watermark's imperceptibility and video quality.The study explores various irreducible polynomials,navigating the trade-offs between computational efficiency and watermark imperceptibility.In parallel,the study pays careful attention to the execution time,a paramount consideration in real-world scenarios,to strike a balance between efficiency and efficacy.This comprehensive analysis provides valuable insights into the interplay of GF multiplication tables,diverse irreducible polynomials,scene selection,adaptive thresholding,imperceptibility,and execution time.The evaluation of the proposed algorithm's robustness was conducted using PSNR and NC metrics,and it was subjected to assessment under the impact of five distinct attack scenarios.These findings contribute to the development of watermarking strategies that balance imperceptibility,robustness,and processing efficiency,enhancing the field's practicality and effectiveness.

Model Reference Adaptive Controller for Simultaneous Voltage and Frequency Restoration of Autonomous AC Microgrids

In an autonomous droop-based microgrid,the sys-tem voltage and frequency(VaF)are subject to deviations as load changes.Despite the existence of various control methods aimed at correcting system frequency deviations at the second-ary control level without any communication network,the chal-lenges associated with these methods and their abilities to simul-taneously restore microgrid VaF have not been fully investigat-ed.In this paper,a multi-input multi-output(MIMO)model ref-erence adaptive controller(MRAC)is proposed to achieve VaF restoration while accurate power sharing among distributed generators(DGs)is maintained.The proposed MRAC,without any communication network,is designed based on two meth-ods:droop-based and inertia-based methods.For the microgrid,the suggested design procedure is started by defining a model reference in which the control objectives,such as the desired settling time,the maximum tolerable overshoot,and steady-state error,are considered.Then,a feedback-feedforward con-troller is established,of which the gains are adaptively tuned by some rules derived from the Lyapunov stability theory.Through some simulations in MATLAB/SimPowerSystem Tool-box,the proposed MRAC demonstrates satisfactory perfor-mance.

Adaptive RISE Control of Winding Tension with Active Disturbance Rejection

A winding system is a time-varying system that considers complex nonlinear characteristics,and how to control the stability of the winding tension during the winding process is the primary problem that has hindered development in this field in recent years.Many nonlinear factors affect the tension in the winding process,such as friction,structured uncertainties,unstructured uncertainties,and external interference.These terms severely restrict the tension tracking performance.Existing tension control strategies are mainly based on the composite control of the tension and speed loops,and previous studies involve complex decoupling operations.Owing to the large number of calculations required for this method,it is inconvenient for practical engineering applications.To simplify the tension generation mechanism and the influence of the nonlinear characteristics of the winding system,a simpler nonlinear dynamic model of the winding tension was established.An adaptive method was applied to update the feedback gain of the continuous robust integral of the sign of the error(RISE).Furthermore,an extended state observer was used to estimate modeling errors and external disturbances.The model disturbance term can be compensated for in the designed RISE controller.The asymptotic stability of the system was proven according to the Lyapunov stability theory.Finally,a comparative analysis of the proposed nonlinear controller and several other controllers was performed.The results indicated that the control of the winding tension was significantly enhanced.

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.

Neurogenesis dynamics in the olfactory bulb:deciphering circuitry organization, function, and adaptive plasticity

Adult neurogenesis persists after birth in the subventricular zone, with new neurons migrating to the granule cell layer and glomerular layers of the olfactory bulb, where they integrate into existing circuitry as inhibitory interneurons. The generation of these new neurons in the olfactory bulb supports both structural and functional plasticity, aiding in circuit remodeling triggered by memory and learning processes. However, the presence of these neurons, coupled with the cellular diversity within the olfactory bulb, presents an ongoing challenge in understanding its network organization and function. Moreover,the continuous integration of new neurons in the olfactory bulb plays a pivotal role in regulating olfactory information processing. This adaptive process responds to changes in epithelial composition and contributes to the formation of olfactory memories by modulating cellular connectivity within the olfactory bulb and interacting intricately with higher-order brain regions. The role of adult neurogenesis in olfactory bulb functions remains a topic of debate. Nevertheless, the functionality of the olfactory bulb is intricately linked to the organization of granule cells around mitral and tufted cells. This organizational pattern significantly impacts output, network behavior, and synaptic plasticity, which are crucial for olfactory perception and memory. Additionally, this organization is further shaped by axon terminals originating from cortical and subcortical regions. Despite the crucial role of olfactory bulb in brain functions and behaviors related to olfaction, these complex and highly interconnected processes have not been comprehensively studied as a whole. Therefore, this manuscript aims to discuss our current understanding and explore how neural plasticity and olfactory neurogenesis contribute to enhancing the adaptability of the olfactory system. These mechanisms are thought to support olfactory learning and memory, potentially through increased complexity and restructuring of neural network structures, as well as the addition of new granule granule cells that aid in olfactory adaptation. Additionally, the manuscript underscores the importance of employing precise methodologies to elucidate the specific roles of adult neurogenesis amidst conflicting data and varying experimental paradigms. Understanding these processes is essential for gaining insights into the complexities of olfactory function and behavior.

Adaptive Network Sustainability and Defense Based on Artificial Bees Colony Optimization Algorithm for Nature Inspired Cyber Security

Cyber Defense is becoming a major issue for every organization to keep business continuity intact.The presented paper explores the effectiveness of a meta-heuristic optimization algorithm-Artificial Bees Colony Algorithm(ABC)as an Nature Inspired Cyber Security mechanism to achieve adaptive defense.It experiments on the Denial-Of-Service attack scenarios which involves limiting the traffic flow for each node.Businesses today have adapted their service distribution models to include the use of the Internet,allowing them to effectively manage and interact with their customer data.This shift has created an increased reliance on online services to store vast amounts of confidential customer data,meaning any disruption or outage of these services could be disastrous for the business,leaving them without the knowledge to serve their customers.Adversaries can exploit such an event to gain unauthorized access to the confidential data of the customers.The proposed algorithm utilizes an Adaptive Defense approach to continuously select nodes that could present characteristics of a probable malicious entity.For any changes in network parameters,the cluster of nodes is selected in the prepared solution set as a probable malicious node and the traffic rate with the ratio of packet delivery is managed with respect to the properties of normal nodes to deliver a disaster recovery plan for potential businesses.

Adaptive Random Effects/Coefficients Modeling

Adaptive fractional polynomial modeling of general correlated outcomes is formulated to address nonlinearity in means, variances/dispersions, and correlations. Means and variances/dispersions are modeled using generalized linear models in fixed effects/coefficients. Correlations are modeled using random effects/coefficients. Nonlinearity is addressed using power transforms of primary (untransformed) predictors. Parameter estimation is based on extended linear mixed modeling generalizing both generalized estimating equations and linear mixed modeling. Models are evaluated using likelihood cross-validation (LCV) scores and are generated adaptively using a heuristic search controlled by LCV scores. Cases covered include linear, Poisson, logistic, exponential, and discrete regression of correlated continuous, count/rate, dichotomous, positive continuous, and discrete numeric outcomes treated as normally, Poisson, Bernoulli, exponentially, and discrete numerically distributed, respectively. Example analyses are also generated for these five cases to compare adaptive random effects/coefficients modeling of correlated outcomes to previously developed adaptive modeling based on directly specified covariance structures. Adaptive random effects/coefficients modeling substantially outperforms direct covariance modeling in the linear, exponential, and discrete regression example analyses. It generates equivalent results in the logistic regression example analyses and it is substantially outperformed in the Poisson regression case. Random effects/coefficients modeling of correlated outcomes can provide substantial improvements in model selection compared to directly specified covariance modeling. However, directly specified covariance modeling can generate competitive or substantially better results in some cases while usually requiring less computation time.

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.