Physical Information Research Articles

Spatiotemporal dominance of afterslip and viscoelastic relaxation revealed by four decades of post-1973 Luhuo earthquake observations

Measuring surface displacements driven by afterslip and viscoelastic relaxation following large earthquakes enables inferring frictional and rheological properties of Earth's outermost layers where hazardous earthquakes occur. However, the two concurrent mechanisms generate similar and intertwined surface deformations, complicating the extraction of physical information from the measurements. Here, we quantify the spatiotemporal dominance of co-evolving afterslip and viscoelastic relaxation following the 1973 Ms 7.6 Luhuo earthquake in eastern Tibet, using 42 years (1976‒2018) of fault-crossing short-baseline observations. The finite-fault slip of this M7+ earthquake was constructed from triangulation data measured in 1961‒1975. Based on the model incorporating two postseismic relaxation mechanisms and calibrated by the measurements over four decades, we show that, in the temporal domain, afterslip may produce geodetically measurable deformations (>1.5 mm/yr) in local near-field regions even 20 years after the mainshock, with spatially broader impact within ∼10 years. Viscoelastic relaxation may last for nearly six decades, imposing a broad influence for three decades. In the spatial domain, afterslip may produce deformations within ∼2 times the seismogenic depth (SD; 20 km) from the fault, but dominantly in the near-field of ∼1 times the SD. In contrast, viscoelastic relaxation may affect a much wider region reaching 200 km. While afterslip and viscoelastic relaxation collectively affected the region ∼2 times the SD from the fault in the early postseismic period, their resulting deformations gradually separated in space with time, with afterslip-induced deformation shrinking toward the fault, and surface deformation caused by viscoelastic relaxation concentrating in the mid-field, ∼2–3 times the SD from the fault. Their spatiotemporal partitioning helps better learn fault frictional properties and lithospheric rheology based on geodetic data acquired from different domains.

DPICEN: Deep physical information consistency embedded network for bearing fault diagnosis under unknown domain

In recent years, intelligent transfer models have focused on narrowing the gap between the source domain and target domain data to improve diagnostic effectiveness. However, collecting unlabelled target domain data in advance is challenging, leading to suboptimal performance of domain adaptation models for unknown target domain data. To address this issue, this paper proposes a deep physical information consistency embedded network (DPICEN) for tackling unknown domain bearing fault diagnosis problems. First, a physical information encoder (PIE) is constructed to encode physical information into tensors with values of 0/1. Second, fault samples and their encoded tensors are embedded into a physically consistent space, and the mean squared error (MSE) is employed to reduce the distance between data feature embeddings and physical information embeddings. Subsequently, to further constrain the distribution differences of unknown domain data, a plug-and-play multiple sparse regularization (MSR) algorithm is proposed. Finally, the embedded features are input into a classifier with MSR to achieve bearing fault diagnosis. The results demonstrate the effectiveness and advancement of DPICEN in comparison with 16 related methods in 13 unknown domain fault diagnosis tasks in three bearing datasets. The code can be found at https://github.com/John-520/Models-for-DPICEN.

Predicting protein conformational motions using energetic frustration analysis and AlphaFold2

Proteins perform their biological functions through motion. Although high throughput prediction of the three-dimensional static structures of proteins has proved feasible using deep-learning-based methods, predicting the conformational motions remains a challenge. Purely data-driven machine learning methods encounter difficulty for addressing such motions because available laboratory data on conformational motions are still limited. In this work, we develop a method for generating protein allosteric motions by integrating physical energy landscape information into deep-learning-based methods. We show that local energetic frustration, which represents a quantification of the local features of the energy landscape governing protein allosteric dynamics, can be utilized to empower AlphaFold2 (AF2) to predict protein conformational motions. Starting from ground state static structures, this integrative method generates alternative structures as well as pathways of protein conformational motions, using a progressive enhancement of the energetic frustration features in the input multiple sequence alignment sequences. For a model protein adenylate kinase, we show that the generated conformational motions are consistent with available experimental and molecular dynamics simulation data. Applying the method to another two proteins KaiB and ribose-binding protein, which involve large-amplitude conformational changes, can also successfully generate the alternative conformations. We also show how to extract overall features of the AF2 energy landscape topography, which has been considered by many to be black box. Incorporating physical knowledge into deep-learning-based structure prediction algorithms provides a useful strategy to address the challenges of dynamic structure prediction of allosteric proteins.

Reflection impulsivity in patients with panic disorder

ABSTRACT Background Individuals with panic disorder (PD) often exhibit a proclivity to conclude that an imminent catastrophe looms, drawing such conclusions from limited physical information. Reflection impulsivity, characterized by decision-making without adequate information, likely affects this bias. This study examines the relationship between reflection impulsivity and self-report impulsive features in individuals with PD. Methods Fifty patients with PD and 50 healthy controls (HC) participated to this study. Reflection impulsivity was assessed using the Information Sampling Task (IST), while trait impulsivity was measured using the Barratt Impulsiveness Scale (BIS). Participants also completed the Beck Anxiety Inventory, Panic and Agoraphobia Scale (P&A), and Anxiety Sensitivity Index-3 (ASI-3). Results Individuals with PD exhibited higher reflection impulsivity compared to HC. Increased reflection impulsivity correlated positively with PD severity as assessed by the P&A and cognitive concerns measured by ASI-3. No significant correlations were found with physical or social concerns. PD patients had higher BIS scores than HC. Higher trait impulsivity was linked to recurrent emergency department visits among PD patients. Discussion The findings of this study reveal the notion of increased impulsivity among individuals with PD and its relationship with cognitive concerns, as well as recurrent visits to the emergency department stemming from panic attacks.

Research on flexible piezoresistive sensors based on nanocomposite materials

As a core component, sensors play a crucial role in fields such as the Internet of Things, biomedicine, and artificial intelligence by converting physical information into electrical signals. With technological advancements, the demand for improved sensor performance and environmental adaptability has been increasing, driving progress in advanced materials, new structures, and refined processing technologies to enhance the efficiency of converting pressure signals into electrical signals. Flexible piezoresistive sensors are widely used due to their high sensitivity, good linear response, and fast response time. The performance of these sensors heavily depends on the microstructure of the materials, and traditional detection methods struggle to capture their dynamic changes. Therefore, developing in-situ characterization techniques to monitor changes in material structure and chemical properties in real-time is crucial for optimizing material performance. Additionally, integrated sensor systems that study signal acquisition, circuit interfaces, and signal processing, combined with artificial intelligence algorithms for data processing and analysis, not only improve system efficiency but also broaden their application range.

Flood scenario spatio-temporal mapping via hydrological and hydrodynamic modelling and a remote sensing dataset: A case study of the Basento river (Southern Italy)

Today, hydrological and hydraulic modelling are essential tools for flood risk management, although these models are still affected by elements of uncertainty that needs to be reduced by optimizing their results. The present research aims to implement an operational mechanism on the Basento river basin in Southern Italy based on the cascading use of a physically based concentrated-parameter hydrological model for the estimation of flood hydrographs, and a two-dimensional hydraulic model for flood mapping. The calibration of the hydrological model uses physical information to reduce the initial range of the set parameter values, and an automated optimisation procedure based on a genetic algorithm to find optimal values of the model parameters by comparing simulated and observed data for the 2013 flood event. To calibrate the hydraulic model, a series of flood maps extracted from multi-temporal SAR images was used. In addition, validation of the hydrological and hydraulic models was carried out on March 2011 flood event. The results show the reliability of the models during both calibration and validation, with the hydrological model achieving a Nash-Sutcliffe Efficiency coefficient between 0.86 and 0.91, and the hydraulic model leading to results with an accuracy close to 70 %. Considering the significance of the results, the developed modelling chain was used to simulate future event scenarios for risk management assessment and could operate as an early warning system.

Origin and tuning of bandgap in chiral phononic crystals

The wave equation revealing the wave propagation in chiral phononic crystals, established through force equilibrium law, conceals the underlying physical information, such as the essence of the motion coupling and the inertial amplification effect. This has led to a controversy over the bandgap mechanism. In this article, we theoretically unveil the reason for this controversy, and put forward an alternative approach from wave behavior to formulate the wave equation, offering an alternative pathway to articulate the bandgap physics directly. Based on the physics revealed by our theory method, we identify the obstacles in coupled acoustic and optic branches to widen and lower the bandgap. Then we introduce an approach based on spherical hinges to decrease the barriers, for customizing the bandgap frequency and width. Finally, we validate our proposal through numerical simulation and experimental demonstration.

(Invited) Wearable Flexible Microfluidic Biosensor for Sweat Monitoring

As we enter the post-pandemic era, our lives have certainly become more convenient than before, due to the advancement and elimination of technologies that became practical or widespread during the pandemic. Among these, technologies related to non-invasive bioinstrumentation, which can be used at an individual level to access one's own health information, have become increasingly important. Non-invasive bioinstrumentation can be broadly divided into the measurement of physical information (shape, activity and so on) and the measurement of chemical information, i.e. the components of the body. For example, facial shape is widely used for personal identification, while weight and energy expenditure related to activity are easily managed by smartphones. In contrast, chemical sensing, which is often difficult to sample and requires a wet environment for measurement, still requires breakthroughs to be used by individuals with the same ease as physical sensing.In the research field of non-invasive biomedical measurements, the technology is often developed in the form of wearable systems. Wearable microfluidic devices have been intensively studied for the measurement of body components. We focused on sweat, which contains a variety of biomarkers, and have developed a wearable microfluidic biosensing system that measures sweat components in real-time. Sweat is secreted from sweat glands on the skin of the entire body, making it easily accessible and less mentally demanding to collect. On the other hand, there are problems with sampling methods for reliable measurement, such as large fluctuations in the sweat rate and evaporation from the skin surface during secretion. We overcame this problem by using a wearable microfluidic device to transport the full amount of sweat from the sweat gland to a downstream biosensor by carrier flow, and developed a wristwatch biosensing system to monitor the constituents released as sweat independent of sweat rate.The wristwatch sweat sensor consists of a PDMS sweat sampling device, a biosensor, a fluid controller and a wireless control circuit with Bluetooth Low Energy and external analogue I/O. Communication with the mobile device is via Bluetooth Low Energy. Our method has the advantage that secretions are transported by dissolution in the carrier stream and can therefore be reliably monitored even at very low sweat levels. The pump is controlled by an microcontroller unit, so the flow rate can be controlled in real time according to the sweat rate and target substances, and the sensitivity can be improved at the expense of temporal resolution by running the pump intermittently, i.e. allowing secretions to accumulate in the carrier flow for a certain time before measurement.We monitored changes in sweat lactic acid in response to exercise load using an ergometer. The results showed an increase in sweat lactate with increasing exercise intensity, with a dependence on sweat rate. By measuring sweat at rest, we found that the lactate accumulated in the sweat glands and on the skin's surface were dissolved by the biosensor in the early stages of measurement, while the signals from the sweat glands became dominant after these had been sufficiently decreased. These results suggest that our system appropriately reflects the physiological phenomena associated with sweating. The presentation will also include the behaviour of lactic acid in sweat, which was detected by our system for the first time.

Comparative effectiveness of perioperative physical activity in older adults with lung cancer and their family caregivers: design of a multicenter pragmatic randomized trial

BackgroundWith a median age at diagnosis of 70, lung cancer remains a significant public health challenge for older Americans. Surgery is a key component in treating most patients with non-metastatic lung cancer. These patients experience postoperative pain, fatigue, loss of respiratory capacity, and decreased physical function. Data on quality of life (QOL) in older adults undergoing lung cancer surgery is limited, and few interventions are designed to target the needs of older adults and their family caregivers (FCGs). The primary aim of this comparative effectiveness trial is to determine whether telephone-based physical activity coaching before and after surgery will be more beneficial than physical activity self-monitoring alone for older adults and their FCGs.MethodsIn this multicenter comparative effectiveness trial, 382 older adults (≥ 65 years) with lung cancer and their FCGs will be recruited before surgery and randomized to either telephone-based physical activity coaching or physical activity self-monitoring alone. Participants allocated to the telephone-based coaching comparator will receive five telephone sessions with coaches (1 pre and 4 post surgery), an intervention resource manual, and a wristband pedometer. Participants in the self-monitoring only arm will receive American Society of Clinical Oncology (ASCO) physical activity information and wristband pedometers. All participants will be assessed at before surgery (baseline), at discharge, and at days 30, 60, and 180 post-discharge. The primary endpoint is the 6-minute walk test (6MWT) at 30 days post-discharge. Geriatric assessment, lower extremity function, self-reported physical function, self-efficacy, and QOL will also be assessed.DiscussionThe trial will determine whether this telephone-based physical activity coaching approach can enhance postoperative functional capacity and QOL outcomes for older adults with lung cancer and their FCGs. Trial results will provide critical findings to inform models of postoperative care for older adults with cancer and their FCGs.Trial RegistrationClinicalTrials.gov Identifier: NCT06196008.

Information compression via hidden subgroup quantum autoencoders

We design a quantum method for classical information compression that exploits the hidden subgroup quantum algorithm. We consider sequence data in a database with a priori unknown symmetries of the hidden subgroup type. We prove that data with a given group structure can be compressed with the same query complexity as the hidden subgroup problem, which is exponentially faster than the best-known classical algorithms. We moreover design a quantum algorithm that variationally finds the group structure and uses it to compress the data. There is an encoder and a decoder, along the paradigm of quantum autoencoders. After the training, the encoder outputs a compressed data string and a description of the hidden subgroup symmetry, from which the input data can be recovered by the decoder. In illustrative examples, our algorithm outperforms the classical autoencoder on the mean squared value of test data. This classical-quantum separation in information compression capability has thermodynamical significance: the free energy assigned by a quantum agent to a system can be much higher than that of a classical agent. Taken together, our results show that a possible application of quantum computers is to efficiently compress certain types of data that cannot be efficiently compressed by current methods using classical computers.

Predicting households’ attitudes and product adoption intentions

PurposeThe present study aims to examine the households’ attitudes and intentions to adopt an indoor air purifier against the smog crisis in India by using a comprehensive theoretical framework based on the combination of the Protective Action Decision Model (PADM) and the Theory of Planned Behavior (TPB). The United Nations Sustainable Development Goals (SDGs) 2030 also emphasized ensuring a healthy and safe life, especially by achieving SDG-3, SDG-11 and SDG-13.Design/methodology/approachUsing purposive sampling, the data were collected through a survey questionnaire distributed to 382 households, and study hypotheses were assessed by using partial least squares structural equation modeling employing SmartPLS.FindingsThe results revealed that mental health risk perception (MHRP) was the most influential determinant of households’ attitudes toward adopting air purifiers, followed by smog knowledge, physical health risk perception (PHRP), information seeking and product knowledge. Notably, results revealed that households’ attitude is a leading determinant of their adoption intention toward the air purifier compared to subjective norms (SN) and perceived behavioral control (PBC).Originality/valueTo the best of the authors’ knowledge, the present study is the first to provide new insights into an individual’s protective behavior response toward ecological hazards by examining the households’ adoption intention toward the air purifier against the smog crisis using PADM and TPB model inclusively. In addition, the present study analyzes the impact of both PHRP and MHRP on individuals’ protective behavior separately. Also, this study provides theoretical contributions and important practical implications for the government, manufacturers and air purifier sellers.

The beliefs and practices used to promote physical and mental health in youth who identify as lesbian, gay, bisexual, transgender, intersex, or queer plus (LGBTIQ+) experiencing housing insecurity: An integrative review.

The purpose of this integrative review was to explore the beliefs and practices used to promote physical and mental health among youth ages 18-25 years, identifying as LGBTIQ+ experiencing housing insecurity. The approach used strategies described by Whittemore and Knafl. Peer-reviewed, published research articles in English were identified using eight electronic databases. Eighteen research reports using qualitative, quantitative, and mixed methods were identified. Articles were evaluated for quality using the American Association of Critical Care Nurses Evidenced-Level Hierarchy evaluation tool. Data were analyzed and synthesized using Braun and Clarke's method. Four themes related to the purpose were extracted: pervasive experiences of stigma and discrimination, constantly attuned to navigating risks, inconsistent engagement in health information and care, and inner strength developed through personal and community experiences. There are strong implications for future research, public health nursing practice, and health policy. Public health nurses should incorporate social determinants of health (addressing harmful social processes such as homophobia and racism) as well as a strength-based upstream approach in research, education, and health care practices. More research must also be done to assess engagement in physical and mental health information and care.

Net evaporation-induced mangrove area loss across low-lying Caribbean islands

Abstract Although mangroves provide many beneficial ecosystem services, such as blue carbon storage and coastal protection, they are currently under threat due to changes in climate conditions, such as prolonged drought exposure. Under drought conditions, evaporation exceeds precipitation and high soil salinities can lead to stunted growth and die-back. To quantify this interplay, we developed a database for low-lying and uninhabited mangrove islands in the Caribbean under various evaporation and precipitation regimes. We extracted physical and biological information from each island using remote sensing techniques and coupled it with a process-based model. We used this database to develop a model that explains both the spatial variability in vegetated area across the Caribbean—as a function of rates of evaporation and precipitation—and porewater salinity concentration and dispersion from island edge towards the interior of mangrove islands. We then used this validated model to predict mangrove area loss associated with increases in evaporation to precipitation rates by 2100 for different Shared Socioeconomic Pathways (SSP). Less wealthy Caribbean regions such as Belize, Puerto Rico, and Venezuela are disproportionally affected, with mangrove area losses ranging from 3%–7% for SSP 2.6 and 13%–21% for SSP 7.0. Furthermore, foregone carbon sequestration in lost biomass under SSP 4.5 and 7.0 scenarios could compromise the ability of low-lying Caribbean mangrove islands to vertically adjust to sea level rise.

The Spatiotemporal Doubled‐Density Operator: A Unified Framework for Analyzing Spatial and Temporal Quantum Processes

AbstractThe measurement statistics for spatial and temporal quantum processes are produced through distinct mechanisms. Measurements that are space‐like separated exhibit non‐signaling behavior. However, time‐like separated measurements can only result in one‐way non‐signaling, as the past is independent of the future, but the opposite is not true. This work presents the doubled‐density operator as a comprehensive framework for studying quantum processes in space‐time. It effectively captures all the physical information of the process, with the measurement and Born rule showing uniformity for both spatial and temporal cases. It is demonstrated that the equal‐time density operator can be derived by performing a partial trace operation on the doubled‐density operator. Furthermore, the temporality of the quantum process can be detected by conducting a partial trace operation on either the left or right half of the doubled‐density operator.

A hybrid physics-corrected neural network for RUL prognosis under random missing data

In order to accurately predict the remaining useful life (RUL) of mechanical equipment under conditions of missing data, this paper proposes a novel integrated framework for data repair and RUL prediction, named DRTCR. DRTCR possesses the dual functionality of missing data repair and RUL prediction. Initially, considering the underlying trends and periodic fluctuations in the signals, polynomial and trigonometric functions are incorporated into the implicit feature matrix (IFM) generated by Gaussian random functions. This approach involves constructing a data repair deep learning framework primarily based on LSTM and CNN. This framework facilitates the repair of missing data. Furthermore, this paper introduces the integration of trend, correlation, and robustness within the LSTM units. A predictive unit named TCRcell is devised, which enhances the feature extraction capability of the prediction model. Additionally, a corrective unit within TCRcell is constructed, predominantly centered around discrete Fourier transform (DFT) and discrete wavelet transform (DWT) as frequency domain feature extraction techniques. This incorporation introduces the physical mechanism information into DRTCR and refines the predictive outcomes of TCRcell. The global frequency perspective of DFT aids in capturing the overall trend in signal variations, while DWT precisely captures localized temporal details in the time series, resulting in a dynamically corrected TCRcell prediction outcome that combines both global trends and local intricacies. Finally, experimental validation was conducted to assess the predictive performance and robustness of DRTCR.

Atomic resolution coherent x-ray imaging with physics-based phase retrieval

Coherent x-ray imaging and scattering from accelerator based sources such as synchrotrons continue to impact biology, medicine, technology, and materials science. Many synchrotrons around the world are currently undergoing major upgrades to increase their available coherent x-ray flux by approximately two orders of magnitude. The improvement of synchrotrons may enable imaging of materials in operando at the atomic scale which may revolutionize battery and catalysis technologies. Current algorithms used for phase retrieval in coherent x-ray imaging are based on the projection onto sets method. These traditional iterative phase retrieval methods will become more computationally expensive as they push towards atomic resolution and may struggle to converge. Additionally, these methods do not incorporate physical information that may additionally constrain the solution. In this work, we present an algorithm which incorporates molecular dynamics into Bragg coherent diffraction imaging (BCDI). This algorithm, which we call PRAMMol (Phase Retrieval with Atomic Modeling and Molecular Dynamics) combines statistical techniques with molecular dynamics to solve the phase retrieval problem. We present several examples where our algorithm is applied to simulated coherent diffraction from 3D crystals and show convergence to the correct solution at the atomic scale.

Design and implementation of college students’ physical education teaching information management system by data mining technology

This study intends to improve the efficiency of physical education teaching management, accelerate the normal teaching process, and meet the modern management requirements that traditional teaching management methods cannot meet. Based on data mining technology, this study designs a college student physical education teaching information management system, and makes a detailed design of each functional module. The main task of this study is to investigate how to effectively integrate data mining techniques with existing university student physical education teaching databases. Then, this study finds useful data information from massive data information to provide information support for university student physical education teaching. In order to effectively mine the relevant information of the data, the student evaluation module in the system is designed based on decision trees, and the teacher-student related data analysis module in the system is designed based on association rules. The research results indicate that 1039 records and 8205 student records are extracted from the teaching management database as mining objects. Rule 1: The support rate for “a professor's degree is a doctoral degree” is 20.4 %, indicating that there are 20.4 % of records in the teacher database that “the title is a professor and a doctoral degree”; the confidence level of Rule 1 is 78.2 %, indicating that 78.2 % of professors have a doctoral degree. Through the analysis of the rules that evaluate teaching as good, it can be found that the three attributes of professional title, education level, and teaching experience are the most important relevant factors affecting teaching effectiveness. Research has shown that the longer and richer the teaching experience, the stronger the teaching ability. Secondly, the mining results obtained through data mining techniques are analyzed. The maximum difference between the original algorithm's support mining results and the true values is 0.08, while the maximum difference between the improved algorithm's support mining results and the true values is 0.01. Compared to the original algorithm, the improved algorithm's mining results are accurate and effective. The application of data mining ideas in this system has laid a solid foundation for the development of physical education and teaching. Moreover, a three-layer system architecture model is adopted to better adapt to the development of school physical education, which is beneficial for later system maintenance and greatly reduces the work pressure of teachers. The system has been successfully launched and running in universities, and it is in good working condition.

A Constrained Spectral Approximation of Subgrid‐Scale Orography on Unstructured Grids

AbstractThe representation of subgrid‐scale orography is a challenge in the physical parameterization of orographic gravity‐wave sources in weather forecasting. A significant hurdle is encoding as much physical information with as simple a representation as possible. Other issues include scale awareness, that is, the orographic representation has to change according to the grid cell size and usability on unstructured geodesic grids with non‐quadrilateral grid cells. This work introduces a novel spectral analysis method approximating a scale‐aware spectrum of subgrid‐scale orography on unstructured geodesic grids. The dimension of the physical orographic data is reduced by more than two orders of magnitude in its spectral representation. Simultaneously, the power of the approximated spectrum is close to the physical value. The method is based on well‐known least‐squares spectral analyses. However, it is robust to the choice of the free parameters, and tuning the algorithm is generally unnecessary. Numerical experiments involving an idealized setup show that this novel spectral analysis performs significantly better than a straightforward least‐squares spectral analysis in representing the physical energy of a spectrum. Studies involving real‐world topographic data are conducted, and reasonable error scores within ±10% error relative to the maximum physical quantity of interest are achieved across different grid sizes and background wind speeds. The deterministic behavior of the method is investigated along with its principal capabilities and potential biases, and it is shown that the error scores can be iteratively improved if an optimization target is known. Discussions on the method's limitations and broader applicability conclude this work.

Cryptography with stochastic photons

Quantum cryptography protocols are based on the use of quantum objects with at least two orthogonal states, for example, the polarization states of a photon. We propose a completely different cryptography protocol using a stochastic flow of single photons. Our method is based on the stochastic decay of an ensemble of radioactive nuclei randomly emitting a stream of γ-photons. We have experimentally demonstrated the transmission of classical information containing binary bits. Reading this information requires precise knowledge of the repetition rate of its sending. Otherwise, it is impossible to make the transmitted information visible, since it will be lost in the noise.

Pre-route timing prediction and optimization with graph neural network models

In recent years, the application of deep learning (DL) models has sparked considerable interest in timing prediction within the place-and-route (P&R) flow of IC chip design. Specifically, at the pre-route stage, an accurate prediction of post-route timing is challenging due to the lack of sufficient physical information. However, achieving precise timing prediction significantly accelerates the design closure process, saving considerable time and effort. In this work, we propose pre-route timing prediction and optimization framework with graph neural network (GNN) models combined with convolution neural network (CNN). Our framework is divided into two main stages, each of which is further subdivided into smaller steps. Precisely, our GNN-driven arc delay/slew prediction model is divided into two levels: in level-1, it predicts net resistance (net R) and net capacitance (net C) using GNN while the arc length is predicted using CNN. These predictions are hierarchically passed on to level-2 where delay/slew is estimated with our GNN based prediction model. The timing optimization model utilizes the precise delay/slew predictions obtained from the GNN-driven prediction model to accurately set the path margin during the timing optimization stage. This approach effectively reduces unnecessary turn-around iterations in the commercial EDA tools. Experimental results show that by using our proposed framework in P&R, we are able to improve the pre-route prediction accuracy by 42%/36% on average on arc delay/slew, and improve timing metrics in terms of WNS, TNS, and the number of timing violation paths by 77%, 77%, and 64%, which are an increase of 32%/35% on arc delay/slew and 30%, 20% and 31% on timing optimization compared with the existing DL prediction model.