Process Approach Research Articles

Lightweight macro-pixel quality enhancement network for light field images compressed by versatile video coding

Previous research demonstrated that filtering Macro-Pixels (MPs) in a decoded Light Field Image (LFI) sequence can effectively enhances the quality of the corresponding Sub-Aperture Images (SAIs). In this paper, we propose a deep-learning-based quality enhancement model following the MP-wise processing approach tailored to LFIs encoded by the Versatile Video Coding (VVC) standard. The proposed novel Res2Net Quality Enhancement Convolutional Neural Network (R2NQE-CNN) architecture is both lightweight and powerful, in which the Res2Net modules are employed to perform LFI filtering for the first time, and are implemented with a novel improved 3D-feature-processing structure. The proposed method incorporates only 205K model parameters and achieves significant Y-BD-rate reductions over VVC of up to 32%, representing a relative improvement of up to 33% compared to the state-of-the-art method, which has more than three times the number of parameters of our proposed model.

When war narratives encounter populist audiences: a case of the Russia-Ukraine War on Chinese social media

ABSTRACT This research explores Chinese netizens’ response to Russia-Ukraine war narratives on Chinese social media, and how online populism affects the reception of war narratives. Taking a comparative perspective, it examines the mechanisms and reasons behind the dynamics in the Chinese social media users’ comments (N = 30261) toward Russian and Ukrainian Weibo posts (N = 124). With the help of the natural language processing (NLP) approach, the article highlights populism as a significant characteristic among comments on these war narratives, emphasizing the role of ideological influences in shaping public perception of geopolitical events. While Russia’s narrative initially garnered support, its popularity waned over time due to the heterogeneous nature of Chinese online populism. Conversely, Ukraine’s narrative faced initial challenges but eventually gained more support, largely due to the decreasing credibility of the opposing narratives.

Presenting a Model for the Evaluation of the Quality of e-learning at Payam Noor University

The current study aims to design a quality evaluation model of the electronic education system at Payam Noor University by applying a mixed methodology. The statistical population of the qualitative section includes twelve professors, researchers, and experts in the field of e-learning, who were selected by selective sampling. The conceptual model of the research was collected after conducting in-depth semi-structured interviews. The quantitative data based on a questionnaire designed by the researcher was collected from 274 professors and students with experience teaching or studying in the electronic education system of Payam Noor University. The data was analyzed using the structural equation modeling method in PLS3 software. The research results show that quality is a concept consisting of four categories behavioral, scientific, cognitive ability, and virtual learning experience. The study’ findings also reveal that cultural, pedagogical, learner, communication, infrastructural, and institutional factors affect the quality of Payam Noor University's electronic education system. Also, the results show that these characteristics will help universities achieve the four outcomes of competitiveness, job opportunities, economy, and reputation by establishing a quality education system. The ideal model for evaluating the quality of e-learning at Payam Noor University is a process approach in which the three dimensions of factors, quality indicators, and outputs are examined and measured. In other words, electronic education is successful when it can create a valuable experience of virtual education while empowering the learners scientifically, behaviorally, and cognitively to let all the stakeholders of higher education benefit from a valuable electronic education.

The Evaluation and Learning of Web Crawler Technology in the Field of Digital Media Art

With the rapid advancement of digital technology, digital media art has progressively emerged as a novel darling in the contemporary art market, primarily due to its distinctive interactivity, generativity, and digital distribution methods.The appraisal of market value is crucial in the transaction of digital art, and web crawling technology presents an innovative approach for data acquisition and processing. This study is dedicated to exploring the convergence of digital media art and web crawling technology, conducting an in-depth investigation on the application of web crawlers in the determination of market value for digital art.In the context of developing a theoretical framework, a novel value assessment model is proposed by integrating the features of the digital art market with established value assessment theories. On this basis, a value assessment tool targeted at the digital media art market was developed.This tool integrates multiple factors such as historical transaction data of artworks, artist backgrounds, work style, and media exposure, and employs machine learning algorithms to conduct market value assessment of artworks.Case analyses have also confirmed the accuracy of the assessment results and the practicality of the assessment model.Results show that this assessment tool not only provides powerful market guidance for art investors and collectors but also offers a pricing decision basis for digital art trading platforms.This research not only provides new perspectives and practical tools for the assessment of digital art but also makes a valuable exploration into the application of web crawling technology in the acquisition of art data information.It is of positive significance for the value discovery of digital media art and the long-term healthy development of the art market.

Prospective prediction of childhood body mass index trajectories using multi-task Gaussian processes.

Body mass index (BMI) trajectories have been used to assess the growth of children with respect to their peers, and to anticipate future obesity and disease risk. While retrospective BMI trajectories have been actively studied, models to prospectively predict continuous BMI trajectories have not been investigated. Using longitudinal BMI measurements between birth and age 10 y from a mother-offspring cohort, we leveraged a multi-task Gaussian process approach to develop and evaluate a unified framework for modeling, clustering, and prospective prediction of BMI trajectories. We compared its sensitivity to missing values in the longitudinal follow-up of children, compared its prediction performance to cubic B-spline and multilevel Jenss-Bayley models, and used prospectively predicted BMI trajectories to assess the probability of future BMIs crossing the clinical cutoffs for obesity. MagmaClust identified 5 distinct patterns of BMI trajectories between 0 to 10 y. The method outperformed both cubic B-spline and multilevel Jenss-Bayley models in the accuracy of retrospective BMI trajectories while being more robust to missing data (up to 90%). It was also better at prospectively forecasting BMI trajectories of children for periods ranging from 2 to 8 years into the future, using historic BMI data. Given BMI data between birth and age 2 years, prediction of overweight/obesity status at age 10 years, as computed from MagmaClust's predictions exhibited high specificity (0.94), negative predictive value (0.89), and accuracy (0.86). The accuracy, sensitivity, and positive predictive value of predictions increased as BMI data from additional time points were utilized for prediction. MagmaClust provides a unified, probabilistic, non-parametric framework to model, cluster, and prospectively predict childhood BMI trajectories and overweight/obesity risk. The proposed method offers a convenient tool for clinicians to monitor BMI growth in children, allowing them to prospectively identify children with high predicted overweight/obesity risk and implement timely interventions.

Factors influencing communication of virtual teams in times of pandemic: a case study in engineering education

ABSTRACT The COVID-19 pandemic has forced most universities to shift from traditional face-to-face teaching to remote learning. This sudden transition has presented numerous challenges for institutions that were unaccustomed to remote work, particularly in the context of senior design projects in engineering. Therefore, this study aimed to identify the influencing factors and their relative importance in affecting team communication in senior design projects during remote work. The study used the Analytical Hierarchy Process (AHP) approach to measure the level of importance of each factor using pairwise comparison in a structured questionnaire. The survey was distributed among group leaders of senior engineering design projects and faculty members who supervised these projects. The study identified five influencing factors: interaction and relations, trust, technology, time, and working environment. The pairwise comparison revealed that interaction and relations were the most important factor in influencing the communication process during remote work. Based on the identified influencing factors, strategies to improve the effectiveness and collaboration of remote meetings were established, providing a roadmap for universities to better prepare for future disruptions and maintain effective communication within student teams during remote work. Furthermore, these findings could have implications for other areas of higher education and the broader workplace.

Comparison of six natural language processing approaches to assessing firearm access in Veterans Health Administration electronic health records.

Access to firearms is associated with increased suicide risk. Our aim was to develop a natural language processing approach to characterizing firearm access in clinical records. We used clinical notes from 36685 Veterans Health Administration (VHA) patients between April 10, 2023 and April 10, 2024. We expanded preexisting firearm term sets using subject matter experts and generated 250-character snippets around each firearm term appearing in notes. Annotators labeled 3000 snippets into three classes. Using these annotated snippets, we compared four nonneural machine learning models (random forest, bagging, gradient boosting, logistic regression with ridge penalization) and two versions of Bidirectional Encoder Representations from Transformers, or BERT (specifically, BioBERT and Bio-ClinicalBERT) for classifying firearm access as "definite access", "definitely no access", or "other". Firearm terms were identified in 36685 patient records (41.3%), 33.7% of snippets were categorized as definite access, 9.0% as definitely no access, and 57.2% as "other". Among models classifying firearm access, five of six had acceptable performance, with BioBERT and Bio-ClinicalBERT performing best, with F1s of 0.876 (95% confidence interval, 0.874-0.879) and 0.896 (95% confidence interval, 0.894-0.899), respectively. Firearm-related terminology is common in the clinical records of VHA patients. The ability to use text to identify and characterize patients' firearm access could enhance suicide prevention efforts, and five of our six models could be used to identify patients for clinical interventions.

Blade tip clearance measurement method based on blade tip timing without the once per revolution sensor

Abstract The rotor blade tip clearance (BTC) of an aeroengine is a critical parameter that significantly impacts its performance and safety. Accurately determining dynamic BTC has been a focal point of research in experimental testing. Among the effective measurement methods for dynamic BTC, the laser triangulation method based on blade tip timing (BTT) stands out. However, this method typically relies on an once-per-revolution (OPR) sensor for rotor speed and blade serial number information during measurement, leading to increased installation and maintenance costs as well as additional measurement uncertainties. In response to this challenge, this paper presents two signal processing method that eliminate the need for an OPR sensor. The first method, referred to as "none OPR method 1," closely follows the measurement principles of the traditional method but employs a skewed dual light probe (SDLP) signal to extract rotational speed information, thus obviating the need for an OPR sensor. The second method, "none OPR method 2," introduces a novel data processing approach that enables BTC determination without any source of rotor speed information. Both methods utilize dynamic and static BTC matching techniques to identify blade serial numbers and achieve BTC measurement without an OPR sensor on a simulated rotor experimental bench. Comparative analysis with traditional method BTC measurements reveals that, under stable rotor speeds, all methods achieve similar levels of accuracy and repeatability errors within 0.025mm. However, when dealing with variable speed conditions, the traditional method's accuracy is significantly affected. None OPR method 1 mitigates the impact of rotor speed changes to some extent, while none OPR method 2 remains unaffected by such changes. Importantly, both none OPR methods demonstrate the capability to measure blade-by-blade tip clearances akin to the traditional method.

IMMU-19. PRECLINICAL THERAPEUTIC ACTIVITY AND PET IMAGING OF STING AGONIST 8803 IN GLIOBLASTOMA

Abstract STING (stimulator of interferon genes) activation triggers interferon (IFN) release within the tumor microenvironment from myeloid cells and other cell types, inducing proinflammatory anti-tumor immune responses. The small molecule STING agonist, 8803, elicits long-term survival in 56% (QPP4; p=0.0003) to 100% (QPP8; p<0.0001) of mice with orthotopically implanted immune checkpoint-resistant glioblastoma models after 2-3 doses. In humanized mice, in which glioblastoma-cell STING is epigenetically silenced, 8803 therapeutic activity is maintained. The combination therapy of 8803 with anti-PD-1 relatively further enhances survival in immune checkpoint-resistant models. Ex vivo flow cytometry and proteomic sequential multiplex profiling during the therapeutic window demonstrate global immunological reprogramming, specific tumor-antigen immune responses, increased tumor immune effector trafficking, and release of IFN. It has been shown that IFN signaling augments intracellular nucleotide metabolism and increases [18F]-FLT uptake in pancreatic cancer. We evaluated the longitudinal [18F]-FLT uptake in CT-2A-bearing mice using MRI/PET/CT at days 0, 2, and 4 after intratumoral 8803 delivery. Brain images were acquired before and after [18F]-FLT tracer and 8803 administrations. The CT was used for PET attenuation/correction, and the MRI was used for tumor segmentation. Regional analysis of PET-derived [18F]-FLT SUV maps used advanced image processing approaches as a function of time to enhance the voxel-by-voxel interpretation of the acquired images. [18F]-FLT uptake increased from baseline in all mice treated with 8803 compared to control mice with a peak at 48-96 hours. Concordant sequential multiplex immunofluorescence demonstrated that the STING expression was prominent along the tumor vasculature, myeloid, and tumor cells. p-IRF-3 expression, reflective of STING pathway activation, showed a diffuse pattern after treatment. Based on the preclinical data, PET imaging at 48-96 hours post-treatment represents the appropriate imaging modality and timepoint to maximize the ability to detect STING-dependent changes for a therapeutic strategy that reprograms the glioblastoma microenvironment and improves survival across multiple preclinical models of glioblastoma.

The New CAP and the Participative Method in Decision‐Making: A Textual Analysis of the Italian Case

AbstractThe main objective of this article is to analyse the role of the partnership approach in the decision process regarding the new CAP reform that guaranteed higher flexibility and better targeting. What was the impact of the multi‐actor decision‐making process on the reform process? How can policies be designed to increasingly listen to stakeholders' needs? To answer these questions, stakeholder interventions at the Partnership Table were analysed with a text mining and a sentiment analysis applied to the transcripts. Despite several weaknesses and biases in bringing national stakeholders to the institutional tables, the decision process moved towards a higher rate of flexibility, subsidiarity and transparency, overtaking the concept of ‘one size fits all’ that has dominated the CAP. The downside of this aspect is that the reform might favour member states with a solid tradition of CAP reception and administrative efficiency, able to move smoothly towards an effective participatory approach.

Using Balancing Equipment in Archer Training

Background and purpose The implementation of balance equipment plays an essential role in archery training. It helps develop stability, accuracy, coordination, and muscular endurance, all critical for successful. Balance platforms, exercise balls, and specialized devices add extra load on stabilizer muscles, leading to a more efficient use of the body and assisting athletes in maintaining balance during string tension and targeting. The objective is to evaluate the effectiveness of balance exercises in archers' training. Material and methods Participants: 23 archers (aged 13-14) from the "KOMUNAR" Kharkiv City Specialized Youth Sports School of Olympic Archery Reserve. The experiment was conducted for 2 months from August to October 2024. At the beginning and end of the experiment, an interactive survey was conducted using a Google form. Theoretical analysis, data generalization, questionnaire method, and mathematical statistics Results Developed and implemented in the training process of exercises with fitness balls, balance pillows, boards, fitness trampolines, balancing platforms. In addition to the usual balance exercises, the archers performed stances with bowstring tension with closed and open eyes and archery on balancing devices. The use of an extended set of preparatory exercises in the training process of archers made it possible to change the attitude of athletes to physical training, improve technical skills and develop psychological stability. The introduction of new training tools contributed to increasing the motivation of archers, understanding the importance of a versatile approach in the training process to achieve high results in archery. Conclusions It is shown that the use of special exercises has a positive effect on the psychological state of young athletes, emotionality and self-confidence. Keywords Archery, balancing equipment, balance, young athletes.

Conferencing: A Catalyst for Developing Children’s Writing

AbstractThe writing process approach is recognized as an effective instructional practice for engaging children in the writing process and developing emerging writing skills. The writing conference is an integral component of the writing process. One-on-one conferencing sessions create differentiated instructional spaces for teachers to respond to the individual needs of learners. Understanding how teachers leverage conferencing sessions to effectively engage and support young learners’ writing remains a limited area of research. This case study documents one experienced teacher’s conferencing practices with 19 first-grade writers. Findings show conferencing conversations worked in an integrated, multidimensional way to support young writers. Conferencing dimensions leveraged children’s funds of knowledge, questioning and affirming statements, and writers’ craft components to nurture relationships and offer feedback aligned with children’s zone of proximal development.

Resource supply and demand model of military settlements in the cold weapon era: case of Zhenbao Town, Ming Great Wall

As an important military defense project in Chinese history, the Ming Dynasty Great Wall and its associated military settlements played a crucial role in maintaining border security. A systematic analysis of how military settlements allocated resources based on external threats and geo-strategic needs is essential to understanding their settlements defense systems. However, this aspect has been relatively under-explored in existing research. Therefore, a resource allocation assessment model for Great Wall military settlements during the Cold Weapon era is established to facilitate a more scientific analysis and quantitative assessment of Military Defense Capabilities(MDC) and Military Requirements(MR). This study employs a combined Analytical Hierarchy Process (AHP) and Principal Component Analysis (PCA) approach to determine the weight of each indicator for both military defense capability and military requirement. Spatial clustering using K-means is conducted to visualize the distribution of these strengths and weaknesses. An Ordinary Least Squares (OLS) regression model links military requirements with defense capabilities, assessing the relationship between settlement locations and historical battle sites. Residual analysis is utilized to identify areas of resource over-allocation or under-allocation. The study reveals that the regional differences in military defense capabilities and requirements within the Zhenbao Town area during the Ming Dynasty correspond closely with the locations of frequent conflicts. This finding suggests that the distribution of defensive capabilities were strengthened in areas with challenging terrain, while the effectiveness and allocation of defense capabilities were determined by logistical support and transportation conditions. This study enhances our understanding of historical military strategies from a historical geography perspective and offers innovative insights for analyzing Great Wall settlement, moving beyond mere sensory intuition and historical experience.

Additive manufacturing of multiscale NiFeMn multi-principal element alloys with tailored composition

Abstract Nanostructured multi-principal element alloys (MPEAs) have been explored as next-generation engineering materials due to unique mechanical and functional properties which have significant advantages over traditional dilute alloys. However, the practical applications of nanostructured MPEAs are still limited due to the lack of scalable processing approaches to prepare a large quantity of nanostructured MPEAs, as well as lack of an efficient pathway for high-throughput discovery of better functional nanostructured MPEAs within their vast compositional space. Here we tackle these challenges by presenting an integrated approach by combining direct-ink-writing-based additive manufacturing, solid-state sintering, and chemical dealloying to manufacture hierarchically porous MPEAs. The hierarchical structure is comprised of macro- and micro-scale pores introduced via extrusion printing and polymer decomposition during sintering, as well as nanoscale pores formed via chemical dealloying. The macro- and micro-scale pores allow efficient dealloying of a large mass of material as the diffusion length that the corroding medium must penetrate remains at the scale of the ligaments formed after sintering (∼10 μm), despite the large volume of the 3D-printed samples. In addition, this integrated approach enables versatile control of the alloy composition via precisely tuning the ratio of elemental powders in the starting ink, thus offering a pathway for high-throughput discovery of novel functional MPEAs. As a case study, multiscale macro/micro/nanoporous NiFeMn MPEAs with three different compositions were investigated as catalysts to reduce the overpotential of oxygen evolution reaction (OER), where NiFeMn-based electrocatalysts display composition-dependent performance such that the overpotential measured at a current of 0.5 A g−1 for OER increases in the order of Ni58Fe29Mn13 ⩽ Ni64Fe26Mn10 < Ni76Fe18Mn6. This introduced manufacturing process offers new opportunities for scalable fabrication and rapid screening of nanostructured multi-component complex alloys.

Capabilities toward adoption of outcome-based contracts

PurposeManufacturing enterprises have started to offer the “outcome” derived from machines with the help of outcome-based contracts (OBCs). Offering OBCs leads to benefits such as increased revenues, stronger customer relationships and sustainability. However, implementing OBCs requires critical capabilities. Existing literature has focused on identifying these necessary capabilities, but the prioritization and interrelationships among them remain unexplored. This study aims to address this gap.Design/methodology/approachOur study employs a hybrid analytical hierarchy process and interpretative structural modeling approach to prioritize and map interrelationships among OBC-related capabilities within small and medium-sized enterprises (SMEs).FindingsThe findings highlight the importance of digitalization capabilities such as data privacy and security, remote monitoring, and data analytics; and organizational and governance capabilities, including quantifying, controlling, and monitoring risks, teamwork, and leadership, are highlighted.Research limitations/implicationsWe quantitatively prioritize OBC capabilities and establish their level-wise structural interrelationships, which will facilitate a more effective and efficient implementation of OBCs. Due to the emergent nature of OBCs, our study could identify just one SME case company meeting our selection criteria.Originality/valueExisting OBC literature focusses on the design of OBCs in large companies. Similarly, earlier capability-related OBC literature is oriented toward identifying the OBC capabilities to perform specific functions. However, in the current study, we propose a systematic decision-making approach that comprehensively prioritizes and identifies the interrelationships among the capabilities necessary to provide OBCs, thus complementing the existing scientific literature on OBCs. In addition, we focus on SMEs, that have specific limitations and characteristics.

The effect of wildfires on flood risk: a multi-hazard flood risk approach for the Ebro River basin, Spain

Abstract. Climate change increases the risk of wildfires and floods in the Mediterranean region. Yet, wildfire hazards are often overlooked in flood risk assessments and treated in isolation, despite their potential to amplify floods. Indeed, by altering the hydrological response of burnt areas, wildfires can lead to increased runoff and amplifying effects. This study aims to comprehensively assess flood risk using a multi-hazard approach, considering the effect of wildfires on flood risk, and integrating diverse socio-economic indicators with hydrological properties. More specifically, this study investigates current and future flood risks in the Ebro River basin in Spain for the year 2100 under the Shared Socioeconomic Pathway 1-2.6 (SSP1-2.6) and SSP5-8.5 scenarios, taking into account projected socio-economic conditions and the effect of wildfires. An analytical hierarchy process (AHP) approach is employed to assign weights to various indicators and components of flood risk based on insights gathered from interviews with seven experts specializing in natural hazards. Results show that the influence of wildfires on the baseline flood risk is not apparent. Under the SSP1-2.6 scenario, regions with high flood risk are expected to experience a slight risk reduction, regardless of the presence of wildfires, due to expected substantial development in adaptive capacity. The highest flood risk, almost double compared to the baseline, is projected to occur in the SSP5-8.5 scenario, especially when considering the effect of wildfires. Therefore, this study highlights the importance of adopting a multi-hazard risk management approach, as reliance solely on single-risk analyses may lead to underestimating the compound and cascading effects of multi-hazards.

An analytical hierarchical process approach to assessing local food preferences among foreign tourists

An analytical hierarchical process approach to assessing local food preferences among foreign tourists

Efficient algorithm for thermal nondestructive testing and evaluation by considering the heteroscedastic nature of noise sources in infrared thermography

Abstract Thermal Imaging is a promising Non Destructive Testing & Evaluation (NDT & E) approach to monitor the health of composite materials. Among various post processing approaches adopted in thermal imaging for NDT & E, statistical analysis schemes gained importance due to their reliability and data reduction capabilities. This paper provides an insight to a factor analysis-based statistical approach to detect the hidden defects in the Glass Fiber Reinforced Polymer (GFRP) sample. The proposed approach models the observed data covariance into combination of temporal signal covariance and noise covariance matrices. The modeling of the diagonal covariance matrix (with different elements) is motivated by the presence of heterogeneity in the experimental data obtained from GFRP sample.This novel method is based on the coordinate descent technique, which estimates the covariance matrix of the noise variances iteratively by minimizing the negative log likelihood function. The obtained results from the chosen GFRP samples compared with the widely used statistical Principal Component Thermography (PCT) technique illustrate the improved performance in terms of defect detection with the proposed technique.

LiDAR-Based Modeling of Individual Tree Height to Crown Base in Picea crassifolia Kom. in Northern China: Comparing Bayesian, Gaussian Process, and Random Forest Approaches

This study compared hierarchical Bayesian, mixed-effects Gaussian process regression, and random forest models for predicting height to crown base (HCB) in Qinghai spruce (Picea crassifolia Kom.) forests using LiDAR-derived data. Both modeling approaches were applied to a dataset of 510 trees from 16 plots in northern China. The models incorporated tree-level variables (height, diameter at breast height, crown projection area) and plot-level spatial competition indices. Model performance was evaluated using leave-one-plot-out cross-validation. The Gaussian mixed-effects process model (with an RMSE of 1.59 and MAE of 1.25) slightly outperformed the hierarchical Bayesian model and the random forest model. Both models identified LiDAR-derived tree height, DBH, and LiDAR-derived crown projection area as primary factors influencing HCB. The spatial competition index (SCI) emerged as the most effective random effect, with the lowest AIC and BIC values, highlighting the importance of local competition dynamics in HCB formation. Uncertainty analysis revealed consistent patterns across the predicted values, with an average relative uncertainty of 33.89% for the Gaussian process model. These findings provide valuable insights for forest management and suggest that incorporating spatial competition indices can enhance HCB predictions.

Research on filling missing GNSS precipitable water vapor time series data using the PSORF model combined with reanalysis datasets

Abstract The inversion of precipitable water vapor (PWV) using the Global Navigation Satellite System (GNSS) has advantages such as all-weather observation, high precision, low cost, and high temporal resolution. Currently, long-term GNSS-PWV data has become an important data source for studying climate change. However, due to factors such as equipment failures, observation technology limitations, and estimation model errors, missing data and outliers often occur in real-time or post-processed PWV time series data. Furthermore, the main sources of GNSS-PWV errors are influenced by the atmospheric weighted mean temperature and surface meteorological data (pressure and temperature). The results indicate that the European Centre for Medium-Range Weather Forecasts Reanalysis v5 (ERA5) dataset exhibits high accuracy in the Chinese region, making it suitable for GNSS-PWV inversion. By utilizing ERA5 meteorological data to calculate hourly GNSS-PWV and conducting accuracy assessments, it is demonstrated that the PWV inverted based on GNSS and ERA5 meteorological parameters possesses high precision. Based on this, this study selects GNSS stations from the Crustal Movement Observation Network of China where the proportion of missing measured data is less than 8%. By combining ERA5, random forest (RF), and particle swarm optimization (PSO) algorithms, a new model called PSORF is proposed to fill in missing values in GNSS-PWV time series data. The research findings reveal that the R 2 and root mean square error (RMSE) of PSORF-PWV are 0.98 and 2.16 mm, respectively. Additionally, GNSS stations with more than 8% missing measured data are utilized to validate the accuracy of the PSORF model. A comparative analysis is conducted between the results obtained through the PSORF model and the ERA5-PWV acquired via traditional interpolation methods. The MAE and RMSE of PSORF-PWV are reduced by 21% and 17%, respectively, indicating that the PSORF model excels in filling missing data and effectively enhances the accuracy and reliability of PWV time series analysis. This study not only presents an effective approach for processing missing PWV data but also evaluates the applicability and accuracy of the ERA5 dataset in PWV inversion. This provides crucial technical support and data security for climate change research, short-term humidity field forecasting, and studies in related fields.