Framework Of Model Research Articles

Simulating seismic wavefields using generative artificial intelligence

Simulating realistic seismic wavefields is crucial for a range of seismic tasks, including acquisition designing, imaging, and inversion. Conventional numerical seismic wave simulators are computationally expensive for large 3D models, and discrepancies between simulated and observed waveforms arise from wave equation selection and input physical parameters such as the subsurface elastic models and the source parameters. To address these challenges, we adopt a data-driven artificial intelligence approach and propose a conditional generative modeling (CGM) framework for seismic wave simulation. The novel CGM framework learns complex 3D wave physics and subsurface heterogeneities from the observed data without relying on explicit physics constraints. As a result, trained CGM-based models act as stochastic wave-propagation operators encoded with a local subsurface model and a local moment tensor solution defined by training data sets. Given these models, we can simulate multicomponent seismic data for arbitrary acquisition settings within the area of the observation, using source and receiver geometries and source parameters as input conditional variables. In this study, we develop four models within the CGM framework — CGM-GM-1D/3D, CGM-Wave, and CGM-FAS — and demonstrate their performance using two seismic data sets: a small low-density data set of natural earthquake waveforms from the San Francisco Bay Area, a region with high seismic risks, and a large high-density data set from induced seismicity records of the Geysers geothermal field. The CGM framework reproduces the waveforms, the spectra, and the kinematic features of the real observations, demonstrating the ability to generate waveforms for arbitrary source locations, receiver locations, and source parameters. We address key challenges, including data density, acquisition geometry, scaling, and generation variability, and we outline future directions for advancing the CGM framework in seismic applications and beyond.

Impact of tislelizumab + chemotherapy versus placebo + chemotherapy on patient-reported symptoms and overall survival (OS) by programmed death-ligand 1 (PD-L1) expression in advanced or metastatic esophageal squamous cell carcinoma (ESCC): A post hoc analysis of the RATIONALE-306 trial.

366 Background: While improved survival has been previously demonstrated, the impact of immunotherapy on HRQoL in ESCC has not been well examined. Traditional PRO-based analyses in oncology trials, such as time to deterioration (TTD) and mixed models for repeated measures (MMRMs), are limited by discounting recurrent PRO events. Thus, we applied a 3-component joint model (JM) framework to define more clinically interpretable associations between patient-reported symptoms, treatment effects, and OS among subgroups of patients with ESCC from RATIONALE-306, which met its primary endpoint, with PD-L1 expression of ≥1%, ≥5%, and ≥10%. Methods: The final analytic sample included 226 patients in the tislelizumab + chemotherapy arm (T+C), 242 in the placebo + chemotherapy arm (P+C) for PD-L1 ≥1%, 113 in the T+C arm and 103 in the P+C arm for PD-L1 ≥5%, and 168 in the T+C arm and 178 in the P+C arm for PD-L1 ≥10%.From EORTC QLQ-C30 and OES18, 7 keysymptom domains were modeled (GHS, physical functioning, fatigue, dysphagia, pain, reflux, dietary restrictions). PRO data were collected at baseline and at every treatment cycle (up to 6 cycles), then every other cycle, and at safety follow-up, and change from baseline (CFBL) was analyzed. The joint model comprised three components: 1) linear mixed model predicting CFBL symptom scores; 2) Cox proportional hazard model (CPH) for time to OS; and 3) frailty (random effects for recurrent deterioration events [RDEs]) CPH model for time to PRO-based RDEs. Osoba (1998) 10-point threshold was used to define RDEs. Results: Adjusted completion rates were >90% in the ITT population for both arms. Significant T+C treatment effects wereobserved for physical functioning in PD-L1 ≥5% ( P =0.0476), and pain in PD-L1 ≥1% ( P =0.0028) and PD-L1 ≥5% ( P =0.0149) subgroups, but not in PD-L1 ≥10%. For other 5 symptoms (ie, GHS, fatigue, reflux, dysphagia, dietary restrictions), there were no statistically significant differences between treatment arms. However, T+C was associated with significant reductions in the risk of death across all 7 key symptoms and PD-L1 subgroups. As one example, with respect to interaction between pain and OS, T+C was associated with a 22% (HR, 0.78 [95% CI, 0.652-0.931]), 33% (HR, 0.67 [95% CI, 0.515-0.860]), and 47% (HR, 0.50 [95% CI, 0.344-0.720]) reduction in the risk of death in PD-L1 ≥1%, ≥5%, and ≥10%, respectively compared with P+C. Conclusions: In this analysis, the addition of tislelizumab to chemotherapy was associated with significantly less deterioration in multiple PRO symptoms including physical functioning and pain, alongside a lower risk of death, after adjusting for recurring deterioration events using a frailty model across multiple PD-L1 expression subgroups.

Advanced Deep Learning Approaches for Forecasting High-Resolution Fire Weather Index (FWI) over CONUS: Integration of GNN-LSTM, GNN-TCNN, and GNN-DeepAR

Wildfires in the United States have increased in frequency and severity over recent decades, driven by climate change, altered weather patterns, and accumulated flammable materials. Accurately forecasting the Fire Weather Index (FWI) is crucial for mitigating wildfire risks and protecting ecosystems, human health, and infrastructure. This study analyzed FWI trends across the Continental United States (CONUS) from 2014 to 2023, using meteorological data from the gridMET dataset. Key variables, including temperature, relative humidity, wind speed, and precipitation, were utilized to calculate the FWI at a fine spatial resolution of 4 km, ensuring the precise identification of wildfire-prone areas. Based on this, our study developed a hybrid modeling framework to forecast FWI over a 14-day horizon, integrating Graph Neural Networks (GNNs) with Temporal Convolutional Neural Networks (TCNNs), Long Short-Term Memory (LSTM), and Deep Autoregressive Networks (DeepAR). The models were evaluated using the Index of Agreement (IOA) and root mean squared error (RMSE). The results revealed that the Southwest and West regions of CONUS consistently exhibited the highest mean FWI values, with the summer months demonstrating the greatest variability across all climatic zones. In terms of model performance on forecasting, Day 1 results highlighted the superior performance of the GNN-TCNN model, achieving an IOA of 0.95 and an RMSE of 1.21, compared to the GNN-LSTM (IOA: 0.93, RMSE: 1.25) and GNN-DeepAR (IOA: 0.92, RMSE: 1.30). On average, across all 14 days, the GNN-TCNN outperformed others with a mean IOA of 0.885 and an RMSE of 1.325, followed by the GNN-LSTM (IOA: 0.852, RMSE: 1.590) and GNN-DeepAR (IOA: 0.8225, RMSE: 1.755). The GNN-TCNN demonstrated robust accuracy across short-term (days 1–7) and long-term (days 8–14) forecasts. This study advances wildfire risk assessment by combining descriptive analysis with hybrid modeling, offering a scalable and robust framework for FWI forecasting and proactive wildfire management amidst a changing climate.

The role of occupational therapy in providing vocational rehabilitation for people living with inflammatory arthritis: A scoping review.

Inflammatory arthritis significantly impacts work participation resulting in cost to individuals, employers, and society. Vocational rehabilitation seeks to address this need, but its pathways, interventions, and efficacy continue to be under investigation. Contributing variables are complex, identifying the need for a conceptual framework to guide practice. Occupational therapy addresses this complexity, providing theoretical frameworks such as the Person-Environment-Occupation-Performance (PEOP) model to understand the occupation of work supporting well-being and design interventions. The aim of this scoping review is to map the role of occupational therapy in providing vocational rehabilitation for people living with inflammatory arthritis. A scoping review following Arksey and O'Malley's (2005) stages was completed. Major databases and grey literature were systematically searched, and hand-searches completed. Descriptive and thematic analysis mapped the findings to the PEOP model framework. There was no consumer or community involvement in this review. Fourteen studies were included. Major themes aligned to the PEOP model with further analysis synthesised in subthemes. A majority of person-related interventions to support work performance was observed. This framework identifies the domains of focus in vocational rehabilitation and current gaps. Work instability, employment retention, and self-efficacy were used to measure effectiveness. This scoping review presents the evidence regarding vocational rehabilitation for the inflammatory arthritis population in the context of occupational therapy theory to provide a framework for clinical practice. A current focus on person-focused interventions was identified. The PEOP model provides a clear framework to understand the complexity and nuances of vocational rehabilitation across the domains. Outcome measures for vocational rehabilitation are heterogenous and require further exploration as capturing the intricacy of achieving balance with work participation remains unclear. Further research into vocational rehabilitation programs incorporating all domains of the PEOP model is needed. Consideration of work performance measurements to inform effectiveness and the resulting impact on a person's well-being is required.

Prediction of waterborne freight activity with Automatic identification System using Machine learning

This paper addresses latency issues related to publicly available port-level commodity tonnage reports. To predict commodity tonnage at the port-level, near real time vessel tracking data is used with historical Waterborne Commerce Statistics (WCS) with a machine learning model. Currently, commodity throughput is derived from WCS data which is released publicly approximately two years after collection. This latency presents a challenge for short-term planning and other operational uses. To reduce latency, this study leverages near real time vessel tracking data from the Automatic Identification System (AIS) data set. Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Temporal Fusion Transformer (TFT) machine learning models are developed using the features extracted from AIS and the historical WCS data. The output of the model is the prediction of the quarterly volume of commodities (in tons) at the port terminals for four quarters in the future. Two types of models are developed: (i) uncategorized- a single model trained on all port terminals; (ii) categorized- four models (one per dominant vessel type at the port terminal, i.e., cargo, tanker, tug/tow, and mixed). The uncategorized model outperformed the categorized model based on the Mean Absolute Percentage Error (MAPE). The uncategorized LSTM model has the highest accuracy among all model types. Results show that the model has higher accuracy for port terminals that handle a specific type of vessel, compared to the port terminals that handle more than one vessel type. Six of seven commodity groups have a MAPE of less than 30% under the LSTM uncategorized model framework. The application of the model enables port authorities and stakeholders to make short-term capacity expansion and infrastructure investment decisions based on commodity volume.

Techno-economic analysis of chemical looping heat pumps based on the levelized cost of energy

The chemical looping heat pump (CLHP) is a promising electrochemical heat pump technology due to high system efficiency, scalability, and use of low-to-zero Global Warming Potential (GWP) fluids. However, similar to other emerging HVAC&R technologies, there is a lack of direct comparison and discussion of economics between CLHPs and conventional vapor compression (VC) heat pumps. In this work, a generalized modeling framework to estimate the levelized cost of energy (LCOE) for space conditioning applications is used to assess the early-stage economic feasibility of CLHP. The LCOE consists of two components: levelized operating expenditures and levelized capital expenditures. These clarify the influence of key factors such as annual cooling and heating delivered and price of electricity. The simulations show that the LCOE of CLHP could be less than that of VC in the case of unit utilization of > 30,000 kWht yr−1, operating current density of > 0.4 A cm−2, and 30% performance improvements. This is despite the projected capital cost of CLHP is nearly 1.6 times higher than that of VC system.

Linking Projected Changes in Seasonal Climate Predictability and ENSO Amplitude

Abstract Recent studies have shown that potential predictability and actual forecast skill have varied throughout the historical record, primarily due to natural decadal variability. In this study, we explore whether and how potential predictability is projected to change in the future as a distinct response to anthropogenic climate change. We estimate the potential predictability of El Niño–Southern Oscillation (ENSO) as well as global surface temperature, precipitation, and upper-atmospheric circulation anomalies from 1921 to 2100, within a perfect model framework, using five coupled model large ensembles. We find that historical and projected ENSO amplitude changes generate global-scale shifts in climate predictability via ENSO-driven changes in the signal-to-noise ratio of seasonal forecasts, with a 10% change in Niño-3.4 standard deviation leading to a 14% change in globally averaged forecast skill at 12-month lead. This relationship suggests that potential predictability changes across much of the globe in the coming decades could be linked to anthropogenic climate change of ENSO. However, since current models substantially disagree on the sign and intensity of projected ENSO change, the trajectory of future global predictability changes cannot yet be determined. This problem is demonstrated by widely varying predictability changes seen across the five large ensembles, with models exhibiting a robust increase, robust decrease, or no significant change in predictability, depending upon their respective projected ENSO amplitude trends. Our results highlight the need for climate model development aimed at better capturing past forced and unforced changes to ENSO variability, which is necessary (if not sufficient) to constrain projected changes to climate predictability worldwide.

Advances and insights into modeling extracellular electron transfer in anaerobic bioprocesses.

Extracellular electron transfer (EET) plays an important role in maintaining redox balance in both natural and engineered anaerobic microbial systems, driving key biochemical processes such as energy generation, bioremediation, and waste degradation. While EET has been characterized in a limited number of microbes and applied in anaerobic digestion and bioelectrochemical systems, further research is needed to explore its mechanism across a broader range of microbial species and anaerobic processes. This review highlights advanced modeling frameworks that provide deeper insights into EET mechanisms and dynamics, aiming to optimize research efforts and minimize time and resource expenditure. Mechanistic models, encompassing thermodynamics and kinetics, are discussed for their utility in calculating conduction rates of electroactive microbes and assessing the energetics of medium chain carboxylic acids production. Genome-scale metabolic models are highlighted for elucidating the roles of cytochromes and conductive pili in the EET pathway. Machine learning is presented as a tool to improve model accuracy and predict EET mechanisms. Furthermore, the integration of quantum mechanics/molecular mechanics methods offers molecular-level insights into electron transfer, while quantum computing addresses limitations of classical computers by simulating complex electron transfer processes in multi-heme cytochromes. Developing advanced modeling techniques will complement experimental techniques, enabling precise predictions and optimization strategies for developing innovative and sustainable anaerobic biotechnologies.

Dilemmas in Linking Microbial Carbon Use Efficiency With Soil Organic Carbon Dynamics.

There are still large uncertainties on the relationships between microbial carbon use efficiency and soil organic carbon across (1) different carbon use efficiency estimation methods, (2) various temporal, spatial and biological scales, and (3) multiple climate change scenarios. These uncertainties call for further efforts to re-examine the relationships between carbon use efficiency and soil organic carbon to better represent microbial processes in the current modelling frameworks.

A modelling framework to analyze climate change effects on radionuclide aquifer contamination

Non-stationarity of climatic variables (e.g., temperature and precipitation) due to Climate Change (CC) can affect the migration processes of radionuclides released from nuclear activities. In this paper, a framework of analysis is developed to predict the evolution in time of contaminant concentration and fluence under different Climatic Boundary Conditions (CBCs) of precipitation scenarios provided by a climate model integrated with an accurate physical coupled hydraulic-transport model. A case study is worked out with respect to the migration of a radioactive contaminant (232Th) at Kirtland Air Force Base (Albuquerque, New Mexico, USA), for which the different CBCs considered are: i) stationary and ii) non-stationary precipitation. The effects of such alternative hypotheses on the physical modelling results are analysed, using a cross-wavelet analysis. It is shown that fluence is strongly affected by precipitation extremes, more than concentration, and it is claimed that a daily scale on the information and data of CBCs is necessary to model, with sufficient accuracy, the migration process and properly assess the impact of future CC on groundwater contamination.

Video Library Construction for International Chinese Education

This paper proposes four principles for digital resource construction for language education and carries out practical video resource construction. We believe that extraction and generation will be the main methods for machine resource construction. For resource extraction, this paper first introduces subtitle-based video resource extraction and example sentence extraction. For resource generation, this paper discusses the present limitations and future ideal working framework of large video generation models. The video extraction process proposed in this paper can be applied for other resource construction purposes, and the Large Language Model (LLM) resource generation framework proposed in this paper can be applied to the generation of other resources. We believe that with the digital transformation of education, a large number of machine-constructed resources will emerge.

A new electoral bottom-up model of institutional governance

The sustainable governance of Global Risky Commons (GRC)—global commons in the presence of a sizable risk of overall failure—is ubiquitous and requires a global solution. A prominent example is the mitigation of the adverse effects of global warming. In this context, the Collective Risk Dilemma (CRD) provides a convenient baseline model which captures many important features associated with GRC type problems by formulating them as problems of cooperation. Here we make use of the CRD to develop, for the first time, a bottom-up institutional governance framework of GRC. We find that the endogenous creation of local institutions that require a minimum consensus amongst group members—who, in turn, decide the nature of the institution (reward/punishment) via an electoral process—leads to higher overall cooperation than previously proposed designs, especially at low risk, proving that carrots and sticks implemented through local voting processes are more powerful than other designs. The stochastic evolutionary game theoretical model framework developed here further allows us to directly compare our results with those stemming from previous models of institutional governance. The model and the methods employed here are relevant and general enough to be applied to a variety of contemporary interdisciplinary problems.

MODELLING AND SIMULATION OF MAXWELL NON-NEWTONIAN FLUID FLOW AND HEAT TRANSFER IN A CAPILLARY TUBE USING THE ATANGANA-BALEANU FRACTIONAL TIME-FRACTIONAL APPROACH

This paper explores the fluid flow and heat transfer characteristics of non-Newtonian fluids within a capillary tube, employing a generalized fractional modeling framework. The analysis utilizes the Maxwell fluid model combined with the Atangana-Baleanu fractional time-fractional derivative. Analytical solutions for velocity and temperature distributions were derived using the finite Hankel and Laplace transform techniques. Key insights reveal that fractional-order models demonstrate notable differences from classical solutions, providing enhanced accuracy in accounting for memory effects and time-dependent dynamics. The fractional fluid velocity shows significant influence at smaller time scales, whereas temperature distribution predominantly varies at larger time intervals.

Identifying Research Hotspots and Trends in Psoriasis Literature: Autotuned Topic Modeling with Agent.

The rapid expansion of psoriasis research literature presents challenges for efficient analysis and trend identification, necessitating advanced approaches. We propose AgenTopic, an interactive topic modeling framework that integrates BERT embeddings, dimensionality reduction, clustering, and a language model feedback loop to analyze psoriasis research literature from 2000 to 2023. Applied to PubMed articles, AgenTopic extracted 158 psoriasis-related topics across 8 categories, outperforming traditional methods in handling complex medical literature. Further trend analysis using multiple modeling techniques, including an SVR-Linear model, revealed non-linear patterns in research growth across categories (R2 values 0.75-0.97). Key trends identified include focus on nail psoriasis and spondyloarthritis, shift from TNF-α to IL-17 in pathogenesis understanding, rapid development of biologics and small molecule inhibitors, and increased attention to comorbidities. We developed an interactive web tool to facilitate literature retrieval and trend identification. To our knowledge, this application of an agent-based interactive topic modeling framework to dermatological literature is previously unreported. Using only topic-modeled data, our framework achieved comparable performance to expert manual review in identifying research trends. AgenTopic performed better than several state-of-the-art topic modeling methods and demonstrated the potential of AI in advancing medical literature analysis.

Intensive Care Nurses' Pain Management Experiences within the Framework of the Biopsychosocial-Spiritual Model in Türkiye: A Qualitative Approach.

Pain, which includes biological, psychological, social and spiritual factors, is a common symptom experienced by patients in intensive care. This study aimed to uncover intensive care nurses' perspectives on pain management strategies, employing the biopsychosocial-spiritual model as the guiding framework. This research employed a descriptive qualitative method, engaging participants from diverse locations across five provinces and eight different institutions. The study involved 16 intensive care nurses and utilized semi-structured online Zoom interviews. Data analysis was conducted using Braun and Clarke's six stages, and reporting followed the consolidated criteria for qualitative studies. The answers of the nurses were grouped under four themes and six subthemes: (1) biological interventions, (2) psychological interventions, (3) social interventions: involving families in the process and (4) spiritual interventions: support religious activities. This study shows that intensive care nurses benefit from many practices in pain management. These interventions included medication management and ensuring physical comfort in the biological factor, distracting activities and being with the patient in the psychological factor, involving the family in care in the social factor and providing an environment that supports the patient's religious needs under the spiritual factor.

Unveiling learners’ intentions toward influencer-led education: an integration of qualitative and quantitative analysis

ABSTRACT In the rapidly evolving landscape of social media, the emergence of Influencer-led Education as a novel learning model presents a paradigm shift in the mobile learning era. To illuminate the underpinnings of learners’ inclination to embrace this model, this study adopts an integrated methodological framework, encompassing grounded theory and fuzzy-set Qualitative Comparative Analysis (fsQCA). Based on 17 in-depth interviews, an Action-Decision Framework of new model is established. Subsequently, a examination of 150 questionnaires through fsQCA uncovers diverse configurations of learners’ adoption intention of Influencer-led Education. The outcomes of the fsQCA disclose five configurations associated with high adoption intention and two configurations leading to low intention, highlighting heterogeneous representations among distinct learner cohorts within the decision framework. This research contributes to the expansion and deepening of theories pertaining to learners’ engagement with Influencer-led Education, while providing insights into the intricate mechanisms driving learning behaviors in the realm of novel learning scenarios.

Emergence and tunability of Fermi-pocket and electronic instabilities in layered Nickelates

Layered Nickelates have gained intensive attention as potential high-temperature superconductors, showing similarities and subtle differences to well-known Cuprates. This study introduces a modelling framework to analyze the tunability of electronic structures by focusing on effective orbitals and additional Fermi pockets, mimicking doping or external pressure qualitatively. It investigates the role of the3dz2orbital in interlayer hybridization, which leads to the formation of a second pocket in the Fermi surface. The resulting effective model also predicts specific charge and spin susceptibility in the form of Lindhard susceptibility at wave vectorq0=(π,π), which can be tuned by doping or pressure. These results provide valuable insights into tunable orbital contributions and their influence on potential ordering and electronic instabilities in Layered Nickelates.

Dynamic performance prediction of PEM electrolyzers combining an electrochemical neural network model and a lumped thermal capacitance model

ABSTRACT The proton exchange membrane (PEM) electrolyzer electrochemical models based on conventional analytical and empirical approaches require numerous parameters, which are difficult to obtain accurately, leading to lower dynamic performance prediction accuracy while the parameters of the lumped thermal capacitance model are relatively simple and easily identifiable. This study proposes an integrated modeling framework, which combines a backpropagation (BP) neural network model for electrochemical performance and a lumped thermal capacitance model for the assessment of thermal performance. The neural network model is trained on polarization data collected from 44°C to 76°C. The BP neural network, optimized through iterative hyperparameter tuning, achieves high predictive accuracy with three hidden layer nodes and tansig and purelin activation functions, exhibiting less than 1% error in polarization curve predictions at four additional temperatures and current densities from 0.04 to 2.6 A/cm2. The thermal model, calibrated with experimental data, predicts thermal-balance temperatures with root mean square error (RMSE) of 0.08°C to 0.52°C under four different operating conditions. The dynamic performance of the integrated model is validated under three different operating conditions. This comprehensive model enables detailed analysis of critical operating variables, providing actionable insights for selecting and optimizing operating conditions in practical applications.

The Impact of Guerrilla Marketing on Perception of Marketing Innovation and Brand Trust

Does guerrilla marketing influence perceptions of marketing innovation and brand trust? Alongside this question, the issue of whether perceptions of marketing innovation impact brand trust arose during the development of the research model and literature review. Thus, besides the main objective of the study, a secondary aim is to investigate the effect of marketing innovation perception on brand trust. To achieve these objectives, data were collected from a target audience using an online survey method within the framework of a quantitative research design. The collected data were first subjected to normality tests, followed by reliability and validity analyses of the scales. To determine the socio-demographic characteristics of the participants, frequency and percentage distributions were used, while regression analysis was employed to test the research hypotheses. Additionally, the mediating effect was tested within the proposed model framework. The study found that guerrilla marketing positively influences consumer perceptions of innovation, affects consumer purchasing decisions, and enhances brand trust. Additionally, marketing innovations were observed to have positive effects on consumer trust and perceived value. It can be stated that guerrilla marketing campaigns indirectly affect brand trust through marketing innovation, and these strategies enhance consumer trust with innovative and creative campaigns.

Cost-efficient behavioral modeling of antennas by means of global sensitivity analysis and dimensionality reduction.

Computational tools, particularly electromagnetic (EM) solvers, are now commonplace in antenna design. While ensuring reliability, EM simulations are time-consuming, leading to high costs associated with EM-driven procedures like parametric optimization or statistical design. Various techniques have been developed to address this issue, with surrogate modeling methods garnering particular attention due to their potential advantages. One key benefit is the promise of unprecedented acceleration in handling design problems that require repetitive system evaluations. However, behavioral modeling of antennas is an intrinsic endeavor. Challenges include the curse of dimensionality and the high nonlinearity of antenna characteristics. Moreover, design utility necessitates that the models are defined across wide ranges of frequency, geometry dimensions, and material parameters, posing a significant bottleneck for existing modeling frameworks. This paper introduces an innovative approach to constructing design-ready behavioral surrogates for antenna structures. Our methodology involves a rapid global sensitivity analysis (GSA) algorithm developed to determine a set of parameter space directions that maximize antenna response variability. The latter are obtained from spectral analysis of the GSA-based sensitivity indicators, and employed to define a reduced-dimensionality domain of the metamodel. The dependability of the model constructed in such a domain is superior over conventional surrogates while being suitable for design purposes. These benefits have been conclusively showcased using several microstrip antennas and illustrated by a number of design scenarios involving antenna geometry optimization for a variety of performance specifications.