Prediction Of Rate Research Articles

Using Short Time Series of Monofractal Synthetic Fluctuations to Estimate the Foreign Exchange Rate: The Case of the US Dollar and the Chilean Peso (USD–CLP)

Short time series are fundamental in the foreign exchange market due to their ability to provide real-time information, allowing traders to react quickly to market movements, thus optimizing profits and mitigating risks. Economic transactions show a strong connection to foreign currencies, making exchange rate prediction challenging. In this study, the exchange rate estimation between the US dollar (USD) and the Chilean peso (CLP) for a short period, from 2 August 2021 to 31 August 2022, is modeled using the nonlinear Schrödinger equation (NLSE) and calculated with the fourth-order Runge–Kutta method, respectively. Additionally, the daily fluctuations of the current exchange rate are characterized using the Hurst exponent, H, and later used to generate short synthetic fluctuations to predict the USD–CLP exchange rate. The results show that the USD–CLP exchange rate can be estimated with an error of less than 5%, while when using short synthetic fluctuations, the exchange rate shows an error of less than 10%.

Resting energy expenditure during spinal cord injury rehabilitation and utility of fat-free mass-based energy prediction equations: a pilot study

Study designLongitudinal observational study. Measurements were undertaken between weeks 4–6 post-spinal cord injury (SCI), repeated at week 8 and every 4 weeks thereafter until week 20 or rehabilitation discharge, whichever occurred first.ObjectivesObserve variation in measured resting energy expenditure (REE) and body composition in males undergoing SCI rehabilitation, compare REE with SCI-specific prediction equations incorporating fat-free mass (FFM), and explore the prevalence of clinical factors that may influence individual REE.SettingSpinal Injuries Unit, Brisbane, Queensland, Australia.MethodsIndirect calorimetry was used to measure REE and bioimpedance spectroscopy to assess body composition. Four SCI-specific FFM-based REE and basal metabolic rate (BMR) prediction equations were compared to measured REE. A clinically significant change in REE was defined as +/− 10% difference from the week 4–6 measurement. Clinical factors that may affect REE variations were collected including infection, pressure injuries, autonomic dysreflexia, spasticity, and medications.ResultsFifteen people participated (mean age 35 ± 13 years, 67% paraplegic). There was no statistically significant change in mean REE, weight, or body composition, and the Chun and Nightingale BMR prediction equations performed best (rc > 0.8 at all time points). One-third of participants had >10% change in REE on 11 occasions, with clinical factors not consistently associated with the observed changes.ConclusionDuring SCI rehabilitation, mean REE, weight, and body composition remain unchanged, and FFM-based BMR prediction equations may be an acceptable alternative to indirect calorimetry. Future research designs should avoid single indirect calorimetry measures as snapshot data may not represent typical REE in this population.

Comparing Machine Learning Models for Sentiment Analysis and Rating Prediction of Vegan and Vegetarian Restaurant Reviews

The paper investigates the relationship between written reviews and numerical ratings of vegan and vegetarian restaurants, aiming to develop a predictive model that accurately determines numerical ratings based on review content. The dataset was obtained by scraping reviews from November 2022 until January 2023 from the TripAdvisor website. The study applies multidimensional scaling and clustering using the KNN algorithm to visually represent the textual data. Sentiment analysis and rating predictions are conducted using neural networks, support vector machines (SVM), random forest, Naïve Bayes, and BERT models. Text vectorization is accomplished through term frequency-inverse document frequency (TF-IDF) and global vectors (GloVe). The analysis identified three main topics related to vegan and vegetarian restaurant experiences: (1) restaurant ambiance, (2) personal feelings towards the experience, and (3) the food itself. The study processed a total of 33,439 reviews, identifying key aspects of the dining experience and testing various machine learning methods for sentiment and rating predictions. Among the models tested, BERT outperformed the others, and TF-IDF proved slightly more effective than GloVe for word representation.

Prediction of hemorrhage rate after tonsil surgery in children based on random forest model

Objective:Hemorrhage after tonsil surgery in children is a serious and potentially life-threatening complication. The purpose of this study was to establish a risk warning model for hemorrhage after tonsil surgery in children through a national multi-center retrospective study, providing a basis for hierarchical management after tonsil surgery in children. Methods:Stratified sampling was performed on 8 854 children who underwent tonsillectomy under general anesthesia from 15 research centers in different provinces from January 15, 2022 to May 15, 2023. The sample size of this study was 2 724 cases, including 1 096 males and 1 628 females. Children were divided into bleeding and non-bleeding groups according to whether or not they had bleeding after surgery. The random forest algorithm was used to build a risk warning model. By continuously exploring the optimized model, the accuracy of predicting the postoperative bleeding rate of tonsils in children was improved, and the prediction effectiveness of the model was verified by ten-fold cross-validation. Results:Among 2 724 children, 117 had postoperative bleeding after tonsillectomy, with a bleeding rate of 4.30%. The model constructed by the random forest algorithm for the training set was verified in the test set, and the obtained prediction accuracy was 98.72%, the recall rate was 78.95%, and the area under the ROC curve AUC was 0.96. Conclusion:Although the recall rate of the random forest model needs to be improved, the overall accuracy is quite excellent. It can effectively avoid misjudging positive cases as negative cases. It is a useful tool that can be used to predict the postoperative bleeding rate of tonsils and clinical medical decision-making, laying a good foundation for subsequent optimization and improvement.

Optic nerve sheath diameters predict mortality and severity in hepatic encephalopathy.

The aim of this study was to compare the predictive power of optic nerve sheath diameter (ONSD) measured by brain computed tomography (CT) in patients diagnosed with hepatic encephalopathy (HE) in the emergency department, with other factors for mortality and disease severity. A total of 217 patients aged 18 years and older with acute decompensation of cirrhosis diagnosed with HE in the emergency department were included in the study. To compare with patients diagnosed with HE, a total of 217 individuals were included in the study as the healthy control group. ONSD measurements were performed on both the HE patients and the healthy control group in the brain CT. The mortality rate of HE patients was 32.7%. Regarding the severity of the disease, 53% of the patients had late-stage HE. The presence of acute-on-chronic liver failure was detected in 51.4% of patients. The mortality rate among acute-on-chronic liver failure patients was 56.6%. According to the study data, ONSD, creatinine, lactate, and procalcitonin were independent predictors of mortality. Meanwhile, Child-Pugh score, direct bilirubin, ONSD, ammonia, and total bilirubin were independent predictors of disease severity. In the receiver operating characteristic curve analysis, the ONSD had the highest predictive power for mortality and disease severity among the determined predictive values. The data from the study suggests that assessing the ONSD through brain CT scans in individuals diagnosed with HE in the emergency department may provide valuable insights for clinicians, aiding in the prediction of both mortality rates and the severity of the disease.

Collision frequencies across collision regimes in two-component systems

Agglomeration is the most important growth process in particle systems but modelling efforts typically assume mono-disperse primary particle distributions for the closure of the collision frequency that determines the growth rates. Real systems such as sooting flames, however, involve poly-disperse primary particle distributions. Also, systems with multiple components, where primary particles are of distinct but different sizes, cannot be treated as mono-disperse. Here, we introduce bi-disperse primary particle distributions and use Langevin dynamics simulations to develop closures for the collision kernels that are applicable over a wide range of agglomerate characteristics. The simulations cover fractal dimensions from 1.4 to 2.2, primary particle diameters from 5 nm to 50 nm, primary particle size ratios from 2 to 10 and agglomerates of up to a size of 200 primary particles with varying particle compositions. The Langevin dynamics simulations cover all collision regimes from ballistic to diffusive and allow to deduce expressions for the respective collision diameters, the hydrodynamic radii and the projected area as functions of particle characteristics. It is shown that existing expressions for the transition regime that were developed for the modelling of the collision kernel of spherical particles continue to hold for collision kernels of agglomerates in two-component systems under the condition that the collision diameters and drag coefficients are modelled accurately. An example ‘a posteriori’ simulation for a particle size ratio of 6 uses the population balance equation and demonstrates that bi-variate kernels are needed for the accurate prediction of the growth rates. Errors in predicted number density at the end of the simulations are less than 12 % while mono-variate kernels developed for mono-disperse primary particle systems overpredict the growth rate by 46%.

Overreaction and underreaction to new information and the directional forecast of exchange rates

Overreaction and underreaction to new information may cause, respectively, sequences and reversals in exchange rate returns. Empirical evidence is that the sign of the difference between the probabilities of a sequence and a reversal predicts the sign of the next day exchange rate return out-of-sample better than the random walk without drift model. Since the effect of overreaction of exchange rates to unexpected news dies out over longer time spans, the directional predictability becomes weaker for the weekly exchange rates. The trading strategy exploiting the directional predictability of the exchange rates generates tangible profits compared to the non-trading and buy-and-hold strategies.

Enhancing Groundwater Recharge Prediction: A Feature Selection‐Based Deep Forest Model With Bayesian Optimisation

ABSTRACTAccurate prediction of groundwater recharge is crucial for the sustainable management of water resources. Existing models, while effective, still have potential for improved accuracy. This study proposed a novel deep forest model—the Feature Selection‐based Deep Forest model (FSDF)—for enhanced groundwater recharge prediction. This model consists of three key essential components: a feature selection layer, a cascade enhancement layer and a decision output layer, all designed to enhance the prediction accuracy of groundwater recharge rates. The feature selection layer effectively filtered out redundant features, ensuring that only relevant features are fed into the subsequent cascade enhancement layer. The cascaded enhancement layer was jointly constructed by random forests and completely random forests, processing the data layer‐by‐layer. Finally, the predictions of groundwater recharge rates were produced through an averaging strategy in the decision output layer. To further enhance the FSDF model's predictive capabilities, Bayesian optimization was applied for fine‐tuning model hyperparameters. The model's performance was evaluated and compared with existing models using a dataset comprising of groundwater recharge rates from 1549 wells in New South Wales, Australia. The FSDF model exhibited exceptional performance, achieving a training accuracy of 95.91% and a testing accuracy of 89.65%. It outperformed the adaptive boosting, categorical boosting, extreme gradient boosting, multiple linear regression and random forests by 2.02%, 6.98%, 9.05%, 17.02% and 2.74% in prediction performance, respectively. This study contributes to both hydrological processes and groundwater management by identifying key factors such as rainfall, surface geology and PET, and refining hydrological models for greater predictive accuracy. The FSDF model offers a powerful tool for accurately forecasting groundwater recharge, outperforming traditional models. The model's adaptability makes it applicable to different geographical regions for managing water resources in the face of challenges such as water scarcity and climate change.

Methods for faster estimation of the entropy profile of a lithium-ion battery: A comparison of accelerated potentiometry and the estimation of entropy through thermal signatures

The operating temperature of a lithium-ion battery (LIB) has strong effects on its electrochemical performance, safety, and lifetime. Reliable predictions of cell temperature and heat generation rate are required for the design and thermal management of battery systems. The entropy variation of a LIB has a significant influence on the heat generation and the cell temperature variation, especially at a lower C-rate. Since the entropy is a function of State-of-Charge (SoC), and may change during ageing, the entropy profile may as well be used as an indicator for battery State-of-Health diagnostics. The present experimental methods, such as potentiometric or calorimetric methods, for determining the entropy variation throughout a battery's full SoC window are time-consuming and require specialized equipment with good thermal insulation and instrumentation. Hence, faster and more convenient methods are needed. In this paper, we compare an accelerated potentiometric method with a new entropy characterization method where the entropy profile is extracted from the thermal signature of a LIB during charge and discharge at low C-rates. The accelerated potentiometric method aims to obtain the entropy from thermal cycling while the cell is still not completely relaxed to its stable OCV. The thermal signature method monitors the variations of a cell's outer surface temperature during a low constant current charge or discharge, from which the continuous variation of entropy with the SoC can be extracted. The obtained entropy profile was validated through a modeling approach that combines a P2D-electrochemical model for battery operation and a 3D-finite-element model for the thermal behavior during battery operation. Good agreement between the model predictions and experiments was achieved on the temporal variation of the cell's outer surface temperature.

New renormalization scheme in the two Higgs doublet models

We propose a new renormalization scheme in the two Higgs doublet models with a softly-broken Z2 symmetry and CP-conservation in the Higgs sector. In this scheme, counterterms for mixing angles of the Higgs bosons are determined by using the decay rates of the discovered Higgs boson h, i.e., h→τ+τ− and h→ZZ⁎→Zℓ+ℓ− at next leading order (NLO) instead of using the renormalized two-point functions which are adopted in the previous scheme. We require that the decay rates at NLO are determined to be the corresponding predictions at NLO in the Standard Model (SM) times square of the scaling factor which describes the deviation of h couplings at tree level from the SM value. The mixing angles then maintain the meaning of the “alignmentness”, i.e., how the properties of h are close to the SM predictions, while they lose such meaning in the previous scheme. We compare the predictions of the decay rates at NLO given in the new scheme and those in the previous scheme.

Kinetic modelling of ozonation and photolytic ozonation of metronidazole removal from water

This work addresses the ozonation, photolysis, and photolytic ozonation of metronidazole (MTZ), a widely used antibiotic frequently detected in urban wastewater. A UVA source emitting radiation between 300 and 400 nm was utilized. The presence of scavengers such as t-butanol and sodium azide confirmed the role of hydroxyl radicals in both ozonation and photolysis processes. Conversely, singlet oxygen did not influence the photolytic processes. The average quantum yields of MTZ and ozone were determined to be 1.2 × 10−3 and 0.72 mol/Einstein, respectively, for the 300–400 nm wavelength range. In direct MTZ photolysis, a stoichiometric ratio of 0.34 mol of hydroxyl radicals formed per mol of photolyzed MTZ was observed. However, the effects of hydroxyl radicals on the MTZ photolytic rate were only significant after 45 min of reaction time. Using rate constant data from literature and quantum yields calculated in this study, a kinetic model for both MTZ ozonation and photolytic ozonation was proposed, enabling the prediction of MTZ conversion and degradation rates. This model includes three intermediate compounds that also consume ozone and hydroxyl radicals. The results show that experimental and calculated concentrations of MTZ are within an error margin of less than 14 % in all cases.

Advanced Prediction of Glomerular Filtration Rate After Kidney Transplantation Using Gradient Boosting Techniques.

Clinicians often face uncertainty when interpreting whether a decline in estimated glomerular filtration rate is within the patient's expected range of fluctuation or if the decline signals a substantial deviation. Thus, accurate predictions of glomerular filtration rate can be an early warning system, prompting timely interventions, such as biopsies to preclude early graft rejection and adjustments in immunosuppression. Traditional models, encompassing linear and conventional methods, typically struggle with variabilities and complexities in posttransplant data. We evaluated the efficacy of a gradient boosting model in predicting posttransplant glomerular filtration rate, to potentially enhance accuracy over traditional prediction approaches. Our patient dataset included 68 pediatric patients aged 1 to 18 years who underwent kidney transplant between 2017 and 2023 at Baskent University Hospital (Ankara, Turkey). The dataset comprised 2285 glomerular filtration rate measurements, along with patient demographics and transplant-related data. For our model, we included "days to transplant" (glomerular filtration rate values pretransplant), "days from transplant" (glomerular filtration rate values up to 7 days posttransplant), patient age, sex, and donor types. We divided the dataset into a training set (70%) and a test set (30%). To evaluate model performance, we used mean absolute error and root mean squared error, with a focus on the accuracy of glomerular filtration rate predictions at various posttransplant stages. In the training set, the gradient boosting model demonstrated a significant improvement in prediction accuracy, achieving an mean absolute error of ~5.64 mL/min/1.73 m². Our model underscored the promise of advanced machine learning techniques in refining prediction of glomerular filtration rate after kidney transplant. With its augmented precision, the model can support clinicians in making informed decisions regarding early biopsies and interventions, thus highlighting the vital role of sophisticated analytical methods in medical prognosis and the monitoring of pediatric patient care.

A hybrid meta-heuristic framework with ensemble deep learning for multi-functional simultaneous optimized automatic intensity-modulated radiotherapy planning

Intensity-modulated radiotherapy (IMRT) is one of the main treatments for patients with cancer, and its treatment planning holds significant importance. Compared to manual treatment planning, automatic treatment planning (ATP) is expected to improve plan quality and efficiency, which is of great clinical importance. However, treatment planning is an intractable “black art” that calls for intuition and heuristics from medical dosimetrists. There are two main issues with the current ATP methods: (i) they rely strongly on prior clinical experience and are not sufficiently scalable, and (ii) they use a single-functional optimization concept that ignores delivery accuracy information, which lowers the delivery accuracy of the generated ATP plans. To address these issues, this paper presents a novel multi-functional simultaneous optimized automatic treatment planning (MFSO-ATP) method. First, to address the issues of high reliance and insufficient scalability, an evolutionary strategy (ES) and simulated annealing (SA)-based hybrid meta-heuristic trial-and-error (ESSA-HMTE) framework is designed to automatically adjust optimization parameters without human intervention. Second, to address the issue of delivery accuracy deterioration, an ensemble deep learning-based gamma passing rate (GPR) prediction (EnDL-GPR) framework was constructed and trained to predict the plan delivery accuracy a priori. The ESSA-HMTE framework effectively fuses dosimetric quality information and delivery accuracy a priori information to simultaneously optimize the two, ensuring delivery accuracy while achieving automatic planning. We tested the MFSO-ATP method using multiple diseases with high inter-tumor heterogeneity. The results showed that the proposed method can improve the quality and delivery accuracy of IMRT plans, reduce the percentage of quality assurance failures, is highly scalable, and has good clinical application prospects.

Study of ship-based carbon capture optimization considering multiple evaluation factors and main engine loads

Ship-Based Carbon Capture (SBCC) technology presents a promising approach to reduce greenhouse gas emissions in the marine transportation. Solvent-based carbon capture has emerged as a leading technology for SBCC, primarily due to its low retrofit costs and effectiveness in treating flue gas with low carbon content. However, challenges remain in optimizing system operation efficiency under the variable conditions of ship main engine loads and in understanding the mechanisms by which process parameters influence key evaluation factors. Consequently, this study established a pilot-scale experimental platform for solvent-based SBCC and developed a carbon capture model based on it. The influence of process parameters, such as main engine exhaust flow rate and liquid/gas ratio (L/G), on the evaluation factors was thoroughly explored. With the utilization of Shapley Additive Explanations (SHAP) analysis to quantify the influence of process parameters on the evaluation factors, a multi-objective optimization equation is proposed. The combination of machine learning and optimization algorithms offers an efficient approach for determining the optimal process of the SBCC system under different main engine loads. The research results show that the main engine exhaust flow rate is the most important process parameter affecting the carbon capture rate (CR), with an influence ratio as high as 64.33%. As the main engine exhaust flow rate increases, the maximum CR decreases from 97.84% to 61.13%. Although the extreme value of the regeneration energy consumption (REC) also decreases from 6.66 to 4.42 GJ/t CO2, the solvent flow rate's influence on REC is also significant, with influence ratios of 38.49% and 35.53%, respectively. A data-driven approach examined the optimal operating conditions at eight main engine loads, achieving a carbon capture rate prediction error of only 1.42% and a maximum REC error of only 0.55 GJ/t CO2. This study provides essential guidance for assessing the suitability of SBCC systems.

Whole body sweat rate prediction: indoor treadmill and cycle ergometer exercise.

This article describes the development and validation of accurate whole body sweat rate prediction equations for individuals performing indoor cycle ergometer and treadmill exercise, where power output can be measured or derived from simple inputs. For cycle ergometry, 112 trials (67 participants) were used for model development and another 56 trials (42 participants) for model validation. For treadmill exercise, 171 trials (67 participants) were used for model development and another 95 trials (63 participants) for model validation. Trials were conducted over a range of dry-bulb temperature (20°C to 40°C), relative humidity (14% to 60%), and exercise intensity (∼40% to 85% of peak aerobic power) conditions, which were matched between model development and model validation. Whole body sweat rates were measured, and proprietary prediction models were developed (accounting for all relevant biophysical factors) and then validated. For model validation, mean absolute error for predicted sweating rate was 0.01 and 0.02 L·h-1 for cycle and treadmill trials, respectively. The 95% confidence intervals were modest for cycle ergometer (+0.25 and -0.22 L·h-1) and treadmill exercise (+0.33 and -0.29 L·h-1). The accounted for variance between predicted and measured values was 92% and 78% for cycle and treadmill exercise, respectively. Bland-Altman analysis indicated that zero and one predicted value exceeded the a priori acceptable level of agreement (equivalent to ±2% of total body mass in 3 h) for cycle and treadmill exercise, respectively. There were fewer trials with female subjects, but their values did not differ from those expected for males. This is the foremost study to develop and validate whole body sweat rate prediction equations for indoor treadmill and cycle ergometer exercise of moderate to high intensity. These prediction equations are publicly available for use (https://sweatratecalculator.com).NEW & NOTEWORTHY This study presents the development of new proprietary whole body sweat rate prediction models for people exercising indoors on a cycle ergometer or treadmill using simple input parameters and delivered through a publicly available online calculator: https://sweatratecalculator.com. In an independent validation group, the predictive models for both indoor cycling and treadmill exercise were accurate across moderate to high exercise intensities in temperate to hot conditions. These equations will enable individualized hydration management during physical training and exercise physiology experiments.

Integration of CFD Analysis and Artificial Neural Networks for Estimation of Erosion Rate in Oil and Gas Pipelines

Transporting oil and gas via pipelines has been creating countless challenges; sand particles deposit and erode the pipelines wall. Generally, conventional erosion rate prediction models are conservative due to numerous generalizations and theories. Finite Element Analysis via computational fluid dynamics (CFD) approach has proven to be useful to solve sand deposition problems and to estimate the eroded pipe due to its capability to precisely determine erosion deficiencies and make predictions with great precision. In this study, a CFD model was developed to calculate sand erosion rates in a 2-inch, 90° elbow pipe. Effects of particle sizes, sand flowrates, fluids velocities and pipe diameters on erosion rates were studied. The model was validated against literature data, and it was then used to generate data via sensitivity analysis simulations. The data became the basis for developing artificial neural network (ANN) models, which were then deployed in the environment of a process simulation software called Symmetry. Based on this approach, a variety of pipelines can be modelled, and maximum erosion rates of pipelines are calculated using deployed ANN models. Hence, a comprehensive study on the fluid flow dynamics and erosion rates of the pipelines can be evaluated simultaneously.

Influence of tungsten carbide spray treatment on anti-wear performance of Francis turbine runner blades surface

Based on the velocity similarity theory, a test system for sediment wear flow around Francis turbine runner blades was established. The sediment wear test was carried out on the surface of Francis turbine runner blades with severe sediment wear before and after tungsten carbide spraying. The wear rate prediction model was established, and the effect of tungsten carbide spraying on the wear resistance of runner blades was analyzed. The results show that the serious wear position of Francis turbine runner blade by sediment appears in the head and tail, and the greater the load, the more serious the wear; after tungsten carbide spraying treatment, the sediment wear of runner blades is reduced by more than 90%, and the wear life is greatly improved. The sprayed tungsten carbide coating treatment is effective in reducing the effects of sediment wear.

Forecasting nominal exchange rates using a dynamic model averaging framework

This paper presents a dynamic model averaging approach for forecasting nominal exchange rates. This framework encompasses most of the approaches commonly used in the forecasting literature and also allows us to study parameters and model uncertainty in exchange rate forecasting. We focus on nine major trading currency pairs: AUD/USD, CAD/USD, CHF/USD, EUR/USD, GBP/USD, NOK/USD, NZD/USD, SEK/USD, and JPY/USD, where we use data for approximately the last two decades. We empirically show statistically and economically significant exchange rate predictability in the medium and long run, and we also present some findings on predictability even in the short run. We offer several theoretical explanations for these results on predictability.

Prediction of Leakage Flow Rate and Blow-Down in Brush Seals via 2D CFD Simulation with Porosity Correction

Brush seals are extensively used in rotating equipment, such as gas turbines and compressors, providing effective sealing while accommodating radial, axial, and angular movements between components. In this study, the performance of brush seals with and without clearances was predicted through axisymmetric 2D computational fluid dynamic (CFD) simulations using a porous media model. Because the accurate modeling of a brush seal requires the appropriate porosity to be determined and the flow resistance to be calculated, a porosity correction was performed based on the brush seal’s geometry and pressure ratio. The corrected porosity was then used to calculate the flow resistance and the leakage flow rate was predicted. Based on the results, the corrected porosity significantly improved the accuracy of the previously unreliable leakage flow rate predictions, regardless of the presence of clearances. For cases with a clearance, the blow-down effect was determined through CFD simulations for the given geometry and was compared with experimental data. The leakage flow rate predictions were highly accurate, with a relative error of less than 5% across a pressure ratio range of 1.5–4.

Corrosion Rate Optimization and Prediction for Enhanced Strength and Structural Integrity of Pipeline Weldments Using RSM and ANN

This study investigates the optimization and prediction of non-elastic performance factors required to augment the pipeline weldments' structural integrity and strength. The study's main focus is on the components of the operation, like the welding current, voltage, and gas flow rate to optimize and predict the corrosion rate of the pipeline weldment. Utilizing Design Expert software for experimental design and data analysis, the study employs the Central Composite Design (CCD) methodology to generate a quadratic model that predicts the responses effectively. The research also integrates Artificial Neural Networks (ANN) to further enhance the prediction accuracy. Experimental results indicate that the optimal welding parameters 160 amps current, 21.28 volts voltage, and 14.67 liters/min gas flow rate—yield a corrosion rate of 0.018 mm/yr. The study concludes that both RSM and ANN can be effectively used for optimization and prediction in welding processes, with RSM showing slightly better predictive capabilities.