Prediction Problem Research Articles

A Perspective on Protein Structure Prediction Using Quantum Computers.

Despite the recent advancements by deep learning methods such as AlphaFold2, in silico protein structure prediction remains a challenging problem in biomedical research. With the rapid evolution of quantum computing, it is natural to ask whether quantum computers can offer some meaningful benefits for approaching this problem. Yet, identifying specific problem instances amenable to quantum advantage and estimating the quantum resources required are equally challenging tasks. Here, we share our perspective on how to create a framework for systematically selecting protein structure prediction problems that are amenable for quantum advantage, and estimate quantum resources for such problems on a utility-scale quantum computer. As a proof-of-concept, we validate our problem selection framework by accurately predicting the structure of a catalytic loop of the Zika Virus NS3 Helicase, on quantum hardware.

Computational drug repositioning with attention walking

Drug repositioning aims to identify new therapeutic indications for approved medications. Recently, the importance of computational drug repositioning has been highlighted because it can reduce the costs, development time, and risks compared to traditional drug discovery. Most approaches in this area use networks for systematic analysis. Inferring drug-disease associations is then defined as a link prediction problem in a heterogeneous network composed of drugs and diseases. In this article, we present a novel method of computational drug repositioning, named drug repositioning with attention walking (DRAW). DRAW proceeds as follows: first, a subgraph enclosing the target link for prediction is extracted. Second, a graph convolutional network captures the structural features of the labeled nodes in the subgraph. Third, the transition probabilities are computed using attention mechanisms and converted into random walk profiles. Finally, a multi-layer perceptron takes random walk profiles and predicts whether a target link exists. As an experiment, we constructed two heterogeneous networks with drug-drug similarities based on chemical structures and anatomical therapeutic chemical classification (ATC) codes. Using 10-fold cross-validation, DRAW achieved an area under the receiver operating characteristic (ROC) curve of 0.903 and outperformed state-of-the-art methods. Moreover, we demonstrated the results of case studies for selected drugs and diseases to further confirm the capability of DRAW to predict drug-disease associations.

Early prediction of Sepsis: A comparative assessment on patients’ covariates

The early prediction of Sepsis is a highly important task regarding its impact on the mortality ratio for ICU patients. The earlier the Sepsis occurrence is foreseen, the sooner the patient can have the chance to be intervened and the patient can be prevented from getting major organ damage. However, it is a challenging task for healthcare professionals even though they have expert knowledge and standardized prediction scoring systems. Therefore the machine learning models that evaluate the patients’ regularly measured covariates as features, and make predictions by utilizing them have been acknowledged and have gathered attention to automatize and improve the early prediction process. However, the nature of the problem of early prediction of Sepsis requires patients to make an estimation based on past measurements, and reliable estimation cannot be made with the use of instant measurement results alone. To this end, additional features obtained by recent measurements have been proposed to be involved in the machine learning model’s estimation process by basing a specific dataset with a specific definition of the illness. This study broadly evaluates the previously proposed features to measure the effectiveness of their single and joint use. Unlike the previous research, this evaluation was done by multiple datasets, different types of additional features, and various machine learning methods for validation purposes. Experimental results have proved that the proposed machine learning model has a significant effect on early prediction, and the best improvement is obtained with the XGBoost classifier. However, it should be noted that quantity, especially the quality of the features used to feed the model has a critical effect on the model’s performance. Consequently, using additional features enhances the model’s performance dramatically.

Short-term energy consumption prediction for university dormitory buildings based on energy consumption grouping by considering meteorological factors and teaching schedules

Accurate short-term energy consumption prediction is essential for studying renewable energy utilization in building technologies. University dormitory energy consumption is affected by meteorological factors and teaching schedules, presenting a more complex time series compared to residential buildings, rendering traditional methods unsuitable. Therefore, in the present study, we developed a model called energy consumption grouping-Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Bi-directional Long Short-Term Memory (ECG-ICEEMDAN-BILSTM) for predicting short-term energy consumption in university dormitory buildings. Model was tested using electricity consumption data from university dormitory buildings in cold regions of China. Based on the energy consumption characteristics, we identified two consumption patterns comprising high power energy consumption (HPEC) and low power energy consumption (LPEC). Using the ECG method, data with similar daily energy consumption distributions for HPEC and LPEC were grouped. Subsequently, individual prediction models were constructed based on ICEEMDAN-BILSTM for each specific energy consumption group. The experimental results showed the ECG-ICEEMDAN-BILSTM model obtained more accurate predictions compared with other neural network models. In addition, the model was more effective at forecasting the complex distribution of the HPEC pattern, with reductions of at least 16.21% and 15.82% in MAPE and PRMSE, respectively. Thus, study still can obtain valuable insights to address the problem of short-term prediction using complex time series.

Convolutional neural network-based wind pressure prediction on low-rise buildings

A new model of wind pressure prediction for low-rise buildings is built based on deep convolutional neural network (CNN), and the model is trained and tested by the aerodynamic data from international open database. The prediction accuracy is compared with that of the literature, and then comprehensive error analysis on all 335 predicted taps under 3 untrained wind directions are carried out for mean and RMS pressure coefficients by various error metrics. The study shows that the distributions of mean and RMS coefficients predicted by the CNN model are closer to the experimental results in comparison with those predicted by the traditional artificial neural network (ANN) model and the common deep neural network (DNN) model without the convolution and pooling layers. The relative error on the corner tap is 13.5%, 4.3% and 0.1% by the ANN, DNN, and CNN models respectively. The mean-square-error (MSE) of the corner bay and the whole roof are also eminently reduced by the CNN model. By introducing the convolutional and pooling layers, more prediction errors are confined within 5% and basically no errors exceed 20%. Consequently, the CNN algorithm can be applied in solving various wind pressure prediction problems on buildings in the future work.

Developing machine learning models with metaheuristic algorithms for droplet size prediction in a microfluidic microchannel

Droplet-based microfluidics holds promise for advanced biomedical applications due to its enhanced accuracy, throughput, rapid reaction time, and minimal reagent consumption. However, achieving droplets with the desired radius often entails costly design iterations. In this paper, we propose a novel approach that combines machine learning algorithms with metaheuristic algorithms to leverage their respective strengths in speed and accuracy. Specifically, we demonstrate the effectiveness of the Rain Optimization Algorithm (ROA) in enhancing the accuracy of five machine learning models. Additionally, we introduce a hybrid model, optimized by ROA, for predicting droplet generation in a cross-junction microfluidic channel, achieving a coefficient of determination (R2) of 0.937, reflecting a 3.6 % increase in accuracy. We employ symbolic regression to validate the hybrid model, yielding an R2 value of 0.987, indicating strong agreement with real data. Furthermore, we utilize the SHAP method in Explainable AI to interpret the hybrid model's performance. Notably, the proposed hybrid model requires only four seconds to solve the prediction problem, significantly reducing computational time compared to the numerical model and experimental method. This approach facilitates the study of each input parameter's impact on droplet size prediction, offering otherwise challenging and costly insights to obtain experimentally.

On the Universal Presence of Mathematics for Incompletely Predictable Problems in Rigorous Proofs for Riemann Hypothesis, Modified Polignac’s and Twin Prime Conjectures

We validly ignore even prime number 2. Based on all arbitrarily large number of even Prime gaps 2, 4, 6, 8, 10...; the complete set and its derived subsets of Odd Primes fully comply with the Prime number theorem for Arithmetic Progressions, and our derived Generic Squeeze theorem and Theorem of Divergent-to-Convergent series conversion for Prime numbers. With these conditions being satisfied by all Odd Primes, we argue Polignac's and Twin prime conjectures are proven to be true when they are usefully treated as Incompletely Predictable Problems. In so doing [and with Riemann hypothesis being a special case], this action also support the generalized Riemann hypothesis formulated for Dirichlet L-function. By broadly applying Hodge conjecture, Grothendieck period conjecture and Pi-Circle conjecture to Dirichlet eta function (proxy function for Riemann zeta function), Riemann hypothesis is separately proven to be true when it is usefully treated as Incompletely Predictable Problem. Crucial connections exist between these Incompletely Predictable Problems and Quantum field theory whereby eligible (sub-)functions and (sub-)algorithms are treated as infinite series.

Predictability‐Aware Subsequence Modeling for Sequential Recommendation

Sequential recommendation frames the recommendation task as a next‐item prediction problem, where the model is trained to predict the next item given a user behavior sequence. While recent research has made significant progress in developing advanced models for this task, there exists a notable gap in the exploration of subsequences and the predictability inherent in user behavior sequences. This oversight can lead models to recall inconsequential sequential patterns, adversely affecting recommendation quality. In this paper, we introduce a novel approach to augmenting sequential recommendation by integrating predictability awareness into subsequence modeling. Our method begins by discerning the predictability of target items; those easily predicted often align with the preceding subsequence, while those that are hard to predict typically indicate transitions to other subsequences. Leveraging this predictability information, we enhance the discovery of meaningful subsequences within individual user behavior sequences. Evaluation of four benchmark data sets using various state‐of‐the‐art sequential models illustrates the efficacy of our approach in enhancing recommendation performance. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

IMAGE CAPTION GENERATOR USING DEEP LEARNING

Image Captioning is a task where each image must be understood properly and are able generate suitable caption with proper grammatical structure.Here it is a hybrid system which uses multilayer CNN (Convolutional Neural Network) for generating keywords which narrates given input images and Long Short Term Memory(LSTM) for precisely constructing the significant captions utilizing the obtained words .Convolution Neural Network (CNN) proven to be so effective that there is a way to get to any kind of estimating problem that includes image data as input. LSTM was developed to avoid the poor predictive problem which occurred while using traditional approaches. We used an encoder-decoder based model that is capable of generating grammatically correct captions for images. This model makes use of VGG16(Visual Geometry Group) as an encoder and LSTM as a decoder. The model will be trained like when an image is given model produces captions that almost describe the image. The efficiency is demonstrated for the given model using Flickr8K data sets which contains 8000 images and captions for each image but we use CNN and LSTM to capture dependencies and tell both the spatial relationships of images and contextual information of captions and generate contextually relevant captions. Keywords—CNN(Convolutional Neural Network),LSTM(Long Short Term Memory),VGG16(Visual Geometry Group),Deep Learning,Encoder-Decoder.

Forecasting Gas Well Classification Based on a Two-Dimensional Convolutional Neural Network Deep Learning Model

In response to the limitations of existing evaluation methods for gas well types in tight sandstone gas reservoirs, characterized by low indicator dimensions and a reliance on traditional methods with low prediction accuracy, therefore, a novel approach based on a two-dimensional convolutional neural network (2D-CNN) is proposed for predicting gas well types. First, gas well features are hierarchically selected using variance filtering, correlation coefficients, and the XGBoost algorithm. Then, gas well types are determined via spectral clustering, with each gas well labeled accordingly. Finally, the selected features are inputted, and classification labels are outputted into the 2D-CNN, where convolutional layers extract features of gas well indicators, and the pooling layer, which, trained by the backpropagation of CNN, performs secondary dimensionality reduction. A 2D-CNN gas well classification prediction model is constructed, and the softmax function is employed to determine well classifications. This methodology is applied to a specific tight gas reservoir. The study findings indicate the following: (1) Via two rounds of feature selection using the new algorithm, the number of gas well indicator dimensions is reduced from 29 to 15, thereby reducing the computational complexity of the model. (2) Gas wells are categorized into high, medium, and low types, addressing a deep learning multi-class prediction problem. (3) The new method achieves an accuracy of 0.99 and a loss value of 0.03, outperforming BP neural networks, XGBoost, LightGBM, long short-term memory networks (LSTMs), and one-dimensional convolutional neural networks (1D-CNNs). Overall, this innovative approach demonstrates superior efficacy in predicting gas well types, which is particularly valuable for tight sandstone gas reservoirs.

Bi-State Prediction Network Model for Mixed Traffic Congestion Prediction

Forecasting traffic congestion has become an important issue than ever before. Information provided by traffic congestion prediction methods becomes helpful to traffic management agencies to take suitable actions in due time. On the other hand, with prior information, passengers can plan their trip routes accordingly. In this paper, we tackle the problem of mixed traffic congestion prediction and develop a new Bi-State Prediction Network (BiSPNet). Two heads form BiSPNet. Each head information passed through the layers of three-dimensional convolution (Conv3D), two-dimensional convolutional long short-term memory (ConvLSTM2D), and two-dimensional convolution (Conv2D). Then the dense layer merges both head outputs. These layers capacitate the model to capture the characteristics of multiple inputs. The proposed model is validated by the ground truth data collected by the video cameras installed on the roadways in Delhi, India. Experimental results confirm that the prediction accuracy of the BiSPNet model surpasses that of several state-of-the-art benchmark models. In particular, the BiSPNet reduces mean absolute error by 53.23%, 40.95%, and 0.38%, respectively, in congestion score prediction for 5, 10, and 15-min time horizons compared to the mixed deep learning network (MDLNet). The source data and code can be accessed on GitHub at the following link: https://github.com/amanojup/ .

A Modified Sine Cosine Algorithm for Numerical Optimization

Sine cosine algorithm (SCA) is a recently developed meta-heuristic method based on the characteristics of sine and cosine functions. However, SCA algorithm may suffer premature convergence in solving complex optimization problems. To mitigate this limitation, a modified SCA (MSCA) is developed to achieve an effective balance between exploration and exploitation. Specifically, the conversion parameter can be configured adaptively by using the individual fitness information in the evolution process to guide the individual search behavior. After that, an inertia weight is embedded in the position updating equation to further improve the search accuracy and accelerate the convergence speed. The performance of MSCA algorithm is investigated on 13 benchmark functions and the chaotic time series prediction problem. Experimental results demonstrate that MSCA algorithm is more effective than the other optimization methods.

Prediction and optimization method for welding quality of components in ship construction

Welding process, as one of the crucial industrial technologies in ship construction, accounts for approximately 70% of the workload and costs account for approximately 40% of the total cost. The existing welding quality prediction methods have hypothetical premises and subjective factors, which cannot meet the dynamic control requirements of intelligent welding for processing quality. Aiming at the low efficiency of quality prediction problems poor timeliness and unpredictability of quality control in ship assembly-welding process, a data and model driven welding quality prediction method is proposed. Firstly, the influence factors of welding quality are analyzed and the correlation mechanism between process parameters and quality is determined. According to the analysis results, a stable and reliable data collection architecture is established. The elements of welding process monitoring are also determined based on the feature dimensionality reduction method. To improve the accuracy of welding quality prediction, the prediction model is constructed by fusing the adaptive simulated annealing, the particle swarm optimization, and the back propagation neural network algorithms. Finally, the effectiveness of the prediction method is verified through 74 sets of plate welding experiments, the prediction accuracy reaches over 90%.

Sleep stage prediction using multimodal body network and circadian rhythm.

Quality sleep plays a vital role in living beings as it contributes extensively to the healing process and the removal of waste products from the body. Poor sleep may lead to depression, memory deficits, heart, and metabolic problems, etc. Sleep usually works in cycles and repeats itself by transitioning into different stages of sleep. This study is unique in that it uses wearable devices to collect multiple parameters from subjects and uses this information to predict sleep stages and sleep patterns. For the multivariate multiclass sleep stage prediction problem, we have experimented with both memoryless (ML) and memory-based models on seven database instances, that is, five from the collected dataset and two from the existing datasets. The Random Forest classifier outclassed the ML models that are LR, MLP, kNN, and SVM with accuracy (ACC) of 0.96 and Cohen Kappa 0.96, and the memory-based model long short-term memory (LSTM) performed well on all the datasets with the maximum attained accuracy of 0.88 and Kappa 0.82. The proposed methodology was also validated on a longitudinal dataset, the Multiethnic Study of Atherosclerosis (MESA), with ACC and Kappa of 0.75 and 0.64 for ML models and 0.86 and 0.78 for memory-based models, respectively, and from another benchmarked Apple Watch dataset available on Physio-Net with ACC and Kappa of 0.93 and 0.93 for ML and 0.92 and 0.87 for memory-based models, respectively. The given methodology showed better results than the original work and indicates that the memory-based method works better to capture the sleep pattern.

Recent advances and challenges in protein complex model accuracy estimation

Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure models accurately and objectively. This process is not only key to screening candidate models that are close to the real structure, but also provides guidance for further optimization of protein structures. With the significant advancements made by AlphaFold2 in monomer structure, the problem of single-domain protein structure prediction has been widely solved. Correspondingly, the importance of assessing the quality of single-domain protein models decreased, and the research focus has shifted to estimation of model accuracy of protein complexes. In this review, our goal is to provide a comprehensive overview of the reference and statistical metrics, as well as representative methods, and the current challenges within four distinct facets (Topology Global Score, Interface Total Score, Interface Residue-Wise Score, and Tertiary Residue-Wise Score) in the field of complex EMA.

An effective multi-time series model of RC column backbone curve identification

Accurate identification of the backbone curves of reinforced concrete (RC) columns is key to engineering design and strengthening renovation. In view of the problems of high cost, long time, low accuracy, large dispersion of calculation results and discontinuous stiffness changes of the existing backbone curve identification methods, such as experimental method, finite element simulation method and semi-theoretical and semi-empirical method, it is proposed to transform the backbone curve identification problem into a multi-time series prediction problem. By introducing the attention mechanism and combining it with the bidirectional long short-term memory (BiLSTM), the backbone curve identification model (BC-ABiLSTM) is established considering the relationship between the front and back points of the backbone curves. Compared with the models for backbone curves with BiLSTM (BC-BiLSTM), long short-term memory (BC-LSTM), multilayer perceptron (BC-MLP), and the existing identification methods, the performance of the BC-ABiLSTM model is better, and the mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R2 of the BC-ABiLSTM model on the testing set are 12.492 kN, 10.595 %, 20.838 kN and 0.9924, respectively, which provides a new method for accurate, efficient and cost-effective prediction of RC column backbone curve points under various cyclic loading levels.

Deep learning prediction of renal anomalies for prenatal ultrasound diagnosis

Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly in the field of medical imaging. In this study, we investigated the application of deep learning models in early detection of fetal kidney anomalies. To provide an enhanced interpretation of those models’ predictions, we proposed an adapted two-class representation and developed a multi-class model interpretation approach for problems with more than two labels and variable hierarchical grouping of labels. Additionally, we employed the explainable AI (XAI) visualization tools Grad-CAM and HiResCAM, to gain insights into model predictions and identify reasons for misclassifications. The study dataset consisted of 969 ultrasound images from unique patients; 646 control images and 323 cases of kidney anomalies, including 259 cases of unilateral urinary tract dilation and 64 cases of unilateral multicystic dysplastic kidney. The best performing model achieved a cross-validated area under the ROC curve of 91.28% ± 0.52%, with an overall accuracy of 84.03% ± 0.76%, sensitivity of 77.39% ± 1.99%, and specificity of 87.35% ± 1.28%. Our findings emphasize the potential of deep learning models in predicting kidney anomalies from limited prenatal ultrasound imagery. The proposed adaptations in model representation and interpretation represent a novel solution to multi-class prediction problems.

Machine learning as alternative strategy for the numerical prediction of the shear response in reinforced and prestressed concrete beams

Some materials, such as reinforced and prestressed concrete, involve non-linear constitutive relationships in elasticity problems defined on them. In particular, the shear strength of a reinforced concrete beam may be calculated by considering a diagonal struts field in the context of the so-called “Compression Field Theories” (CFTs). This work presents an efficient Machine Learning method alternative to numerical methods for obtaining the full shear response of reinforced and prestressed concrete beams based on CFT regarding stresses, strains, and crack angles. For that, a regression task is developed using state-of-the-art Machine Learning (ML) models. A ML model per output variable is trained with the existing Newton-Raphson solutions database. The solvability region of the embedded steel constitutive model is also considered, demonstrating the comprehensive character of the proposed method. The model is validated on two real beam responses, where the results obtained demonstrate that this alternative method based on ML algorithms effectively addresses the problem of prediction of the shear response in reinforced and prestressed concrete beams. The proposed ML approximation performs reasonably well without requiring any initial approximations. Moreover, the ML regressor here developed shows a low dependence on the concrete tension stiffening area surrounding the steel reinforcement, which significantly improves the performance of this methodology in a higher number of design cases. Thus, in the practical context of structural engineering, this last approach establishes an efficient alternative procedure for obtaining numerical solutions of mechanical models based on the CFTs framework.

Smoothed Analysis with Adaptive Adversaries

We prove novel algorithmic guarantees for several online problems in the smoothed analysis model. In this model, at each time step an adversary chooses an input distribution with density function bounded above pointwise by  \(\tfrac{1}{\sigma } \) times that of the uniform distribution; nature then samples an input from this distribution. Here, σ is a parameter that interpolates between the extremes of worst-case and average case analysis. Crucially, our results hold for adaptive adversaries that can base their choice of an input distribution on the decisions of the algorithm and the realizations of the inputs in the previous time steps. An adaptive adversary can nontrivially correlate inputs at different time steps with each other and with the algorithm’s current state; this appears to rule out the standard proof approaches in smoothed analysis. This paper presents a general technique for proving smoothed algorithmic guarantees against adaptive adversaries, in effect reducing the setting of an adaptive adversary to the much simpler case of an oblivious adversary (i.e., an adversary that commits in advance to the entire sequence of input distributions). We apply this technique to prove strong smoothed guarantees for three different problems: (1) Online learning: We consider the online prediction problem, where instances are generated from an adaptive sequence of σ -smooth distributions and the hypothesis class has VC dimension d . We bound the regret by \(\tilde{O}\big (\sqrt {T d\ln (1/\sigma)} + d\ln (T/\sigma) \big) \) and provide a near-matching lower bound. Our result shows that under smoothed analysis, learnability against adaptive adversaries is characterized by the finiteness of the VC dimension. This is as opposed to the worst-case analysis, where online learnability is characterized by Littlestone dimension (which is infinite even in the extremely restricted case of one-dimensional threshold functions). Our results fully answer an open question of Rakhlin et al. [64]. (2) Online discrepancy minimization: We consider the setting of the online Komlós problem, where the input is generated from an adaptive sequence of σ -smooth and isotropic distributions on the ℓ 2 unit ball. We bound the ℓ ∞ norm of the discrepancy vector by \(\tilde{O}\big (\ln ^2\big (\frac{nT}{\sigma }\big) \big) \) . This is as opposed to the worst-case analysis, where the tight discrepancy bound is \(\Theta (\sqrt {T/n}) \) . We show such polylog( nT / σ ) discrepancy guarantees are not achievable for non-isotropic σ -smooth distributions. (3) Dispersion in online optimization: We consider online optimization with piecewise Lipschitz functions where functions with ℓ discontinuities are chosen by a smoothed adaptive adversary and show that the resulting sequence is \(\big ({\sigma }/{\sqrt {T\ell }}, \tilde{O}\big (\sqrt {T\ell } \big)\big) \) -dispersed. That is, every ball of radius \({\sigma }/{\sqrt {T\ell }} \) is split by \(\tilde{O}\big (\sqrt {T\ell } \big) \) of the partitions made by these functions. This result matches the dispersion parameters of Balcan et al. [13] for oblivious smooth adversaries, up to logarithmic factors. On the other hand, worst-case sequences are trivially (0, T )-dispersed.

Neural networks as effective surrogate models of radio-frequency quadrupole particle accelerator simulations

Radio-frequency quadrupoles (RFQs) are multi-purpose linear particle accelerators that simultaneously bunch and accelerate charged particle beams. They are ubiquitous in accelerator physics, especially as injectors to higher-energy machines, owing to their impressive efficiency. The design and optimization of these devices can be lengthy due to the need to repeatedly perform high-fidelity simulations. Several recent papers have demonstrated that machine learning can be used to build surrogate models (fast-executing replacements of computationally costly beam simulations) for order-of-magnitude computing time speedups. However, while these pilot studies are encouraging, there is room to improve their predictive accuracy. Particularly, beam summary statistics such as emittances (an important figure of merit in particle accelerator physics) have historically been challenging to predict. For the first time, we present a surrogate model trained on 200 000 samples that yields < 6% mean average percent error for the predictions of all relevant beam output parameters from defining RFQ design parameters, solving the problem of poor emittance predictions by identifying and including hidden variables which were not accounted for previously. These surrogate models were made possible by using the Julia language and GPU computing; we briefly discuss both. We demonstrate the utility of surrogate modeling by performing a multi-objective optimization using our best model as a callback in the objective function to select an optimal RFQ design. We consider trade-offs in RFQ performance for various choices of Pareto-optimal design variables—common issues for any multi-objective optimization scheme. Lastly, we make recommendations for input data preparation, selection, and neural network architectures that pave the way for future development of production-capable surrogate models for RFQs and other particle accelerators.