Convolutional Deep Learning Research Articles

Improving vertebral diagnosis in computed tomography scans: a clinically oriented attention-driven asymmetric convolution network for segmentation

ObjectiveVertebral segmentation in computed tomography (CT) images remains an essential issue in medical image analysis, stemming from the variability of vertebral shapes, high complex deformations, and the inherent ambiguity in CT scans. The purpose of this study is to develop advanced methods to effectively address this challenging task. MethodsWe proposed an attention-driven asymmetric convolution deep learning (AACDL) framework for vertebral segmentation. Specifically, our approach involves constructing a novel asymmetric convolutional U-shaped deep learning architecture to enhance feature extraction capabilities by increasing its depth for capturing richer spatial details. Further, we construct a pyramid global context module that integrates global context information through pyramid pooling to boost segmentation accuracy particularly in smaller anatomical regions. Sequential channel and spatial attention mechanisms are also implemented within the network to enable it to automatically concentrate on learning the most salient features and regions across different dimensions. ResultsThe performance precision of our network was rigorously assessed using a suite of four benchmark metrics: the Dice coefficient, mean intersection over union (mIoU), Precision rate, and F1-score. When compared against the ground truth (GT), our model delivered outstanding scores, attaining a Dice coefficient of 82.79%, an mIoU of 90.72%, a Precision rate of 90.19%, and an F1-score of 90.09%, each reflecting the commendable accuracy and reliability of our network's segmentation output. ConclusionThe proposed AACDL method successfully realizes accurate segmentation of vertebral CT images, thereby demonstrating significant potential for clinical applications with its robust performance metrics. Its ability to handle the complexities associated with vertebral segmentation paves the way for enhanced diagnostic and treatment planning processes in healthcare settings.

Segmentation of stroke lesions using transformers-augmented MRI analysis.

Accurate segmentation of chronic stroke lesions from mono-spectral magnetic resonance imaging scans (e.g., T1-weighted images) is a difficult task due to the arbitrary shape, complex texture, variable size and intensities, and varied locations of the lesions. Due to this inherent spatial heterogeneity, existing machine learning methods have shown moderate performance for chronic lesion delineation. In this study, we introduced: (1) a method that integrates transformers' deformable feature attention mechanism with convolutional deep learning architecture to improve the accuracy and generalizability of stroke lesion segmentation, and (2) an ecological data augmentation technique based on inserting real lesions into intact brain regions. Our combination of these two approaches resulted in a significant increase in segmentation performance, with a Dice index of 0.82 (±0.39), outperforming the existing methods trained and tested on the same Anatomical Tracings of Lesions After Stroke (ATLAS) 2022 dataset. Our method performed relatively well even for cases with small stroke lesions. We validated the robustness of our method through an ablation study and by testing it on new unseen brain scans from the Ischemic Stroke Lesion Segmentation (ISLES) 2015 dataset. Overall, our proposed approach of transformers with ecological data augmentation offers a robust way to delineate chronic stroke lesions with clinically relevant accuracy. Our method can be extended to other challenging tasks that require automated detection and segmentation of diverse brain abnormalities from clinical scans.

Model-less multi-input analysis of pulmonary blood flow using deep learning convolution

The study investigates two categories of perfusion-based pulmonary blood flow analysis: model-based and model-less methods. The model-based approach yields plausible results, but requires strict parameter settings and presents challenges in handling. On the other hand, the model-less approach is simpler but limited to a single input analysis, necessitating an inverse problem to estimate the impulse response from input–output relationships. To overcome these limitations, this article proposes a model-less method that combines simplicity and accuracy, enabling multi-input system analysis and aiming for standardized analysis. They leverage deep learning convolution to directly estimate the impulse response, allowing for multi-input analysis. Comparative experiments demonstrate that the proposed method is easy to implement and exhibits a low estimation error within the measured signal-to-noise ratio (SNR) range, even though it is sensitive to noise. Furthermore, the proposed method is evaluated through waveform analysis, specifically Delay and Dispersion in Experiment 1, where it is compared with conventional methods. In Experiment 2, blood flow analysis is performed on a patient with a defect in the left pulmonary artery. The results indicate high convergence, independence from input waveforms, and effective analysis of cases with vascular stenosis. Moreover, the method enables multi-input system analysis, consistently yielding results consistent with medical findings, even for patients with left pulmonary artery defects.

From image-level to pixel-level labeling: A weakly-supervised learning method for identifying aquaculture ponds using iterative anti-adversarial attacks guided by aquaculture features

Aquaculture mapping is essential for monitoring and managing aquaculture resources. However, accurately geotargeting individual aquaculture ponds from medium-resolution remote sensing imagery remains challenging, and convolutional deep learning methods for identifying aquaculture ponds require labor-intensive pixel-level annotations. This paper presents a novel weakly-supervised learning method to derive pixel-level labels from image-level annotations for aquaculture ponds. Our approach uses iterative anti-adversarial attacks to refine localization results from multi-scale class activation maps (CAMs). The improved method integrates two regularization methods guided by aquaculture features to form a joint loss function for adversarial samples: discriminative water region suppression and non-aquaculture water class suppression. We also propose an aquaculture feature termed CFNDWI to constrain the localization results and generate high-quality pseudo-labels. As a result, the pseudo-labels are used to train semantic segmentation networks for accurately identifying aquaculture ponds. We evaluated the performance of our method using commonly-used backbones on 10 m Sentinel-2 imagery. Our method achieves Intersection over Union (IoU) values of 0.618–0.655 for pseudo-label generation, and IoU values of 0.664–0.708 for semantic segmentation, outperforming state-of-the-art weakly-supervised methods and public datasets. The effectiveness of each module of our method was also testified through ablation experiments. Our method leverages knowledge-driven aquaculture features to guide the data-driven adversarial learning process, addressing the lack of high-quality aquaculture datasets for model training. The code for implementing our method will be accessible at https://github.com/designer1024/WSLM-AQ.

A Novel Approach to Detect Drones Using Deep Convolutional Neural Network Architecture.

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the "vanishing gradient" problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the "dying relu" problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters.

Encoding temporal information in deep convolution neural network.

A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets-physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.

Preliminary study on AI-assisted diagnosis of bone remodeling in chronic maxillary sinusitis

ObjectiveTo construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary sinusitis (CMS) based on CT image data to improve the accuracy of image diagnosis.MethodsMaxillary sinus CT data of 1000 samples in 500 patients from January 2018 to December 2021 in our hospital was collected. The first part is the establishment and testing of chronic maxillary sinusitis detection model by 461 images. The second part is the establishment and testing of the detection model of chronic maxillary sinusitis with bone remodeling by 802 images. The sensitivity, specificity and accuracy and area under the curve (AUC) value of the test set were recorded, respectively.ResultsPreliminary application results of CT based AI in the diagnosis of chronic maxillary sinusitis and bone remodeling. The sensitivity, specificity and accuracy of the test set of 93 samples of CMS, were 0.9796, 0.8636 and 0.9247, respectively. Simultaneously, the value of AUC was 0.94. And the sensitivity, specificity and accuracy of the test set of 161 samples of CMS with bone remodeling were 0.7353, 0.9685 and 0.9193, respectively. Simultaneously, the value of AUC was 0.89.ConclusionIt is feasible to use artificial intelligence research methods such as deep learning and machine learning to automatically identify CMS and bone remodeling in MSCT images of paranasal sinuses, which is helpful to standardize imaging diagnosis and meet the needs of clinical application.

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

Recognizing online video genres using ensemble deep convolutional learning for digital media service management

It's evident that streaming services increasingly seek to automate the generation of film genres, a factor profoundly shaping a film's structure and target audience. Integrating a hybrid convolutional network into service management emerges as a valuable technique for discerning various video formats. This innovative approach not only categorizes video content but also facilitates personalized recommendations, content filtering, and targeted advertising. Given the tendency of films to blend elements from multiple genres, there is a growing demand for a real-time video classification system integrated with social media networks. Leveraging deep learning, we introduce a novel architecture for identifying and categorizing video film genres. Our approach utilizes an ensemble gated recurrent unit (ensGRU) neural network, effectively analyzing motion, spatial information, and temporal relationships. Additionally,w we present a sophisticated deep neural network incorporating the recommended GRU for video genre classification. The adoption of a dual-model strategy allows the network to capture robust video representations, leading to exceptional performance in multi-class movie classification. Evaluations conducted on well-known datasets, such as the LMTD dataset, consistently demonstrate the high performance of the proposed GRU model. This integrated model effectively extracts and learns features related to motion, spatial location, and temporal dynamics. Furthermore, the effectiveness of the proposed technique is validated using an engine block assembly dataset. Following the implementation of the enhanced architecture, the movie genre categorization system exhibits substantial improvements on the LMTD dataset, outperforming advanced models while requiring less computing power. With an impressive F1 score of 0.9102 and an accuracy rate of 94.4%, the recommended model consistently delivers outstanding results. Comparative evaluations underscore the accuracy and effectiveness of our proposed model in accurately identifying and classifying video genres, effectively extracting contextual information from video descriptors. Additionally, by integrating edge processing capabilities, our system achieves optimal real-time video processing and analysis, further enhancing its performance and relevance in dynamic media environments.

Diagnostic support in pediatric craniopharyngioma using deep learning.

We studied a pediatric group of patients with sellar-suprasellar tumors, aiming to develop a convolutional deep learning algorithm for radiological assistance to classify them into their respective cohort. T1w and T2w preoperative magnetic resonance images of226 Chilean patientswere collected at theInstitute of Neurosurgery Dr. Alfonso Asenjo (INCA), which were divided into three classes: healthy control (68subjects), craniopharyngioma (58 subjects) and differential sellar/suprasellar tumors (100 subjects). The PPV among classes was 0.828±0.039, and the NPVwas 0.919±0.063. Also explainable artificial intelligence (XAI) was used, finding thatstructures that are relevantduring diagnosis and radiological evaluationhighly influence the decision-making process of the machine. This is the first experience of this kind of study in our institution, and it led to promising results on the task of radiological diagnostic support based on explainable artificial intelligence (AI) and deep learning models.

Interpretable Cognitive Ability Prediction: A Comprehensive Gated Graph Transformer Framework for Analyzing Functional Brain Networks.

Graph convolutional deep learning has emerged as a promising method to explore the functional organization of the human brain in neuroscience research. This paper presents a novel framework that utilizes the gated graph transformer (GGT) model to predict individuals' cognitive ability based on functional connectivity (FC) derived from fMRI. Our framework incorporates prior spatial knowledge and uses a random-walk diffusion strategy that captures the intricate structural and functional relationships between different brain regions. Specifically, our approach employs learnable structural and positional encodings (LSPE) in conjunction with a gating mechanism to efficiently disentangle the learning of positional encoding (PE) and graph embeddings. Additionally, we utilize the attention mechanism to derive multi-view node feature embeddings and dynamically distribute propagation weights between each node and its neighbors, which facilitates the identification of significant biomarkers from functional brain networks and thus enhances the interpretability of the findings. To evaluate our proposed model in cognitive ability prediction, we conduct experiments on two large-scale brain imaging datasets: the Philadelphia Neurodevelopmental Cohort (PNC) and the Human Connectome Project (HCP). The results show that our approach not only outperforms existing methods in prediction accuracy but also provides superior explainability, which can be used to identify important FCs underlying cognitive behaviors.

POAS: a framework for exploiting accelerator level parallelism in heterogeneous environments

In the era of heterogeneous computing, a new paradigm called accelerator level parallelism (ALP) has emerged. In ALP, accelerators are used concurrently to provide unprecedented levels of performance and energy efficiency. To reach that there are many problems to be solved, one of the most challenging being co-execution. In this paper, we present a new scheduling framework called POAS, a general method for providing co-execution to applications. Our proposal consists of four steps: predict, optimize, adapt and schedule. With POAS, an unseen application can be executed concurrently in ALP with little effort. We evaluate POAS on a heterogeneous environment consisting of CPUs, GPUs (CUDA cores), and XPUs (Tensor cores) on two different fields, namely linear algebra (matrix multiplication benchmark) and deep learning (convolution benchmark). Our experiments prove that POAS provides excellent performance and completes the tasks within a time very close to the optimal time for the hardware and applications used, with a negligible execution time overhead. Moreover, the POAS predictor performed exceptionally well, achieving very low RMSE values for both use cases. Therefore, POAS can be a valuable tool for fully exploiting ALP and improving overall performance over offloading in heterogeneous settings.

A novel radiological software prototype for automatically detecting the inner ear and classifying normal from malformed anatomy

BackgroundTo develop an effective radiological software prototype that could read Digital Imaging and Communications in Medicine (DICOM) files, crop the inner ear automatically based on head computed tomography (CT), and classify normal and inner ear malformation (IEM). MethodsA retrospective analysis was conducted on 2053 patients from 3 hospitals. We extracted 1200 inner ear CTs for importing, cropping, and training, testing, and validating an artificial intelligence (AI) model. Automated cropping algorithms based on CTs were developed to precisely isolate the inner ear volume. Additionally, a simple graphical user interface (GUI) was implemented for user interaction. Using cropped CTs as input, a deep learning convolutional neural network (DL CNN) with 5-fold cross-validation was used to classify inner ear anatomy as normal or abnormal. Five specific IEM types (cochlear hypoplasia, ossification, incomplete partition types I and III, and common cavity) were included, with data equally distributed between classes. Both the cropping tool and the AI model were extensively validated. ResultsThe newly developed DICOM viewer/software successfully achieved its objectives: reading CT files, automatically cropping inner ear volumes, and classifying them as normal or malformed. The cropping tool demonstrated an average accuracy of 92.25%. The DL CNN model achieved an area under the curve (AUC) of 0.86 (95% confidence interval: 0.81-0.91). Performance metrics for the AI model were: accuracy (0.812), precision (0.791), recall (0.8), and F1-score (0.766). ConclusionThis study successfully developed and validated a fully automated workflow for classifying normal versus abnormal inner ear anatomy using a combination of advanced image processing and deep learning techniques. The tool exhibited good diagnostic accuracy, suggesting its potential application in risk stratification. However, it is crucial to emphasize the need for supervision by qualified medical professionals when utilizing this tool for clinical decision-making.

Optimal gene therapy network: Enhancing cancer classification through advanced AI-driven gene expression analysis

Gene therapy is an advanced medical approach that aims to find solutions for various cancers by identifying optimal gene expressions. In this context, computer-aided detection of gene expressions becomes a research challenge, where artificial intelligence methods are employed to classify cancer types. However, traditional machine learning models must be improved for accurately classifying cancers, leading to unsatisfactory quantitative performance. Therefore, this work implemented the optimal gene therapy network (OGT-Net) for identifying the different types of cancers from the gene expression sequences. Initially, the dataset pre-processing operation normalizes the dataset, which maintains the uniform nature of all records in the dataset. Then, the light gradient boosting model (LGBM) extracts the correlated features from the pre-processed dataset, which contains the relationship among the pre-processed gene expression data. In addition, interrupt-based Harris Hawk optimization (IHHO) extracts the optimal features from LGBM data, decreasing the total number of features by removing redundant gene sequences. Then, a customized deep learning convolution neural network (DLCNN) is used to categorize diseases using gene expression datasets based on lymphography, colon, lung, ovarian, and prostate cancers. The simulation results reveal that the proposed OGT-Net improved performance on various datasets compared to existing approaches, with an average accuracy of 91.128 %, precision of 90.836 %, recall of 91.25 %, and F1-score of 90.7 %.

Research on Artificial Intelligence-Assisted Teaching Methods in Chinese Classical Dance Movement Training

Abstract Taking movement training in the teaching of classical Chinese dance as an entry point, combined with the application of digital technology, improves and enriches the existing teaching methods of movement training of classical Chinese dance. Based on the Kinect skeleton data acquisition technology, the study pre-processes the collected data and proposes a dance movement data segmentation method based on movement rhythm to segment dance movement segments. The ST-GCN network structure is improved to recognize Chinese classical dance by AAST-GCN, a spatio-temporal graph convolutional network based on adaptive and attention mechanisms. Finally, the DTW algorithm is used to analyze the degree of similarity between the recognized action sequences and the standard action sequences, so as to provide targeted assisted teaching of classical Chinese dance. The results show that the intersection and concurrency ratio of the human dance posture detection method based on deep convolutional learning is always located in [0.5, 1.0], and the system can give training suggestions according to the comparison results, and the trainer can reasonably adjust the movements according to the software prompts, so as to achieve the purpose of assisted training, and then effectively improve the trainer’s dance level. After 12 weeks of AI-assisted training, the dancers obtained more obvious improvement than the control group in both rotational speed and the number of rotations, and the enhancement of these two abilities is precisely the necessary condition for realizing high-quality classical dance turn-like movements.

An efficient convolutional histogram‐oriented gradients and deep convolutional learning approach for accurate classification of bone cancer

AbstractIn our human body bones are the most significant part, which helps people to move and perform several activities. But, the cancer is caused by producing abnormal cell, which is rapidly spread to the whole parts of the body. Bone cancer is one of the critical types due to its malignancy more than other cancers. The approach involves preprocessing and segmentation of input images to remove noise and resize images, followed by feature extraction using a Convolutional histogram of oriented gradients (ConvHisOrGrad). The ROI extraction helps to accurately identify abnormal parts around the cancerous area. The Extreme Deep Convolutional learning machine (Ex‐ConVLM) is used for normal and cancerous bone classification based on the texture properties of bone MRI images. The proposed technique was evaluated using a dataset of 220 bone MRIs for tumor classes classified as necrotic, non‐tumor, and viable‐tumor. Results showed that the proposed technique outperformed existing techniques with the highest accuracy of 97% for the necrotic tumor class, 98.2% for the non‐tumor class, and 98.6% for the viable tumor class. The fine‐tuned model shows promising performance in detecting malignancy in bone based on histological images. In summary, the proposed technique utilizes deep learning architectures and ROI extraction for the accurate identification of abnormal parts in bone MRI images, achieving state‐of‐the‐art performance in the detection and categorization of bone cancers.

Deep Learning-Based Metasurface Design for Smart Cooling of Spacecraft

A reconfigurable metasurface constitutes an important block of future adaptive and smart nanophotonic applications, such as adaptive cooling in spacecraft. In this paper, we introduce a new modeling approach for the fast design of tunable and reconfigurable metasurface structures using a convolutional deep learning network. The metasurface structure is modeled as a multilayer image tensor to model material properties as image maps. We avoid the dimensionality mismatch problem using the operating wavelength as an input to the network. As a case study, we model the response of a reconfigurable absorber that employs the phase transition of vanadium dioxide in the mid-infrared spectrum. The feed-forward model is used as a surrogate model and is subsequently employed within a pattern search optimization process to design a passive adaptive cooling surface leveraging the phase transition of vanadium dioxide. The results indicate that our model delivers an accurate prediction of the metasurface response using a relatively small training dataset. The proposed patterned vanadium dioxide metasurface achieved a 28% saving in coating thickness compared to the literature while maintaining reasonable emissivity contrast at 0.43. Moreover, our design approach was able to overcome the non-uniqueness problem by generating multiple patterns that satisfy the design objectives. The proposed adaptive metasurface can potentially serve as a core block for passive spacecraft cooling applications. We also believe that our design approach can be extended to cover a wider range of applications.

Application of Graph Convolutional Neural Networks Combined with Single-Model Decision-Making Fusion Neural Networks in Structural Damage Recognition

In cases with a large number of sensors and complex spatial distribution, correctly learning the spatial characteristics of the sensors is vital for structural damage identification. Graph convolutional neural networks (GCNs), unlike other methods, have the ability to learn the spatial characteristics of the sensors, which is targeted at the above problems in structural damage identification. However, under the influence of environmental interference, sensor instability, and other factors, part of the vibration signal can easily change its fundamental characteristics, and there is a possibility of misjudging structural damage. Therefore, on the basis of building a high-performance graphical convolutional deep learning model, this paper considers the integration of data fusion technology in the model decision-making layer and proposes a single-model decision-making fusion neural network (S_DFNN) model. Through experiments involving the frame model and the self-designed cable-stayed bridge model, it is concluded that this method has a better performance of damage recognition for different structures, and the accuracy is improved based on a single model and has good damage recognition performance. The method has better damage identification performance in different structures, and the accuracy rate is improved based on the single model, which has a very good damage identification effect. It proves that the structural damage diagnosis method proposed in this paper with data fusion technology combined with deep learning has a strong generalization ability and has great potential in structural damage diagnosis.

Real-Time Person Detection in Wooded Areas Using Thermal Images from an Aerial Perspective.

Detecting people in images and videos captured from an aerial platform in wooded areas for search and rescue operations is a current problem. Detection is difficult due to the relatively small dimensions of the person captured by the sensor in relation to the environment. The environment can generate occlusion, complicating the timely detection of people. There are currently numerous RGB image datasets available that are used for person detection tasks in urban and wooded areas and consider the general characteristics of a person, like size, shape, and height, without considering the occlusion of the object of interest. The present research work focuses on developing a thermal image dataset, which considers the occlusion situation to develop CNN convolutional deep learning models to perform detection tasks in real-time from an aerial perspective using altitude control in a quadcopter prototype. Extended models are proposed considering the occlusion of the person, in conjunction with a thermal sensor, which allows for highlighting the desired characteristics of the occluded person.

On the use of convolutional deep learning to predict shoreline change

Abstract. The process of shoreline change is inherently complex, and reliable predictions of shoreline position remain a key challenge in coastal research. Predicting shoreline evolution could potentially benefit from deep learning (DL), which is a recently developed and widely successful data-driven methodology. However, so far its implementation for shoreline time series data has been limited. The aim of this contribution is to investigate the potential of DL algorithms to predict interannual shoreline position derived from camera system observations at a New Zealand study site. We investigate the application of convolutional neural networks (CNNs) and hybrid CNN-LSTM (Long Short-Term Memory) networks. We compare our results with two established models: a shoreline equilibrium model and a model that addresses timescales in shoreline drivers. Using a systematic search and different measures of fitness, we found DL models that outperformed the reference models when simulating the variability and distribution of the observations. Overall, these results indicate that DL models have potential to improve accuracy and reliability over current models.