Variable data structures and customized deep learning surrogates for computationally efficient and reliable characterization of buried objects.

In this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model have been used. The task is to independently predict characteristic parameters of a buried object of diverse radii allocated at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable data structures (raw B-scans, extracted features, consecutive A-scans) with respect to computational cost and accuracy of surrogates. The usage of raw B-scan data and the applications for processing steps on B-scan profiles in the context of object characterization incur high computational cost so it can be a challenging issue. The proposed surrogate model referred to as the deep regression network (DRN) is utilized for time frequency spectrogram (TFS) of consecutive A-scans. DRN is developed with the main aim being computationally efficient (about 13 times acceleration) compared to conventional network models using B-scan images (2D data). DRN with TFS is favorably benchmarked to the state-of-the-art regression techniques. The experimental results obtained for the proposed model and second-best model, CNN-1D show mean absolute and relative error rates of 3.6 mm, 11.8 mm and 4.7%, 11.6% respectively. For the sake of supplementary verification under realistic scenarios, it is also applied for scenarios involving noisy data. Furthermore, the proposed surrogate modeling approach is validated using measurement data, which is indicative of suitability of the approach to handle physical measurements as data sources.

Optimal design of transmitarray antennas via low-cost surrogate modelling.

Over the recent years, reflectarrays and transmitarrays have been drawing a considerable attention due to their attractive features, including a possibility of realizing high gain and pencil-like radiation patterns without the employment of complex feeding networks. Among the two, transmitarrays seem to be superior over reflectarrays in terms of achieving high radiation efficiency without the feed blockage. Notwithstanding, the design process of transmitarrays is more intricate due to the necessity of manipulating both the transmission phase and magnitude of its unit elements. For reliability, the design process has to be conducted at the level of full-wave electromagnetic models, which makes direct optimization prohibitive. The most widely used workaround is to employ surrogate modeling techniques to construct fast representations of the unit elements, yet the initial model setup cost is typically high and includes acquisition of thousands of training data points. In this paper, we propose a novel approach to cost-efficient design of transmitarrays. It is based on artificial-intelligence-enabled data-driven surrogates, which can be constructed using only a few hundreds of training data samples, while exhibiting the predictive power sufficient for reliable design. Our methodology is demonstrated by re-using the presented surrogate for the design of high-performance transmitarrays operating at various frequency ranges of 8-14 GHz, 22-28 GHz, and 28-36 GHz.

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction.

This work addresses artificial-intelligence-based buried object characterization using FDTD-based electromagnetic simulation toolbox of a Ground Penetrating Radar (GPR) to generate B-scan data. In data collection, FDTD-based simulation tool, gprMax is used. The task is to estimate geophysical parameters of a cylindrical shape object of various radii, buried at different positions in the dry soil medium simultaneously and independently of each other. The proposed methodology capitalizes on a fast and accurate data-driven surrogate model developed for object characterization in terms of its vertical and lateral position, and the size. The surrogate is constructed in a computationally efficient manner as compared to methodologies using 2D B-scan image. This is achieved by operating at the level of hyperbolic signatures extracted from the B-scan data through linear regression, which effectively reduces the dimensionality and the size of data. The proposed methodology relies on reducing of 2D B-scan image to 1D data including variation of reflected electric fields' amplitudes with respect to the scanning aperture. The input of the surrogate model is the extracted hyperbolic signature obtained through linear regression executed on the background subtracted B-scan profiles. The hyperbolic signatures encode information about the geophysical parameters of the buried object, including depth, lateral position, and radius, all of which can be extracted using proposed methodology. Parametric estimation of the object radius and the estimation of the location parameters simultaneously is a challenging problem. Applying the application of processing steps on B-scan profiles incurs high computational costs, which is a limitation of the current methodologies. The metamodel itself is rendered using a novel deep-learning-based modified multilayer perceptron (M2LP) framework. The presented object characterization technique is favourably benchmarked against the state-of-the-art regression techniques, including Multilayer Perceptron (MLP), Support Vector Regression Machine (SVRM), and Convolutional Neural Network (CNN). The verification results demonstrate the average mean absolute error of 10 mm, and the average relative error of 8 percent, both corroborating the relevance of the proposed M2LP framework. In addition, the presented methodology provides a well-structured relation between the geophysical parameters of object and the extracted hyperbolic signatures. For the sake of supplementary verification under realistic scenarios, it is also applied for scenarios involving noisy data. The environmental and internal noise of the GPR system and their effect is analyzed as well. Furthermore, the proposed surrogate modeling approach is validated using measurement data, which is indicative of suitability of the approach to handle physical measurements as data sources.

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates.

Accurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning (DL), have been found suitable for this task by capitalizing on their flexibility and generality. Yet, rendering reliable transistor surrogates is hindered by a number of issues such as the need for finding good match between the input data and the network architecture and hyperparameters (number and sizes of layers, activation functions, data pre-processing methods), possible overtraining, etc. This work proposes a novel methodology, referred to as Fully Adaptive Regression Model (FARM), where all network components and processing functions are automatically determined through Tree Parzen Estimator. Our technique is comprehensively validated using three examples of microwave transistors and demonstrated to offer a competitive edge over the state-of-the-art methods in terms of modeling accuracy and handling the aforementioned issues pertinent to standard ANN-based surrogates.