Mapping of earth resources, environmental monitoring, and many other systems require high-resolution wide-area imaging. Since images often have to be captured at night or in inclement weather conditions, a capability is provided by Synthetic Aperture Radar (SAR). SAR systems exploit radar signal's long-range propagation and utilize digital electronics to process complex information, all of which enables high-resolution imagery. This gives SAR systems advantages over optical imaging systems, since, unlike optical imaging, SAR is effective at any time of day and in any weather conditions. Moreover, advanced technology called Interferometric Synthetic Aperture Radar (InSAR), has the potential to apply phase information from SAR images and to measure ground surface deformation. However, given the current state of technology, the quality of InSAR data can be distorted by several factors, such as image co-registration, interferogram generation, phase unwrapping, and geocoding. Image co-registration aligns two or more images so that the same pixel in each image corresponds to the same point of the target scene. Super-Resolution (SR), on the other hand, is the process of generating high-resolution (HR) images from a low-resolution (LR) one. SR influences the co-registration quality and therefore could potentially be used to enhance later stages of SAR image processing. Our research resulted in two major contributions towards the enhancement of SAR processing. The first one is a new learning-based SR model that can be applied with SAR, and similar applications. A second major contribution is utilizing the devised model for improving SAR co-registration and InSAR interferogram generation, together with methods for evaluating the quality of the resulting images. In the case of phase unwrapping, the process of recovering unambiguous phase values from a two-dimensional array of phase values known only modulo $2\pi$ rad, our research produced a third major contribution. This third major contribution is the finding that quantum annealers can resolve problems associated with phase unwrapping. Even though other potential solutions to this problem do currently exist - based on network programming for example - network programming techniques do not scale well to larger images. We were able to formulate the phase unwrapping problem as a quadratic unconstrained binary optimization (QUBO) problem, which can be solved using a quantum annealer. Since quantum annealers are limited in the number of qubits they can process, currently available quantum annealers do not have the capacity to process large SAR images. To resolve this limitation, we developed a novel method of recursively partitioning the image, then recursively unwrapping each partition, until the whole image becomes unwrapped. We tested our new approach with various software-based QUBO solvers and various images, both synthetic and real. We also experimented with a D-Wave Systems quantum annealer, the first and only commercial supplier of quantum annealers, and we developed an embedding method to map the problem to the D-Wave 2000Q_6, which improved the result images significantly. With our method, we were able to achieve high-quality solutions, comparable to state-of-the-art phase-unwrapping solvers. / Graduate

<p>High-throughput phenotyping has emerged as a powerful approach to expedite crop breeding programs. Modern remote sensing systems, including manned aircraft, unmanned aerial vehicles (UAVs), and terrestrial platforms equipped with multiple sensors, such as RGB cameras, multispectral, hyperspectral, and infrared thermal sensors, as well as light detection and ranging (LiDAR) scanners are now widely used technologies in advancing high throughput phenotyping. These systems can collect high spatial, spectral, and temporal resolution data on various phenotypic traits, such as plant height, canopy cover, and leaf area. Enhancing the capability of utilizing such remote sensing data for automated phenotyping is crucial in advancing crop breeding. This dissertation focuses on developing deep learning and transfer learning methodologies for crop phenotyping using multi-modality remote sensing and environmental data. The techniques address two main areas: multi-temporal/across-field biomass prediction and multi-scale remote sensing data fusion.</p> <p><br></p> <p>Biomass is a plant characteristic that strongly correlates with biofuel production, but is also influenced by genetic and environmental factors. Previous studies have shown that deep learning-based models are effective in predicting end-of-season biomass for a single year and field. This dissertation includes development of transfer learning methodologies for multiyear,</p> <p>across-field biomass prediction. Feature importance analysis was performed to identify and remove redundant features. The proposed model can incorporate high-dimensional genetic marker data, along with other features representing phenotypic information, environmental conditions, or management practices. It can also predict end-of-season biomass using mid-season remote sensing and environmental data to provide early rankings. The framework was evaluated using experimental trials conducted from 2017 to 2021 at the Agronomy Center for Research and Education (ACRE) at Purdue University. The proposed transfer learning techniques effectively selected the most informative training samples in the target domain, resulting in significant improvements in end-of-season yield prediction and ranking. Furthermore, the importance of input remote sensing features was assessed at different growth stages.</p> <p><br></p> <p>Remote sensing technology enables multi-scale, multi-temporal data acquisition. However, to fully exploit the potential of the acquired data, data fusion techniques that leverage the strengths of different sensors and platforms are necessary. In this dissertation, a generative adversarial network (GAN) based multiscale RGB-guided model and domain adaptation framework were developed to enhance the spatial resolution of multispectral images. The model was trained on limited high spatial resolution images from a wheel-based platform and then applied to low spatial resolution images acquired by UAV and airborne platforms.</p> <p>The strategy was tested in two distinct scenarios, sorghum plant breeding, and urban areas, to evaluate its effectiveness.</p>

[pt] A super resolução (SR) é um tema de suma importância em domínios de conhecimentos variados, como por exemplo a área médica, de monitoramento e de segurança. O uso de redes neurais profundas para a resolução desta tarefa é algo extremamente recente no universo da sísmica, tendo poucas referências, as quais começaram a ser divulgadas há menos de 2 anos. Todavia, a literatura apresenta uma vasta gama de métodos, que utilizam redes neurais para a super resolução de imagens naturais. Tendo isto em vista, o objetivo deste trabalho é explorar tais abordagens aplicadas em dados sísmicos sintéticos de reservatórios. Para isto, foram empregados modelos de importância cronológica na literatura e foram comparados com um método clássico de interpolação e com os modelos da literatura de super resolução de imagens sísmicas. São estes modelos: o SRCNN, o RDN, a abordagem do Deep Image Prior e o SAN. Por fim, os resultados apresentam que o PSNR obtido por arquiteturas de projetos no domínio da sísmica equivale a 38.23 e o melhor resultado das arquiteturas propostas 38.62, mostrando o avanço que tais modelos trazem ao campo da sísmica. / [en] Super resolution (SR) is a topic of notable importance in domains of assorted knowledge, such as the medical, monitoring, and security areas. The use of deep neural networks to solve this task is something extremely recent in the seismic field, with few references, which began to be published less than 2 years ago. However, the literature presents a wide range of methods, using neural networks for the super resolution of natural images. With this in mind, the objective of this work is to explore such approaches applied to synthetic seismic data from reservoirs. For this, models of chronological importance in the literature were used and compared with a classic interpolation method and with models of the literature of super resolution of seismic images. These models are: SRCNN, RDN, the Deep Image Prior approach and SAN. The results show that the PSNR obtained by architectures developed for the seismic domain is equivalent to 38.23 and the best result of the proposed architectures is 38.62, showing the progress that such models bring to the seismic domain.

No description available.

Using a near-field array of acoustic resonators, it is possible to modify a focused pressure field and enforce a spatial frequency corresponding to the resonator array spacing. This higher spatial frequency makes it possible to focus and image with a resolution that is better than if the focusing were in free space. This near-field effect is caused by the phase shifting properties of resonators and, specifically, the delayed phase found in waves with a temporal frequency lower than that of the resonators in the array. Using time reversal, arrays of resonators are explored and the subwavelength focusing is used to describe the ability to image subwavelength features. A one-dimensional equivalent circuit model accurately predicts this interaction of the wave field with an array of resonators and is able to model the aggregate effect of the phononic crystal of resonators while describing the fine spatial details of individual resonators. This model is validated by a series of COMSOL full-wave simulations of the same system. The phase delay caused by a single resonator is explored in a simple experiment as well as in the equivalent circuit model. A series of experiments is conducted with a two-dimensional array of resonators and complex images are produced which indicate the ability to focus complex sources with better resolution.

Accelerating the simulation of turbulence to stationarity is a critical challenge in various engineering applications. This study presents an innovative equation-free multiscale approach combined with a machine learning technique to address this challenge in the context of the one-dimensional stochastic Burgers' equation, a widely used toy model for turbulence. We employ an encoder-decoder recurrent neural network to perform super-resolution reconstruction of the velocity field from lower-dimensional energy spectrum data, enabling seamless transitions between fine and coarse levels of description. The proposed multiscale-machine learning framework significantly accelerates the computation of the statistically stationary turbulent Burgers' velocity field, achieving up to 442 times faster wall clock time compared to direct numerical simulation, while maintaining three-digit accuracy in the velocity field. Our findings demonstrate the potential of integrating equation-free multiscale methods with machine learning methods to efficiently simulate stochastic partial differential equations and highlight the possibility of using this approach to simulate stochastic systems in other engineering domains. / Master of Science / In many practical engineering problems, simulating turbulence can be computationally expensive and time-consuming. This research explores an innovative method to accelerate these simulations using a combination of equation-free multiscale techniques and deep learning. Multiscale methods allow researchers to simulate the behavior of a system at a coarser scale, even when the specific equations describing its evolution are only available for a finer scale. This can be particularly helpful when there is a notable difference in the time scales between the coarser and finer scales of a system. The ``equation-free approach multiscale method coarse projective integration" can then be used to speed up the simulations of the system's evolution. Turbulence is an ideal candidate for this approach since it can be argued that it evolves to a statistically steady state on two different time scales. Over the course of evolution, the shape of the energy spectrum (the coarse scale) changes slowly, while the velocity field (the fine scale) fluctuates rapidly. However, applying this multiscale framework to turbulence simulations has been challenging due to the lack of a method for reconstructing the velocity field from the lower-dimensional energy spectrum data. This is necessary for moving between the two levels of description in the multiscale simulation framework. In this study, we tackled this challenge by employing a deep neural network model called an encoder-decoder sequence-to-sequence architecture. The model was used to capture and learn the conversions between the structure of the velocity field and the energy spectrum for the one-dimensional stochastic Burgers' equation, a simplified model of turbulence. By combining multiscale techniques with deep learning, we were able to achieve a much faster and more efficient simulation of the turbulent Burgers' velocity field. The findings of this study demonstrated that this novel approach could recover the final steady-state turbulent Burgers' velocity field up to 442 times faster than the traditional direct numerical simulations, while maintaining a high level of accuracy. This breakthrough has the potential to significantly improve the efficiency of turbulence simulations in a variety of engineering applications, making it easier to study and understand these complex phenomena.

The nuclear pore complex (NPC) is a pivotal subcellular structure governing nucleocytoplasmic transport through a selectively permeable barrier. Comprising approximately 30 distinct proteins, it includes FG-Nups with phenylalanine-glycine (FG) motifs and non-FG Nups forming the pore's scaffold. The selectively permeable barrier formed by FG-Nups enables the passive diffusion of small molecules and facilitates the transport of larger ones recognized by nuclear transport receptors (NTRs). Their roles are critical in regulating mRNA and pre-ribosome nuclear export and the nuclear import of transcription factors, underscoring their significance in cellular processes. However, studying NPCs remains challenging due to their structural complexity, heterogeneity, dynamic interactions, and inaccessibility within live cells. In this dissertation, three core questions were investigated to elucidate the structure and function of the NPC. First, the nuclear export dynamics of pre-ribosomal subunits revealed significantly higher transport efficiency compared to other large cargos. Through inhibition of nuclear transport receptor (NTR), CRM1, by small-molecule inhibitor, leptomycin B, we found a dose-dependent inhibition of CRM1s played a crucial role in pre-ribosome export efficiency. We confirmed these results through a series of controlled environments with both import and export NTRs. Our results suggest that cooperative NTR mechanisms may enhance the nucleocytoplasmic transport of not only pre-ribosomal subunits but other protein complexes as well. Second, we investigated the dynamic properties of the NPC’s selectivity barrier by altering the concentration of O-linked β-N-acetylglucosamine (O-GlcNAc) sites on nuclear pore proteins. Using small-molecule inhibitors of O-GlcNAc transferase (OGT) or O-GlcNAcase (OGA) to decrease or increase NPC O-GlcNAcylation, respectively, we found a significant change in the overall 3D spatial density of NPC O-GlcNAc sites. Then, by applying the same OGT- and OGA-inhibited conditions, we found that NPC O-GlcNAcylation significantly impacted the nuclear export of mRNA, suggesting that NPC O-GlcNAcylation regulates mRNA’s passage through the NPC’s selective permeability barrier. Third, we examined the nuclear transport mechanism for intrinsically disordered proteins (IDPs). Our findings revealed that IDPs, unlike large folded proteins, can passively diffuse through NPCs independent of size, and their diffusion behaviors are differentiated by the content ratio of charged (Ch) and hydrophobic (Hy) amino acids. Thus, we proposed a Ch/Hy-ratio mechanism for IDP nucleocytoplasmic transport. In summary, comprehending the dynamic behavior of the NPC selectivity barrier and its involvement in mediating large transiting complexes and IDPs has provided valuable insights into the fundamental nucleocytoplasmic transport mechanism, emphasizing the NPC's crucial role in cellular health and function. / Biology

Segmentation of the knee cartilage is an important step for surgery planning and manufacturing patient-specific prostheses. What has been a promising technology in recent years is deep learning-based super-resolution methods that are composed of feed-forward models which have been successfully applied on natural and medical images. This thesis aims to test the feasibility to super-resolve thick slice 2D sequence acquisitions and acquire sufficient segmentation accuracy of the articular cartilage in the knee. The investigated approaches are single- and multi-contrast super-resolution, where the contrasts are either based on the 2D sequence, 3D sequence, or both. The deep learning models investigated are based on predicting the residual image between the high- and low-resolution image pairs, finding the hidden latent features connecting the image pairs, and approximating the end-to-end non-linear mapping between the low- and high-resolution image pairs. The results showed a slight improvement in segmentation accuracy with regards to the baseline bilinear interpolation for the single-contrast super-resolution, however, no notable improvements in segmentation accuracy were observed for the multi-contrast case. Although the multi-contrast approach did not result in any notable improvements, there are still unexplored areas not covered in this work that are promising and could potentially be covered as future work. / Segmentering av knäbrosket är ett viktigt steg för planering inför operationer och tillverkning av patientspecifika proteser. Idag segmenterar man knäbrosk med hjälp av MR-bilder tagna med en 3D-sekvens som både tidskrävande och rörelsekänsligt, vilket kan vara obehagligt för patienten. I samband med 3D-bildtagningar brukar även thick slice 2D-sekvenser tas för diagnostiska skäl, däremot är de inte anpassade för segmentering på grund av för tjocka skivor. På senare tid har djupinlärningsbaserade superupplösningsmetoder uppbyggda av så kallade feed-forwardmodeller visat sig vara väldigt framgångsrikt när det applicerats på verkliga- och medicinska bilder. Syftet med den här rapporten är att testa hur väl superupplösta thick slice 2D-sekvensbildtagningar fungerar för segmentering av ledbrosket i knät. De undersökta tillvägagångssätten är superupplösning av enkel- och flerkontrastbilder, där kontrasten är antingen baserade på 2D-sekvensen, 3D-sekvensen eller både och. Resultaten påvisar en liten förbättring av segmenteringnoggrannhet vid segmentering av enkelkontrastbilderna över baslinjen linjär interpolering. Däremot var det inte någon märkvärdig förbättring i superupplösning av flerkontrastbilderna. Även om superupplösning av flerkontrastmetoden inte gav någon märkbar förbättring segmenteringsresultaten så finns det fortfarande outforskade områden som inte tagits upp i det här arbetet som potentiellt skulle kunna utforskas i framtida arbeten.

The primary cilium is an immotile, microtubule-based protrusion on the surface of many eukaryotic cells and contains a unique complement of proteins that function critically in cell motility and signaling. Critically, the transport of membrane and cytosolic proteins into the primary cilium is essential for its role in cellular signaling. Since cilia are incapable of synthesizing their own protein, nearly 200 unique ciliary proteins need to be trafficked between the cytosol and primary cilia. However, it is still a technical challenge to map three-dimensional (3D) locations of transport pathways for these proteins in live primary cilia due to the limitations of currently existing techniques. To conquer the challenge, this work employed a high-speed virtual 3D super-resolution microscopy, termed single-point edge-excitation sub-diffraction (SPEED) microscopy, to determine the 3D spatial location of transport pathways for both cytosolic and membrane proteins in primary cilia of live cells. Using SPEED microscopy and single molecule tracking, we mapped the movement of membrane and soluble proteins at the base of the primary cilium. In addition to the well-known intraflagellar transport (IFT) route, we identified two new pathways within the lumen of the primary cilium - passive diffusional and vesicle transport routes - that are adopted by proteins for cytoplasmic-cilium transport in live cells. Independent of the IFT path, approximately half of IFT motors (KIF3A) and cargo (α-tubulin) take the passive diffusion route and more than half of membrane-embedded G protein coupled receptors (SSTR3 and HTR6) use RAB8A-regulated vesicles to transport into and inside cilia. Furthermore, ciliary lumen transport is the preferred route for membrane proteins in the early stages of ciliogenesis and inhibition of SSTR3 vesicle transport completely blocks ciliogenesis. Furthermore, clathrin-mediated, signal-dependent internalization of SSTR3 also occurs through the ciliary lumen. These transport routes were also observed in Chlamydomonas reinhardtii flagella, suggesting their conserved roles in trafficking of ciliary proteins. While the 3D transport pathways in this work are always replicated multiple times with a high degree of consistency, several experimental parameters directly affect the 3D transport routes’ error, such as single molecule localization precision and the number of single molecule localizations. In fact, if these experimental parameters do not meet a minimum threshold, the resultant 3D transport pathways may not have significant resolution to determine any biological details. To estimate the 3D transport routes’ error, this work will explain in detail the component of SPEED microscopy that estimates 3D sub-diffraction-limited structural or dynamic information in rotationally symmetric bio-structures, such as the primary cilium. This component is a post-localization analysis that transforms 2D super-resolution images or 2D single-molecule localization distributions into their corresponding 3D spatial probability distributions based on prior known structural knowledge. This analysis is ideal in cases where the ultrastructure of a cellular structure is known but the sub-structural localization of a particular protein is not. This work will demonstrate how the 2D-to-3D component of SPEED microscopy can be successfully applied to achieve 3D structural and functional sub-diffraction-limited information for 25-300 nm subcellular organelles that meet the rotational symmetry requirement, such as the primary cilium and microtubules. Furthermore, this work will provide comprehensive analyses of this method by using computational simulations which investigate the role of various experimental parameters on the 3D transport pathway error. Lastly, this work will demonstrate that this method can distinguish different types of 3D transport pathway distributions in addition to their locations. / Biology

The nucleus of eukaryotic cells is a vitally important organelle that sequesters the genetic information of the cell, and protects it with the help of two highly evolved structures, the nuclear envelope (NE) and nuclear pore complexes (NPCs). Together, these two structures mediate the bidirectional trafficking of molecules between the nucleus and cytoplasm by forming a barrier. NE transmembrane proteins (NETs) embedded in either the outer nuclear membrane (ONM) or the inner nuclear membrane (INM) play crucial roles in both nuclear structure and functions, including: genome architecture, epigenetics, transcription, splicing, DNA replication, nuclear structure, organization and positioning. Furthermore, numerous human diseases are associated with mutations and mislocalization of NETs on the NE. There are still many fundamental questions that are unresolved with NETs, but we focused on two major questions: First, the localization and transport rate of NETs, and second, the transport route taken by NETs to reach the INM. Since NETs are involved with many of the mechanisms used to maintain cellular homeostasis, it is important to quantitatively determine the spatial locations of NETs along the NE to fully understand their role in these vital processes. However, there are limited available approaches for this task, and moreover, these methods provide no information about the translocation rates of NETs between the two membranes. Furthermore, while the trafficking of soluble proteins between the cytoplasm and the nucleus has been well studied over the years, the path taken by NETs into the nucleus remains in dispute. At least four distinct models have been proposed to suggest how transmembrane proteins destined for the INM cross the NE through NPC-dependent or NPC-independent mechanisms, based on specific features found on the soluble domains of INM proteins. In order to resolve these two major questions, it is necessary to employ techniques with the capabilities to observe these dynamics at the nanoscale. Current experimental techniques are unable to break the temporal and spatial resolution barriers required to study these phenomena. Therefore, we developed and modified single-molecule techniques to answer these questions. First, to study the distribution of NETs on the NE, we developed a new single-molecule microscopy method called single-point single-molecule fluorescence recovery after photobleaching (smFRAP), which is able to provide spatial resolution &lt;10 nm and, furthermore, provide previously unattainable information about NET translocation rates from the ONM to INM. Secondly, to examine the transport route used by NETs destined for the INM, we used a single-molecule microscopy technique previously developed in our lab called single-point edge-excitation sub-diffraction (SPEED) microscopy, which provides spatio-temporal resolution of &lt;10 nm precision and 0.4 ms detection time. The major findings from my doctoral research work can be classified into two categories: (i) Technical developments to study NETs in vivo, and (ii) biological findings from employing these microscopy techniques. In regards to technical contributions, we created and validated of a new single-molecule microscopy method, smFRAP, to accurately determine the localization and distribution ratios of NETs on both the ONM and INM in live cells. Second, we adapted SPEED microscopy to study transmembrane protein translocation in vivo. My work has also contributed four main biological findings to the field: first, we determined the in vivo translocation rates for lamin-B receptor (LBR), a major INM protein found in the nucleus of cells. Second, we verified the existence of peripheral channels in the scaffolding of NPCs and, for the first time, directly observed the transit of INM proteins through these channels in live cells. Third, our research has elucidated the roles that both the nuclear localization signal (NLS) and intrinsically disordered (ID) domains play in INM protein transport. Finally, my work has elucidated which transport routes are used by NETs destined to localize in the INM. / Biology