COE Faculty Works

Permanent URI for this collectionhttps://hdl.handle.net/1969.6/94847

Browse

Now showing 1 - 20 of 160

Stage and discharge prediction from documentary time-lapse imagery
(2024-04-16) Chapman, Kenneth W.; Gilmore, Troy E.; Mehrubeoglu, Mehrube; Chapman, Christian D.; Mittelstet, Aaron R.; Stranzi, John E.
Imagery from fixed, ground-based cameras is rich in qualitative and quantitative information that can improve stream discharge monitoring. For instance, time-lapse imagery may be valuable for filling data gaps when sensors fail and/or during lapses in funding for monitoring programs. In this study, we used a large image archive (>40,000 images from 2012 to 2019) from a fixed, ground-based camera that is part of a documentary watershed imaging project (https://plattebasintimelapse.com/). Scalar image features were extracted from daylight images taken at one-hour intervals. The image features were fused with United States Geological Survey stage and discharge data as response variables from the site. Predictions of stage and discharge for simulated year-long data gaps (2015, 2016, and 2017 water years) were generated from Multi-layer Perceptron, Random Forest Regression, and Support Vector Regression models. A Kalman filter was applied to the predictions to remove noise. Error metrics were calculated, including Nash-Sutcliffe Efficiency (NSE) and an alternative threshold-based performance metric that accounted for seasonal runoff. NSE for the year-long gap predictions ranged from 0.63 to 0.90 for discharge and 0.47 to 0.90 for stage, with greater errors in 2016 when stream discharge during the gap period greatly exceeded discharge during the training periods. Importantly, and in contrast to gap-filling methods that do not use imagery, the high discharge conditions in 2016 could be visually (qualitatively) verified from the image data. Half-year test sets were created for 2016 to include higher discharges in the training sets, thus improving model performance. While additional machine learning algorithms and tuning parameters for selected models should be tested further, this study demonstrates the potential value of ground-based time-lapse images for filling large gaps in hydrologic time series data. Cameras dedicated for hydrologic sensing, including nighttime imagery, could further improve results.
Simplified indoor localization using Bluetooth beacons and received signal strength fingerprinting with smartwatch
(2024-03-25) Bouse, Leana; King, Scott A.; Chu, Tianxing
Variations in Global Positioning Systems (GPSs) have been used for tracking users’ locations. However, when location tracking is needed for an indoor space, such as a house or building, then an alternative means of precise position tracking may be required because GPS signals can be severely attenuated or completely blocked. In our approach to indoor positioning, we developed an indoor localization system that minimizes the amount of effort and cost needed by the end user to put the system to use. This indoor localization system detects the user’s room-level location within a house or indoor space in which the system has been installed. We combine the use of Bluetooth Low Energy beacons and a smartwatch Bluetooth scanner to determine which room the user is located in. Our system has been developed specifically to create a low-complexity localization system using the Nearest Neighbor algorithm and a moving average filter to improve results. We evaluated our system across a household under two different operating conditions: first, using three rooms in the house, and then using five rooms. The system was able to achieve an overall accuracy of 85.9% when testing in three rooms and 92.106% across five rooms. Accuracy also varied by region, with most of the regions performing above 96% accuracy, and most false-positive incidents occurring within transitory areas between regions. By reducing the amount of processing used by our approach, the end-user is able to use other applications and services on the smartwatch concurrently.
Lower-Dimensional model of the flow and transport processes in thin domains by numerical averaging technique
(2023-12-25) Vasilyeva, Maria; Mbroh, Nana Adjoah; Mehrubeoglu, Mehrube
In this work, we present a lower-dimensional model for flow and transport problems in thin domains with rough walls. The full-order model is given for a fully resolved geometry, wherein we consider Stokes flow and a time-dependent diffusion–convection equation with inlet and outlet boundary conditions and zero-flux boundary conditions for both the flow and transport problems on domain walls. Generally, discretizations of a full-order model by classical numerical schemes result in very large discrete problems, which are computationally expensive given that sufficiently fine grids are needed for the approximation. To construct a computationally efficient numerical method, we propose a model-order-reduction numerical technique to reduce the full-order model to a lower-dimensional model. The construction of the lower-dimensional model for the flow and the transport problem is based on the finite volume method and the concept of numerical averaging. Numerical results are presented for three test geometries with varying roughness of walls and thickness of the two-dimensional domain to show the accuracy and applicability of the proposed scheme. In our numerical simulations, we use solutions obtained from the finite element method on a fine grid that can resolve the complex geometry at the grid level as the reference solution to the problem.
Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters
(2023-10-30) Krell, Evan; Kamangir, Hamid; Collins, Waylon; King, Scott A.; Tissot, Philippe
Complex machine learning architectures and high-dimensional gridded input data are increasingly used to develop highperformance geoscience models, but model complexity obfuscates their decision-making strategies. Understanding the learned patterns is useful for model improvement or scientific investigation, motivating research in eXplainable artificial intelligence (XAI) methods. XAI methods often struggle to produce meaningful explanations of correlated features. Gridded geospatial data tends to have extensive autocorrelation so it is difficult to obtain meaningful explanations of geoscience models. A recommendation is to group correlated features and explain those groups. This is becoming common when using XAI to explain tabular data. Here, we demonstrate that XAI algorithms are highly sensitive to the choice of how we group raster elements. We demonstrate that reliance on a single partition scheme yields misleading explanations. We propose comparing explanations from multiple grouping schemes to extract more accurate insights from XAI. We argue that each grouping scheme probes the model in a different way so that each asks a different question of the model. By analyzing where the explanations agree and disagree, we can learn information about the scale of the learned features. FogNet, a complex three-dimensional convolutional neural network for coastal fog prediction, is used as a case study for investigating the influence of feature grouping schemes on XAI. Our results demonstrate that careful consideration of how each grouping scheme probes the model is key to extracting insights and avoiding misleading interpretations.
Identification of brush species and herbicide effect assessment in Southern Texas using an Unoccupied Aerial System (UAS)
(2023-06-21) Shen, Xiaoqing; Clayton, Megan K.; Starek, Michael J.; Chang, Anjin; Jessup, Russell W.; Foster, Jamie L.
Cultivation and grazing since the mid-nineteenth century in Texas has caused dramatic changes in grassland vegetation. Among these changes is the encroachment of native and introduced brush species. The distribution and quantity of brush can affect livestock production and water holding capacity of soil. Still, at the same time, brush can improve carbon sequestration and enhance agritourism and real estate value. The accurate identification of brush species and their distribution over large land tracts are important in developing brush management plans which may include herbicide application decisions. Near-real-time imaging and analyses of brush using an Unoccupied Aerial System (UAS) is a powerful tool to achieve such tasks. The use of multispectral imagery collected by a UAS to estimate the efficacy of herbicide treatment on noxious brush has not been evaluated previously. There has been no previous comparison of band combinations and pixel and object-based methods to determine the best methodology for discrimination and classification of noxious brush species with Random Forest (RF) classification. In this study, two rangelands in southern Texas with encroachment of huisache (Vachellia farnesianna [L.]Wight & Arn.) and honey mesquite (Prosopis glandulosa Torr. var. glandulosa) were studied. Two study sites were flown with an eBee X fixed-wing to collect UAS images with four bands (Green, Red, Red-Edge, and Near-infrared) and ground truth data points pre- and post-herbicide application to study the herbicide effect on brush. Post-herbicide data were collected one year after herbicide application. Pixel-based and object-based RF classifications were used to identify brush in orthomosaic images generated from UAS images. The classification had an overall accuracy in the range 83–96%, and object-based classification had better results than pixel-based classification since object-based classification had the highest overall accuracy in both sites at 96%. The UAS image was useful for assessing herbicide efficacy by calculating canopy change after herbicide treatment. Different effects of herbicides and application rates on brush defoliation were measured by comparing canopy change in herbicide treatment zones. UAS-derived multispectral imagery can be used to identify brush species in rangelands and aid in objectively assessing the herbicide effect on brush encroachment.
Designing UAV swarm experiments: A simulator selection and experiment design process
(2023-08-23) Phadke, Abhishek; Medrano, F. Antonio; Sekharam, Chandra N.; Chu, Tianxing
The rapid advancement and increasing number of applications of Unmanned Aerial Vehicle (UAV) swarm systems have garnered significant attention in recent years. These systems offer a multitude of uses and demonstrate great potential in diverse fields, ranging from surveillance and reconnaissance to search and rescue operations. However, the deployment of UAV swarms in dynamic environments necessitates the development of robust experimental designs to ensure their reliability and effectiveness. This study describes the crucial requirement for comprehensive experimental design of UAV swarm systems before their deployment in real-world scenarios. To achieve this, we begin with a concise review of existing simulation platforms, assessing their suitability for various specific needs. Through this evaluation, we identify the most appropriate tools to facilitate one’s research objectives. Subsequently, we present an experimental design process tailored for validating the resilience and performance of UAV swarm systems for accomplishing the desired objectives. Furthermore, we explore strategies to simulate various scenarios and challenges that the swarm may encounter in dynamic environments, ensuring comprehensive testing and analysis. Complex multimodal experiments may require system designs that may not be completely satisfied by a single simulation platform; thus, interoperability between simulation platforms is also examined. Overall, this paper serves as a comprehensive guide for designing swarm experiments, enabling the advancement and optimization of UAV swarm systems through validation in simulated controlled environments.
Navigating the skies: Examining the FAA’s remote identification rule for unmanned aircraft systems
(2023-01) Phadke, Abhishek; Boyd, Josh; Medrano, F. Antonio; Starek, Michael
As technology and innovations in unmanned aerial vehicles progress, so does the need for regulations in place to create safe and controlled flying scenarios. The Federal Aviation Administration (FAA) is a governing body under the United States Department of Transportation that is responsible for a wide range of regulatory activities related to the United States airspace. In a recently published final rule, the FAA addresses several concerns such as the need for a system to identify all aircrafts flying in national airspace, as well as the implementation of a separate system from the prevalent Automatic Dependent Surveillance– Broadcast system to prevent interference with manned aircrafts. Their solution to these concerns is the deployment of remote identification (RID) on all unmanned aircraft systems (UAS) flying under its implied jurisdiction. While US governing agencies retain the use of the word UAS for now, the International Civil Aviation Organization terminology is remotely piloted aircraft systems. The FAA describes the RID implementation as a “Digital license plate” for all UAS flying in the United States airspace. They outline additional policies including several options for compliance, operating rules, and design and production guidelines for manufacturers. As the September 2023 deadline for compliance draws near, this article highlights possible deployment applications and challenges.
Optimization of the fluted force-feed seeder meter with the helical roller using the discrete element method and response surface analysis
(2023-07-14) Wang, Jianxiao; Sun, Wei; Simionescu, Petru Aurelian; Ju, Yuanjin
The seed metering process of a fluted force-feed seeder was simulated using the Discrete Element Method and its parameters optimized using the Box–Behnken Design of Experiments and the Response Surface Method. The rotational speed of the feed roller, the lead (helix) angle of the flutes, and the number of flutes were the independent variables, while the response value was the seeding uniformity index. Two regression models were investigated, and the following conclusions drawn. For the flute lead angle between 0 and 10 degrees, and the number of flutes between 10 and 14, it was found that the number of flutes and the lead angle influenced the seeding performance the most, with the order of importance being the (i) number of flutes, (ii) lead angle and (iii) roller speed. For the flute lead angle between 5 and 15 degrees, and the number of flutes between 12 and 16, it was found that the roller speed and the number of flutes influenced the seeding performance the most, with the order of importance being the (i) roller speed, (ii) number of flutes and (iii) flute lead angle. The two regression models were then minimized for the seeding uniformity index and the corresponding optima verified experimentally on a conveyor belt test stand fitted with an image recognition system.
Aggregating XAI methods for insights into geoscience models with correlated and high-dimensional rasters
(2023-05-13) Krell, Evan; Kamangir, Hamid; Collins, Waylon; King, Scott A; Tissot, Philippe
Geoscience applications have been using sophisticated machine learning methods to model complex phenomena. These models are described as black boxes since it is unclear what relationships are learned. Models may exploit spurious associations that exist in the data. The lack of transparency may limit user’s trust, causing them to avoid high performance models since they cannot verify that it has learned realistic strategies. EXplainable Artificial Intelligence (XAI) is a developing research area for investigating how models make their decisions. However, XAI methods are sensitive to feature correlations. This makes XAI challenging for high-dimensional models whose input rasters may have extensive spatial-temporal autocorrelation. Since many geospatial applications rely on complex models for target performance, a recommendation is to combine raster elements into semantically meaningful feature groups. However, it is challenging to determine how best to combine raster elements. Here, we explore the explanation sensitivity to grouping scheme. Experiments are performed on FogNet, a complex deep learning model that uses 3D Convolutional Neural Networks (CNN) for coastal fog prediction. We demonstrate that explanations can be combined with domain knowledge to generate hypotheses about the model. Meteorological analysis of the XAI output reveal FogNet’s use of channels that capture relationships related to fog development, contributing to good overall model performance. However, analyses also reveal several deficiencies, including the reliance on channels and channel spatial patterns that correlate to the predominate fog type in the dataset, to make predictions of all fog types. Strategies to improve FogNet performance and trustworthiness are presented.
Topic 13: Design patterns
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand the concept of design patterns, Evaluate various design patterns by category, Analyze the advantages of the design patterns in question, Understand how some significant patterns are used
Topic 12: Exception handling
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand the usages of exception handling, Recognize the differences between errors and exceptions, Understand the usage of try-catch-finally to achieve exception handling, Program using Java’s exception-handling syntax, Understand how assertions are used
Topic 11: Thread synchronization
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand the need for thread synchronization, Recognize basic constructs of thread synchronization, Implement synchronized solutions to problems
Topic 10: Concurrency basics[63]
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand concurrency and relevant terminology, Recognize various thread states, Recognize various problems that may arise due to incorrect organization of threads, Program using Runnable objects
Topic 9: Graphical user interfaces
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand the concept of a graphical user interface, Build graphical user interfaces and handle various events, Recognize different components such as buttons, text fields, frames
Topic 8: Interfaces
(2023-03-02) Hadimlioglu, Alihan
Objectives for this topic: Understand the concept of interfaces, Recognize the requirements of interfaces, Evaluate the differences between other polymorphic concepts and interfaces, Program using Java’s interface syntax
Topic 7: Polymorphism
(2023-03-02) Hadimlioglu, Alihan
Objectives of this topic: Understand the concept of polymorphism, Recognize the advantages of polymorphic development, Evaluate the differences between abstract and concrete classes, Use overridden methods to add more specificity to children, Program a polymorphic implementation
Topic 6: Inheritance
(2023-03-02) Hadimlioglu, Alihan
In this module, you will learn about: Inheritance, Subclasses and Superclasses, Protected Access, Method Overriding
Topic 5.3: Multidimensional arrays and arraylists
(2023-03-02) Hadimlioglu, Alihan
In this module, you will learn about: Multidimensional Arrays, Variable-length argument list, Arraylist
Topic 5.2: Constants and configuration files
(2023-03-02) Hadimlioglu, Alihan
In this module, you will learn about: Constants, Configuration Files
Topic 5.1: Arrays
(2023-03-02) Hadimlioglu, Alihan
In this module, you will learn about: Single Dimension Arrays, Arrays of Primitive Types, Arrays of Reference Types

Browse

Recent Submissions