Browsing by Author "Runions, Adam Drew"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Efficient Calculation of Distance Transform on Discrete Global Grid Systems and Its Application in Automatic Soil Sampling Site Selection
    (2023-09-20) Kazemi, Meysam; Samavati, Faramarz Famil; Stefanakis, Emmanuel; Maleki, Farhad; Runions, Adam Drew
    Geospatial data analysis often requires the computing of a distance transform (DT) for a given vector feature. For instance, in wildfire management, it is helpful to find the distance of all points in an area from the wildfire’s boundary. Computing a distance transform on traditional Geographic Information Systems (GIS) is usually adopted from image processing methods, albeit prone to distortion resulting from flat maps. Discrete Global Grid Systems (DGGS) are relatively new low-distortion globe-based GIS that discretize the Earth into highly regular cells using multiresolution grids. In this thesis, we introduce an efficient DT algorithm for DGGS. Our novel algorithm heavily exploits the hierarchy of a DGGS and its mathematical properties and applies to many different DGGSs. We evaluate our method by comparing its distortion with the DT methods used in traditional GIS and its speed with the application of general 3D mesh DT algorithms on the DGGS grid. We demonstrate that our method is efficient and has lower distortion. To evaluate our DT algorithm further, we have used a real-world case study of selecting soil test points within agricultural fields. Multiple criteria including the distance of soil test points to different features should be considered to select representative points in a field. We show that DT can help to automate the process of selecting test points, by allowing us to efficiently calculate objectives for a representative test point. DT also allows for efficient calculation of buffers from certain features such as farm headlands and underground pipelines, to avoid certain regions when selecting the test points.
  • Thumbnail Image
    ItemOpen Access
    Evaluation of Data Sufficiency for Crop Classification Model Transfer
    (2024-12-18) Osouli, Mohammadreza; Samavati, Faramarz Famil; Runions, Adam Drew; Maleki, Farhad
    This thesis investigates the effectiveness of using varying data sizes to transfer crop type classification models from one year to the other, with a focus on balancing data sufficiency and model accuracy. The significance of crop detection through satellite imaging lies in its potential to enhance agricultural productivity and resource management. Machine learning techniques, particularly long short-term memory (LSTM) models, have become instrumental in interpreting satellite data due to their predictive accuracy and adaptability. However, applying models trained in one year to subsequent years poses challenges due to variations in environmental conditions and agricultural practices. To address these challenges, in this thesis, we explore the cost-benefit of fine-tuning existing models versus developing new ones based on the quantity of new data. Using smaller datasets for fine-tuning is more computationally efficient and reduces the cost of data collection. Experiments conducted using satellite data from farms in southern Alberta reveal that smaller datasets, with fewer than 25 fields per class, can effectively fine-tune models for accurate interannual classification, while larger datasets are more conducive to training new models. This highlights the key challenge of optimizing data usage for crop classification, balancing data sufficiency and computational efficiency. Additionally, this thesis contributes to the field by selecting the best combination of bands and information from Sentinel-1 and Sentinel-2 satellites. Another significant contribution is the incorporation of crop rotation as a feature for crop classification, which enhances the model's predictive capabilities. The findings of this research offer valuable insights for optimizing data use in crop classification, benefiting both academic research and practical agricultural applications.
  • Thumbnail Image
    ItemOpen Access
    Physically-based animation of plant motions
    (2023-06) Garcia, Alejandro; Prusinkiewicz, Przemysław; Runions, Adam Drew; Alim, Usman
    The creation of realistic and lifelike plants has been a long-standing challenge in computer graphics. While signifcant progress has been made regarding the generation of plants using procedural methods, there is still a gap in understanding how to simulate their dynamics as effciently and realistically as possible. One of the major challenges in this area is the incorporation of complicated non-inertial effects into plant motion. Previous works tend to either focus on quasistatic simulations - which by defnition assume the absence of non-inertial effects - or ignore secondary motion in their dynamics calculations altogether. Either of these result in incomplete simulations that do not adequately capture the wide range of plant motion observed in nature. This is important because the human eye is keenly critical of inconsistencies in motion, meaning that incomplete models can easily appear off-putting and uncanny. To address these limitations, this thesis proposes a generalized and comprehensive physics model that aims to better capture the dynamics of procedurally-generated plants.