Image Processing Techniques for Water Droplet Penetration Time and Contact Angle Estimation

Water droplet behavior on soil surfaces plays a critical role in numerous environmental processes, including soil erosion, hydrological dynamics, and ecosystem health. Accurate characterization of soil water repellency, quantified by parameters such as water droplet penetration time (WDPT) and contact angles (WDCA), is essential for informed decision-making in agricultural management, forestry practices, and land-use planning. Despite the significance of these parameters, challenges exist in reliably estimating them due to the complex and dynamic nature of soil-water interactions. This thesis address challenges in estimating WDPT and WDCA, by leveraging state-of-the-art image processing techniques and machine learning algorithms. The research focuses on advancing our understanding of water droplet interactions with soil surfaces and developing accurate methods for estimating WDPT and contact angles. Specifically, the thesis explores the utilization of deep machine learning models, such as the Yolov8 instance segmentation model, for water droplet detection, followed by the application of various deep learning methods for WDPT and contact angle estimation. The methodology involves the collection of an extensive dataset comprising over 200 samples of water droplets interacting with different soil textures and types. Through rigorous experimentation and model training, the research achieves a remarkable accuracy of 90% in distinguishing between drowning and fully submerged droplets. Comparative analysis with existing techniques further validates the effectiveness of the proposed methodologies. For Water Droplet Penetration Time (WDPT) and Water Droplet Contact Angle (WDCA), the study demonstrates an error rate below 15% when compared to ground truth data, ensuring the reliability and precision of the approach in analyzing soil-water interactions. The findings of this study have significant implications for environmental science, hydrological modeling, and agricultural sustainability. By providing reliable tools for characterizing soil water repellency, the research contributes to enhancing environmental management practices and informed decision-making in various fields.