Smart Aquatic Terrain Mapping

Water resources are vital for sustaining ecosystems, supporting agriculture, and fulfilling the needs of human populations. Accurate measurement of water body areas, such as lakes, rivers, and wetlands, is crucial for effective water resource management, flood control, and environmental conservation. Traditional methods of water body measurement often rely on manual interpretation or simplistic thresholding techniques. However, these approaches are limited by their reliance on subjective assessments, and they struggle with issues such as image noise, seasonal variations, and the diverse characteristics of different water bodies, resulting in challenges in achieving consistent accuracy and scalability. This project explores the potential of employing Denoising Convolutional Neural Networks (DnCNN) for the precise measurement of water body areas from satellite imagery. Originally developed for image denoising, DnCNNs leverage deep learning techniques to automatically extract features and perform segmentation in complex images. By training the model on labeled satellite data, the study aims to enhance the accuracy of water body delineation and measurement while minimizing the impact of noise and variability present in satellite images. The findings demonstrate that the DnCNN approach significantly outperforms traditional methods in terms of measurement accuracy, providing more reliable results for water body area estimation. This advancement has significant implications for environmental monitoring, enabling more effective assessment of water resources and their changes over time. Ultimately, the integration of deep learning methodologies, specifically DnCNN, into water body area measurement processes represents a substantial leap forward in remote sensing capabilities, offering robust tools for researchers and policymakers dedicated to sustainable water resource management.