INTEGRATION OF SUPPORT VECTOR MACHINE (SVM) A MACHINE LEARNING AND REMOTE SENSING IMAGERY FOR ENHANCED WATER QUALITY ASSESSMENT: A TECHNOLOGICALLY ADVANCED APPROACH TOWARDS ENVIRONMENTAL MONITORING AND MANAGEMENT

Abstract

Water quality is a pivotal factor in ensuring the health and safety of the terrain and the individuals who rely on it. With the rise of technology and machine learning, it has become easier to assess water quality using powerful algorithms. This paper aims to classify water quality using a support vector machine (SVM) and image datasets. The SVM model is trained to classify the images as either dirty, muddy, clean, or polluted based on features extracted from the images. The performance of the model is evaluated using metrics such as accuracy and precision. In addition to the SVM model, a front-end interface is displayed using a Streamlit framework. The Streamlit framework provides an interactive way to display the model results to users. The framework allows users to upload an image and view its classification result in real time. The Streamlit framework provides a user-friendly interface, making it easy for individuals to interact with the model. Overall, this paper demonstrates the effectiveness of machine learning algorithms in classifying water quality based on image datasets. The use of a Streamlit framework provides an intuitive way to display the model results to users. This paper can serve as a starting point for further exploration in water quality assessment and can be extended to other types of classification problems. Keywords— Water quality, machine learning, classification, support vector machine (SVM), image datasets, Streamlit operation, exploration