Enhanced Hybrid Machine Learning Algorithm for Water Quality Assessment Using Decision Tree Regression Model
Keywords:
Water-quality-assessment, environmental-monitoring,, remote-sensing, Sentinel-2- data,, fuzzy-similarity- analysis, fuzzy-logic, machine-learning,, decision- tree-regression,, real-time- monitoring,, water- resource-management.Abstract
Environmental monitoring and public health depend on a good quality of water. Historically, conventional techniques
like laboratory assessments and hand collecting have been used to evaluate water quality indicators. These methods
do, however, have some restrictions in terms of time and space, a limited scope, and drawn-out procedures and
expensive expenses. Previous studies have tried to increase estimate accuracy by merging Sentinel-2 remote sensing
data with Fuzzy Similarity Analysis, therefore obtaining over 73% accuracy using Fuzzy Logic. Though progress in
this area is commendable, real-time data processing and accurate prediction capability remain difficult. This work
suggests a hybrid machine learning-driven approach to address these problems by means of Decision Tree
Regression to evaluate water quality. Combining machine learning approaches with data from remote sensing this
proposed system improves real-time monitoring efficacy and forecast accuracy. By means of state-of- the-art sensing
technologies and data-driven algorithms, the framework detects minute variations in water quality parameters, hence
improving water resource management decision-making.
