A Novel Approach for Enhancing Global Water Quality Monitoring Using Satellite Images 1. Introduction Water is essential for life and ecosystems, yet only about 60% of the world's inland water bodies meet good quality standards. Traditional water quality monitoring is costly and challenging to implement on a large scale. Remote sensing provides an alternative by detecting water color changes in satellite imagery, which indicate Optically Active Water Quality Parameters (OAWQPs), such as Chlorophyll-a (Chl-a) and suspended particles, enabling efficient large-scale assessments. 2. Challenge Empirical models correlate remote sensing reflectance (Rrs) at different wavelengths with OAWQPs. However, when multiple OAWQPs affect the same wavelengths, distinguishing their contributions becomes challenging. For instance, both Chl-a and suspended particles increase Rrs at 550 nm; predicting either of these water quality parameters from the Rrs measurements is thus not straight-forward. 3. Proposed Method This study introduces an iterative modeling approach that jointly estimates multiple OAWQPs, improving model performance and interpretability. Instead of modeling each OAWQP independently, this method incorporates iterative feedback across all parameters. Initially, each OAWQP is modeled separately. In subsequent iterations, predictions from other OAWQPs serve as additional inputs, refining estimates until convergence. By integrating multiple OAWQPs, this method helps disentangle their contributions to Rrs, reducing misinterpretation. The process is akin to refining a recipe—adjusting each ingredient individually, then reviewing the overall balance to achieve the best result.