Abstract: Environmental monitoring using smartphones for parameter inversion is gaining increasingly popular, particularly in the field of optical active parameter inversion using visible light reflectance. This paper utilized smartphones to capture water images using polarizers, mobile phone telescopes, filters of different specifications, and 24-color standard color cards. Through stepwise regression and artificial neural network methods, we performed inverse monitoring of optical parameters (chlorophyll and turbidity) and non-optical parameters (DOC) in small water bodies in the Yangtze River Delta region. The results showed that the DOC concentration ranged from 2.73 to 16.90 mg/L, turbidity ranged from 6.53 to 91.10 NTU, and chlorophyll concentration ranged from 0.36 to 245.47 μg/L. Stepwise regression identified five image feature parameters of DOC concentration: R1', B/G2', R2'', R4'', B/G6'. Turbidity image feature parameters were B/R3', G5', R6', and chlorophyll a were B/G1', R2', B/G4'. Combined with the artificial neural network model, the water quality parameters were successfully inverted, with NSE values of 0.62 for DOC concentration, 0.65 for turbidity, and 0.67 for chlorophyll, indicating high inversion accuracy. This study established a method for inverting water quality optical parameters using smartphones and explored the feasibility of inverting non-optical parameters, providing a foundation for the development of smartphone applications and the inversion of water quality parameters.