Highly Accurate Detection Of Ph Value And Dissolved Oxygen In Pond Water Using Underwater Microscopic Camera With Coati-Dncnn Algorithm

Abstract

Effective monitoring of water quality in pond ecosystems is crucial for maintaining aquatic life and ecological balance. In this study, we propose the application of advanced deep learning algorithms in conjunction with underwater microscopic camera technology to precisely detect pH values and dissolved oxygen levels in pond water. We evaluate three deep neural network architectures, namely, WaOA-DNCNN, PSO-DNCNN, and Coati-DNCNN, for their capability to predict these essential water quality parameters.Our findings reveal that the Coati-DNCNN algorithm outperforms the other methods, achieving an outstanding accuracy of approximately 99%. Coati-DNCNN excels in accurately predicting the pH and dissolved oxygen levels by utilizing tuned underwater images as inputs. The integration of Coati-DNCNN with machine learning techniques enhances the precision and reliability of water quality assessment, offering a valuable tool for environmental monitoring and management in pond ecosystems.This research demonstrates the potential of state-of-the-art deep learning algorithms in combination with underwater imaging technology to provide real-time, high-accuracy monitoring of pH and dissolved oxygen levels in pond water. Such advancements are pivotal for the sustainable management of aquatic environments and the preservation of aquatic ecosystems.