Water Quality Measurement and Modelling Based on Deep Learning Techniques: Case Study for the Parameter of Secchi...

Area of Science:

• Environmental Science
• Computer Science
• Image Processing

Background:

• Secchi disk measurements are standard for water transparency but are subjective and time-consuming.
• Advancements in computer vision offer potential for more objective and efficient water quality monitoring.

Purpose of the Study:

• To develop an automated algorithm for water transparency measurement using deep learning and image processing.
• To improve the objectivity and accuracy of Secchi disk measurements.

Main Methods:

• A novel algorithm combining deep learning (resnet18, Deeplabv3+) and image processing for transparency measurement.
• Image processing isolates the Secchi disk; deep learning identifies critical positions and segments water gauge characters.

Main Results:

• The algorithm accurately classifies segmented water gauge characters and determines transparency values.
• Experimental results demonstrate superior accuracy and objectivity compared to manual Secchi disk observations.

Conclusions:

• The proposed deep learning and image processing algorithm provides an effective and objective method for water transparency assessment.
• This automated approach enhances the reliability of water quality monitoring data.