New method for calibrating optical dissolved oxygen sensors in seawater based on an intelligent learning algorithm.

Area of Science:

• Environmental Science
• Sensor Technology
• Analytical Chemistry

Background:

• Luminescence quenching oxygen sensors are vital for in situ seawater measurements due to accuracy and stability.
• Conventional calibration methods for these sensors are complex, time-consuming, and require strict environmental control.
• Improving calibration efficiency and accuracy is essential for reliable dissolved oxygen monitoring.

Purpose of the Study:

• To develop and validate a new, intelligent calibration method for optical dissolved oxygen sensors in seawater.
• To overcome the limitations of conventional calibration techniques, enhancing operational simplicity and data quality.
• To demonstrate the feasibility and efficiency of an intelligent learning algorithm for sensor calibration.

Main Methods:

• Synchronous measurement of the sensor under calibration and a reference sensor deployed in seawater.
• Implementation of a calibration system with a temperature-regulated device and optimized sampling.
• Application of an intelligent learning algorithm to train calibration data and model sensor response.

Main Results:

• The new calibration method proved feasible and efficient in both laboratory and field tests.
• Intelligent learning algorithms effectively modeled the oxygen response of the optical dissolved oxygen sensor.
• The proposed method simplifies calibration operations while maintaining high accuracy.

Conclusions:

• The intelligent learning-based calibration method offers a significant advancement for optical dissolved oxygen sensors in seawater.
• This approach enhances the reliability and efficiency of in situ dissolved oxygen measurements.
• The findings are highly relevant for the development of next-generation sensors and improved oceanographic monitoring.