Artificial Intelligence-Aided Low Cost and Flexible Graphene Oxide-Based Paper Sensor for Ultraviolet and Sunlight...

Area of Science:

• Materials Science
• Sensor Technology
• Nanotechnology

Background:

• Growing concern over the adverse effects of ultraviolet (UV) radiation necessitates advanced monitoring solutions.
• Existing UV sensors often lack cost-effectiveness, flexibility, or biodegradability, limiting widespread application.
• Graphene oxide (GO) presents promising optoelectronic properties for novel sensor development.

Purpose of the Study:

• To develop and characterize a novel, low-cost, and flexible graphene oxide (GO)-based paper sensor for quantifying UV and solar energy exposure.
• To investigate the sensor's response to UV and solar radiation using a simple colorimetric analysis.
• To explore the use of an artificial neural network (ANN) for accurate digital readout of UV exposure levels.

Main Methods:

• Incorporation of graphene oxide (GO) into standard cellulose paper using a cost-effective fabrication technique.
• Exposure of the GO-based paper sensor to UV and solar radiation.
• Color change analysis of the sensor to determine UV/solar energy levels.
• Development and application of an artificial neural network (ANN) model to correlate color intensity with exposure time.

Main Results:

• The developed GO-based paper sensor exhibits a discernible color change upon exposure to UV and solar radiation.
• A simple color analysis application allows for easy determination of received UV or solar energy.
• The artificial neural network (ANN) model achieved a high accuracy of 96.83% in correlating color intensity with UV exposure time.
• The sensor demonstrated disposable, cost-effective, biodegradable, and flexible characteristics.

Conclusions:

• A novel, low-cost, and flexible graphene oxide (GO)-based paper sensor has been successfully developed for UV and solar exposure monitoring.
• The sensor offers a user-friendly method for quantifying UV energy through simple color analysis, enhanced by an accurate ANN model.
• The disposable and biodegradable nature of the sensor makes it a sustainable and attractive option for diverse sensing applications, paving the way for efficient GO-based photosensors.