Assessment of CO2 Reduction Potential of Indoor Plants Using Artificial Neural Network in Classrooms

Abstract

Carbon dioxide gas (CO2) is one of the critical factors used to measure indoor air quality that affects the well-being of school building occupants daily. Therefore, efforts to reduce the indoor-CO2 amounts have been made by adding indoor plants to absorb the CO2. The critical knowledge is to understand the factors affecting the rate of CO2 adsorption. This research aims to study the relationship between indoor CO2 reduction using trees and environments. First, a flowerpot with snake plants is placed in a room of 24.5 m2 for the data collection of the temperature, the relative humidity, light intensity, and the amount of CO2 using sensors. Then, the data were used to create a forecast model using the Artificial Neural Network (ANN) technique, which its accuracy was 99.64%. The results showed that the snake plants could reduce 2.13% of the indoor CO2. The suitable environment for plant photosynthesis is a temperature of 25 to 30°C and relative humidity of 40% at a light intensity of 200 Lux. The results can be used as data in the design of rooms in educational institutions to effectively increase the air quality in response to building occupants' health.