Digi-Nose Part 2: Enhancing Accuracy and Efficiency of a Digital Nose System With Sensor Technology for Early Detection of Changes in the Forest

The detection of forest health has become significant for maintaining the forest environment, especially now in the time of increasing ecological stressors. The objective of this project is to design an electronic nose (e-nose) using metal-oxide (MOx) gas sensors to be able to distinguish between healthy and stressed trees by detecting unique volatile organic components (VOCs). The project involved the development and implementation of a gas sensor array, combining multiple MOx sensors, to detect VOCs. Taking advantage of the Arduino microcontroller, data was able to be received from gas sensors, while Python was utilized for data analysis. Data analysis involved machine learning methods, such as Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), for classification and dimensionality reduction of the sensor data. Python also came in handy for the creation of graphical user interfaces. The capacity of the e-noses to differentiate between healthy and sick trees was demonstrated in the initial results, where it showed a reasonable level of accuracy. Initially, PCA provided good separation, however, with an increased number of target gases, the separation accuracy deteriorated. The LDA provided a clear separation between two classes, with slight overlaps. The e-nose was further assessed for different substances that may be present in stressed trees. Although it has shown the good separability of some substances, others overlapped. The great sensitivity of the MOx sensor comes with a cost of selectivity for different gases. Future research will focus on detecting these specific substances contained in the tree’s odor using a neural network, enhancing the electronic nose’s ability to detect a wider range of compounds.