Machine Learning-Assisted Multifunctional Environmental Sensing Based on Piezoelectric Cantilever

Dongsheng Li, Weiting Liu*, Boyi Zhu, Mengjiao Qu, Qian Zhang, Yongqing Fu, Jin Xie*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Downloads (Pure)


Multifunctional environmental sensing is crucial for various applications in agriculture, pollution monitoring, and disease diagnosis. However, most of these sensing systems consist of multiple sensors, leading to significantly increased dimensions, energy consumption, and structural complexity. They also often suffer from signal interferences among multiple sensing elements. Herein, we report a multifunctional environmental sensor based on one single sensing element. A MoS2 film was deposited on the surface of a piezoelectric micro-cantilever (300×1000 μm2) and used as both a sensing layer and top electrode to make full use of the changes in multiple properties of MoS2 after its exposure to various environments. The proposed sensor has been demonstrated for humidity detection, and achieved a high resolution (0.3% RH), low hysteresis (5.6%), and fast response (1 s) and recovery (2.8 s). Based on the analysis of the magnitude spectra for transmission using machine-learning algorithms, the sensor accurately quantifies temperature and CO2 concentrations in the interference of humidity with the accuracies of 91.9% and 92.1%, respectively. Furthermore, the sensor has been successfully demonstrated in real-time detections of humidity and temperature or CO2 concentrations for various applications, revealing its great potentials in human-machine interactions and health monitoring of plants and human beings.
Original languageEnglish
Pages (from-to)A-K
Number of pages11
JournalACS Sensors
Early online date15 Sept 2022
Publication statusE-pub ahead of print - 15 Sept 2022


Dive into the research topics of 'Machine Learning-Assisted Multifunctional Environmental Sensing Based on Piezoelectric Cantilever'. Together they form a unique fingerprint.

Cite this