Articles | Volume 13, issue 4
https://doi.org/10.5194/amt-13-1693-2020
https://doi.org/10.5194/amt-13-1693-2020
Research article
 | 
07 Apr 2020
Research article |  | 07 Apr 2020

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Minxing Si, Ying Xiong, Shan Du, and Ke Du

Related authors

A minimum curvature algorithm for tomographic reconstruction of atmospheric chemicals based on optical remote sensing
Sheng Li and Ke Du
Atmos. Meas. Tech., 14, 7355–7368, https://doi.org/10.5194/amt-14-7355-2021,https://doi.org/10.5194/amt-14-7355-2021, 2021
Short summary
Characterization of nighttime formation of particulate organic nitrates based on high-resolution aerosol mass spectrometry in an urban atmosphere in China
Kuangyou Yu, Qiao Zhu, Ke Du, and Xiao-Feng Huang
Atmos. Chem. Phys., 19, 5235–5249, https://doi.org/10.5194/acp-19-5235-2019,https://doi.org/10.5194/acp-19-5235-2019, 2019
Short summary
Quantification of atmospheric visibility with dual digital cameras during daytime and nighttime
K. Du, K. Wang, P. Shi, and Y. Wang
Atmos. Meas. Tech., 6, 2121–2130, https://doi.org/10.5194/amt-6-2121-2013,https://doi.org/10.5194/amt-6-2121-2013, 2013

Related subject area

Subject: Aerosols | Technique: In Situ Measurement | Topic: Validation and Intercomparisons
A 2-year intercomparison of three methods for measuring black carbon concentration at a high-altitude research station in Europe
Sarah Tinorua, Cyrielle Denjean, Pierre Nabat, Véronique Pont, Mathilde Arnaud, Thierry Bourrianne, Maria Dias Alves, and Eric Gardrat
Atmos. Meas. Tech., 17, 3897–3915, https://doi.org/10.5194/amt-17-3897-2024,https://doi.org/10.5194/amt-17-3897-2024, 2024
Short summary
Comparison of the LEO and CPMA-SP2 techniques for black-carbon mixing-state measurements
Arash Naseri, Joel C. Corbin, and Jason S. Olfert
Atmos. Meas. Tech., 17, 3719–3738, https://doi.org/10.5194/amt-17-3719-2024,https://doi.org/10.5194/amt-17-3719-2024, 2024
Short summary
Aerosol trace element solubility determined using ultrapure water batch leaching: an intercomparison study of four different leaching protocols
Rui Li, Prema Piyusha Panda, Yizhu Chen, Zhenming Zhu, Fu Wang, Yujiao Zhu, He Meng, Yan Ren, Ashwini Kumar, and Mingjin Tang
Atmos. Meas. Tech., 17, 3147–3156, https://doi.org/10.5194/amt-17-3147-2024,https://doi.org/10.5194/amt-17-3147-2024, 2024
Short summary
Field comparison of dual- and single-spot Aethalometers: equivalent black carbon, light absorption, Ångström exponent and secondary brown carbon estimations
Liangbin Wu, Cheng Wu, Tao Deng, Dui Wu, Mei Li, Yong Jie Li, and Zhen Zhou
Atmos. Meas. Tech., 17, 2917–2936, https://doi.org/10.5194/amt-17-2917-2024,https://doi.org/10.5194/amt-17-2917-2024, 2024
Short summary
Comparison of the imaginary parts of the atmospheric refractive index structure parameter and aerosol flux based on different measurement methods
Renmin Yuan, Hongsheng Zhang, Jiajia Hua, Hao Liu, Peizhe Wu, Xingyu Zhu, and Jianning Sun
Atmos. Meas. Tech., 17, 2089–2102, https://doi.org/10.5194/amt-17-2089-2024,https://doi.org/10.5194/amt-17-2089-2024, 2024
Short summary

Cited articles

Bergstra, J. and Bengio, Y.: Random Search for Hyper-Parameter Optimization, J. Mach. Learn. Res., 13, 281–305, 2012. 
CDNova Instrument Ltd.: SHARP Cost Estimate, Calgary, Canada, 2017. 
Charlson, R. J., Schwartz, S. E., Hales, J. M., Cess, R. D., Coakley, J. A., Hansen, J. E., and Hofmann, D. J.: Climate Forcing by Anthropogenic Aerosols, Science, 255, 423–430, https://doi.org/10.1126/science.255.5043.423, 1992. 
Chen, T. and Guestrin, C.: XGBoost: A Scalable Tree Boosting System, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – KDD '16, 785–794, ACM Press, San Francisco, California, USA, 2016. 
Chong, C.-Y. and Kumar, S. P.: Sensor networks: Evolution, opportunities, and challenges, Proc. IEEE, 91, 1247–1256, https://doi.org/10.1109/JPROC.2003.814918, 2003. 
Download
Short summary
The study evaluated the performance of a low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine-learning algorithms with random search techniques for the best model architectures. The two machine-learning algorithms are XGBoost and a feedforward neural network (NN).