Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Sep 2;22(17):6638.
doi: 10.3390/s22176638.

Development and Calibration of a Low-Cost, Piezoelectric Rainfall Sensor through Machine Learning

Andrea Antonini  1 , Samantha Melani  1   2 , Alessandro Mazza  1   2 , Luca Baldini  3 , Elisa Adirosi  3 , Alberto Ortolani  1   2
Affiliations

Development and Calibration of a Low-Cost, Piezoelectric Rainfall Sensor through Machine Learning

Andrea Antonini et al. Sensors (Basel). .

Abstract

In situ measurements of precipitation are typically obtained by tipping bucket or weighing rain gauges or by disdrometers using different measurement principles. One of the most critical aspects of their operational use is the calibration, which requires the characterization of instrument responses both in laboratory and in real conditions. Another important issue with in situ measurements is the coverage. Dense networks are desirable, but the installation and maintenance costs can be unaffordable with most of the commercial conventional devices. This work presents the development of a prototype of an impact rain gauge based on a very low-cost piezoelectric sensor. The sensor was developed by assembling off-the-shelf and reused components following an easy prototyping approach; the calibration of the relationship between the different properties of the voltage signal, as sampled by the rain drop impact, and rainfall intensity was established using machine-learning methods. The comparison with 1-minute rainfall obtained by a co-located commercial disdrometer highlights the fairly good performance of the low-cost sensor in monitoring and characterizing rainfall events.

Keywords: low-cost acoustic disdrometer; machine learning; precipitation estimation; rain gauge.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Prototype architecture of the PRS.
Figure 2
Figure 2
The sensor signal (normalized amplitude) in time domain.
Figure 3
Figure 3
Block diagram of the processing for each 55 s wave file (see text for description of the blocks).
Figure 4
Figure 4
Outputs from the impact disdrometer quantities (graphs in blue) as compared with the 1-minute averaged rainfall intensity obtained by a commercial disdrometer (graph in red).
Figure 5
Figure 5
Instantaneous rainfall rate as measured by a co-located reference laser disdrometer (on top) and as estimated by the ML (DTR, RF, KNNR) approaches (from top to bottom, respectively). Data are relative to 3 May 2019.
Figure 6
Figure 6
Instantaneous rainfall rate as measured by a co-located reference laser disdrometer (on top) and as estimated by the ML (DTR, RF, KNNR) approaches (from top to bottom, respectively). Data are relative to 18 and 19 May 2019.
Figure 7
Figure 7
Instantaneous rainfall rate as measured by a co-located reference laser disdrometer (on top) and as estimated by the ML (DTR, RF, KNNR) approaches (from top to bottom, respectively). Data are relative to 27 and 28 July 2019.
Figure 8
Figure 8
Instantaneous rainfall rate as measured by a co-located reference laser disdrometer (on top) and as estimated by the ML (DTR, RF, KNNR) approaches (from top to bottom, respectively). Data are relative to 15 and 16 July 2019.
Figure 9
Figure 9
Comparison of the 1-min rainfall intensities estimated by the PRS with the reference laser disdrometer for all the two-month period (May and July).
See this image and copyright information in PMC

References

    1. Lanza L.G., Cauteruccio A., Stagnaro M. Chapter 4—Rain gauge measurements. In: Morbidelli E., editor. Rainfall. Elsevier; Amsterdam, The Netherlands: 2022. pp. 77–108. - DOI
    1. Kathiravelu G., Lucke T., Nichols P. Rain Drop Measurement Techniques: A Review. Water. 2016;1:29. doi: 10.3390/w8010029. - DOI
    1. Jameson A.R., Larsen M.L., Kostinski A.B. An example of persistent microstructure in a long rain event. J. Hydrometeorol. 2016;17:1661–1673. doi: 10.1175/JHM-D-15-0180.1. - DOI
    1. Friedrich K., Kalina E.A., Aikins J., Steiner M., Gochis D., Kucera P.A., Ikeda K., Sun J. Raindrop size distribution and rain characteristics during the 2013 Great Colorado Flood. J. Hydrometeorol. 2013;17:53–72. doi: 10.1175/JHM-D-14-0184.1. - DOI
    1. Bringi V.N., Tolstoy L., Thurai M., Petersen W.A. Estimation of spatial correlation of drop size distribution parameters and rain rate using NASA’s S-band polarimetric radar and 2D video disdrometer network: Two case studies from MC3E. J. Hydrometeorol. 2015;16:1207–1221. doi: 10.1175/JHM-D-14-0204.1. - DOI

LinkOut - more resources