Abstract
Accurate rainfall measurements are essential for many applications including watershed management and hydrological modeling. This is particularly true in sub-Saharan Africa where environmental and hydro-meteorological hazards are recurrent. Microwave links have been proposed as an alternative or an additional source of measurement to the traditional rainfall measurement instruments. However, the estimation of rainfall based on microwave links relies on some assumptions and approximations which induce considerable differences between resulting rainfall estimations and ground observations. One of the major sources of errors in the process of estimating rainfall from microwave links is the determination of the adequate drop size distribution. Deep learning models have been recently proposed with satisfaction to improve rainfall estimates from microwave links of mobile telecommunication networks. But these models were built based on experimental setups and require large datasets. Moreover, base transceiver stations of mobile telecommunication networks operate with different signals resolutions, and a poor signal resolution increases the difficulty for data-driven approaches. In this paper, we propose to use machine learning techniques for rainfall estimation from microwave links based on existing infrastructures, in the context of information and technical restrictions from the mobile telecommunication network. Observations collected from four microwave links and two weather radars in the Netherlands (Western Europe) are used to build regression models for rainfall estimation using path integrated attenuations from these links, and received signals levels as explanatory variables. The results are satisfactory as the values of the coefficient of determination and the correlation coefficient between predictions and observations are up to 0.92 and 0.96, respectively. This proves that simple machine learning regressors can be successfully used to estimate rainfall using microwave links of mobile telecommunication networks, and they clearly outperform the empirical computational methods in the literature.
Similar content being viewed by others
Availability of Data and Materials
The datasets used in this work are freely available online
Code Availability
The code used to obtain the results in this study is available online
Notes
Available online at https://climate4impact.eu/.
References
Overeem A, Leijnse H, Uijlenhoet R. Country-wide rainfall maps from cellular communication networks. PNAS Environm Sci. 2013;110(8):2741–5. https://doi.org/10.1073/pnas.1217961110.
Overeem A, Leijnse H, Uijlenhoet R. Measuring urban rainfall using microwave links from commercial cellular communication networks. Water Resour Res. 2011. https://doi.org/10.1029/2010WR010350.
Upton G, Holt AR, Cummings RJ, Rahimi AR, Goddard JWF. Microwave links: The future for urban rainfall measurement? Atmospher Res. 2005;77(1–4):300–12. https://doi.org/10.1016/j.atmosres.2004.10.009.
Messer H, Zinevich A, Alpert P. Environmental monitoring by wireless communication networks. Science. 2006;312(5774):713–26. https://doi.org/10.1126/science.1120034.
Song K, Liu X, Gao T. Real-time rainfall estimation using microwave links: A case study in east china during the plum rain season in 2020. Sensors. 2021;21(3):858. https://doi.org/10.3390/s21030858.
Song K, Liu X, Gao T, He B. Rainfall estimation using a microwave link based on an improved rain-induced attenuation model. Remote Sens Lett. 2019;10(11):1057–66. https://doi.org/10.1080/2150704X.2019.1648902.
Gaona MFR, Overeem A, Raupach TH, Leijnse H, Uijlenhoet R, et al. Rainfall retrieval with commercial microwave links in são paulo, brazil. Atmospher Measur Techn. 2018;11(7):4465–76. https://doi.org/10.5194/amt-11-4465-2018.
Roversi G, Alberoni PP, Fornasiero A, Porcù F. Commercial microwave links as a tool for operational rainfall monitoring in northern italy. Atmospher Measur Techn. 2020;13(11):5779–97. https://doi.org/10.5194/amt-13-5779-2020.
David N, Liu Y, Kumah KK, Hoedjes JC, Su BZ, Gao HO. On the power of microwave communication data to monitor rain for agricultural needs in africa. Water. 2021;13(5):730. https://doi.org/10.3390/w13050730.
Kim M-S, Kwon BH. Rainfall detection and rainfall rate estimation using microwave attenuation. Atmosphere. 2018;9(8):287. https://doi.org/10.3390/atmos9080287.
Overeem A, Leijnse H, Uijlenhoet R. Rainfall monitoring using microwave links from cellular communication networks: The dutch experience. In: 2018 IEEE Statistical Signal Processing Workshop (SSP), 2018; pp. 110–114. https://doi.org/10.1109/SSP.2018.8450708. IEEE
Overeem A, Leijnse H, van Leth TC, Bogerd L, Priebe J, Tricarico D, Droste A, Uijlenhoet R. Tropical rainfall monitoring with commercial microwave links in sri lanka. Environm Res Lett. 2021;16(7): 074058. https://doi.org/10.1088/1748-9326/ac0fa6.
Sohail Afzal M, Shah SHH, Cheema MJM, Ahmad R. Real time rainfall estimation using microwave signals of cellular communication networks: a case study of faisalabad, pakistan. Hydrol Earth Syst Sci Discuss. 2018. https://doi.org/10.5194/hess-2017-740.
Špačková A, Bareš V, Fencl M, Schleiss M, Jaffrain J, Berne A, Rieckermann J. A year of attenuation data from a commercial dual-polarized duplex microwave link with concurrent disdrometer, rain gauge, and weather observations. Earth Syst Sci Data. 2021;13(8):4219–40. https://doi.org/10.5194/essd-13-4219-2021.
Andersson J, Berg P, Hansryd J, Jacobsson A, Olsson J, Wallin J. Microwave links improve operational rainfall monitoring in gothenburg, Sweden. Proc. CEST, 2017;1–4.
Liu D, Zhang Y, Zhang J, Xiong L, Liu P, Chen H, Yin J. Rainfall estimation using measurement report data from time-division long term evolution networks. J Hydrol. 2021;600: 126530. https://doi.org/10.1016/j.jhydrol.2021.126530.
Zinevich A, Messer H, Alpert P. Frontal rainfall observation by a commercial microwave communication network. J Appl Meteorol Climatol. 2009;48(7):1317–34. https://doi.org/10.1175/2008JAMC2014.1.
David N, Alpert P, Messer H. The potential of cellular network infrastructures for sudden rainfall monitoring in dry climate regions. Atmospher Res. 2013;131:13–21. https://doi.org/10.1016/j.atmosres.2013.01.004.
Fencl M, Dohnal M, Rieckermann J, Bareš V. Gauge-adjusted rainfall estimates from commercial microwave links. Hydrol Earth Syst Sci. 2017;21(1):617–34. https://doi.org/10.5194/hess-21-617-2017.
Chwala C, Gmeiner A, Qiu W, Hipp S, Nienaber D, Siart U, Eibert T, Pohl M, Seltmann J, Fritz J, Kunstmann H. Precipitation observation using microwave backhaul links in the alpine and pre-alpine region of southern germany. Hydrol Earth Syst Sci. 2012;16(8):2647–61. https://doi.org/10.5194/hess-16-2647-2012.
Overeem A, Leijnse H, Uijlenhoet R. Two and a half years of country-wide rainfall maps using radio links from commercial cellular telecommunication networks. Water Resour Res. 2016;52(10):8039–65. https://doi.org/10.1002/2016WR019412.
Zinevich A, Messer H, Alpert P. Prediction of rainfall intensity measurement errors using commercial microwave communication links. Atmospher Measur Techn. 2010;3(5):1385–402. https://doi.org/10.5194/amt-3-1385-2010.
Overeem A, Leijnse H, Uijlenhoet R. Retrieval algorithm for rainfall mapping from microwave links in a cellular communication network. Atmospher Measur Techn. 2016;9(5):2425–44. https://doi.org/10.5194/amt-9-2425-2016.
Schleiss M, Rieckermann J, Berne A. Quantification and modeling of wet-antenna attenuation for commercial microwave links. IEEE Geosci Remote Sens Lett. 2013;10(5):1195–9. https://doi.org/10.1109/LGRS.2012.2236074.
Gaona MR, Overeem A, Leijnse H, Uijlenhoet R. Sources of uncertainty in rainfall maps from cellular communication networks. Hydrol Earth Syst Sci Discuss. 2015;12(3):3289–317. https://doi.org/10.5194/hessd-12-3289-2015.
Leijnse H, Uijlenhoet R, Stricker JNM. Microwave link rainfall estimation: Effects of link length and frequency, temporal sampling, power resolution, and wet antenna attenuation. Adv Water Resour. 2008;31:1481–93. https://doi.org/10.1016/j.advwatres.2008.03.004.
Van Leth TC, Overeem A, Leijnse H, Uijlenhoet R. A measurement campaign to assess sources of error in microwave link rainfall estimation. Atmospheric Measur Techn. 2018;11(8):4645–69. https://doi.org/10.5194/amt-11-4645-2018.
Turko M, Gosset M, Kacou M, Bouvier C, Chahinian N, Boone A, Alcoba M. Rainfall measurement from commercial microwave links for urban hydrology in africa: A simulation framework for sensitivity analysis. J Hydrometeorol. 2021;22(7):1819–34. https://doi.org/10.1175/JHM-D-20-0163.1.
Doumania A. Estimation des précipitations a partir des liens microondes commerciaux de télécommunication cellulaire en afrique. PhD thesis, University of Ouagadougou. 2015.
Liberman Y, Samuels R, Alpert P, Messer H. New algorithm for integration between wireless microwave sensor network and radar for improved rainfall measurement and mapping. Atmospher Measur Techn. 2014;7:3549–63. https://doi.org/10.5194/amt-7-3549-2014.
Bianchi B, Leeuwen PJV, Hogan RJ, Berne A. A variational approach to retrieve rain rate by combining information from rain gauges, radars, and microwave links. Atmospher Measure Techn. 2013;14(6):1897–909. https://doi.org/10.1175/JHM-D-12-094.1.
Bianchi B, Rieckermann J, Berne A. Quality control of rain gauge measurements using telecommunication microwave links. J Hydrol. 2013;492:15–23. https://doi.org/10.1016/j.jhydrol.2013.03.042.
Pudashine J, Guyot A, Petitjean F, Pauwels VR, Uijlenhoet R, Seed A, Prakash M, Walker JP. Deep learning for an improved prediction of rainfall retrievals from commercial microwave links. Water Resour Res. 2020;56(7):2019–026255. https://doi.org/10.1029/2019WR026255.
Diba FD, Samad MA, Ghimire J, Choi D-Y. Wireless telecommunication links for rainfall monitoring: Deep learning approach and experimental results. IEEE Access. 2021;9:66769–80. https://doi.org/10.1109/ACCESS.2021.3076781.
Atlas D, Ulbrich CW. Path and area-integrated rainfall measurement by microwave attenuation in the 1–3 cm band. J Appl Meteorol. 1977;16(12):1322–31. https://doi.org/10.1175/1520-0450(1977)016$<$1322:PAAIRM$>$2.0.CO;2.
Olsen, R., Rogers, D., Hodge, D.: The \(ar^{b}\) relation in the calculation of rain attenuation. Transact Antennas Propag 26(2), 318–329 (1978). https://doi.org/0018-926X/78/0300-0318
Saunders SR, Aragón-Zavala A. Antennas and Propagation for Wireless Communication Systems. New Jersey: John Wiley & Sons; 2007.
Shalev-Shwartz S, Ben-David S. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, University Printing House Shaftesbury Road, Cambridge CB2 8BS, UK 2014.
Alavi A, Gandomi A, Lary D. Progress of machine learning in geosciences: Preface. Geosci Front. 2016;7:1–2. https://doi.org/10.1016/j.gsf.2015.10.006.
David JL, Amir HA, Amir HG, Annette LW. Machine learning in geosciences and remote sensing. Geosci Front. 2016;7(1):3–10. https://doi.org/10.1016/j.gsf.2015.07.003.
Parmar A, Mistree K, Sompura M. Machine learning techniques for rainfall prediction: A review. In: 2017 International Conference on Innovations in Information Embedded and Communication Systems. 2017.
Mosavi A, Ozturk P, Chau K-w. Flood prediction using machine learning models: Literature review. Water. 2018;10(11):1536. https://doi.org/10.3390/w10111536.
Sarker IH. Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2021;2(3):1–21. https://doi.org/10.1007/s42979-021-00592-x.
Pandit P, Dey P, Krishnamurthy K. Comparative assessment of multiple linear regression and fuzzy linear regression models. SN Comput Sci. 2021;2(2):1–8. https://doi.org/10.1007/s42979-021-00473-3.
Zhang C, Ma Y. Ensemble Machine Learning: Methods and Applications. Berlin/Heidelberg: Springer; 2012.
Krawczyk B, Trawiński B. Hybrid ensemble machine learning for complex and dynamic data. New Gener Comput. 2015;33(4):341–4. https://doi.org/10.1007/s00354-015-0400-6.
Jackowski K. Adaptive splitting and selection algorithm for regression. New Gener Comput. 2015;33(4):425–48. https://doi.org/10.1007/s00354-015-0405-1.
Krawczyk B. Forming ensembles of soft one-class classifiers with weighted bagging. New Gener Comput. 2015;33(4):449–66. https://doi.org/10.1007/s00354-015-0406-0.
Overeem A. Commercial microwave link data for rainfall monitoring. 4TU.ResearchData. Dataset. 2019. https://doi.org/10.4121/uuid:323587ea-82b7-4cff-b123-c660424345e5
Moraux A, Dewitte S, Cornelis B, Munteanu A. A deep learning multimodal method for precipitation estimation. Remote Sens. 2021;13(16):3278. https://doi.org/10.3390/rs13163278.
Acknowledgements
We are very grateful to Aart Overeem and the Royal Netherlands Meteorological Institute (KNMI) for providing the radar rainfall dataset and microwave link data used in this work. We really appreciated his availability for complementary information. We are also very grateful to Dr Marielle Gosset of IRD (Institut de Recherche pour le Développement) for the facilities provided in the course of this work through the SMART and DVD (Douala Ville Durable) projects.
Funding
No funding was received to assist with the preparation of this manuscript.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Kamtchoum Venceslas Evrad, Armand Nzeukou and Clémentin Tayou. The first draft of the manuscript was written by Kamtchoum Venceslas Evrad and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest
Ethics Approval
All procedures performed in this study are in accordance with the ethical standards of the Committee on Publication Ethics (COPE)
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kamtchoum, E.V., Nzeukou Takougang, A.C. & Djamegni, C.T. Using Machine Learning Techniques for Rainfall Estimation Based on Microwave Links of Mobile Telecommunication Networks. SN COMPUT. SCI. 4, 46 (2023). https://doi.org/10.1007/s42979-022-01458-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-022-01458-6