Abstract
Rainfall prediction is a major problem with considerable socio-economic, industrial, and environmental impacts. The expansion of mobile telecommunication networks around the world is being used as an alternative to the declining number of rain gauges. Many researches, using those networks, have been carried out to solve water related issues in particular, and to propose hydro-meteorological applications in general. However, the possibility to use mobile telecommunications networks for rainfall prediction is still at its premises. Machine learning algorithms and techniques have been widely proven to be effective for rainfall prediction, using different geo-physical and environmental variables. In this paper, we propose to use machine learning algorithms, namely ensemble methods, to predict rainy events and their corresponding rainfall depths based on signal levels attenuations along microwave links of commercial mobile telecommunication networks. A sample of four microwave links, extracted from a dataset containing commercial microwave links data from the Netherlands, is considered. This dataset contains minimum and maximum powers received by base transceiver stations over 15-min intervals, i.e. four records per hour. A radar rainfall dataset with a spatial resolution of 1 km2, and a temporal resolution of 5 min, is used as rainfall observations. The predictions are done at two levels. First, the nature (wet or dry) of upcoming 15-min periods is predicted. Second, rainfall depths are estimated for upcoming 15-min wet periods. The results obtained show a prediction accuracy between 72% and 93% for the prediction of upcoming periods with a prediction horizon between 1 and 60 min. The correlation coefficient between predictions of rainfall depths and radar rainfall observations is between 0.70 and 0.98, and the coefficient of determination between 0.72 and 0.90. In addition, the prediction horizon can be extended up to 5 h with a prediction accuracy above 60%. These results reveal the potential of microwave links of mobile telecommunication for short-term warning systems in general, and flood prediction in particular, as our models tend to be very accurate for the prediction of heavy rainy events.
Similar content being viewed by others
Notes
Available online at https://climate4impact.eu/
References
Abrahamsen EB, Brastein OM, Lie B (2018) Machine learning in python for weather forecast based on freely available weather data. In: Linköping electronic conference proceedings, pp 169–176
Aftab S, Ahmad M, Hameed N et al (2018) Rainfall prediction using data mining techniques: a systematic literature review. Int J Adv Comput Sci Appl 9(5):143–150
Anupam S, Pani P (2020) Flood forecasting using a hybrid extreme learning machine-particle swarm optimization algorithm (elm-pso) model. Model Earth Syst Environ 6(1):341–347. https://doi.org/10.1007/s40808-019-00682-z
Atlas D, Ulbrich C W (1977) Path and area-integrated rainfall measurement by microwave attenaution in the 1-3 cm band. J Appl Meteorol 16 (12):1322–1331
Bagirov AM, Mahmood A, Barton A (2017) Prediction of monthly rainfall in victoria, australia: clusterwise linear regression approach. Atmospheric Res 188:20–29
Burlando P, Rosso R, Cadavid LG et al (1993) Forecasting of short-term rainfall using arma models. J Hydrol 144(1-4):193–211
Cerenzia I, Pincini G, Paccagnella T et al (2020) Forecast of precipitation for the 1994 flood in piedmont: performance of an ensemble system at convection-permitting resolution. Bullet Atmospher Sci Technol 1(3):319–338. https://doi.org/10.1007/s42865-020-00025-2
Chattopadhyay A, Nabizadeh E, Hassanzadeh P (2020) Analog forecasting of extreme-causing weather patterns using deep learning. J Adv Model Earth Syst 12(2):e2019MS001,958
David N, Gao HO (2016) Using cellular communication networks to detect air pollution. Environ Sci Technol 50(17):9442–9451
David N, Alpert P, Messer H (2012) Novel method for fog monitoring using cellular networks infrastructures. Atmospher Measure Tech Discuss 5:5725–5752. https://doi.org/10.5194/amtd-5-5725-2012
David N, Alpert P, Messer H (2013) The potential of commercial microwave networks to monitor dense fog-feasibility study. J Geophys Res Atmospheres 118:750–761. https://doi.org/10.1002/2013JD020346
Doumania A, Gosset M, Cazenave F et al (2014) Rainfall monitoring based on microwave links from cellular telecommunication networks:first results from a west african test bed. Geophys Res Lett, vol 41. https://doi.org/10.1002/2014GL060724
Fencl M, Rieckermann J, Schleiss M et al (2013) Assessing the potential of using telecommunication microwave links in urban drainage modelling. Water Sci Technol 68(8):1810–1818. https://doi.org/10.2166/wst.2013.429
Grover A, Kapoor A, Horvitz E (2015) A deep hybrid model for weather forecasting. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pp 379–386
Habi HV, Messer H (2018) Wet-dry classification using lstm and commercial microwave links. In: 2018 IEEE 10th sensor array and multichannel signal processing workshop (SAM), pp 149–153. https://doi.org/10.1109/SAM.2018.8448679
Harel O, David N, Alpert P et al (2015) The potential of microwave communication networks to detect dew-experimental study. IEEE J Select Topics Appl Earth Observations Remote Sensing 8(9):4396–4404. https://doi.org/10.1109/JSTARS.2015.2465909
Hernández E, Sanchez-Anguix V, Julian V et al (2016) Rainfall prediction: a deep learning approach. In: International conference on hybrid artificial intelligence systems. Springer, pp 151–162
Imhoff R, Overeem A, Brauer C et al (2020) Rainfall nowcasting using commercial microwave links. Geophys Res Lett 47(19):e2020GL089,365
Jacoby D, Ostrometzky J, Messer H (2021) Short-term prediction of the attenuation in a commercial microwave link using lstm-based rnn. In: 2020 28Th european signal processing conference (EUSIPCO), IEEE, pp 1628–1632
Kaur M, Sood SK (2020) Hydro-meteorological hazards and role of ict during 2010-2019: a scientometric analysis. Earth Sci Inf 13(4):1201–1223
Lee S, Cho S, Wong PM (1998) Rainfall prediction using artificial neural networks. J Geo Inf Decis Anal 2(2):233–242
Leijnse H, Uijlenhoet R, Stricker J (2007a) Hydrometeorological application of a microwave link: 1. evaporation. Water Resources Res, vol 43(4)
Leijnse H, Uijlenhoet R, Stricker J (2007b) Rainfall measurement using radio links from cellular communication networks. Water Res Resources, vol 43(3). https://doi.org/10.1029/2006WR005631
Linh N T T, Ruigar H, Golian S et al (2021) Flood prediction based on climatic signals using wavelet neural network. Acta Geophysica 69(4):1413–1426. https://doi.org/10.1007/s11600-021-00620-7
Manandhar S, Lee YH, Meng YS (2019) Gps-pwv based improved long-term rainfall prediction algorithm for tropical regions. Remote Sens 11(22):2643
Mandal T, Jothiprakash V (2012) Short-term rainfall prediction using ann and mt techniques. ISH J Hydraulic Eng 18(1):20–26
Marndi A, Patra G, Gouda K (2020) Short-term forecasting of wind speed using time division ensemble of hierarchical deep neural networks. Bullet Atmospher Sci Technol 1(1):91–108. https://doi.org/10.1007/s42865-020-00009-2
Messer H, Zinevich A, Alpert P (2006) Environmental monitoring by wireless communication networks. Science 312:713–726. https://doi.org/10.1126/science.1120034
Mirzaei S, Vafakhah M, Pradhan B, et al (2021) Flood susceptibility assessment using extreme gradient boosting (egb), iran. Earth Sci Inf 14 (1):51–67
Mosavi A, Ozturk P, Chau K (2018) Flood prediction using machine learning models: literature review. Water 10(11):1536
Nayak DR, Mahapatra A, Mishra P (2013) A survey on rainfall prediction using artificial neural network. Int J Comput Appl, vol 72(16)
Olsen R, Rogers D, Hodge D (1978) The arb relation in the calculation of rain attenuation. Trans Antennas Propagation AP-26 (2):318–329. https://doi.org/10.1109/TAP.1978.1141845
Overeem A (2019) Commercial microwave link data for rainfall monitoring. 4tu.researchdata. dataset. https://doi.org/10.4121/uuid:323587ea-82b7-4cff-b123-c660424345e5
Overeem A, Leijnse H, Uijlenhoet R (2011) Measuring urban rainfall using microwave links from commercial cellular communication networks. Water Resources Res 47:W12,505. https://doi.org/10.1029/2010WR010350
Overeem A (2013) Country-wide rainfall maps from cellular communication networks. PNAS Environ Sci. https://doi.org/10.1073/pnas.1217961110, Uijlenhoet R
Overeem A, Leijnse H, Uijlenhoet R (2016a) Retrieval algorithm for rainfall mapping from microwave links in a cellular communication network. Atmospher Measure Techniq 9(5):2425–2444
Overeem A, Leijnse H, Uijlenhoet R (2016b) Two and a half years of country-wide rainfall maps using radio links from commercial cellular telecommunication networks. Water Resour Res 52(10):8039–8065
Overeem A, Leijnse H, van Leth TC et al (2021) Tropical rainfall monitoring with commercial microwave links in sri lanka. Environ Res Lett 16(7):074,058. https://doi.org/10.1088/1748-9326/ac0fa6
Parmar A, Mistree K, Sompura M (2017) Machine learning techniques for rainfall prediction: a review. In: International conference on innovations in information embedded and communication systems
Polz J, Chwala C, Graf M et al (2020) Rain event detection in commercial microwave link attenuation data using convolutional neural networks. Atmospher Meas Tech 13 (7):3835–3853. https://doi.org/10.5194/amt-13-3835-2020, https://amt.copernicus.org/articles/13/3835/2020/. Accessed 02 Sept 2021
Pudashine J, Guyot A, Petitjean F et al (2020) Deep learning for an improved prediction of rainfall retrievals from commercial microwave links. Water Resources Res 56(7):e2019WR026,255. https://doi.org/10.1029/2019WR026255
Qiu M, Zhao P, Zhang K et al (2017) A short-term rainfall prediction model using multi-task convolutional neural networks. In: 2017 IEEE international conference on data mining (ICDM), IEEE, pp 395-404
Refonaa J, Lakshmi M, Abbas R, et al (2019) Rainfall prediction using regression model. Int J Recent Technol Eng (IJRTE) 8(2S3):543–546
Rios Gaona M, Overeem A, Leijnse H et al (2015) Measurement and interpolation uncertainties in rainfall maps from cellular communication networks. Hydrol Earth Syst Sci 19(8):3571–3584
Roy V, Gishkori S, Leus G (2016) Dynamic rainfall monitoring using microwave links. EURASIP J Adv Signal Process, 77(1-17). https://doi.org/10.1186/s13634-016-0367-6
Shi X, Gao Z, Lausen L et al (2017) Deep learning for precipitation nowcasting: a benchmark and a new model. arXiv:170603458
Sumi SM, Zaman MF, Hirose H (2012) A rainfall forecasting method using machine learning models and its application to the fukuoka city case. Int J Appl Math Comput Sci 22:841–854
Toth E, Brath A, Montanari A (2000) Comparison of short-term rainfall prediction models for real-time flood forecasting. J Hydrol 239(1-4):132–147
Upton G, Holt A, Cummings R et al (2005) Microwave links: the future for urban rainfall measurement? Atmos Res 77(1-4):300–312. https://doi.org/10.1016/j.atmosres.2004.10.009
Van het Schip T, Overeem A, Leijnse H, et al (2017) Rainfall measurement using cell phone links: classification of wet and dry periods using geostationary satellites. Hydrol Sci J 62(9):1343–1353
Vieira AC, Garcia G, Pabón RE et al (2021) Improving flood forecasting through feature selection by a genetic algorithm–experiments based on real data from an amazon rainforest river. Earth Sci Inf 14(1):37–50
Yen MH, Liu DW, Hsin YC et al (2019) Application of the deep learning for the prediction of rainfall in southern taiwan. Sci Reports 9(1):1–9
Zainudin S, Jasim DS, Bakar AA (2016) Comparative analysis of data mining techniques for malaysian rainfall prediction. Int J Adv Sci Eng Inf Technol 6(6):1148–1153
Zhang CJ, Wang HY, Zeng J et al (2020) Tiny-rainnet: a deep convolutional neural network with bi-directional long short-term memory model for short-term rainfall prediction. Meteorol Appl 27(5):e1956
Zhao Q, Liu Y, Yao W et al (2021) Hourly rainfall forecast model using supervised learning algorithm. IEEE Trans Geosci Remote Sens 60:1–9. https://doi.org/10.1109/TGRS.2021.3054582
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 the availability of Aart Overeem 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.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
All procedures performed in this study are in accordance with the ethical standards of the Committee on Publication Ethics (COPE).
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
42865_2022_47_MOESM1_ESM.pdf
The microwave links and radar rainfall datasets used in this work are freely available, and can be downloaded respectively at https://data.4tu.nl/articles/dataset/Commercial_microwave_link_data_for_rainfall_monitoring/12688253/1and https://climate4impact.eu/.
Supplementary file 1 (pdf 182 KB)
Rights and permissions
Springer Nature or its licensor 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., Takougang, A.C.N. & Djamegni, C.T. Short-term rainfall prediction using MLA based on commercial microwave links of mobile telecommunication networks. Bull. of Atmos. Sci.& Technol. 3, 5 (2022). https://doi.org/10.1007/s42865-022-00047-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42865-022-00047-y