Abstract
Accurate prediction of precipitation is beneficial to many aspects of modern society, such as emergency planning, farming, and public weather forecasting. Prediction on the scale of several kilometres over forecast horizons of 0–6 h (nowcasting) is extrapolated from current weather conditions using radar and satellite observations. However, in Australia, the use of radar for nowcasting is challenging due to sparse radar coverage, particularly in regional areas. Satellite-based methods of precipitation estimation are therefore an appealing alternative; however, the ever-increasing spatial and temporal resolution of satellite data prompts investigation into options that can meet operational performance needs while also managing the large volume of data. In this chapter, the use of Artificial Neural Networks to nowcast precipitation in Australia is explored, and the current limitations of this technique are discussed. The Artificial Neural Network in this study is found to be capable of meeting or exceeding the performance of the industry-standard Hydro-Estimator method using a variety of Machine Learning metrics for the chosen verification scene. Further research is required to determine the optimal configuration of model parameters and generalisation of the model to different times and areas. This may assist Artificial Neural Networks to better reflect seasonal and orographic influences, and to meet operational performance benchmarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Australian Bureau of Meteorology. How Radar Works (2015), http://www.bom.gov.au/australia/radar/about/what_is_radar.shtml. Accessed 3 March 2015
P. May, A. Protat, A. Seed, S. Rennie, X. Wang, C. Cass et al., The use of advanced radar in the Bureau of Meteorology, presented at the International Conference on Radar (Barton, A.C.T., 2013)
J. Sun, M. Xue, J.W. Wilson, I. Zawadzki, S.P. Ballard, J. Onvlee-Hooimeyer et al., Use of NWP for nowcasting convective precipitation: recent progress and challenges, Bull. Am. Meteorol. Soc. 95, 409–426 (2014/03/01 2013)
Australian Bureau of Meteorology, Numerical Prediction Charts—Weather and Waves (2015), http://www.bom.gov.au/australia/charts/chart_explanation.shtml. Accessed 25 Aug 2015
Australian Bureau of Meteorology, Optimal Radar Coverage Areas (2015), http://www.bom.gov.au/australia/radar/about/radar_coverage_national.shtml. Accessed 1 March 2015
Australian Bureau of Meteorology, Japan launches new weather satellite (2014), http://media.bom.gov.au/releases/16/japan-launches-new-weather-satellite/. Accessed 3 March 2014
D. Jakob, A. Seed, Spatio-temporal characteristics of blended radar/gauge data and the estimation of design rainfalls, presented at the hydrology and water resources symposium 2014, 2014
S. Sinclair, G. Pegram, Combining radar and rain gauge rainfall estimates using conditional merging. Atmos. Sci. Lett. 6, 19–22 (2005)
R.J. Kuligowski, Hydro-Estimator—Technique Description (2015), http://www.star.nesdis.noaa.gov/smcd/emb/ff/HEtechnique.php. Accessed 27 Feb 2015
National Oceanic and Atmospheric Administration, STAR Satellite Rainfall Estimates—Hydro-Estimator—Digital Global Data (2014), http://www.star.nesdis.noaa.gov/smcd/emb/ff/digGlobalData.php. Accessed 30 Jan 2014
T.J. Schmit, M.M. Gunshor, W.P. Menzel, J.J. Gurka, J. Li, A.S. Bachmeier, Introducing the next-generation advanced baseline imager on GOES-R. Bull. Am. Meteorol. Soc. 86, 1079–1096 (2005)
D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning representations by back-propagating errors. Cogn. Model. vol. 5 (1988)
S. Hochreiter, Untersuchungen zu dynamischen neuronalen Netzen, Master’s thesis, Institut fur Informatik, Technische Universitat, Munchen, 1991
A.P. Engelbrecht, Computational Intelligence: An Introduction (Wiley, 2007)
G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R.R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, arXiv preprint (2012). arXiv:1207.0580
E.E. Ebert, Methods for verifying satellite precipitation estimates, in Measuring Precipitation from Space: EURAINSAT and the Future, ed. by V. Levizzani, P. Bauer, F.J. Turk (Springer, Dordrecht, The Netherlands, 2007), pp. 345–356
C.J. Willmott, K. Matsuura, Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30, 79 (2005)
M.D. Schluchter, Mean Square Error, in Wiley StatsRef: Statistics Reference Online, (Wiley, 2014)
Kaggle Inc., Root Mean Squared Error (RMSE) (2015), https://www.kaggle.com/wiki/RootMeanSquaredError. Accessed 17 March 2015
T. Chai, R. Draxler, Root mean square error (RMSE) or mean absolute error (MAE)? Geoscientific Model Dev. Discuss. 7, 1525–1534 (2014)
J.S. Armstrong, F. Collopy, Error measures for generalizing about forecasting methods: empirical comparisons. Int. J. Forecast. 8, 69–80 (1992)
Japan Meteorological Agency, Imager (AHI) (2015), http://www.data.jma.go.jp/mscweb/en/himawari89/space_segment/spsg_ahi.html. Accessed 2 March 2015
C. Dancy, J. Reidy, Statistics without maths for psychology, IEEE Statistics without maths for psychology, 2004
H.B. McMahan, G. Holt, D. Sculley, M. Young, D. Ebner, J. Grady et al., Ad click prediction: a view from the trenches, in Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, 2013, pp. 1222–1230
I.J. Goodfellow, D. Warde-Farley, P. Lamblin, V. Dumoulin, M. Mirza, R. Pascanu et al. Pylearn2: a machine learning research library, arXiv preprint (2013). arXiv:1308.4214
T. Bacastow, Understanding Spatial Fallacies (2010), https://www.e-education.psu.edu/sgam/node/214. Accessed 25 May 2010
S.S. Chen, J.A. Knaff, F.D. Marks Jr, Effects of vertical wind shear and storm motion on tropical cyclone rainfall asymmetries deduced from TRMM. Mon. Weather Rev. 134, 3190–3208 (2006)
L. Bottou, Feature Engineering (2010), http://www.cs.princeton.edu/courses/archive/spring10/cos424/slides/18-feat.pdf. Accessed 20 May 2010
I.H. Witten, E. Frank, M.A. Hall, Data Mining—Practical Machine Learning Tools and Techniques, 3rd edn. (Morgan Kaufmann, Burlington, MA, 2011)
F. Provost, Machine learning from imbalanced data sets 101, in Proceedings of the AAAI’2000 workshop on imbalanced data sets (2000), pp. 1–3
F. Fabry, I. Zawadzki, Long-term radar observations of the melting layer of precipitation and their interpretation. J. Atmos. Sci. 52, 838–851 (1995)
Centre for Australian Weather and Climate Research, Forecast Verification: Issues, Methods and FAQ (2015), http://www.cawcr.gov.au/projects/verification/. Accessed 5 Sept 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Schroeter, B.J.E. (2016). Artificial Neural Networks in Precipitation Nowcasting: An Australian Case Study. In: Shanmuganathan, S., Samarasinghe, S. (eds) Artificial Neural Network Modelling. Studies in Computational Intelligence, vol 628. Springer, Cham. https://doi.org/10.1007/978-3-319-28495-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-28495-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28493-4
Online ISBN: 978-3-319-28495-8
eBook Packages: EngineeringEngineering (R0)