MEAN SQUARED ERROR APPLIED IN BACK PROPAGATION FOR NON LINEAR RAINFALL PREDICTION
Abstract
Analyzing global weather forecasts is challenging and expensive. Machine learning algorithms analyze trends in weather data by adopting regression model and neural network model. Our proposed model is based on two methodologies Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) to predict rainfall. MLR determines most significant parameters of rainfall data for ANN. Mean Squared Error (MSE) generated at ANN model was back propagated to get more accurate results. The model was tested on five year (2013 to 2017) meteorological data of Bengaluru station. ANN with Back Propagation Neural Network (BPNN) was applied to forecast low rainfall, average rainfall and heavy rainfall. Performance of the model was measured by R and MSE value. Experimental result shows that back propagation of MSE and data normalization yields good results.
Downloads
References
Wassamon Phusakulkajorn, Chidchanok Lursinsap and Jack Asavanant, “Wavelet-Transform Based Artificial Neural Network For Daily Rainfall Prediction in Southern Thailandâ€, ISCIT 2009.
Mislana, Haviluddinb, Sigit Hardwinartoc, Sumaryonod and Marlon Aipassa, “Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia,†Elsevier, Procedia Computer Science 59 ( 2015 ) 142 – 151, International Conference on Computer Science and Computational Intelligence (ICCSCI 2015).
John ABBOT and Jennifer MAROHASY, “Application of Artificial Neural Networks to Rainfall Forecasting in Queensland, Australia,†ADVANCES IN ATMOSPHERIC SCIENCES, VOL. 29, NO. 4, 2012, 717–730, doi: 10.1007/s00376-012-1259-9.
Adil M Bagirov, et al., "Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach," Elsevier, Atmospheric Research (2017), doi:10.1016/j.atmosres.2017.01.003.
Harsha S, N Bhaskar, Amith Kumar, V Pujari and Nibha, “A Novel Method to Dig Information from Generic Groups of Enriched Records (DIgGER),†ResearchGate, IJCSSEIT, Vol. 5, No. 2, December 2012, pp. 243-248.
A. Troncoso, P. Ribera, G. Asencio-Cort, I. Vega and D. Gallego, “Imbalanced classiï¬cation techniques for monsoon forecasting based on a new climatic time series,†Elsevier, Environmental Modelling & Software (2017) 1-9.
Shobha N, Asha T, “Influential parameters on rainfall forecasting using multiple linear regression,†2019 JETIR February 2019, Volume 6, Issue 2 (ISSN-2349-5162).
Jiansheng Wu, Jin Long, Mingzhe Liu, “Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm,†ELSEVIER, Neurocomputing 148 (2015) 136–142.
F. Mekanik, M.A. Imteaz, S. Gato-Trinidad, A. Elmahdi, “Multiple regression and Artiï¬cial Neural Network for long-term rainfall forecasting using large scale climate modesâ€, Journal of Hydrology 503 (2013) 11–21.
Chiang, Y.M., Chang, F.J., 2009. “Integrating hydrometeorological information for rainfall–runoff modelling by artiï¬cial neural networksâ€. Hydrological Processes 23 (11), (2009) 1650–1659.
R. Shukla, K. Tripathi, A. Pandey, I. Das, “Prediction of Indian summer monsoon rainfall using nino indices: A neural network approachâ€, Atmospheric Research 102 (1-2) (2011) 99-109.
T. Mandal, V. Jothiprakash, “Short-term rainfall prediction using ANN and MT techniques â€, ISH J. of Hydraulic Engineering 18 (1) (2012) 20-26.
W. DeSarbo, W. Cron, “A maximum likelihood methodology for clusterwise linear regressionâ€, Journal of Classication, 5 (2) (1988) 249-282.
L. Garcia-Escudero, A. Gordaliza, A. Mayo-Iscar, R. San Martin, “Robust clusterwise linear regression through trimmingâ€, Computational Statistics and Data Analysis 54 (2010) 3057-3069.
http://www.imd.gov.in (Accessed on October 20, 2018)
http://www.uasbangalore.edu.in/index.php/research/agrometeorology (Accessed on March 04, 2018)
Pang-Ning Tan , Michael Steinbach , Vipin Kumar, Introduction to Data Mining, (First Edition), Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 2005
Jiawei Han and Micheline Kamber, “Data Mining Concepts and Techniques,†Second Edition, ELSEVIER Science Technology, Morgan Kaufmann, 2006, San Francisco.
The submitter hereby warrants that the Work (collectively, the “Materials”) is original and that he/she is the author of the Materials. To the extent the Materials incorporate text passages, figures, data or other material from the works of others, the undersigned has obtained any necessary permissions. Where necessary, the undersigned has obtained all third party permissions and consents to grant the license above and has all copies of such permissions and consents.
The submitter represents that he/she has the power and authority to make and execute this assignment. The submitter agrees to indemnify and hold harmless the COMPUSOFT from any damage or expense that may arise in the event of a breach of any of the warranties set forth above. For authenticity, validity and originality of the research paper the author/authors will be totally responsible.