A novel approach for optimizing climate features and network parameters in rainfall forecasting
- 187 Downloads
Artificial neural networks are widely applied for different forecasting applications including rainfall forecasting. The climate input features and parameters for neural networks highly affect the overall performance of the prediction model. Therefore, an appropriate approach for the selection of features and parameters is needed. In this paper, a novel approach is proposed to select the input features and neural network parameters. A hybrid genetic algorithm that combines natural reproduction and particle swarm optimization characteristics was developed to select the best input features and network parameters for each month. The developed model was compared against alternative climate and network parameters feature selection model, climate feature selection model and climatology where a better accuracy was recorded with the proposed model. The skill score against the three alternative climate models was 17.41, 21.68 and 32.12%, respectively. The aggregated time series of the proposed model showed a root-mean-square error of 141.67 mm for a location with 3553.00 mm annual average.
KeywordsRainfall forecasting Neural networks Feature selection Optimization Genetic algorithms
This study was funded by CQU Research Division.
Compliance with ethical standards
Conflict of interest
Ali Haidar declares that he has no conflict of interest. Brijesh Verma declares that he has no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Everingham YL, Clarke AJ, Chen CCM, Gorder Sv, McGuire P (2007a) Exploring the capabilities of a long lead climate forecasting system for the NSW sugar industry. In: Proceedings of the 2007 conference of the Australian society of sugar cane technologists held at Cairns, Queensland, Australia, Australian Society of Sugar Cane Technologists, Mackay, Australia, 8–11 May 2007Google Scholar
- Haidar A, Verma B (2016) A Genetic algorithm based feature selection approach for rainfall forecasting in sugarcane areas. Paper presented at the 2016 IEEE symposium series on computational intelligence, Athens, GreeceGoogle Scholar
- Nagahamulla H, Ratnayake U, Ratnaweera (2011) A Monsoon rainfall forecasting in Sri Lanka using artificial neural networks. In: 2011 6th international conference on industrial and information systems, 16–19 Aug 2011. pp 305–309. doi: 10.1109/ICIINFS.2011.6038085
- Nagahamulla H, Ratnayake U, Ratnaweera A (2012) An ensemble of artificial neural networks in rainfall forecasting. In: 2012 international conference on advances in ICT for emerging regions (ICTer), 12–15 Dec 2012. pp 176–181. doi: 10.1109/ICTer.2012.6423032
- Nagahamulla H, Ratnayake U, Ratnaweera A (2014) Selecting most suitable members for neural network ensemble rainfall forecasting model. In: Herawan T, Ghazali R, Deris MM (eds) Recent advances on soft computing and data mining: Proceedings of the first international conference on soft computing and data mining (SCDM-2014), Universiti Tun Hussein Onn Malaysia, Johor, Malaysia, 16th–18th June 2014. Springer, Cham, pp 591–601. doi: 10.1007/978-3-319-07692-8_56 Google Scholar
- Rivero CR, Patiño HD, Pucheta JA (2015) Short-term rainfall time series prediction with incomplete data. In: 2015 international joint conference on neural networks (IJCNN), 12–17 July 2015. pp 1–6. doi: 10.1109/IJCNN.2015.7280315
- Sumathi S, Surekha P (2010) Computational intelligence paradigms: theory and applications using MATLAB, vol Book, Whole. CRC Press, Boca RatonGoogle Scholar
- Zhi-liang W, Hui-hua S (2010) Rainfall prediction using generalized regression neural network: case study Zhengzhou. In: 2010 international conference on computational and information sciences (ICCIS), 17–19 Dec 2010. pp 1265–1268. doi: 10.1109/ICCIS.2010.312