Flood forecasting using a hybrid extreme learning machine-particle swarm optimization algorithm (ELM-PSO) model
- 5 Downloads
Flood forecasting in India is carried out by the determination of the water level at flood-forecasting stations. The level forecasts are issued once water levels in a station reach a predefined warning level, which helps local authorities to determine response measures to the floods. A new approach has been explored in this paper, which involves using the mean daily gauge heights, mean daily rainfall, and the mean daily river discharge values of prior days to forecast the mean gauge heights up to 4 days in advance. These features were used as input for an extreme learning machine (ELM) regression model. The number of units in the ELM was optimized to obtain the maximum coefficient of determination using the particle swarm optimization algorithm (PSO) to create a hybrid ELM-PSO model. Gauge, rainfall, and discharge data of 4 decades from the Jenapur flood-forecasting station (Brahmani river, Odisha) and the Anandpur station (Baitarani river, Odisha) were used to create models for mean gauge height prediction. These models were then cross-validated using tenfold cross-validation, with mean-squared error (MSE) and the coefficient of determination (R-squared) as parameters for evaluation of the models. The models show promising results, with the 1-day-in-advance model having MSE 0.14 and R-squared 0.85 for Jenapur and MSE 0.23 and R-squared 0.75 for Anandpur.
KeywordsFlood forecasting Machine learning Optimization Extreme learning machine Particle swarm optimization
We are grateful to the Central Water Commission (CWC) and the Odisha State Disaster Management Authority (OSDMA) for their support in acquiring the river system data. We would also like to thank the Department of Science and Technology of the Government of India, the Indo-US Science and Technology Forum, and Intel India, the organizers of IRIS 2018, where this study was initially presented. We would also like to thank the Society for Science and the Public, organizers of ISEF 2019, held at Phoenix, Arizona, where this study was presented as well.
- Amarnath G, Alahacoon N, Gismalla Y, Mohammed Y, Sharma BR, Smakhtin V (2016) Increasing early warning lead time through improved transboundary flood forecasting in the Gash river basin, Horn of Africa. In: Flood forecasting. Elsevier, pp 183–200. https://doi.org/10.1016/B978-0-12-801884-2.00008-6 CrossRefGoogle Scholar
- Central Water Commission (2015) Policy and Advisory Technical Assistance 8089 IND Phase II—operational research to support mainstreaming of integrated flood management under climate change. (Vol. 2., Basin Flood Management Plan Brahmani-Baitarani, Odisha). http://mowr.gov.in/sites/default/files/NWM_OR-FM-CC_2015_Vol-2_0.pdf
- Central Water Commission (2019) Standard operating procedure for flood forecasting, April 2019. http://cwc.gov.in/sites/default/files/admin/SOP_ff_apr_19.pdf
- Faris H, Aljarah I, Mirjalili S, Castillo PA, Guervós JJM (2016) EvoloPy: an open-source nature-inspired optimization framework in Python. In: IJCCI (ECTA), pp 171–177. https://www.scitepress.org/Papers/2016/60482/60482.pdf
- Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations (ICLR). arXiv:1412.6980
- Liong S-Y, Sivapragasam C (2002) Flood stage forecasting with support vector machines. J Am Water Resour Assoc 38(1):173–186. https://doi.org/10.1111/j.1752-1688.2002.tb01544.x CrossRefGoogle Scholar
- Liu T, Ding Y, Cai X, Zhu Y, Zhang X (2017) Extreme learning machine based on particle swarm optimization for estimation of reference evapotranspiration. In: 2017 36th Chinese control conference (CCC), pp 4567–4572. IEEE. https://doi.org/10.23919/ChiCC.2017.8028076
- Parsaie A, Yonesi H, Najafian S (2017b) Prediction of flow discharge in compound open channels using adaptive neuro fuzzy inference system method. Flow Meas Instrum 54:288–297. https://doi.org/10.1016/j.flowmeasinst.2016.08.013 CrossRefGoogle Scholar