Wavelet Random Forest Research Articles

Development of an indirect method for modelling the water footprint of electricity using wavelet transform coupled with the random forest model

ABSTRACT Hydropower is essential for global electricity production, but it consumes water by evaporation from the reservoir surface. Here, a new approach is introduced in relation to modelling the water footprint of electricity (WFe) from hydropower. Two of the most important variables in calculating the WFe are volume of evaporation (EV) and electricity production (EP). In this study, the random forest (RF) model was used to predict both EV and EP. For analysing hybrid models, wavelet transform was used and wavelet RF (WRF) models were developed. After decomposing the input variables by wavelet transform, the relief algorithm (RA) was used to recognize important components and inserted into the RF model. The proposed approach was applied at Mahabad Hydropower in Iran. The results suggest that applying the wavelet transform on input data and using algorithms such as RA can be regarded as a good approach for modelling of EV and EP.

Improving the North American multi-model ensemble (NMME) precipitation forecasts at local areas using wavelet and machine learning

Seasonal precipitation forecasts at regional or local areas can help guide agricultural practice and urban water resource management. The North American multi-model ensemble (NMME) is a seasonal forecasting system providing precipitation forecasts globally. Bias correction and downscaling of the NMME is a critical step before applied at local scales. Here, the machine learning methods coupling with wavelet are used to correct the precipitation forecasts in NMME for 518 meteorological stations in China for eight models at 0.5–8.5 months leads. Compared with the traditional quantile mapping (QM) approach, the wavelet support vector machine (WSVM) and wavelet random forest (WRF) methods exhibit obvious advantage in downscaling, with an overall average improvement of Pearson’s correlation coefficient increasing by 0.05–0.3 and root mean square error (RMSE) reducing by 18–40 mm (21–33%) for individual models. Both the spatial and seasonal patterns of downscaled results demonstrate the superiority of wavelet machine learning methods over QM. A spatial analysis indicates that the corrected NMME precipitation forecasts show the best skill in South China, with an average RMSE of about 30 mm, while the worst skill in Central and Southwest China with a RMSE of 80 mm. In spite of the correction, the uncertainties of seasonal precipitation forecasts in summer and extreme wet cases are still large. However, the WSVM and WRF methods may serve as an effective tool in the bias correction of NMME precipitation forecasts.

Improving the performance of the mass transfer-based reference evapotranspiration estimation approaches through a coupled wavelet-random forest methodology

Among different reference evapotranspiration (ETo) modeling approaches, mass transfer-based methods have been less studied. These approaches utilize temperature and wind speed records. On the other hand, the empirical equations proposed in this context generally produce weak simulations, except when a local calibration is used for improving their performance. This might be a crucial drawback for those equations in case of local data scarcity for calibration procedure. So, application of heuristic methods can be considered as a substitute for improving the performance accuracy of the mass transfer-based approaches. However, given that the wind speed records have usually higher variation magnitudes than the other meteorological parameters, application of a wavelet transform for coupling with heuristic models would be necessary. In the present paper, a coupled wavelet-random forest (WRF) methodology was proposed for the first time to improve the performance accuracy of the mass transfer-based ETo estimation approaches using cross-validation data management scenarios in both local and cross-station scales. The obtained results revealed that the new coupled WRF model (with the minimum scatter index values of 0.150 and 0.192 for local and external applications, respectively) improved the performance accuracy of the single RF models as well as the empirical equations to great extent.