Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models

Khalil, Bahaa; Broda, Stefan; Adamowski, Jan; Ozga-Zielinski, Bogdan; Donohoe, Amanda

Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models | Prévision à court terme des niveaux d’eau souterraine sous conditions de recharge au travers de terrils miniers utilisant des modèles d’ensemble d’ondelettes et de réseaux neuronaux Pronósticos a corto plazo de niveles de agua subterránea bajo condiciones de recarga en escombreras de minas usando conjuntos de wavelet con modelos de redes neuronales 利用小波神经网络集成模型对尾矿排泄条件下地下水位进行短期 Previsão a curto prazo dos níveis de águas subterrâneas em condições de recarga de rejeitados mineiros utilizando modelos de redes neuronais conjuntos de onduletas

2015

Khalil, Bahaa | Broda, Stefan | Adamowski, Jan | Ozga-Zielinski, Bogdan | Donohoe, Amanda

Several groundwater-level forecasting studies have shown that data-driven models are simpler, faster to develop, and provide more accurate and precise results than physical or numerical-based models. Five data-driven models were examined for the forecasting of groundwater levels as a result of recharge via tailings from an abandoned mine in Quebec, Canada, for lead times of 1 day, 1 week and 1 month. The five models are: a multiple linear regression (MLR); an artificial neural network (ANN); two models that are based on de-noising the model predictors using the wavelet-transform (W-MLR, W-ANN); and a W-ensemble ANN (W-ENN) model. The tailing recharge, total precipitation, and mean air temperature were used as predictors. The ANN models performed better than the MLR models, and both MLR and ANN models performed significantly better after de-noising the predictors using wavelet-transforms. Overall, the W-ENN model performed best for each of the three lead times. These results highlight the ability of wavelet-transforms to decompose non-stationary data into discrete wavelet-components, highlighting cyclic patterns and trends in the time-series at varying temporal scales, rendering the data readily usable in forecasting. The good performance of the W-ENN model highlights the usefulness of ensemble modeling, which ensures model robustness along with improved reliability by reducing variance.

Afficher plus [+]