Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models
PBN-AR
Instytucja
Wydział Instalacji Budowlanych, Hydrotechniki i Inżynierii Środowiska (Politechnika Warszawska)
Informacje podstawowe
Główny język publikacji
angielski
Czasopismo
Hydrogeology Journal
ISSN
1431-2174
EISSN
Wydawca
DOI
URL
Rok publikacji
2015
Numer zeszytu
1
Strony od-do
121-141
Numer tomu
23
Identyfikator DOI
Liczba arkuszy
1
Autorzy
(liczba autorów: 5)
Pozostali autorzy
+ 4
Słowa kluczowe
angielski
Groundwater levels
Forecasting
Groundwater recharge
Ensemble modeling
Canada
Streszczenia
Język
angielski
Treść
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 denoising 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 wavelettransforms 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 sefulness of ensemble modeling, which ensures model robustness along with improved reliability by reducing variance.
Inne
System-identifier
WUT21d3a1e868d14aae95c717ff1689ac6c
CrossrefMetadata from Crossref logo
Cytowania
Liczba prac cytujących tę pracę
Brak danych
Referencje
Liczba prac cytowanych przez tę pracę
Brak danych