Comparative Analysis of Artificial Intelligence Methods for Streamflow Forecasting
Deep learning excels at managing spatial and temporal time series with variable patterns for streamflow forecasting, but traditional machine learning algorithms may struggle with complicated data, including non-linear and multidimensional complexity. Empirical heterogeneity within watersheds and lim...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
IEEE
2024
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/44862/2/Comparative%20Analysis.pdf http://ir.unimas.my/id/eprint/44862/ https://ieeexplore.ieee.org/document/10384879 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Deep learning excels at managing spatial and temporal time series with variable patterns for streamflow forecasting, but traditional machine learning algorithms may struggle with complicated data, including non-linear and multidimensional complexity. Empirical heterogeneity within watersheds and limitations inherent to each estimation methodology pose challenges in effectively measuring and appraising hydrological statistical frameworks of spatial and temporal variables. This study emphasizes streamflow
forecasting in the region of Johor, a coastal state in Peninsular Malaysia, utilizing a 28-year streamflowpattern dataset from Malaysia’s Department of Irrigation and Drainage for the Johor River and its tropical
rainforest environment. For this dataset, wavelet transformation significantly improves the resolution of
lag noise when historical streamflow data are used as lagged input variables, producing a 6% reduction
in the root-mean-square error. A comparative analysis of convolutional neural networks and artificial neural
networks reveals these models’ distinct behavioral patterns. Convolutional neural networks exhibit lower
stochasticity than artificial neural networks when dealing with complex time series data and with data
transformed into a format suitable for modeling. However, convolutional neural networks may suffer from
overfitting, particularly in cases in which the structure of the time series is overly simplified. Using Bayesian
neural networks, we modeled network weights and biases as probability distributions to assess aleatoric
and epistemic variability, employing Markov chain Monte Carlo and bootstrap resampling techniques.
This modeling allowed us to quantify uncertainty, p |
|---|