Super ensemble learning for daily streamflow forecasting: Large-scale demonstration and comparison with multiple machine learning algorithms

TL;DR

This study demonstrates that super ensemble learning, combining ten machine learning algorithms, significantly improves daily streamflow forecasting accuracy across a large dataset of 511 basins, outperforming individual models and simpler ensemble methods.

Contribution

The paper introduces a super learning ensemble approach for daily streamflow forecasting and validates its superior performance on a large-scale dataset, advancing data-driven hydrological predictions.

Findings

Super learner improves over linear regression by 20.06%.

Neural networks are the best individual algorithm with 16.73% improvement.

Super learning outperforms equal weight ensemble and individual models.

Abstract

Daily streamflow forecasting through data-driven approaches is traditionally performed using a single machine learning algorithm. Existing applications are mostly restricted to examination of few case studies, not allowing accurate assessment of the predictive performance of the algorithms involved. Here we propose super learning (a type of ensemble learning) by combining 10 machine learning algorithms. We apply the proposed algorithm in one-step ahead forecasting mode. For the application, we exploit a big dataset consisting of 10-year long time series of daily streamflow, precipitation and temperature from 511 basins. The super learner improves over the performance of the linear regression algorithm by 20.06%, outperforming the "hard to beat in practice" equal weight combiner. The latter improves over the performance of the linear regression algorithm by 19.21%. The best performing individual machine learning algorithm is neural networks, which improves over the performance of the linear regression algorithm by 16.73%, followed by extremely randomized trees (16.40%), XGBoost (15.92%), loess (15.36%), random forests (12.75%), polyMARS (12.36%), MARS (4.74%), lasso (0.11%) and support vector regression (-0.45%). Based on the obtained large-scale results, we propose super learning for daily streamflow forecasting.