Ensemble learning for uncertainty estimation with application to the correction of satellite precipitation products

Abstract

Predictions in the form of probability distributions are crucial for effective decision-making. Quantile regression enables such predictions within spatial prediction settings that aim to create improved precipitation datasets by merging remote sensing and gauge data. However, ensemble learning of quantile regression algorithms remains unexplored in this context and, at the same time, it has not been substantially developed so far in the broader machine learning research landscape. Here, we introduce nine quantile-based ensemble learners and address the aforementioned gap in precipitation dataset creation by presenting the first application of these learners to large precipitation datasets. We employed a novel feature engineering strategy, which reduces the number of predictors by using distance-weighted satellite precipitation at relevant locations, combined with location elevation. Our ensemble learners include six that are based on stacking ideas and three simple methods (mean, median, best combiner). Each of them combines the following six individual algorithms: quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), light gradient boosting machines (LightGBM), and quantile regression neural networks (QRNN). These algorithms serve as both base learners and combiners within different ensemble learning methods. We evaluated performance against a reference method (i.e., QR) using quantile scoring functions and a large dataset. The latter comprises 15 years of monthly gauge-measured and satellite precipitation in the contiguous United States (CONUS). Ensemble learning with QR and QRNN yielded the best results across the various investigated quantile levels, which range from 0.025 to 0.975, outperforming the reference method by 3.91% to 8.95%...

References in corpus (15)

• Using stacking to average Bayesian predictive distributions
• Higher order elicitability and Osband's principle
• The Evolution of Boosting Algorithms - From Machine Learning to Statistical Modelling
• A review of predictive uncertainty estimation with machine learning
• Regression Diagnostics meets Forecast Evaluation: Conditional Calibration, Reliability Diagrams, and Coefficient of Determination
• Merging satellite and gauge-measured precipitation using LightGBM with an emphasis on extreme quantiles
• Comparison of tree-based ensemble algorithms for merging satellite and earth-observed precipitation data at the daily time scale
• Comparison of machine learning algorithms for merging gridded satellite and earth-observed precipitation data
• Forecast Evaluation of Quantiles, Prediction Intervals, and other Set-Valued Functionals
• Hydrological post-processing for predicting extreme quantiles
• Characterizing M-estimators
• Ensemble learning for blending gridded satellite and gauge-measured precipitation data
• Uncertainty estimation of machine learning spatial precipitation predictions from satellite data
• Model Comparison and Calibration Assessment: User Guide for Consistent Scoring Functions in Machine Learning and Actuarial Practice
• Combinations of distributional regression algorithms with application in uncertainty estimation of corrected satellite precipitation products