Boosted Regression Tree Algorithm for the Reconstruction of GRACE-Based Terrestrial Water Storage Anomalies in the Yangtze River Basin

Abstract

The terrestrial water storage anomaly (TWSA) from the previous Gravity Recovery and Climate Experiment (GRACE) covers a relatively short period (15 years) with several missing periods. This study explores the boosted regression trees (BRT) and the artificial neural network (ANN) to reconstruct the TWSA series between 1982 and 2014 over the Yangtze River basin (YRB). Both algorithms are trained with several hydro-climatic variables (e.g., precipitation, soil moisture, and temperature) and climate indices for the YRB. The results from this study show that the BRT is capable of reconstructing TWSA and shows Nash–Sutcliffe efficiency (NSE) of 0.89 and a root-mean-square error (RMSE) of 18.94 mm during the test stage, outperforming ANN in about 2.3% and 7.4%, respectively. As a step further, the reliability of this technique in reconstructing TWSA beyond the GRACE era was also evaluated. Hence, a closed-loop simulation using the artificial TWSA series over 1982–2014 under the same scenarios for the actual GRACE data shows that BRT can predict TWSA (NSE of 0.92 and RMSE of 6.93 mm). Again, the BRT outperformed the ANN by approximately 1.1% and 5.3%, respectively. This study provides a new perspective for reconstructing and filling the gaps in the GRACE–TWSA series over data-scarce regions, which is desired for hydrological drought characterization and environmental studies. BRT offers such an opportunity for the GRACE Follow-On mission to predict 11 months of missing TWSA data by relying on a limited number of predictive variables, hence being adjudged to be more economical than the ANN.

Anthropogenic climate change drives non-stationary phytoplankton internal variability

“…We quantified the drivers of phytoplankton carbon biomass CoV in key ocean regions by generating an ensemble of boosted regression trees. Unlike linear models, boosted trees are able to capture non-linear interaction between the predictors and the response and have been used in a number of ecological applications (Elith et al, 2008;Roberts et al, 2016;Lamb et al, 2021;Dannouf et al, 2022;Denvil-Sommer et al, 2023). A regression tree ensemble is a predictive model composed of a weighted combination of multiple regression trees.…”