The Shuttle Radar Topographic Mission (SRTM) digital elevation model (DEM) is a widely utilized product for geological, climatic, oceanic, and ecological applications. However, the accuracy of the SRTM DEM is constrained by topography and vegetation. Using machine learning models to correct SRTM DEM with high-accuracy reference elevation observations has been proven to be useful. However, most of the reference observation-aided approaches rely on either parametric or non-parametric regression (e.g., a single machine learning model), which may lead to overfitting or underfitting and limit improvements in the accuracy of SRTM DEM products. In this study, we presented an algorithm for correcting SRTM DEM using a stacking ensemble machine learning algorithm. The proposed algorithm is capable of learning how to optimally combine the predictions from multiple well-performing machine learning models, resulting in superior performance compared to any individual model within the ensemble. The proposed approach was tested under varying relief and vegetation conditions in Hunan Province, China. The results indicate that the accuracy of the SRTM DEM productions improved by approximately 46% using the presented algorithm with respect to the original SRTM DEM. In comparison to two conventional algorithms, namely linear regression and artificial neural network models, the presented algorithm demonstrated a reduction in root-mean-square errors of SRTM DEM by 28% and 12%, respectively. The approach provides a more robust tool for correcting SRTM DEM or other similar DEM products over a wide area.

The Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) is extensively utilized in various fields, such as forestry, oceanography, geology, and hydrology. However, due to limitations in radar side-view imaging, the SRTM DEM still contains gaps and anomalies, particularly in areas with an intricate topography, like forests. To enhance the accuracy of the SRTM DEM in forested regions, commonly employed approaches include regression analysis and artificial neural networks (ANN). Nevertheless, existing regression methods struggle to accurately capture the intricate nonlinear relationship between the error and influencing factors. Additionally, traditional ANN models are susceptible to overfitting, resulting in subpar accuracy. Deep Belief Network (DBN) is a highly precise algorithm in deep learning. However, the intricate combination of hyperparameters often leads to limited generalization ability and model robustness when correcting DEM. The present study proposes an error prediction model based on the DBN optimized by Particle Swarm Optimization (PSO) for SRTM DEM correction. By utilizing the PSO algorithm, we aim to identify the optimal combination of hyperparameters of DBN, including the number of neurons in the hidden layer and the learning rates. The experiment focuses on two regions in Hunan Province, China, characterized by abundant vegetation cover. The reference data utilized for comparison is ICESat/GLAS data. The experimental results demonstrate that the mean error (ME) and root mean square error (RMSE) of the SRTM DEM corrected by the proposed algorithm in these two regions are significantly reduced by 93.5%–96.0% and 21.5%–23.5%, respectively. Moreover, there is an improvement of over 26.1% in accuracy within complex terrain areas. Specifically, in broadleaf forest, the PSO-DBN method exhibits a remarkable accuracy improvement of 26.2%, while the DBN-corrected SRTM DEM shows an improvement of 15.3%. In coniferous forest, the PSO-DBN method achieves an accuracy improvement of 14.8%, whereas the DBN-corrected SRTM DEM demonstrates a gain of 5.8%. The approach provides a more effective and robust tool for correcting SRTM DEM or other similar DEMs over vegetated mountain areas.

Near-global Digital Elevation Model (DEM) products generated through space-based radar techniques have become a basic data source for a variety range of applications. However, these DEM products often contain typical errors such as vegetation bias and topography-related errors, which impede their practical utility. Despite the development of numerous correction methods based on mathematical fitting and artificial neural networks over recent decades, reliably correcting large-scale spaceborne radar-derived DEMs remains an open challenge due to issues like underfitting or overfitting. This paper introduces a novel framework called Feature-Reinforced Ensemble Learning (FREEL) designed specifically for correcting space-based radar-derived DEMs. Within this FREEL framework, a feature derivation module and a feature reinforcement module are integrated to enhance the original input features. Subsequently, an adaptive weighting variant of the DeepForest algorithm is proposed to emphasize critical features and improve training robustness, even with limited training data. The Shuttle Radar Topographic Mission (SRTM) DEMs of Hunan Province, China, characterized by diverse surface terrain and vegetation coverage, were selected to evaluate the FREEL framework. The results indicate that the accuracy of the SRTM DEM corrected using the FREEL framework improved by 40%, surpassing several mathematical fitting and machine learning baseline algorithms by an average of 45% and 23%, respectively. This method provides a more robust solution for correcting near-global space-based radar-derived DEM products.