A new methodology for establishing an SOC content prediction model that is spatiotemporally transferable at multidecadal and intercontinental scales

Abstract

Quantifying and tracking the soil organic carbon (SOC) content is a key step toward long-term terrestrial ecosystem monitoring. Over the past decade, numerous models have been proposed and have achieved promising results for predicting SOC content. However, many of these studies are confined to specific temporal or spatial contexts, neglecting model transferability. Temporal transferability refers to a model’s ability to be applied across different periods, while spatial transferability relates to its applicability across diverse geographic locations for prediction. Therefore, developing a new methodology to establish a prediction model with high spatiotemporal transferability for SOC content is critically important. In this study, two large intercontinental study areas were selected, and measured topsoil (0–20 cm) sample data, 27,059 cloudless Landsat 5/8 images, digital elevation models, and climate data were acquired for 3 periods. Based on these data, monthly average climate data, monthly average data reflecting soil properties, and topography data were calculated as original input (OI) variables. We established an innovative multivariate deep learning model with high spatiotemporal transferability, combining the advantages of attention mechanism, graph neural network, and long short-term memory network model (A-GNN-LSTM). Additionally, the spatiotemporal transferability of A-GNN-LSTM and commonly used prediction models were compared. Finally, the abilities of the OI variables and the OI variables processed by feature engineering (FEI) for different SOC prediction models were explored. The results show that 1) the A-GNN-LSTM that used OI as the input variable was the optimal prediction model (RMSE = 4.86 g kg−1, R2 = 0.81, RPIQ = 2.46, and MAE = 3.78 g kg−1) with the highest spatiotemporal transferability. 2) Compared to the temporal transferability of the GNN, the A-GNN-LSTM demonstrates superior temporal transferability (ΔR2T = −0.10 vs. −0.07). Furthermore, compared to the spatial transferability of LSTM, the A-GNN-LSTM shows enhanced spatial transferability (ΔR2S = −0.16 vs. −0.09). These findings strongly suggest that the fusion of geospatial context and temporally dependent information, extracted through the integration of GNN and LSTM models, effectively enhances the spatiotemporal transferability of the models. 3) By introducing the attention mechanism, the weights of different input variables could be calculated, increasing the physical interpretability of the deep learning model. The largest weight was assigned to climate data (39.55 %), and the smallest weight was assigned to vegetation (19.96 %). 4) Among the commonly used prediction models, the deep learning model had higher prediction accuracy (RMSE = 6.64 g kg−1, R2 = 0.64, RPIQ = 1.78, and MAE = 4.78 g kg−1) and spatial transferability (ΔRMSES = 1.43 g kg−1, ΔR2S = −0.13, ΔRPIQS = −0.50, and ΔMAES = 1.09 g kg−1), and the linear model had the higher temporal transferability (ΔRMSET = 1.46 g kg−1, ΔR2T = −0.14, ΔRPIQT = −0.45, and ΔMAET = 1.29 g kg−1). 5) The deep learning models necessitated the OI, whereas the linear and traditional machine learning models necessitated FEI to achieve higher prediction accuracy. This study presents an important step forward in integrating multiple deep learning models to build a highly spatiotemporal transferability SOC prediction model.