Multivariate prediction of soil aggregate-associated organic carbon by simulating satellite sensor bands

• Published in: Computers and electronics in agriculture 2023-06, Vol.209, p.107859, Article 107859
• Main Authors: Gao, ChunRui, Yan, XiaoBin, Qiao, XingXing, Wei, KunXi, Zhang, XiaoMei, Yang, Sha, Wang, Chao, Yang, WuDe, Feng, MeiChen, Xiao, LuJie, Zhang, MeiJun, Zhang, Zhou, Shafiq, Fahad, Song, XiaoYan
• Format: Article
• Language: English
• Subjects: Multivariate methods; Organic carbon; Resampling; Simulated bands; Soil aggregates; Spectral index
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2023.107859

•Applying spectral resampling method to simulate the multi-sources satellite bands.•Constructed three-band indexes were high related with SAOC.•Evaluating the three calibrated methods on predicting SAOC. Soil aggregate-associated organic carbon (SAOC) is critical for maintaining soil quality and environmental health. To realize non-destructive and potentially applicable assessments on SAOC by using the hyperspectral technology, the resampling method was adopted to simulate the different satellites bands and the three multivariate methods of support vector machine (SVM), back propagation neural network (BPNN) and random forest (RF) were also implemented to calibrate the predictive models on SAOC. The results showed that the computed Three-band index 2 (TBI2) was proved to be highly related to both soil micro- and macroaggregate-associated organic carbon (OC) among all spectral indexes, and the highest correlation coefficient (R = −0.443) was obtained between the microaggregate-associated OC and TBI2 derived from the simulated bands 7, 4, 10 of Sentinel-2 satellite. For the macroaggregate-associated OC, the good correlation (R = −0.422) was also acquired with TBI2 which was constructed by using the simulated bands 7, 6, and 1 from the Sentinel-2 satellite. The calibrated models show that accepted accuracy for microaggregate-associated OC was achieved with R2 = 0.773, RMSE = 0.853, RPD = 1.808, and it outperformed than macroaggregates model (R2 = 0.709; RMSE = 0.969, RPD = 1.255) which was limited in the practical application with lower predictive accuracy. The results of correlation analysis and multivariate models performance indicated that the microaggregate-associated OC is highly related to responding to the spectral band simulated with different satellites than macroaggregates. This study provides a possible way to link the hyperspectral and remote sensing satellites, and open up opportunity for large-scale estimation on SAOC.