An integrated solar-induced chlorophyll fluorescence model for more accurate soil organic carbon content estimation in an Alpine agricultural area

Background and aims Solar-induced chlorophyll fluorescence (SIF) is closely related to vegetation photosynthesis and can sensitively reflect the growth and health of vegetation. Using the advantages of SIF in photosynthetic physiological diagnosis, this study carried out a collaborative study of SIF, land attrib-utes and image reflectance spectra to estimate soil organic carbon (SOC) content in typical agricultural areas of the Qinghai-Tibet plateau (QTP).Methods The spectral reflectance (R), first deriva-tive of reflectance (FDR), second derivative of reflectance (SDR) of spectral band of Landsat 8 Operational Land Imager (OLI) data were selected together with land attributes (i.e. elevation, slope, soil temperature, and soil moisture content) and SIF index and vegetation indices to establish the SOC content estimation models using the random forest (RF), back propagation neural network (BPNN) and partial least squares regression (PLSR), respectively.Results SIF index can significantly improve the SOC content estimation compared to the veg-etation indices. The accuracy of the BPNN model established by combining SIF index with the FDR of Landsat 8 OLI data and land attributes was the highest (R-2 = 0.977, RMSEC = 2.069 gmiddotkg(- 1), MAE = 0.945 gmiddotkg(- 1), RPD = 3.970, d-factor = 0.010). Conclusion This study confirmed the good effect of BPNN model driven by SIF index, land attributes, and Landsat 8 OLI data on the estimation of SOC content, which can provide a new way for the accu-rate estimation of the soil internal components in the agricultural areas.