Transferability and scaling of soil total carbon prediction models in Florida

Abstract

The applicability, transfer, and scalability of visible/near-infrared (VNIR)-derived soil models are still poorly understood. The objectives of this study in Florida, U.S. were to: (i) compare three methods to predict soil total carbon (TC) using five fields (local scale) and a pooled (regional scale) VNIR spectral dataset, (ii) assess the model's transferability among fields, and (iii) evaluate the up-and down-scaling behavior of TC prediction models. A total of 560 TC-spectral sets were modeled by Partial Least Square Regression (PLSR), Support Vector Machine (SVM), and Random Forest. The transferability and up-and down-scaling of models were limited by the following factors: (i) the spectral data domain, (ii) soil attribute domain, (iii) methods that describe the internal model structure of VNIR-TC relationships, and (iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R 2 > 0.86, bias < 0.01%, root mean square prediction error (RMSE) = 0.09%, residual predication deviation (RPD) > 2.70% , and ratio of prediction error to inter-quartile range (RPIQ) > 4.54. PLSR performed substantially better than SVM to scale and transfer models. Upscaled soil TC models performed somewhat better in terms of model fit (R 2 ), RPD, and RPIQ, whereas downscaled models showed less bias and smaller RMSE based on PLSR. Given the many factors that can impinge on empirically derived soil spectral prediction models, as demonstrated by this study, more focus on the applicability and scaling of them is needed.PeerJ PrePrints | http://dx.doi.org/10.7287/peerj.preprints.494v1 | CC-BY 4.0

Accuracy Assessment of Kriging, artificial neural network, and a hybrid approach integrating spatial and terrain data in estimating and mapping of soil organic carbon

“…Therefore, the selection of the parameters to be used in a model to determine the temporal and spatial distribution of the SOC content is very important. In addition, the relationship between the variables affecting the SOC storage is not linear but hierarchical [ 35 ]. Therefore, the ability to accurately determine the SOC spatial distribution in large areas is closely related to the relationship between the soil forming factors and the input parameters in the study area.…”