Abstract

This paper evaluates the capability of visible-near-infrared (VIS-NIR) spectroscopy to estimate soil organic carbon (SOC) at multiple depths including 0–15, 15–40, 40–60, and 60–80 cm. Four modeling algorithms, namely partial least squares regression (PLSR), principal component regression (PCR), support vector regression (SVR), and random forest (RF) were implemented calibrated to process the spectroscopy data. Overall, 120 soil samples were taken from 30 profiles at the depth of 0–80 cm. We implemented the four models considering different pre-processing techniques including Savitzky-Golay first deviation (SGD), normalization (N), and standard normal variate transformation (SNV). Results revealed that the RF model outperformed other models and the highest accuracy was reached with no pre-processing for all depths excluding 40–60 cm, where the R² and RMSE were between 0.55–0.77 and 0.75–0.84% respectively. For the depth of 40–60 cm, the maximum accuracy was observed when SGD pre-processing was applied, resulting in R²=0.73 and RMSE = 0.78%. Generally, our findings indicate that the spectral data can provide useful information to predict SOC at multiple depths.

摘要

本文评估了可见-近红外 (VIS-NIR) 光谱在 0-15、15-40、40-60 和 60-80 cm 等多个深度估计土壤有机碳 (SOC) 的能力。实施了四种建模算法，即偏最小二乘回归 (PLSR)、主成分回归 (PCR)、支持向量回归 (SVR) 和随机森林 (RF)，以处理光谱数据。总体而言，从 0-80 厘米深度的 30 个剖面中采集了 120 个土壤样品。我们实施了四个模型，考虑了不同的预处理技术，包括 Savitzky-Golay 一阶偏差 (SGD)、归一化 (N) 和标准正态变量变换 (SNV)。结果表明，RF 模型优于其他模型，并且在除 40-60 cm 以外的所有深度没有预处理的情况下达到了最高精度，其中 R²和 RMSE 分别在 0.55–0.77 和 0.75–0.84% 之间。对于 40-60 cm 的深度，当应用 SGD 预处理时观察到最大精度，导致 R ² =0.73 和 RMSE = 0.78%。一般来说，我们的研究结果表明，光谱数据可以提供有用的信息来预测多个深度的 SOC。