Machine learning based pedotransfer function improves soil bulk density prediction but not for soil organic carbon stock

Abstract

Being a fundamental indicator of soil health and quality, soil bulk density (BD) plays an important role in plant growth, nutrient availability, and water retention. Due to its limited availability of BD in databases, pedotransfer functions (PTFs) has been widely used in predicting BD, while the impact of PTFs’ accuracy on soil organic carbon (SOC) stock calculation has not been explored. Herein, we proposed a local modeling approach for predicting BD across EU and UK using LUCAS Soil 2018. Our approach involved a combination of neighbor sample search, Forward Recursive Feature Selection (FRFS) and Random Forest (RF) model (local-RFFRFS). The results showed that local-RFFRFS had a good performance in predicting BD (R2 of 0.58, RMSE of 0.19 g cm-3), surpassing the traditional PTFs (R2 of 0.40-0.45, RMSE of 0.22 g cm-3) and global PTFs using RF with and without FRFS (R2 of 0.56-0.57, RMSE of 0.19 g cm-3). Interestingly, we found the best traditional PTF (R2=0.84, RMSE=1.39 kg m-2) performed close to the local-RFFRFS (R2=0.85, RMSE=1.32 kg m-2) in SOC stock calculation using BD predictions. However, the local-RFFRFS still performed better (ΔR2>0.2 and ΔRMSE>0.1 g cm-3) for soil samples with low SOC stock (<3 kg m-2). Therefore, we suggest that the local-RFFRFS is a promising method for BD prediction while traditional PTFs would be more efficient when BD is subsequently utilized for calculating SOC stock.