Prediction of soil bulk density in agricultural soils using mid-infrared spectroscopy

Soil bulk density (BD) is a key physical parameter in soil quality control and in the calculation from soil organic carbon (SOC) mass (g/kg) content to area stock (kg/ha). However, BD laboratory analysis is time-consuming, labour intensive and expensive, especially for a national-scale soil assessment. Hence, how to fill the omis-sions of BD values for all or some records in soil databases is widely discussed. This study employed different chemometric and machine learning algorithms to estimate BD in Irish soil from 671 horizon-based samples from MIR spectral libraries by partial least square regression (PLSR), random forest, Cubist and support vector ma-chine (SVM). The best performance was observed for the SVM model with a higher ratio of performance to interquartile distance (RPIQ = 3.61) and R2 (0.81) values and lower root mean square error of prediction (RMSEP = 0.132). Moreover, BD highly correlated wavenumber bands were determined by principal compo-nents analysis (PCA) and variable importance analysis. Soil organic matter (SOM) was identified as the primary factor in the spectral soil BD model. The generalisation error of predicting unknown samples using a spectral soil bulk density (BD) model was calculated by employing leave-one-out cross-validation (LOO-CV) on SVM. Esti-mation of BD by the spectral BD model was compared with published traditional pedo-transfer functions (PTFs), results were then compared for the overall models, different horizon types and specific depth categories. The spectral soil BD model is significantly better than traditional PTFs overall, with RMSEP equalling 0.132 g/cm3 and 0.196 g/cm3 respectively. The spectral soil BD model showed a similar accuracy on the A horizon, but considerable performance improvements were found on the other types of horizon. As for different depth cat-egories, there is no significant accuracy difference between shallow (A-Samples: 5-20 cm) and deep (S-Samples: 35-50 cm) topsoil for the spectral soil BD model, which differs from traditional PTFs. Hence, high accuracy and the homogeneity of performance on different depth layers above 50 cm could be noteworthy strengths of spectral modelling techniques when carrying out national soil surveys and large-scale carbon stock assessments.

Automated summary

Soil bulk density (BD) is an important physical parameter for soil quality control and calculation of soil organic carbon (SOC) stock. However, laboratory analysis of BD is time-consuming and expensive, making it difficult for national-scale soil assessments. This study used chemometric and machine learning algorithms to estimate BD in Irish soil based on MIR spectral libraries. The best performance was achieved with a SVM model, which had a RPIQ of 3.61, R2 value of 0.81, and RMSEP of 0.132. The spectral soil BD model outperformed traditional pedo-transfer functions overall and showed similar accuracy for the A horizon but improved performance for other horizons.