Soil Nutrient Detection for Precision Agriculture Using Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and Multivariate Regression Methods (PLSR, Lasso and GPR)

Abstract

Precision agriculture (PA) strongly relies on spatially differentiated sensor information. Handheld instruments based on laser-induced breakdown spectroscopy (LIBS) are a promising sensor technique for the in-field determination of various soil parameters. In this work, the potential of handheld LIBS for the determination of the total mass fractions of the major nutrients Ca, K, Mg, N, P and the trace nutrients Mn, Fe was evaluated. Additionally, other soil parameters, such as humus content, soil pH value and plant available P content, were determined. Since the quantification of nutrients by LIBS depends strongly on the soil matrix, various multivariate regression methods were used for calibration and prediction. These include partial least squares regression (PLSR), least absolute shrinkage and selection operator regression (Lasso), and Gaussian process regression (GPR). The best prediction results were obtained for Ca, K, Mg and Fe. The coefficients of determination obtained for other nutrients were smaller. This is due to much lower concentrations in the case of Mn, while the low number of lines and very weak intensities are the reason for the deviation of N and P. Soil parameters that are not directly related to one element, such as pH, could also be predicted. Lasso and GPR yielded slightly better results than PLSR. Additionally, several methods of data pretreatment were investigated.

Combining Laser-Induced Breakdown Spectroscopy (LIBS) and Visible Near-Infrared Spectroscopy (Vis-NIRS) for Soil Phosphorus Determination

“…Another study used PLSR for TP and plant-available P determination on 137 samples sharing the same parent material and similar textures. The authors obtained low Rv 2 values of 0.14 and 0.22 and RMSE of 80.4 and 3.3 mg kg −1 for TP and plant-available P, respectively [ 33 ]. Unfortunately, they did not report their ranges in TP and plant-available P, but only the average content of TP, which was low compared to our study.…”

“…For P, only one study tried to estimate plant-available soil P fractions by the use of multivariate calibration methods, in which not only spectral P signals but also signals from other soil elements affected the model. However, low coefficients of determination between 0.22 and 0.35 were obtained [ 33 ].…”

Application of Scikit and Keras Libraries for the Classification of Iron Ore Data Acquired by Laser-Induced Breakdown Spectroscopy (LIBS)

“…The elements can be detected whether sample is solid [1][2][3], liquid [4,5] or gas [6]. LIBS has been applied to various fields: environment [7][8][9], biomedical [10][11][12], industry [13][14][15][16], and agriculture [17][18][19]. In addition, LIBS is also used for examination of band emissions from small molecules and for detection of organic molecules [20][21][22][23][24][25].…”

Simultaneous Determination of Metal Ions in Zinc Sulfate Solution Using UV–Vis Spectrometry and SPSE-XGBoost Method

“…Therefore, the idea of variable combination is introduced into the spectrum analysis. For multivariate calibration, the commonly applied approaches are the linear method (e.g., partial least squares (PLS)) and the nonlinear modeling method (e.g., support vector machine (SVM)) [ 26 , 27 ]. At present, ensemble learning becomes a common technology to enhance the generalization ability by combining the prediction results of multiple base learners [ 28 , 29 , 30 ].…”