Predicting plant available phosphorus using infrared spectroscopy with consideration for future mobile sensing applications in precision farming

Abstract

Phosphorus (P) fertilisation recommendations rely primarily on soil content of plant available P (P avl) that vary spatially within farm fields. Spatially optimized P fertilisation for precision farming requires reliable, rapid and non-invasive P avl determination. This laboratory study aimed to test and to compare visible-near infrared (Vis-NIR) and mid-infrared (MIR) spectroscopy for P avl prediction with emphasis on future application in precision agriculture. After calibration with the conventional calcium acetate lactate (CAL) extraction method, limitations of Vis-NIRS and MIRS to predict P avl were evaluated in loess topsoil samples from different fields at six localities. Overall calibration with 477 (Vis-NIRS) and 586 (MIRS) samples yielded satisfactory model performance (R 2 0.70 and 0.72; RPD 1.8 and 1.9, respectively). Local Vis-NIRS models yielded better results with R 2 up to 0.93 and RPD up to 3.8. For MIRS, results were comparable. However, an overall model to predict P avl on independent test data partly failed. Sampling date, pre-crop harvest residues and fertilising regime affected model transferability. Varying transferability could partly be explained after deriving the cellulose absorption index from the Vis-NIR spectra. In 62 (Vis-NIRS) and 67% (MIRS) of all samples, prediction matched the correct P avl content class. Rapid discrimination between high, optimal and low P classes could be carried out on many samples from single fields thus marking an improvement over the common practice. However, P avl determination by means of IR spectroscopy is not yet satisfactory for determination of precision fertilizer dosage. For introduction into agricultural practice, a standardized sampling protocol is recommended to help achieve reliable spectroscopic P avl prediction.

Evaluation of Near Infrared Spectroscopy (NIRS) for Estimating Soil Organic Matter and Phosphorus in Mediterranean Montado Ecosystem

“…Additionally, the RPD in our study (2.2) fits within the range of values obtained in these works (between 1.8 and 2.7). It is widely referred to in the literature that P can be indirectly detected by NIR spectroscopy if organically bound [34][35][36], which we believe is the reason for P detection in these soils. According to Morón and Cozzolino [35], the success of NIR spectroscopy in the calibration of P fractions in the soil is dependent on the selected reference method.…”

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

“…The regions between 400–600 nm and 2300–2500 nm were repeatedly selected for all the different P pools by this method ( Figure 4 b, Table S2 ). In a recent study, the most relevant variables for P models were selected based on the variable importance in the projection (VIP) method and the PLSR coefficients, similar to our study, were located around 500 and 2200–2400 nm [ 51 ]. Another study in the same year identified important Pox regions at 454–660 nm and 1732–2312 nm based on five runs of the variable selection method Generic Algorithm (GA) followed by PLSR [ 93 ].…”

Predicting the growth of lettuce from soil infrared reflectance spectra: the potential for crop management

“…Most of the few existing studies on macro nutrient prediction using portable (V)NIR/MIR spectroscopy show limited success (Wenjun et al 2014 ; Ji et al 2016a ). Poor prediction performance is commonly attributed to the absence of distinct features in the IR spectrum and varying relationships between total and available element content (Kuang et al 2012 ; Pätzoldt et al 2019 ). Consequently, the prediction models for available major and trace nutrients from soil spectra often prove to be less robust than those developed for particle size fractions and soil organic carbon.…”