Estimation of Secondary Soil Properties by Fusion of Laboratory and On-Line Measured Vis–NIR Spectra

Abstract

Visible and near infrared (vis–NIR) diffuse reflectance spectroscopy has made invaluable contributions to the accurate estimation of soil properties having direct and indirect spectral responses in NIR spectroscopy with measurements made in laboratory, in situ or using on-line (while the sensor is moving) platforms. Measurement accuracies vary with measurement type, for example, accuracy is higher for laboratory than on-line modes. On-line measurement accuracy deteriorates further for secondary (having indirect spectral response) soil properties. Therefore, the aim of this study is to improve on-line measurement accuracy of secondary properties by fusion of laboratory and on-line scanned spectra. Six arable fields were scanned using an on-line sensing platform coupled with a vis–NIR spectrophotometer (CompactSpec by Tec5 Technology for spectroscopy, Germany), with a spectral range of 305–1700 nm. A total of 138 soil samples were collected and used to develop five calibration models: (i) standard, using 100 laboratory scanned samples; (ii) hybrid-1, using 75 laboratory and 25 on-line samples; (iii) hybrid-2, using 50 laboratory and 50 on-line samples; (iv) hybrid-3, using 25 laboratory and 75 on-line samples, and (v) real-time using 100 on-line samples. Partial least squares regression (PLSR) models were developed for soil pH, available potassium (K), magnesium (Mg), calcium (Ca), and sodium (Na) and quality of models were validated using an independent prediction dataset (38 samples). Validation results showed that the standard models with laboratory scanned spectra provided poor to moderate accuracy for on-line prediction, and the hybrid-3 and real-time models provided the best prediction results, although hybrid-2 model with 50% on-line spectra provided equally good results for all properties except for pH and Na. These results suggest that either the real-time model with exclusively on-line spectra or the hybrid model with fusion up to 50% (except for pH and Na) and 75% on-line scanned spectra allows significant improvement of on-line prediction accuracy for secondary soil properties using vis–NIR spectroscopy.

Map-based site-specific seeding of seed potato production by fusion of proximal and remote sensing data

“…Table 5 presents the quality of vis-NIR spectral models obtained from PLSR for the prediction of the seven SFI. Both the cross-validation and independent validation (prediction) results showed almost similar prediction performance for all SFI, which were in agreement with previous studies although some properties (i.e., Mg and Na) showed better prediction in this study (Kuang et al, 2012;Marín-González et al, 2013;Munnaf et al, 2019). In addition, the number of latent variables (LV = 3-7) used in cross-validation in this study was relatively smaller than those of other studies (Mouazen et al, 2007;Kuang and Mouazen, 2011;Nawar and Mouazen, 2017), reflecting model's robustness.…”

Data Fusion of XRF and Vis-NIR Using Outer Product Analysis, Granger–Ramanathan, and Least Squares for Prediction of Key Soil Attributes

“…Spectroscopy is one of the methods that is becoming pervasive in PA due to its potential in evaluating the properties of soils and plants [2][3][4] provided in speedy, cost-effective, and environmentally friendly ways. Reports show that the visible and near-infrared (vis-NIR) spectroscopy is the most promising technique in PA, whose performance in prediction of primary properties is usually better than that of the secondary properties [5][6][7][8]. Another powerful method of PSS is XRF spectrometry, which is extensively used in elemental analysis [9].…”

“…effective, and environmentally friendly ways. Reports show that the visible frared (vis-NIR) spectroscopy is the most promising technique in PA, whose in prediction of primary properties is usually better than that of the seconda [5][6][7]8]. Another powerful method of PSS is XRF spectrometry, which is ext in elemental analysis [9].…”

Multi-Sensor Approach for Tropical Soil Fertility Analysis: Comparison of Individual and Combined Performance of VNIR, XRF, and LIBS Spectroscopies

“…Although VNIR, XRF, and LIBS techniques have been evaluated individually for predicting fertility attributes [16][17][18][19][20][21], the combination of these techniques is still at its early stages of development. Recent studies have evaluated different data fusion approaches for combining VNIR and XRF data for predicting fertility attributes [22][23][24].…”