Proximal sensor data fusion and auxiliary information for tropical soil property prediction: Soil texture

A Proximal Sensor-Based Approach for Clean, Fast, and Accurate Assessment of the Eucalyptus spp. Nutritional Status and Differentiation of Clones

“…The best prediction models were achieved using the random forest (5 times), cubist regression (3 times), support vector machine (2 times), and projection pursuit regression (1 time) algorithms. The random forest algorithm has proven to be very robust for soil nutrient prediction [ 16 , 19 , 33 ], and also for other soil attributes such as particle size distribution [ 18 ] and fertility [ 20 , 34 ].…”

“…The categorical validation showed the practical performance of the prediction models while considering the nutrient status classes. Classification models constitute an elegant solution to compensate for datasets with many outliers, or when only a mixed dataset (composed of both categorical and numerical information) is available [ 16 , 18 ]. In this sense, even B and Mg that obtained poor R 2 values (0.33 and 0.49, respectively) could be reasonably and well predicted, respectively, using categorical modeling (B, overall accuracy = 0.63, and Mg, overall accuracy = 0.70).…”

“…Despite all the variability in the dataset, general prediction models (i.e., applicable to multiple conditions and with data from different clones and plant development stages) with high accuracy may be yielded ( Figure 2 , Figure 3 and Figure 4 , and Table 3 and Table 4 ). Usually, general prediction models are not restricted by the number of samples [ 18 , 19 , 20 ], and can be extended to many different conditions.…”

“…Several studies have previously supported the applicability of this modern greentech approach for water [ 17 ], soil [ 18 , 19 , 20 ] (being already recognized as an official soil analysis method by the US Environmental Protection Agency [ 13 , 21 ]), and other vegetable matrices, such as needles, thatch, tree bark, deciduous leaves, and sapwood [ 22 , 23 , 24 , 25 ]. However, there are very few studies discussing pXRF spectrometry application for foliar analysis in the literature [ 26 , 27 , 28 , 29 ], and none of them focused specifically on Eucalyptus .…”

Multinational prediction of soil organic carbon and texture via proximal sensors

“…Models that included pXRF data (alone or combined) presented the best scores (R 2 > 0.80). Likewise, Andrade et al (2022) tested a similar approach with 464 samples in Brazil and also achieved R 2 scores > 0.80 for all texture fractions using models including pXRF data alone or combined with Vis-NIR data. pXRF was more effective in predicting soil texture (Table 5).…”