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

Spectra Fusion of Mid-Infrared (MIR) and X-ray Fluorescence (XRF) Spectroscopy for Estimation of Selected Soil Fertility Attributes

Previous works indicate that data fusion, compared to single data modelling can improve the assessment of soil attributes using spectroscopy. In this work, two different kinds of proximal soil sensing techniques i.e., mid-infrared (MIR) and X-ray fluorescence (XRF) spectroscopy were evaluated, for assessment of seven fertility attributes. These soil attributes include pH, organic carbon (OC), phosphorous (P), potassium (K), magnesium (Mg), calcium (Ca) and moisture contents (MC). Three kinds of spectra fusion (SF) (spectra concatenation) approaches of MIR and XRF spectra were compared, namely, spectra fusion-Partial least square (SF-PLS), spectra fusion-Sequential Orthogonalized Partial least square (SF-SOPLS) and spectra fusion-Variable Importance Projection-Sequential Orthogonalized Partial least square (SF-VIP-SOPLS). Furthermore, the performance of SF models was compared with the developed single sensor model (based on individual spectra of MIR and XRF). Compared with the results obtained from single sensor model, SF models showed improvement in the prediction performance for all studied attributes, except for OC, Mg, and K prediction. More specifically, the highest improvement was observed with SF-SOPLS model for pH [R2p = 0.90, root mean square error prediction (RMSEP) = 0.15, residual prediction deviation (RPD) = 3.30, and ratio of performance inter-quantile (RPIQ) = 3.59], successively followed by P (R2p = 0.91, RMSEP = 4.45 mg/100 g, RPD = 3.53, and RPIQ = 4.90), Ca (R2p = 0.92, RMSEP = 177.11 mg/100 g, RPD = 3.66, and RPIQ = 3.22) and MC (R2p = 0.80, RMSEP = 1.91%, RPD = 2.31, RPIQ = 2.62). Overall the study concluded that SF approach with SOPLS attained better performance over the traditional model developed with the single sensor spectra, hence, SF is recommended as the best SF method for improving the prediction accuracy of studied soil attributes. Moreover, the multi-sensor spectra fusion approach is not limited for only MIR and XRF data but in general can be extended for complementary information fusion in order to improve the model performance in precision agriculture (PA) applications.

Clustering and Smoothing Pipeline for Management Zone Delineation Using Proximal and Remote Sensing

In precision agriculture (PA) practices, the accurate delineation of management zones (MZs), with each zone having similar characteristics, is essential for map-based variable rate application of farming inputs. However, there is no consensus on an optimal clustering algorithm and the input data format. In this paper, we evaluated the performances of five clustering algorithms including k-means, fuzzy C-means (FCM), hierarchical, mean shift, and density-based spatial clustering of applications with noise (DBSCAN) in different scenarios and assessed the impacts of input data format and feature selection on MZ delineation quality. We used key soil fertility attributes (moisture content (MC), organic carbon (OC), calcium (Ca), cation exchange capacity (CEC), exchangeable potassium (K), magnesium (Mg), sodium (Na), exchangeable phosphorous (P), and pH) collected with an online visible and near-infrared (vis-NIR) spectrometer along with Sentinel2 and yield data of five commercial fields in Belgium. We demonstrated that k-means is the optimal clustering method for MZ delineation, and the input data should be normalized (range normalization). Feature selection was also shown to be positively effective. Furthermore, we proposed an algorithm based on DBSCAN for smoothing the MZs maps to allow smooth actuating during variable rate application by agricultural machinery. Finally, the whole process of MZ delineation was integrated in a clustering and smoothing pipeline (CaSP), which automatically performs the following steps sequentially: (1) range normalization, (2) feature selection based on cross-correlation analysis, (3) k-means clustering, and (4) smoothing. It is recommended to adopt the developed platform for automatic MZ delineation for variable rate applications of farming inputs.