A Real-time soil sensor (RTSS) can be predicted soil parameters using near-infrared underground soil reflectance sensor in commercial farms.

The soil parameters that RTSS could predict was moisture content (MC), soil organic matter (SOM), pH, nitrate nitrogen (NN), total nitrogen (TN) and total carbon (TC).

Actually, detailed soil maps of phosphorus, potassium and other soil parameters are necessary to perform site-specific soil management in a farm.

The objective of this study was to investigate the potential of near-infrared reflectance spectroscopy (NIRS) to estimate available phosphate (P-a), phosphorus absorptive coefficient (PAC), solube nitrogen (N-s), soil ammonium nitrogen (N-a), electrical conductivity (EC), and cation exchange capacity (CEC)  content in an alluvial soil.

The experiment field is a commercial farm in Memuro-cho, Hokkaido, Japan. The cultivation system is five crops for five years: wheat - sugar beet - soy bean - potato - green manure.

The results were developed by using partial least squares regression (PLSR) coupled with the full cross-validation technique. For calibration purposes of the PLSR, a total of 144 soil samples and near-infrared soil reflectance spectra (including the visible range, 350 to 1700 nm, 5-nm intervals) were collected from same underground position in the field (8.94ha). To reduce the noise and enhance the weak signals, Vis-NIR soil reflectance spectra were subjected to smoothing and the second derivative treatment (Savitzky-Golay).

Furthermore, we show the detailed soil map which is necessary for site-specific soil management with DGPS data.