The data and findings discussed here come from the cited paper and do not represent test results from VISPEK equipment.
By adding a known proportion of urea to the soil, the response of the spectrum to changes in the proportion can be examined; however, this is still far from the measurement of natural nitrogen status in the field. This study compares derivative treatments and regression performance across multiple soil types, focusing on whether relationships in formulated samples hold on validation data.
Summary
This study prepared dry mixed samples with different urea ratios for multiple types of soil, and established a near-infrared reflectance PLSR model using the weighing addition ratio as a label. Derivative processing improved some verification results, but the calibration performance was not fully maintained. The target is a high nominal urea ratio, which does not equate to naturally available nitrogen, and changes in homogenization and drying are not directly reflected by the label.
(AI-generated conceptual illustration for context; it is not data from the paper, a photograph of the research equipment, or a VISPEK product diagram.)
Why It Matters
A high proportion of urea mixed soil demonstrates the response in a controlled matrix, providing proof of principle before moving into real soil concentrations.
Methods and Reference Measurements
Six Italian soil/commercial Japanese volcanic soil, passed through a 2mm sieve and dried at 85°C for 48 hours; 8-9 urea ratio for each type, 0-17.5/20%, a total of 50 mixed samples, added water to homogenize for seven days and then controlled drying. 1100–1700nm reflection probe, four times average, the reference is the nominal addition ratio of weighing rather than chemical nitrogen measurement after mixing. SG/first and second derivatives, PCA and PLSR, SPXY sub-calibration verification; the actual optical path is not reported.
Wavelengths and Acquisition Parameters
| Band/parameter | Original meaning and usage instructions |
|---|---|
| 1100–1700 nm | The actual micro spectrometer range is 128 yuan InGaAs; the NIST1100–2500nm chart is for reference only. |
| 1490、1520 nm | This study focuses on the spectral peaks added with a high proportion of urea; it cannot be used as an exclusive measurement channel for all natural soil nitrogen. |
Key Findings
The first-order derivative verification R²0.77, RPD2.06, the second-order derivative 0.65/1.77; the calibration R²>0.9 is not maintained until verification. The model range is well above common soil nitrogen backgrounds.
Limitations and Interpretation
Nominal urea mass percent varies from naturally available nitrogen; drying and seven-day homogenization may cause chemical changes not captured by the weighing label.
Image copyright belongs to the paper’s original authors. License: CC BY 4.0.
Source Paper
Crescini D, Mascialino G, Moggia N, Piubeni G, Serpelloni M, Sardini E. (2025). PCA- and PLSR-Based Machine Learning Model for Prediction of Urea-N Content in Heterogeneous Soils Using Near-Infrared Spectroscopy. Sensors (Basel, Switzerland). https://doi.org/10.3390/s25134176
Contact Us
Whether portable equipment can be used for similar detection needs to be evaluated based on samples and experimental conditions, and the specific effect still needs to be verified through actual testing. Welcome to contact VISPEK to exchange your sample and testing needs, jointly evaluate experimental plans, and explore the feasibility of using our company's equipment for actual measurement and verification.
- Email: contact@vispek.cn
- Website: https://www.vispek.cn
VISPEK products shown for illustration; these were not the devices used in the cited study.