with the collaboration of Iranian Society of Mechanical Engineers (ISME)

Document Type : Research Article


1 Department of Biosystems engineering, University of Tehran

2 Department of Biosystems engineering, university of Tehran

3 Agricultural Engineering Research Institute, Agricultural Research, Education and Extension Organization (AREEO)

4 University of Tehran


One of the most frequently consumed fruit in all over the world is apple. An apple fruit includes large source of minerals, fiber and several biologically compounds such as vitamin C, special phenolic compounds (natural antioxidant). The amount of nutrients plays a significant role in the growth, reproduction and performance of agricultural products and plants. By predicting these elements, chemical inputs can be accurately managed. Thus, timely and accurate monitoring and management of crop nutrition status are crucial for recommended fertilization, yield increase, and quality improvement, whilst by reducing the amount of chemical fertilizers applied, the risk of environmental degradation can be reduced. In crop plants, leaf samples are typically analyzed to diagnose nutrient deficiencies and imbalances, as well as to evaluate the effectiveness of current nutrient management programs. Thus, the main aim of this study was to non-destructively estimate the level of Nitrogen (N), Phosphorus (P) and Potassium (K) elements of apple tree leaves using Visible/Near-infrared (Vis/NIR) spectroscopy at wavelength range of 500 to 1000 nm coupled with chemometrics analysis.
Materials and Methods
This research investigated the potential of the Vis/NIR spectroscopy system with chemometrics analysis for predicting NPK nutrients of apple trees. To do so, 80 leaf samples of apple trees were randomly picked and transferred to the laboratory for spectral measurement. The Green-Wave spectrometer (StellarNet Inc, Florida, USA) utilized to collect the spectral data. In the next step, the spectral data were transferred to the laptop using the Spectra Wiz software (StellarNet Inc, Florida, USA). For this purpose, spectroscopy of apple tree leaf samples was done in intractance mode. Furthermore, ten reflectance spectra were captured randomly on each apple tree leaf at different points. The averaged spectrum was used to determine the reflectance (R). The data was then transformed into absorbance (log 1/R) for chemometrics analysis. The NPK contents were measured using reference methods following spectroscopy measurements. Then Partial Least Square (PLS) multivariate calibration models were developed based on reference measurements and spectral information with different pre-processing techniques. In order to remove the unwanted effects, various pre-processing methods were used to obtain an accurate calibration model. To evaluate the proposed models, Root Mean Square Error of calibration and prediction sets (RMSEC and RMSEP), as well as correlation coefficient of calibration and prediction sets (rc and rp), and Residual Predictive Deviation (RPD) were calculated.
 Results and Discussion
The statistical metrics were calculated for evaluation of PLSR model. The results indicated that the PLSR model could efficiently predicted the NPK contents with a satisfactory accuracy. The best developed model based on the standard normal variation pre-processing method in combination with the second derivative (SNV+D2) with the values of rc= 0.9859, RMSEC=0.028%, rp=0.978, RMSEP=0.034% and RPD of 7.47 was related to nitrogen prediction. The best model for prediction of P content resulted in rc= 0.967, RMSEC=0.0051%, rp=0.958, RMSEP=0.0057% and RPD of 5.96. Also the PLSR model based on MSC+D2 preprocessing method resulted in the in rc= 0.984, RMSEC=0.017%, rp=0.976, RMSEP=0.021% and RPD of 7.10, indicating the high potential of PLSR model in prediction of K content. Moreover, the weakest model was related to estimation of P content based on data without pre-processing with rc = 0.774, RMSEC = 0.013%, rp = 0.675, RMSEP = 0.018% and RPD value of 1.87. Based on the obtained results, the proposed PLSR model coupled with preprocessing methods was able to predict the nutrients content with high precision.
Field spectroscopy has recently gained popularity due to its portability, ease of use, and low cost. Consequently, the use of a portable system for estimating nutrient levels in the fields can significantly reduce time wastage and laboratory expenses. Therefore, according to the ability of the Vis/NIR spectroscopy technique and according to the obtained results, this method can be used to implement a field portable system based on Vis/NIR spectroscopy in order to estimate the Nutrient elements needed by apple trees in the orchards and increased the productivity of the orchards.


Main Subjects