Access to this full-text is provided by MDPI.
Content available from Agriculture
This content is subject to copyright.
Citation: Guo, Y.; Zhang, L.; Li, Z.; He,
Y.; Lv, C.; Chen, Y.; Lv, H.; Du, Z.
Online Detection of Dry Matter in
Potatoes Based on Visible Near-
Infrared Transmission Spectroscopy
Combined with 1D-CNN. Agriculture
2024,14, 787. https://doi.org/
10.3390/agriculture14050787
Academic Editor: Matteo Perini
Received: 16 December 2023
Revised: 26 April 2024
Accepted: 29 April 2024
Published: 20 May 2024
Copyright: © 2024 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
agriculture
Article
Online Detection of Dry Matter in Potatoes Based on Visible
Near-Infrared Transmission Spectroscopy Combined
with 1D-CNN
Yalin Guo 1, Lina Zhang 1, Zhenlong Li 1, Yakai He 2, Chengxu Lv 1, Yongnan Chen 3, Huangzhen Lv 1,2
and Zhilong Du 1, *
1Chinese Academy of Agricultural Mechanization Sciences Group Co., Ltd., Beijing 100083, China;
yalinguoguo@126.com (Y.G.); zhanglina@caams.org.cn (L.Z.); 13463669512@163.com (Z.L.);
wangmumu0101001@163.com (C.L.)
2Key Laboratory of Agricultural Products Processing Equipment, Ministry of Agriculture and Rural Affairs,
Beijing 100083, China; hlyakai@163.com
3College of International Education, Beijing University of Agriculture, Beijing 102206, China;
lzl2679439905@outlook.com
*Correspondence: duzhilong_caams@163.com
Abstract: More efficient resource utilization and increased crop utilization rate are needed to address
the growing demand for food. The efficient quality testing of key agricultural products such as
potatoes, especially the rapid testing of key nutritional indicators, has become an important strategy
for ensuring their quality and safety. In this study, visible and near infrared (Vis/NIR) transmittance
spectroscopy (600–900 nm) was used for the online analysis of multiple quality parameters in potatoes.
The study concentrated on comparing three one-dimensional convolutional neural network (1D-
CNN) models, specifically, the fine-tuned DeepSpectra, the fine-tuned 1D-AlexNet, and classic CNN,
with UVE-PLS (uninformative variable elimination–partial least squares) models. These models
utilized spectral data for the real-time detection of dry matter (DM) content in potatoes. To address
the challenges posed by limited data from Vis/NIR, this study strategically implemented data
augmentation techniques. This approach significantly enhanced the robustness and generalization
capabilities of the models. The 1D-AlexNet and DeepSpectra models achieved 0.934 and 0.913 R
2P
and 0.0603 and 0.0695 g/100 g RMSEP for DM, respectively. Compared to UVE-PLS, the R
2P
value
improved by 21.31% (0.770 to 0.934) for the 1D-AlexNet model and 18.64% (0.770 to 0.913) for the
DeepSpectra model. The RMSEP value was reduced by 47.31% (0.114 to 0.0603) for 1D-AlexNet,
and 39.30% (0.114 to 0.0695) for the DeepSpectra model. As a result, this study would be helpful for
researching the online Vis/NIR transmission determination of potato DM using deep learning. These
results highlighted the immense potential of employing specific spectral features in deep-learning
models for a more precise and efficient online assessment of agricultural quality. This advancement
provided some insight and reference for further contributing to the evolution of more targeted and
efficient quality assessment methods in agricultural products.
Keywords: potato; transmission spectroscopy; dry matter; online; 1D-CNN
1. Introduction
Potatoes, rich in starch, dry matter, and other nutrients, play a critical role as food crops
and industrial raw materials in over 150 countries [
1
]. According to the GB/T 31784-2015 [
2
],
dry matter (DM), starch (SC), and reducing sugar (RS) serve as key nutritional indicators.
However, traditional nutrient determination methods, including physical, chemical, and
enzymatic techniques, are often time-consuming, labor-intensive, and expensive, requiring
specialized training and facilities.
To address these challenges, fast and effective methods must be developed for the
real-time determination of nutrition content in potatoes. Researchers have utilized the
Agriculture 2024,14, 787. https://doi.org/10.3390/agriculture14050787 https://www.mdpi.com/journal/agriculture
Agriculture 2024,14, 787 2 of 14
properties of light, sound, and electricity to form a series of emerging sensing and detection
technologies, including machine vision, near-infrared spectroscopy, and hyperspectral
imaging [
3
]. Among the aforementioned non-destructive techniques, Vis/NIR spectroscopy
serves as one of the most commonly used techniques due to its lack of contact, rapid
response rate, and low operating cost [
4
–
6
]. The effectiveness of Vis/NIR spectroscopy in
determining sugar [
6
,
7
], starch [
8
,
9
], and dry matter [
10
,
11
] content in agricultural products
highlights its potential for determining potato quality.
Short-wavelength near-infrared spectroscopy (over a wavelength region of 750–950 nm),
used in partial transmittance optical geometry, was assessed as a means of estimating the
dry matter concentration of potato tubers by P. P. Subedi. A prediction accuracy of R
2
of 0.85
with a root mean square error of prediction (RMSEP) of 1.52% was achieved for intact whole
tubers [11]. Rady A M aimed to extract the primary wavelengths related to the prediction
of glucose and sucrose for potato tubers and investigated the potential of classification of
potatoes based on sugar levels important to the frying industry. Prediction models showed
a strong correlation with the R (RPD) correlation coefficient (ratio of reference standard
deviation to the root mean square error of the model) values for whole tubers, with glucose
values as high as 0.81 (1.70) [
12
]. Wang et al. [
13
] used a localized transmission spectroscopy
acquisition system for the rapid detection of potato dry matter, starch, and reducing sugar
content. The coefficients of determination of the prediction model validation set were
0.878, 0.865, and 0.888, and the root mean square errors of the validation set were 0.449%,
0.930%, and 0.0167%, respectively. Tang et al. [
14
] established a near-infrared spectroscopy
(NIRS) assay for the high-throughput analysis of sweet potato root quality, including total
starch, amylose, amylopectin, the ratio of amylopectin to amylose, soluble sugar, crude
protein, total flavonoid content, and total phenolic content. Eight optimal equations were
developed with an excellent coefficient of determination for calibration (R2C) of 0.95–0.99,
validation (R
2V
) of 0.89–0.96, and RPD of 6.33–11.35. The internal quality inspection of a
single sample could be accomplished with high accuracy, satisfying the requirements of
non-damage inspection. However, these studies were based on static testing, which has
not been able to solve the industrial demand for online real-time detection and grading of
internal quality.
Vis/NIR spectroscopy combined chemometrics have been extensively investigated,
with the most prevalent methods typically employing classical machine-learning tech-
niques such as PLS regression, a time-proven standard in the field [
15
,
16
]. However, PLS
performance heavily relies on the chosen data preprocessing technique for each dataset. As
a result, diverse approaches have often been used in the literature, resulting in a trial-and-
error approach. A practical method for one dataset may negatively affect the analysis of
another, even if assessing the same substance, leading to unexpectedly inferior results [
17
].
Therefore, adopting a deep-learning approach offers a promising solution to address this
issue. To the best of our knowledge, a notable gap exists in the literature regarding the
non-destructive and online detection of DM content by deep learning in potatoes, requiring
the establishment of efficient and effective methods for the simultaneous online detection of
multiple potato nutrients. Addressing this gap is critical for advancing the potato industry
in China.
In this research, fine-tuned state-of-the-art deep-learning-based methods were applied
to detect dry matter in potatoes using Vis/NIR spectroscopy. The specific objectives in-
volved (1) adopting added random Gaussian noise to expand data before model calibration
strategically. (2) This study also adopted 1D-CNNs and UVE-PLS to rapidly and accurately
complete the online potato DM evaluation and (3) performed a visualization wavelength
contribution for DM prediction.
2. Materials and Methods
2.1. Sample Preparation
Given that the Favorita potato variety is the most widely distributed potato variety
in China [
18
], this study specifically selected Favorita potatoes from a farmer’s market in
Agriculture 2024,14, 787 3 of 14
Chaoyang, Beijing, China, for analysis. All potatoes were thoroughly cleaned and stored
for a standardized 24 h period at room temperature before experimentation to ensure that
external factors such as dust, temperature, humidity, and storage duration did not affect
the research findings, followed by spectral analysis. To maintain consistency, 100 potato
samples were selected that were free from defects such as insect damage or mechanical
injuries on their surfaces to create dependable quantitative prediction models for dry
matter content.
2.2. Vis/NIR Spectroscopy System
The potato acquisition system for Vis/NIR transmission spectroscopy consisted of
a delivery module, a light source module, spectral acquisition module, control module,
and data analysis module. A 100 W halogen lamp was used vertically as a light source on
the sample. The system used a USB2000+ spectrometer (OceanOptics, Orlando, FL, USA),
which had a scanning wavelength range of 350–1000 nm and spectral resolution of 1 nm.
The spectrometer was positioned in a black box and controlled by custom-built software.
The software was installed on a 12th Gen Intel (R) Core (TM) i9-12900K CPU @3.20 GHz
(32G RAM) system (Intel Corporation, Santa Clara, CA, USA). Two blue conveyor belts (v-
belt), controlled by a PLC system, were used to place the potatoes (Figure 1). In Figure 1b,c,
the dashed box emphasizes the spectral acquisition module, containing the spectrometer
and associated optics crucial for capturing and analyzing the light sample. The green arrow
shows the direction of sample movement within the system. The blue arrows signify a
detailed explanation or an expanded view of the spectral acquisition module.
Figure 1. Vis/NIR transmission spectroscopy systems: (a) three-dimensional figure; (b) cutaway
view; (c) light source module and spectral acquisition module. (1) Vis/NIR spectrometer; (2) probe;
(3) sample; (4) tray; (5) light source; (6) computer.
Before spectral analysis, the system was warmed up for 30 min to prevent any pos-
sible impact on the experimental results caused by system instability. Following energy
stabilization of the light source, the dark light source was calibrated and spectral analysis
of the samples was conducted. The home-built software controlled the conveyor belt to
sequentially drive the potatoes through a spectral acquisition module. Once the potato
arrived at the detection position, an in-place sensor triggered the acquisition of the trans-
mission spectra of the potatoes. As light passed through the interior of the potatoes, it
carried internal quality information to the spectrometer, which received the spectral signals.
Agriculture 2024,14, 787 4 of 14
The integration time for spectrum acquisition was 25 ms, and the online inspection speed
of the samples was approximately 5 samples per second. Each sample was repeatedly
measured 10 times, and the average of 10 measurements was used to determine the raw
Vis/NIR spectrum of the samples.
2.3. Functional Components
The functional components detection of the potato samples involved several active
steps. The edible portion of the potatoes was peeled, and the peeled potatoes were then
crushed immediately. Finally, the crushed potato samples were analyzed for DM con-
tent, utilizing a direct drying method [
19
]. The SC was measured by the acid hydrolysis
method [
20
], and the RS content was measured using the 3.5-dinitrosalicylic acid colorimet-
ric method [21]. Testing was performed twice for each sample to ensure accuracy.
2.4. Data Augmentation of Spectra
Samples were actively engaged in data-driven training to achieve the exceptional
performance of the CNN model in this study. This technique allowed the neural network
to learn the intrinsic characteristics of the sample data and for the categories to be dif-
ferentiated in-depth, which enhanced the model’s robustness and minimized overfitting.
However, due to practical experimental constraints, collecting a significant amount of data
at once often poses a challenge, which can be detrimental to deep-learning models [22].
In this study, this issue was addressed by strategically expanding our experimental
samples before model calibration. Data augmentation techniques were implemented to
increase the diversity of the sample data, and random Gaussian noise was added to the
original spectra, increasing the total number of spectra from 100 to 1000. This method
effectively expanded datasets, providing a more robust foundation for training the CNNs
and improving the generalization performance and robustness of the network [23,24].
2.5. UVE-PLS Model
The PLS approach was established around 50 years ago by Herman Wold for the
modeling of complicated data. This approach can analyze data with strongly collinear
(correlated), noisy, and numerous X-variables, and simultaneously model several response
variables [
25
]. The spectral bands related to the maximum and minimum of beta-coefficient
values can present the most important wavelengths [
26
]. Uninformative variable elimina-
tion by PLS (UVE-PLS) [
27
] can remove uninformative variables in multivariate data, i.e.,
those not containing more information than random noise.
2.6. Convolution Neural Network
DeepSpectra [
28
], a robust deep-learning architecture developed for spectral analysis,
contains the Inception model. Figure 2displays the framework of DeepSpectra. This model
consists of three convolutional layers, with the last two convolutional layers incorporating
a connection in parallel, followed by a flattened layer, a fully connected layer, and an output
layer. A convolution kernel of larger size possesses a broader receptive field, enabling it to
effectively capture more global features. Nevertheless, employing several large convolution
kernels can result in a rapid increase in the number of parameters [
29
,
30
]. As a solution,
a strategy was adopted where a smaller kernel was utilized for the initial convolution
layer, while a larger kernel was chosen for the subsequent convolution layer. This study
used five-point (5-pts) kernel sizes for the first two convolutional layers and 11-pts for
the third layer, and the stride sizes were 3-pts and 1-pts for the convolutional layers [
28
].
DeepSpectra has demonstrated a dropout value of 0.5 for DM.
Agriculture 2024,14, 787 5 of 14
Figure 2. Structure of the DeepSpectra model.
This study adopted a fine-tuned 1D-AlexNet architecture, which was comprised of
three convolutional stages with one-dimension layers, each supplemented with batch
normalization (BN) and ReLU activation for efficient feature extraction (Figure 3). This
study also integrated max pooling layers to reduce dimensionality and transition to fully
connected layers to map the extracted features to outputs [
31
]. The kernel_size was 3, the
stride was 1 of the convolutional layers, and the kernel_size was 2, where the stride was 2
of the MaxPool layers. The 1D-AlexNet model had a dropout value of 0.1.
Figure 3. The structure of the 1D-AlexNet model.
This study introduced a classic CNN for data processing (Figure 4), which was com-
prised of three layers. In the first layer, Conv1, one-dimensional convolution was imple-
mented using 16 channels, each with a kernel size of 1, which was enhanced with batch
normalization and ReLU activation. This layer was designed to capture distinctive features
in the input data. In the second layer, the channels count was increased to 32 with a kernel
size of 3, thereby advancing the feature refinement process. In this layer, batch normal-
ization and ReLU activation were also integrated. In the third and final convolutional
layer, the feature extraction capability with 64 channels and a kernel size of 5 was escalated
and continued with batch normalization and ReLU. The network culminated with a fully
connected layer, where the high-dimensional features extracted by the preceding layers
were mapped to a single output tailored for tasks such as classification and detection. The
classic CNN has shown a dropout value of 1.
All spectral data are standardized and all target labels are normalized before input. To
prevent overfitting and reduce the need to set an exact number of epochs, early stopping,
and L2 regularization were used. The optimizer was AdamW, the learning rate was 0.0001,
and the weight_decay was 0.0001. The model was trained for 100 epochs. For the objective
function, the mean squared error (MSE) and L2 regularization were used to minimize the
sum of squares loss and prevent overfitting.
Agriculture 2024,14, 787 6 of 14
Figure 4. Structure of the CNN model.
2.7. GRAD-CAM
Understanding why a model makes a certain prediction can be as crucial as the
prediction’s accuracy in many applications. However, the highest accuracy for large modern
datasets is often achieved by complex models that even experts struggle to interpret, such as
ensemble or deep-learning models, creating a tension between accuracy and interpretability.
Gradient-weighted class activation mapping (GRAD-CAM) has been used in the field
of computer vision, particularly in CNNs, to provide visual explanations for decisions
made by CNNs in tasks such as image classification and object detection. Essentially, this
approach backpropagates the signal from the output layer to the convolutional layers to
understand which parts contribute most to the output decision. The gradient of the target
(i.e., class, object) can be computed with respect to the feature maps of a convolutional layer.
These gradients can be global-average-pooled to obtain the neuron importance weights,
and the feature maps of the convolutional layer can be combined with these weights to
generate a heatmap [32].
2.8. Statistical Analysis
In this study, the Gaussian filtering preprocessing, standardization, and normalization
were employed to analyze the data and subsequently the 1D-CNN models and UVE-PLS
prediction of the nutritional quality components of the potato samples. Finally, the three
1D-CNN models were compared to the UVE-PLS prediction of the nutritional quality
components of potato samples.
In this study, potatoes were mixed and then divided into datasets. The spectral data
were randomly divided into two groups: the calibration set and the prediction set by
an 8:2 ratio (random scale factor of 42 for 1D-CNNs and 0 for UVE-PLS). The utilized
evaluation metrics consisted of R-squared (R
2
), mean absolute error (MAE), and root mean
square error (RMSE). RMSE measured the square root of the average of the squared differ-
ences (errors) between predicted and actual values, while a smaller RMSE indicated more
accurate model predictions. MAE calculated the average absolute discrepancy between
the predicted and actual values, while a smaller MAE indicated more accurate model
predictions. R
2
quantified the fraction of variance that the model accounted for on a scale
of 0 to 1, where higher values (closer to 1) indicated the greater explanatory effectiveness of
the model.
The experiments in this study were conducted on a Windows 10 operating system,
using the Python programming language in the PyCharm platform. All models and chemo-
metric procedures used throughout this work were implemented based on Python 3.9.
Agriculture 2024,14, 787 7 of 14
3. Results and Discussion
3.1. Analyzing the Determination of the Standard Physical and Chemical Values of Potatoes
Table 1displays statistical results of the compositional and physical characteristics in
potatoes, indicating that the reference DM values were in the range of
13.10–20.38 g/100 g,
the reference SC was in the range of 9.20–17.91 g/100 g, and RS was in the range of
0.090–1.17 g/100 g,
respectively. The dimensions of the samples varied, with widths rang-
ing from 51.5 to 80.0 mm, heights from 42.0 to 68.0 mm, and lengths from 47.0 to 105.0 mm.
Their weight ranged between 159.14 and 326.95 g.
Table 1. Statistical results of compositional and physical characteristics in potatoes.
Indexes Min Max Mean Std
DM (g/100 g) 13.10 20.38 16.04 1.71
SC (g/100 g) 9.20 17.91 12.38 1.82
RS (g/100 g) 0.090 1.17 0.48 0.21
Weight (g) 159.14 326.95 237.43 39.06
Length (mm) 47.0 105.0 85.3 10.93
Width (mm) 51.5 80.0 65.1 5.0
Height (mm) 42.0 68.0 54.0 5.4
This was conducted to determine the Pearson’s correlation coefficient between the
variables compositional and physical characteristics. Figure 5shows the results of the
Pearson’s correlation coefficient, which revealed some interesting insights. The results
indicated a strong positive linear relationship (0.92) between DM and SC, suggesting
that an increase in dry matter content proportionally increased starch content. However,
there was a weak negative linear relationship (
−
0.18) between DM and RS, indicating a
slight tendency for the reducing sugars to decrease as the dry matter content increased.
Similarly, a weak negative linear relationship (
−
0.16) was observed between SC and RS.
This suggested that SC and RS varied more independently with each other than DM and SC.
However, it should be acknowledged that this observed relationship may not be universally
applicable across different environmental conditions or developmental stages of tubers.
Figure 5. Histograms and correlation plots for the different parameters.
3.2. Analysis of the Visible/Near-Infrared Spectra of the Potatoes
The transmission spectrum (Figure 6a) of the potato was transformed into an ab-
sorbance spectrum, and the transformed spectral curve is shown in Figure 6b. Prominent
transmission band peaks were observed between 600 and 850 nm, specifically, major trans-
mission peaks were observed around 625–675, 675–725, and 780–810 nm. Major absorbance
Agriculture 2024,14, 787 8 of 14
peaks found around 675 nm were the chlorophyll absorption peak [
7
,
33
], and the ab-
sorbance of the 675–700 nm spectrum gradually decreased with the weakening effect of
chlorophyll on the spectra, demonstrating a small range of variation in the 700–900 nm
range. Another absorbance peak normally attributed to the OH functional groups was
found near 780 nm [34].
Figure 6. Average Vis/NIR transmission spectrum and absorbance spectrum of the Vis/NIR spectra
of all samples: (a) transmission spectrum; (b) absorbance spectrum.
3.3. NIRS Modeling of Quality Components
Table 2shows the results of a UVE-PLS model applied to predict the DM contents
in potatoes using spectral data in the 600–900 nm wavelength range (dataset I for the
raw spectral data and dataset II for the augmented spectral data). Table 2showed im-
provements in the model’s predictive capabilities with the augmentation of the spectral
data. Specifically, dataset I demonstrated R
2C
= 0.626 and RMSEC = 0.140 g/100 g; how-
ever, the model’s fit on validation data was poor (R
2P
= 0.552), accompanied by a high
error rate
(RMSEP = 0.171 g/100 g).
By contrast, dataset II exhibited a better calibration fit
(R2C= 0.837)
and a reduced error (RMSEC = 0.0943 g/100 g), alongside a notably improved
validation fit (R2P= 0.770) with a lower error rate (RMSEP = 0.114 g/100 g).
Table 2. Results of the UVE-PLS model developed for the DM content prediction using wavelength
ranges of 600–900 nm in the potatoes (dataset I: raw spectral data; dataset II: augmented spectral data).
Parameters Dataset LVs Calibration Prediction
R2CRMSEC (g/100 g) R2PRMSEP (g/100 g)
DM I 10 0.626 0.140 0.552 0.171
II 10 0.837 0.0943 0.770 0.114
Overall, these results indicated that spectral data augmentation contributed positively
to the model’s accuracy in predicting the DM content in potatoes, as evidenced by the
improved fit and reduced error rates in both the calibration and prediction phases. Specifi-
cally, for DM predictions, the augmentation led to an improvement of 0.211 for R
2C
and R
2P
showed an improvement of 0.217. Additionally, the RMSEC decreased by
0.0459 g/100 g,
and RMSEP had a reduction of 0.0567 g/100 g. In related research, the addition of data
augmentation to the PLS model has shown significant benefits. Compared to the PLS
model without data augmentation, the model with data augmentation improved from
0.63 to 0.88 in identifying vegetable oil species in oil admixtures for food analysis [
35
]. This
improvement serves as a robust example supporting the efficacy of data augmentation
techniques in enhancing analytical accuracy, reinforcing the positive outcomes observed in
our own experiments with DM content prediction in potatoes.
Agriculture 2024,14, 787 9 of 14
The data augmentation significantly improved the model’s ability to fit and predict
the data. Both the RMSEC and RMSEP values were lower in dataset II for DM, indicating
that the augmented data led to more accurate predictions. The improvement in model
performance was more pronounced in the prediction set, suggesting that the augmented
data helped with model generalization. In conclusion, augmenting the spectral data ap-
peared to have a positive impact on the UVE-PLS model’s performance for predicting DM
content in potatoes. This improved both the fit of the training data and the predictive
accuracy of prediction data, thereby enhancing the overall reliability of the model’s predic-
tions. The presence of identical characteristic wavelengths for DM content prediction in
potatoes before and after data augmentation, specifically near 840 and 870 nm, presented
an interesting aspect for analysis within the context of PLS regression coefficients (Figure 7).
The identical characteristic wavelengths across datasets implied that these regions were
critical for the model’s predictive capability, irrespective of data augmentation. Despite
these improvements, it should be noted that the R
2P
values for DM in both datasets were
not very high, indicating some limitations in the model’s predictive ability.
Figure 7. Regression coefficients of the PLS model developed for the DM content prediction using
wavelength ranges of 600–900 nm in the potatoes ((a): DM for the raw spectral data; (b): DM for the
augmented spectral data).
The deep-learning model was randomly run five times to test its robustness, with the
training samples and test samples remaining unchanged. To enhance comprehension and
facilitate a clear comparison of the overall parameters, a spider diagram was generated
to illustrate the average performance from five runs of the employed UVE-PLS and 1D-
CNN models (Figure 8). In the DM prediction, the analytical results suggested that the
1D-AlexNet model exhibited superior calibration with the better R
2
c (0.940), which denoted
a robust model fit to the calibration data. This was complemented by its minimal RMSEC
(0.0574 g/100 g) and MAEC (0.0410 g/100 g) values, indicating high precision in the
calibration set. Meanwhile, 1D-AlexNet showed a good performance in the prediction set,
with an R
2P
value of 0.934 and an RMSEP value of 0.0603 g/100 g, denoting its efficacious
generalization capability. Additionally, DeepSpectra demonstrated substantial predictive
Agriculture 2024,14, 787 10 of 14
accuracy with an R
2P
value of 0.913 and an RMSEP value of 0.0695 g/100. The consistency
of the observed trends across various metrics for the calibration set and prediction set
reinforced the robustness of the models, suggesting their versatility in the calibration and
prediction sets of the potato online testing capabilities. The classic CNN model achieved
an R2Pvalue of 0.859, which underscored its potential predictive validity. However, UVE-
PLS, while exhibiting reasonable calibration and prediction results, was surpassed by
the CNN models in most metrics. Compared to UVE-PLS, the R
2P
value improved by
21.31%
(0.770 to 0.934)
and the RMSEP value was reduced by 47.31% (0.114 to 0.0603) of
1D-AlexNet. The R
2P
value improved by 18.64% (0.770 to 0.913) and the RMSEP value was
reduced by 39.30% (0.114 to 0.0695) compared to DeepSpectra. The R
2P
value improved
by 11.62% (0.770 to 0.859) and the RMSEP value was reduced by 18.81% (0.114 to 0.0865)
compared to the classic CNN model.
Figure 8. Dry matter predictive performance of the four models for the quality components. R
2C
,
coefficient determination of calibration; R
2P
, coefficient determination of prediction; RMSEC, root
mean standard error of calibration; RMSEP, root mean square error of prediction; MAEC, mean
absolute error of calibration; MAEP, mean absolute error of prediction.
The spectral data of the calibration and prediction sets were read into the initialization
network for iterative training, while the spectral data of the prediction set were used to
evaluate the accuracy of 1D-AlexNet and DeepSpectra. The modeling results of five runs
are shown in Table 3. The results indicate that the prediction rate of the 1D-AlexNet model
had the lowest rate of 0.914 and the highest rate of 0.954, and the prediction rate of the
DeepSpectra model had the lowest rate of 0.903 and the highest rate of 0.930. The difference
between the lowest rate and the highest rate was only 0.040 and 0.027 for 1D-AlexNet and
DeepSpectra, respectively, indicating that the models were relatively robust. Furthermore,
the 1D-AlexNet and DeepSpectra results in this study were superior to those obtained
using the Vis/NIR PLS models with R
2P
values of 0.878 and an RMSEV of 0.449% based on
the diffuse reflectance principle in off-line conditions, respectively [
13
]. Compared to the
results obtained in off-line conditions, the performance of 1D-AlexNet and DeepSpectra
in this research showed the possibility of using the online system for measuring the DM
of potatoes. These results were possibly due to the fact that the transmission mode in this
study was better than the diffuse reflectance mode, which possibly carried less sample
information and showed negative effects on the accuracies [
16
]. Consequently, this served
as a promising and accessible method when combined with Vis/NIR and deep learning for
the online detection of agricultural product quality.
Agriculture 2024,14, 787 11 of 14
Table 3. Results of the calibration and prediction sets following five parallel runs of the DeepSpectra
model developed for DM contents using wavelength ranges of 600–900 nm in potatoes.
Parameters Serial
No.
Calibration Prediction
R2C
RMSEC (g/100 g)
MAEC (g/100 g) R2P
RMSEP (g/100 g)
MAEP (g/100 g)
1D-AlexNet
1 0.959 0.0478 0.0349 0.954 0.0509 0.0387
2 0.940 0.0574 0.0437 0.930 0.0626 0.0482
3 0.922 0.0655 0.0463 0.920 0.0667 0.0475
4 0.916 0.0678 0.0461 0.914 0.0693 0.0478
5 0.957 0.0484 0.0339 0.951 0.0522 0.0377
DeepSpectra
1 0.936 0.0593 0.0461 0.930 0.0625 0.0478
2 0.927 0.0635 0.0477 0.910 0.0708 0.0533
3 0.922 0.0655 0.0502 0.910 0.0710 0.0532
4 0.925 0.0644 0.0507 0.913 0.0697 0.0539
5 0.910 0.0704 0.0534 0.903 0.0734 0.0564
Understanding the reason behind a model’s prediction may be just as crucial as its
accuracy in practical applications [
36
]. The essential bands for 1D-AlexNet to predict DM
are marked by GRAD-CAM analysis in Figure 9. The more effective wavelengths were
between 730 and 900 nm, which were recommended for good DM prediction [
8
,
37
]. In a
previous study, the optimal wavelength range within short-wave NIR spectroscopy for
DM assessment was expected to encompass the water-related peaks at around 840 and
870 nm [
38
]. In this study, in particular, 780–800 and 830–900 nm are more helpful for
predicting DM content. This indicated the crucial role of these wavelengths in predicting
the DM within the samples, which was possibly due to the following reasons: (1) The
wavelengths with high weight values were mostly in the near-infrared range, avoiding
the influence of surface color variations and internal pigment absorption on the model.
(2) Wavelengths near 780 nm were attributed to the OH functional groups; wavelengths
near 840 nm provided absorption information for the combined bands of C–H3, C–H2, and
C–H; and wavelengths near 870 nm were possibly relative to the third overtone of C–H [
13
],
exhibiting a strong correlation with DM.
Figure 9. Weight values of the 1D-AlexNet model developed for the DM content prediction using
wavelength ranges of 600–900 nm in the potatoes.
Agriculture 2024,14, 787 12 of 14
4. Conclusions
This comprehensive study demonstrated the significant potential of deep-learning
methods for enhancing the efficiency and accuracy of nutrient detection in potatoes, explic-
itly focusing on DM using an online Vis/NIR transmission spectroscopy technique. The
accuracy and efficiency offered by the DeepSpectra, 1D-AlexNet, and classic CNN models,
especially the 1D-AlexNet and DeepSpectra model, suggested a significant advancement in
agricultural product assessment, enhancing the production and quality control processes.
Data augmentation techniques, including the addition of Gaussian noise, were utilized
to expand the limited sample size for practical deep-learning model training. The 1D-
AlexNet model showed an R
2P
value of 0.934 and an RMSEP value of 0.0603 g/100 g.
Compared to UVE-PLS, the R
2P
value improved by 21.31% (0.770 to 0.934) and the RMSEP
value was reduced by 47.31% (0.114 to 0.0603). Additionally, the DeepSpectra models
achieved 0.913 and 0.0695 g/100 g RMSEP for DM. Compared to UVE-PLS, the R
2P
value
improved by 18.64% (0.770 to 0.913) and the RMSEP value was reduced by 39.30% (0.114
to 0.0695). Thus, this study may assist the online Vis/NIR transmission determination
research of DM in potatoes using deep learning.
These findings underscored the potential of using specific spectral features in deep-
learning models for more precise and efficient agricultural quality online assessment. This
advancement provided some insight and reference for further development in contributing
to the evolution of more targeted and efficient quality assessment methods in agricultural
products. Although these results are encouraging, additional research is still needed to
focus on a larger number of potato samples and cultivars with a wide range of DM values
to develop an accurate and robust online sorting system.
Author Contributions: Y.G. and L.Z.: methodology; Z.L. and Y.C.: original draft preparation; Y.H.
and C.L.: validation; H.L. and Z.D.: review and editing. All authors have read and agreed to the
published version of the manuscript.
Funding: The authors would like to thank the National Potato Industry Technical System Project
(CARS-10-P23) and Key Laboratory of Agro-Products Primary Processing, Ministry of Agriculture
and Rural Affairs of China (KLAPPP2022-01).
Institutional Review Board Statement: Not applicable.
Data Availability Statement: The data presented in this study are available on request from the
corresponding author.
Conflicts of Interest: Authors Yalin Guo, Lina Zhang, Zhenlong Li, Chengxu Lv, Huangzhen Lv,
and Zhilong Du were employed by the company Chinese Academy of Agricultural Mechanization
Sciences Group Co., Ltd. However, the Chinese Academy of Agricultural Mechanization Sciences
Group Co., Ltd. did not contribute financially, nor in the optimization, analysis of the results, or
writing of the paper. Therefore, there is no conflict of interest in relation with the company Chinese
Academy of Agricultural Mechanization Sciences Group Co., Ltd. The remaining authors declare that
the research was conducted in the absence of any commercial or financial relationships that could be
construed as a potential conflict of interest.
References
1.
Lal, K.; Tiwari, R.K.; Jaiswal, A.; Luthra, S.K.; Singh, B.; Kumar, S.; Gopalakrishnan, S.; Gaikwad, K.; Kumar, A.; Paul, V.; et al.
Combinatorial interactive effect of vegetable and condiments with potato on starch digestibility and estimated
in vitro
glycemic
response. J. Food Meas. Charact. 2022,16, 2446–2458. [CrossRef]
2.
GB/T 31784-2015; Code of Practice for Grading and Inspecting of Commercial Potatoes. Ministry of Agriculture: Beijing,
China, 2015.
3.
Guo, Z.; Wang, X.; Song, Y.; Zou, X.; Cai, J. Advances in sensing and monitoring technology for quality deterioration of fruits and
vegetables. Smart Agric. 2021,3, 14–28.
4.
Alfatni, M.S.M.; Shariff, A.R.M.; Abdullah, M.Z.; Marhaban, M.H.B.; Ben Saaed, O.M. The application of internal grading system
technologies for agricultural products-Review. J. Food Eng. 2013,116, 703–725. [CrossRef]
5.
Wang, H.; Peng, J.; Xie, C.; Bao, Y.; He, Y. Fruit quality evaluation using spectroscopy technology: A review. Sensors 2015,15,
11889–11927. [CrossRef] [PubMed]
Agriculture 2024,14, 787 13 of 14
6.
Li, J.; Wang, Q.; Xu, L.; Tian, X.; Xia, Y.; Fan, S. Comparison and optimization of models for determination of sugar content in pear
by portable Vis-NIR spectroscopy coupled with wavelength selection algorithm. Food Anal. Methods 2019,12, 12–22. [CrossRef]
7.
Martins, J.A.; Rodrigues, D.; Cavaco, A.M.; Antunes, M.D.; Guerra, R. Estimation of soluble solids content and fruit temperature
in ‘Rocha’ pear using Vis-NIR spectroscopy and the SpectraNet-32 deep learning architecture. Postharvest Biol. Technol. 2023,
199, 112281. [CrossRef]
8.
He, H.-J.; Wang, Y.; Wang, Y.; Ou, X.; Liu, H.; Zhang, M. Towards achieving online prediction of starch in postharvest sweet
potato [Ipomoea batatas (L.) Lam] by NIR combined with linear algorithm. J. Food Compos. Anal. 2023,118, 105220. [CrossRef]
9.
Lu, P.; Li, X.; Janaswamy, S.; Chi, C.; Chen, L.; Wu, Y.; Liang, Y. Insights on the structure and digestibility of sweet potato starch:
Effect of postharvest storage of sweet potato roots. Int. J. Biol. Macromol. 2020,145, 694–700. [CrossRef] [PubMed]
10.
de Freitas, S.T.; Guimarães, T.; Vilvert, J.C.; Amaral, M.H.P.D.; Brecht, J.K.; Marques, A.T.B. Mango dry matter content at harvest
to achieve high consumer quality of different cultivars in different growing seasons. Postharvest Biol. Technol. 2022,189, 111917.
[CrossRef]
11.
Subedi, P.P.; Walsh, K.B. Assessment of potato dry matter concentration using short-wave near-infrared spectroscopy. Potato Res.
2009,52, 67–77. [CrossRef]
12.
Rady, A.M.; Guyer, D.E. Evaluation of sugar content in potatoes using NIR reflectance and wavelength selection techniques.
Postharvest Biol. Technol. 2015,103, 17–26. [CrossRef]
13.
Wang, F.; Li Y-y Peng Y-k Yang B- Li, L.; Liu, Y.-c. Multi-Parameter Potato Quality Non-Destructive Rapid Detection by
Visible/Near-Infrared Spectra. Spectrosc. Spectr. Anal. 2018,38, 3736–3742.
14.
Tang, C.; Jiang, B.; Ejaz, I.; Ameen, A.; Zhang, R.; Mo, X.; Wang, Z. High-throughput phenotyping of nutritional quality
components in sweet potato roots by near-infrared spectroscopy and chemometrics methods. Food Chem. X 2023,20, 100916.
[CrossRef]
15.
Tian, H.; Xu, H.; Ying, Y. Can light penetrate through pomelos and carry information for the non-destructive prediction of soluble
solid content using Vis-NIRS? Biosyst. Eng. 2022,214, 152–164. [CrossRef]
16.
Zheng, Y.; Cao, Y.; Yang, J.; Xie, L. Enhancing model robustness through different optimization methods and 1-D CNN to
eliminate the variations in size and detection position for apple SSC determination. Postharvest Biol. Technol. 2023,205, 112513.
[CrossRef]
17.
Martins, J.; Guerra, R.; Pires, R.; Antunes; Panagopoulos, T.; Brázio, A.; Afonso, A.; Silva, L.; Lucas, M.; Cavaco, A. SpectraNet-53:
A deep residual learning architecture for predicting soluble solids content with VIS–NIR spectroscopy. Comput. Electron. Agric.
2022,197, 106945. [CrossRef]
18.
Zhang, H.; Li, Z.; Wang, X. Analysis of the Characteristics of Potato Varieties and Industrial Distribution in China. China Potato
2022,36, 78–85.
19.
GB 5009.3-2016; National Food Safety Standard—Determination of Moisture in Foods. Ministry of Agriculture: Beijing,
China, 2016.
20.
GB 5009.9-2016; National Food Safety Standard—Determination of Starch in Foods. Ministry of Agriculture: Beijing, China, 2016.
21.
Zhu, H.; Shi, Y.; Zhang, Q.; Chen, Y. Determination of reducing sugars in potato by colorimetric method of 3,5-dinitrosalicylic
acid (DNS). China Potato 2005,19, 14–17.
22.
Wang, S.; Tian, H.; Tian, S.; Yan, J.; Wang, Z.; Xu, H. Evaluation of dry matter content in intact potatoes using different optical
sensing modes. J. Food Meas. Charact. 2023,17, 2119–2134. [CrossRef]
23.
Jiang, H.; Deng, J.; Zhu, C. Quantitative analysis of aflatoxin B1 in moldy peanuts based on near-infrared spectra with two-
dimensional convolutional neural network. Infrared Phys. Technol. 2023,131, 104672. [CrossRef]
24.
Ma, D.; Shang, L.; Tang, J.; Bao, Y.; Fu, J.; Yin, J. Classifying breast cancer tissue by Raman spectroscopy with one-dimensional
convolutional neural network, Spectrochim. Acta Part A-Mol. Biomol. Spectrosc. 2021,256, 119732. [CrossRef] [PubMed]
25.
Wold, H. Soft modelling, the basic design and some extensions. In Systems under Indirect Observations; Joreskog, K.-G., Wold, H.,
Eds.; North-Holland: Amsterdam, The Netherlands, 1982; Volumes I–II.
26.
Sun, M.; Zhang, D.; Liu, L.; Wang, Z. How to predict the sugariness and hardness of melons: A near-infrared hyperspectral
imaging method. Food Chem. 2017,218, 413–421. [CrossRef] [PubMed]
27.
Centner, V.; Massart, D.L.; de Noord, O.E.; de Jong, S.; Vandeginste, B.G.M.; Sterna, C. Elimination of uninformative variables for
multivariate calibration. Anal. Chem. 1996,68, 3851–3858. [CrossRef] [PubMed]
28.
Zhang, X.; Lin, T.; Xu, J.; Luo, X.; Ying, Y. DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis.
Anal. Chim. Acta 2019,1058, 48–57. [CrossRef] [PubMed]
29.
Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with
convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA,
USA, 7–12 June 2015; IEEE: Piscataway, NJ, USA, 2015; pp. 1–9.
30.
Yu, G.; Li, H.; Li, Y.; Hu, Y.; Wang, G.; Ma, B.; Wang, H. Multiscale DeepSpectra Network: Detection of Pyrethroid Pesticide
Residues on the Hami Melon. Foods 2023,12, 1742. [CrossRef] [PubMed]
31.
Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in
Neural Information Processing Systems; Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q., Eds.; Curran Associates, Inc.: Lake
Tahoe, NV, USA, 2012; Volume 25.
Agriculture 2024,14, 787 14 of 14
32.
Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-cam: Visual explanations from deep networks
via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29
October 2017; pp. 618–626.
33.
McGlone, V.A.; Martinsen, P.J.; Clark, C.J.; Jordan, R.B. On-line detection of brownheart in Braeburn apples using near infrared
transmission measurements. Postharvest Biol. Technol. 2005,37, 142–151. [CrossRef]
34.
Huang, Y. Research and Application of Spatially Resolved Spectroscopy Based on Multi-Channel Hyperspectral Imaging System.
Ph.D. Thesis, Nanjing Agricultural University, Nanjing, China, 2018.
35.
Georgouli, K.; Osorio, M.T.; Martinez Del Rincon, J.; Koidis, A. Data Augmentation in Food Science: Synthesising Spectroscopic
Data of Vegetable Oils for Performance Enhancement. J. Chemom. 2018,32, e3004. [CrossRef]
36.
Scott, M.; Lundberg, S.-I.L. Authors Info & Claims. A Unified Approach to Interpreting Model Predictions. In Proceedings of the
31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017.
37.
Subedi, P.P.; Walsh, K.B. Assessment of avocado fruit dry matter content using portable near infrared spectroscopy: Method and
instrumentation optimisation. Postharvest Biol. Technol. 2020,161, 111078. [CrossRef]
38.
Golic, M.; Walsh, K.; Lawson, P. Short-wavelength near-infrared spectra of sucrose, glucose, and fructose with respect to sugar
concentration and temperature. Appl. Spectrosc. 2003,57, 139–145. [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.
Available via license: CC BY 4.0
Content may be subject to copyright.
