Feasibility of Using VIS/NIR Spectroscopy and Multivariate Analysis for Pesticide Residue Detection in Tomatoes

Rapid smartphone-based assays for pesticides inspection in foods: current status, limitations, and future directions

Smartphone-based assays to inspect pesticides in foods have attracted much attention as such assays can transform tedious laboratory-based assays into real-time, on-site, or even home-based assay and hence overcoming the limitations of conventional assays. Although an array of smartphone-based assays is available, information on the use of these assays for pesticides inspection is scattered. The purposes of this review are therefore to compile, summarize and discuss state-of-the-art as well as advantages and limitations of the relevant technologies. Suggestions are provided for further development of smartphone-based assays for rapid inspection of pesticides in foods. Smartphone-based assays relying on enzyme inhibitions are noted to be nonselective qualitative, capable of reporting results in a quantitative manner only when a sample contains an individual pesticide. Smartphone-based assays relying on chemical reactions also target only individual pesticides. Smartphone-based visible spectroscopy can, on the other hand, inspect individual and multiple pesticides with the aid of appropriate colorimetry-, luminescence-, or fluorescence-based assay. Smartphone-based visible-near infrared and Raman spectroscopies are suitable for simultaneous multiple pesticides inspection. Raman spectroscopy is of particular interest as it can detect pesticides even at lower concentrations. This spectroscopic technique can also serve as a real-time assay with the aid of cloud network computations.

Pesticide residue detection technology for herbal medicine: current status, challenges, and prospects

The domains of cancer therapy, disease prevention, and health care greatly benefit from the use of herbal medicine. Herbal medicine has become the mainstay of developing characteristic agriculture in the planting area increasing year by year. One of the most significant factors in affecting the quality of herbal medicines is the pesticide residue problem caused by pesticide abuse during the cultivation of herbal medicines. It is urgent to solve the problem of detecting pesticide residues in herbal medicines efficiently and rapidly. In this review, we provide a comprehensive description of the various methods used for pesticide residue testing, including optical detection, the enzyme inhibition rate method, molecular detection methods, enzyme immunoassays, lateral immunochromatographic, nanoparticle-based detection methods, colorimetric immunosensor, chemiluminescence immunosensor, smartphone-based immunosensor, etc. On this basis, we systematically analyze the mechanisms and some of the findings of the above detection strategies and discuss the challenges and prospects associated with the development of pesticide residue detection tools.

Research Status in the Use of Surface-Enhanced Raman Scattering (SERS) to Detect Pesticide Residues in Foods and Plant-Derived Chinese Herbal Medicines

Surface-enhanced Raman scattering (SERS) technology has unique advantages in the rapid detection of pesticides in plant-derived foods, leading to reduced detection limits and increased accuracy. Plant-derived Chinese herbal medicines have similar sources to plant-derived foods; however, due to the rough surfaces and complex compositions of herbal medicines, the detection of pesticide residues in this context continues to rely heavily on traditional methods, which are time consuming and laborious and are unable to meet market demands for portability. The application of flexible nanomaterials and SERS technology in this realm would allow rapid and accurate detection in a portable format. Therefore, in this review, we summarize the underlying principles and characteristics of SERS technology, with particular focus on applications of SERS for the analysis of pesticide residues in agricultural products. This paper summarizes recent research progress in the field from three main directions: sample pretreatment, SERS substrates, and data processing. The prospects and limitations of SERS technology are also discussed, in order to provide theoretical support for rapid detection of pesticide residues in Chinese herbal medicines.

Qualitative and Quantitative Assessments of Apple Quality Using Vis Spectroscopy Combined with Improved Particle-Swarm-Optimized Neural Networks

Exploring a cost-effective and high-accuracy optical detection method is of great significance in promoting fruit quality evaluation and grading sales. Apples are one of the most widely economic fruits, and a qualitative and quantitative assessment of apple quality based on soluble solid content (SSC) was investigated via visible (Vis) spectroscopy in this study. Six pretreatment methods and principal component analysis (PCA) were utilized to enhance the collected spectra. The qualitative assessment of apple SSC was performed using a back-propagation neural network (BPNN) combined with second-order derivative (SD) and Savitzky-Golay (SG) smoothing. The SD-SG-PCA-BPNN model's classification accuracy was 87.88%. To improve accuracy and convergence speed, a dynamic learning rate nonlinear decay (DLRND) strategy was coupled with the model. After that, particle swarm optimization (PSO) was employed to optimize the model. The classification accuracy was 100% for testing apples via the SD-SG-PCA-PSO-BPNN model combined with a Gaussian DLRND strategy. Then, quantitative assessments of apple SSC values were performed. The correlation coefficient (r) and root-square-mean error for prediction (RMSEP) in testing apples were 0.998 and 0.112 °Brix, surpassing a commercial fructose meter. The results demonstrate that Vis spectroscopy combined with the proposed synthetic model has significant value in qualitative and quantitative assessments of apple quality.

Multiscale Deepspectra Network: Detection of Pyrethroid Pesticide Residues on the Hami Melon

The problem of pyrethroid residues has become a topical issue, posing a potential food safety concern. Pyrethroid pesticides are widely used to prevent and combat pests in Hami melon cultivation. Due to its high sensitivity and accuracy, gas chromatography (GC) is used most frequently for detecting pyrethroid pesticide residues. However, GC has a high cost and complex operation. This study proposed a deep-learning approach based on the one-dimensional convolutional neural network (1D-CNN), named Deepspectra network, to detect pesticide residues on the Hami melon based on visible/near-infrared (380-1140 nm) spectroscopy. Three combinations of convolution kernels were compared in the single-scale Deepspectra network. The convolution group of "5 × 1" and "3 × 1" kernels obtained a better overall performance. The multiscale Deepspectra network was compared to three single-scale Deepspectra networks on the preprocessing spectral data and obtained better results. The coefficient of determination (R2) for lambda-cyhalothrin and beta-cypermethrin was 0.758 and 0.835, respectively. The residual predictive deviation (RPD) for lambda-cyhalothrin and beta-cypermethrin was 2.033 and 2.460, respectively. The Deepspectra networks were compared with two conventional regression models: partial least square regression (PLSR) and support vector regression (SVR). The results showed that the multiscale Deepspectra network outperformed the other models. It was found that the multiscale Deepspectra network could be a novel approach for the quantitative estimation of pyrethroid pesticide residues on the Hami melon. These findings can also provide an effective strategy for spectral analysis.

The Application of Hyperspectral Imaging Technologies for the Prediction and Measurement of the Moisture Content of Various Agricultural Crops during the Drying Process

Drying is one of the common procedures in the food processing steps. The moisture content (MC) is also of crucial significance in the evaluation of the drying technique and quality of the final product. However, conventional MC evaluation methods suffer from several drawbacks, such as long processing time, destruction of the sample and the inability to determine the moisture of single grain samples. In this regard, the technology and knowledge of hyperspectral imaging (HSI) were addressed first. Then, the reports on the use of this technology as a rapid, non-destructive, and precise method were explored for the prediction and detection of the MC of crops during their drying process. After spectrometry, researchers have employed various pre-processing and merging data techniques to decrease and eliminate spectral noise. Then, diverse methods such as linear and multiple regressions and machine learning were used to model and predict the MC. Finally, the best wavelength capable of precise estimation of the MC was reported. Investigation of the previous studies revealed that HSI technology could be employed as a valuable technique to precisely control the drying process. Smart dryers are expected to be commercialised and industrialised soon by the development of portable systems capable of an online MC measurement.

Nondestructive testing methods for pesticide residue in food commodities: A review

Pesticides play an important role in increasing the overall yield and productivity of agricultural foods by controlling pests, insects, and numerous plant-related diseases. However, the overuse of pesticides has resulted in pesticide contamination of food products and water bodies, as well as disruption of ecological and environmental systems. Global health authorities have set limits for pesticide residues in individual food products to ensure the availability of safe foods in the supply system and to assist farmers in developing the best agronomic practices for crop production. Therefore, the use of nondestructive testing (NDT) methods for pesticide residue detection is gaining interest in the food supply chain. The NDT techniques have several advantages, such as simultaneous measurement of chemical and physical characteristics of food without destroying the product. Although numerous studies have been conducted on NDT for pesticide residue in agro-food products, there are still challenges in real-time implementation. Further study on NDT methods is needed to establish their potential for supplementing existing methods, identifying mixed pesticides, and performing volumetric quantification (not surface accumulation alone).

Nondestructive Detection of Pesticide Residue (Chlorpyrifos) on Bok Choi (Brassica rapa subsp. Chinensis) Using a Portable NIR Spectrometer Coupled with a Machine Learning Approach

The contamination of agricultural products, such as vegetables, by pesticide residues has received considerable attention worldwide. Pesticide residue on vegetables constitutes a potential risk to human health. In this study, we combined near infrared (NIR) spectroscopy with machine learning algorithms, including partial least-squares discrimination analysis (PLS-DA), support vector machine (SVM), artificial neural network (ANN), and principal component artificial neural network (PC-ANN), to identify pesticide residue (chlorpyrifos) on bok choi. The experimental set comprised 120 bok choi samples obtained from two small greenhouses that were cultivated separately. We performed pesticide and pesticide-free treatments with 60 samples in each group. The vegetables for pesticide treatment were fortified with 2 mL/L of chlorpyrifos 40% EC residue. We connected a commercial portable NIR spectrometer with a wavelength range of 908-1676 nm to a small single-board computer. We analyzed the pesticide residue on bok choi using UV spectrophotometry. The most accurate model correctly classified 100% of the samples used in the calibration set in terms of the content of chlorpyrifos residue on samples using SVM and PC-ANN with raw data spectra. Thus, we tested the model using an unknown dataset of 40 samples to verify the robustness of the model, which produced a satisfactory F1-score (100%). We concluded that the proposed portable NIR spectrometer coupled with machine learning approaches (PLS-DA, SVM, and PC-ANN) is appropriate for the detection of chlorpyrifos residue on bok choi.

Automatic detection of pesticide residues on the surface of lettuce leaves using images of feature wavelengths spectrum

The inappropriate application of pesticides to vegetable crops often results in environmental pollution, which seriously impacts the environment and human health. Given that current methods of pesticide residue detection are associated with issues such as low accuracy, high equipment cost, and complex flow, this study puts forward a new method for detecting pesticide residues on lettuce leaves. To establish this method, spectral analysis was used to determine the characteristic wavelength of pesticide residues (709 nm), machine vision equipment was improved, and a bandpass filter and light source of characteristic wavelength were installed to acquire leaf image information. Next, image preprocessing and feature information extraction were automatically implemented through programming. Several links were established for the training model so that the required feature information could be automatically extracted after the batch input of images. The pesticide residue detected using the chemical method was taken as the output and modeled, together with the input image information, using the convolutional neural network (CNN) algorithm. Furthermore, a prediction program was rewritten to generalize the input images during the prediction process and directly obtain the output pesticide residue. The experimental results revealed that when the detection device and method designed in this study were used to detect pesticide residues on lettuce leaves in a key state laboratory, the coefficient of determination of the equation reached 0.883, and the root mean square error (RMSE) was 0.134 mg/L, indicating high accuracy and that the proposed method integrated the advantages of spectrum detection and deep learning. According to comparison testing, the proposed method can meet Chinese national standards in terms of accuracy. Moreover, the improved machine vision equipment was less expensive, thus providing powerful support for the application and popularization of the proposed method.

Investigating Changes in pH and Soluble Solids Content of Potato during the Storage by Electronic Nose and Vis/NIR Spectroscopy

Potato is an important agricultural product, ranked as the fourth most common product in the human diet. Potato can be consumed in various forms. As customers expect safe and high-quality products, precise and rapid determination of the quality and composition of potatoes is of crucial significance. The quality of potatoes may alter during the storage period due to various phenomena. Soluble solids content (SSC) and pH are among the quality parameters experiencing alteration during the storage process. This study is thus aimed to assess the variations in SSC and pH during the storage of potatoes using an electronic nose and Vis/NIR spectroscopic techniques with the help of prediction models including partial least squares (PLS), multiple linear regression (MLR), principal component regression (PCR), support vector regression (SVR) and an artificial neural network (ANN). The variations in the SSC and pH are ascending and significant. The results also indicate that the SVR model in the electronic nose has the highest prediction accuracy for the SSC and pH (81, and 92%, respectively). The artificial neural network also managed to predict the SSC and pH at accuracies of 83 and 94%, respectively. SVR method shows the lowest accuracy in Vis/NIR spectroscopy while the PLS model exhibits the best performance in the prediction of the SSC and pH with respective precision of 89 and 93% through the median filter method. The accuracy of the ANN was 85 and 90% in the prediction of the SSC and pH, respectively.

Discrimination of Pesticide Residue Levels on the Hami Melon Surface Using Multiscale Convolution

Pesticide residues directly or indirectly threaten the health of humans and animals. We need a rapid and nondestructive method for the safety evaluation of fruits. In this study, the feasibility of visible/near-infrared (Vis/NIR) spectroscopy technology was explored for the discrimination of pesticide residue levels on the Hami melon surface. The one-dimensional convolutional neural network (1D-CNN) model was proposed for spectral data discrimination. We compared the effect of different convolutional architectures on the model performance, including single-depth, symmetric, and asymmetric multiscale convolution. The results showed that the 1D-CNN model could discriminate the presence or absence of pesticide residues with a high accuracy above 99.00%. The multiscale convolution could significantly improve the model accuracy while reducing the modeling time. In particular, the asymmetric convolution had a better comprehensive performance. For two-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 93.68% and 95.79%, respectively. For three-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 86.32% and 89.47%, respectively. For four-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 87.37% and 93.68%, respectively, and the average modeling time was 3.5 s. This finding will encourage more relevant research to use multiscale 1D-CNN as a spectral analysis strategy for the detection of pesticide residues in fruits.

Rapid Analysis of Raw Meal Composition Content Based on NIR Spectroscopy for Cement Raw Material Proportioning Control Process

Due to fast analysis speed, analyzing composition content of cement raw meal utilizing near infrared (NIR) spectroscopy, combined with partial least squares regression (PLS), is a reliable alternative method for the cement industry to obtain qualified cement products. However, it has hardly been studied. The raw materials employed in different cement plants differ, and the spectral absorption intensity in the NIR range of the raw meal component is weaker than organic substances, although there are obvious absorption peaks, which place high demands on the generality of modeling and accuracy of the analytical model. An effective modeling procedure is proposed, which optimizes the quantitative analytical model from several modeling stages, and two groups of samples with different raw material types and origins are collected to validate it. For the samples in the prediction set from Qufu, the root mean square error of prediction (RMSEP) of CaO, SiO2, Al2O3, and Fe2O3 were 0.1910, 0.2307, 0.0921, and 0.0429, respectively; the average prediction errors for CaO, SiO2, Al2O3, and Fe2O3 were 0.171%, 0.193%, 0.069%, and 0.032%, respectively; for the samples in the prediction set from Linyi, the RMSEP of CaO, SiO2, Al2O3, and Fe2O3 were 0.1995, 0.1267, 0.0336 and 0.0242, respectively, the average prediction errors for CaO, SiO2, Al2O3, and Fe2O3 were 0.154%, 0.100%, 0.022%, and 0.018%, respectively. The standard methods for chemical analysis of cement require that the mean measurement error for CaO, SiO2, Al2O3, and Fe2O3 should be within 0.40%, 0.30%, 0.20%, and 0.15%, respectively. It is obvious that the results of both groups of samples fully satisfied the requirements of raw material proportioning control of the production line, demonstrating that the modeling procedure has excellent generality, the models established have high prediction accuracy, and the NIR spectroscopy combined with the proposed modeling procedure is a rapid and accurate alternative approach for the analysis of cement raw meal composition content.

Optimization of diffuse reflectance spectroscopy measurements for direct and rapid screening of pesticides: A case study of spinach

Although diffuse reflectance spectroscopy (DRS) measurements can be collected rapidly and simultaneously, the resulting datasets are imbalanced and redundant due to the highly correlated spectral features collected on relatively few samples. Consequently, modelling these datasets using machine learning (ML) techniques is challenging and necessitates longer training times and more computational resources. Furthermore, models developed with such data are frequently prone to overfitting, resulting in promising but often non-reproducible results. We demonstrate the advantage of using an eigenvector decomposition principal component analysis (PCA) in reducing the dimensionality and data mining of DRS measurements in the short near-infrared region (750-900 nm). A total of 547 DRS measurements consisting of 151 wavelengths were acquired from spinach samples sprayed with two different pesticides and control samples. The measurements were later preprocessed with a Savitzky-Golay filter and multiplicative scatter analysis. After performing PCA on the preprocessed data, two principal components (PCs) that explained 77% of the cumulative variance and maximized the interclass variation were extracted and used as inputs to three ML models namely; artificial neural networks, support vector machine and random forest, to classify the samples. Re-sampling was used to tune the models and avoid overfitting. The performance of the models was compared using raw DRS data, pre-processed (PP) DRS data, and PCs data. The results show that pesticide classification using PCs data requires the least amount of training time (average 2.4 s) for all the models, and achieves 100% classification accuracy. In addition, it was observed that spectral data pre-processing improves accuracy and training time when compared to using raw spectral data. These findings are particularly encouraging since they demonstrate the possibility of developing rapid and accurate classification models for screening pesticide residues in fresh produce based on DRS measurements with minimal computational resources.

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Rapid and accurate detection of pesticide residue levels can help to prevent the harm of pesticide residue. This study used visible/near-infrared (Vis-NIR) (376–1044 nm) and near-infrared (NIR) (915–1699 nm) hyperspectral imaging systems (HISs) to detect the level of pesticide residues. Three different varieties of grapes were sprayed with four levels of pesticides. Logistic regression (LR), support vector machine (SVM), random forest (RF), convolutional neural network (CNN), and residual neural network (ResNet) models were used to build classification models for pesticide residue levels. The saliency maps of CNN and ResNet were conducted to visualize the contribution of wavelengths. Overall, the results of NIR spectra performed better than those of Vis-NIR spectra. For Vis-NIR spectra, the best model was ResNet, with the accuracy of over 93%. For NIR spectra, LR was the best, with the accuracy of over 97%, but SVM, CNN, and ResNet also showed closed and fine results. The saliency map of CNN and ResNet presented similar and closed ranges of crucial wavelengths. Overall results indicated deep learning performed better than conventional machine learning. The study showed that the use of hyperspectral imaging technology combined with machine learning can effectively detect the level of pesticide residues in grapes.

A New LC-MS Method for Evaluating the Efficacy of Pesticide Residue Removal from Fruit Surfaces by Washing Agents

Modern agriculture uses pesticides to improve the quality and quantity of crops. However, pesticide residues can remain on agricultural products, posing very serious risks to human health and life. It is recommended to wash fruits and vegetables before consumption. To assess the removal efficacy of pesticide residue, a sensitive and reliable method based on ultrahigh-performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS) was developed and optimized for the simultaneous determination of four pesticide residues (acetamiprid, boscalid, pyraclostrobin, and pendimethalin). Isotope-labeled standards were used to validate the method in terms of recovery, linearity, matrix effects, precision, and sensitivity. The mean recovery values for both low-quality control (LQC) and high-quality control (HQC) transitions were in the range of 89–105%, and the intra-day precision was less than 13.7%. The limits of detection (LOD) and quantification (LOQ) were 0.003 mg/kg and 0.01 mg/kg, respectively. The proposed method is suitable for evaluating the quality of detergents for removing pesticide residues from fruit surfaces.