Identification Of Pesticide Residues Research Articles

Classification of Pesticide Residues in Sorghum Based on Hyperspectral and Gradient Boosting Decision Trees

ABSTRACTTo address the challenges posed by chemical methods for detecting pesticide residues in sorghum, such as complicated sample preparation and prolonged detection periods, this study presents a rapid and nondestructive detection approach based on hyperspectral imaging (HSI) technology. A group of sorghum without pesticide residues and three groups uniformly sprayed with pesticides were used in this study. Firstly, support vector machine (SVM) classification models were built using spectral data preprocessed with Savitzky–Golay (SG), discrete wavelet transform (DWT), and standard normal variate (SNV) methods, respectively, and SNV was determined to be the best preprocessing method. Secondly, the gradient boosting decision tree (GBDT) algorithm, principal component analysis (PCA), and the successive projections algorithm (SPA) were respectively used to extract feature wavelengths. Pesticide residue identification models based on full and feature wavelengths were then respectively established using backpropagation neural network (BPNN), SVM, and partial least squares discriminant analysis (PLS‐DA). The results show that the BPNN model developed using the feature wavelengths obtained from GBDT was the best for identification of pesticide residues, with an accuracy of 97.8% for both the training and testing sets. Finally, visualization of pesticide residue species in sorghum was achieved using the optimal model. This study demonstrates that utilizing HSI in conjunction with the GBDT‐BPNN model is an effective, rapid, and nondestructive method for identifying pesticide residues in sorghum.

Integrating transformer-based machine learning with SERS technology for the analysis of hazardous pesticides in spinach

This study introduces an innovative strategy for the rapid and accurate identification of pesticide residues in agricultural products by combining surface-enhanced Raman spectroscopy (SERS) with a state-of-the-art transformer model, termed SERSFormer. Gold-silver core-shell nanoparticles were synthesized and served as high-performance SERS substrates, which possess well-defined structures, uniform dispersion, and a core-shell composition with an average diameter of 21.44 ± 4.02 nm, as characterized by TEM-EDS. SERSFormer employs sophisticated, task-specific data processing techniques and CNN embedders, powered by an architecture features weight-shared multi-head self-attention transformer encoder layers. The SERSFormer model demonstrated exceptional proficiency in qualitative analysis, successfully classifying six categories, including five pesticides (coumaphos, oxamyl, carbophenothion, thiabendazole, and phosmet) and a control group of spinach data, with 98.4% accuracy. For quantitative analysis, the model accurately predicted pesticide concentrations with a mean absolute error of 0.966, a mean squared error of 1.826, and an R2 score of 0.849. This novel approach, which combines SERS with machine learning and is supported by robust transformer models, showcases the potential for real-time pesticide detection to improve food safety in the agricultural and food industries.

Applications of chemically modified screen-printed electrodes in food analysis and quality monitoring: a review.

Food analysis and food quality monitoring are vital aspects of the food industry, ensuring the safety and authenticity of various food products, from packaged goods to fast food. In this comprehensive review, we explore the applications of chemically modified Screen-Printed Electrodes (SPEs) in these critical domains. SPEs have become extremely useful devices for ensuring food safety and quality assessment because of their adaptability, affordability, and convenience of use. The Introduction opens the evaluation, that covers a wide spectrum of foods, encompassing packaged, junk food, and food quality concerns. This sets the stage for a detailed exploration of chemically modified SPEs, including their nature, types, utilization, and the advantages they offer in the context of food analysis. Subsequently, the review delves into the multitude applications of SPEs in food analysis, ranging from the detection of microorganisms such as bacteria and fungi, which are significant indicators of food spoilage and safety, to the identification of pesticide residues, food colorants, chemicals, toxins, and antibiotics. Furthermore, chemically modified SPEs have proven to be invaluable in the quantification of metal ions and vitamins in various food matrices, shedding light on nutritional content and quality.

Identification of procymidone in rapeseed oils based on olfactory visualization technology

A new method for qualitative identification of pesticide residues in edible oil based on olfactory visualization technology is proposed. Firstly, according to the pre-experimental experience, 12 suitable chemical dyes were selected to prepare sensor arrays to form an olfactory visualization system. The system was used to gather volatile odor information in rapeseed oil samples that had different levels of procymidone residues. Subsequently, the olfactory information was translated into a visual representation. Then, the visual data, i.e. color features, were preprocessed and underwent principal component analysis to extract and reduce the dimensionality of sensor image information, resulting in the optimal number of principal components (PCs). Finally, three different models based on the sensor image features were constructed for analysis. These models included the support vector machine (SVM), the random forest (RF) and the kernel based extreme learning machine (KELM). In process of model correction, the parameters of the three models were optimized by dung beetle optimizer (DBO) algorithm, resulting in the identification of the optimal parameters. The results show that the cumulative variance contribution increases slowly when the number of PCs starts from 6, and the three models (i.e. DBO-SVM, DBO-RF, and DBO-KELM) have the best prediction results when PCs = 6. Compared to the DBO-RF and DBO-KELM models, the training and prediction performance of the SVM model based on the DBO optimization algorithm is more stable and has the higher recognition accuracy of the samples, reaching 100%. The results show that it is feasible to use olfactory visualization technology to achieve high-precision qualitative identification of edible oil pesticide residues.

The Open Pesticide Transition Library (oPestTL).

The identification of pesticide residues is a critical application in environmental and food safety analysis. The most common methods for pesticide residue detection and quantification are performed with liquid chromatography tandem mass spectrometry (LCMS) using instruments with varying architectures and characteristics. Pesticides have diverse structural and elemental compositions and often require laborious instrument-specific user optimization to identify ideal adducts and fragment ions. While pesticide transition libraries can be purchased from instrument vendors, little of this information exists in the public domain. The Open Pesticide Transition Library (oPestTL) is an effort to compile a comprehensive list of pesticide ion targets and fragments to facilitate the rapid development of screening methods for any LCMS hardware configuration. While a work that must inevitably evolve, the oPestTL library release detailed here contains over 4,000 individual transitions spread across seven separate LCMS platforms making it the largest openly available collection of pesticide methods ever assembled. The oPestTL library can be freely downloaded or interrogated through an open web application: https://proteomicsnews.shinyapps.io/oPestTLv104/.

Identification of pesticide residues on black tea by fluorescence hyperspectral technology combined with machine learning

Black tea has a long history in China, but in export trade, pesticide residues often exceed the standard. To obtain a rapid, accurate, and non-destructive identification method of pesticide residues on black tea, the fluorescence hyperspectral data of dry black tea sprayed with distilled water and six pesticides were collected in this study. The spectra were preprocessed by multiplicative scatter correction (MSC) and standard normal variate (SNV). Then the uninformative variable elimination (UVE), successive projections algorithm (SPA), competitive adaptive re-weighted sampling (CARS), UVE-SPA, and CARS-SPA were used to feature extraction. This study proposes a machine learning model composed of a one-dimensional convolutional neural network backbone (1D CNN backbone) and a random forest classifier (RF classifier) to identify pesticide residues on black tea, and the 1D CNN-RF model was compared with three other machine learning models (support vector machine, RF, and 1D CNN). The results show that MSC-CARS-SPA-1D CNN-RF is the best model for identifying pesticide residues on black tea in which the accuracy of the test set is 99.05%. Combined with fluorescence hyperspectral technology, the proposed 1D CNN-RF model has great potential in the non-destructive identification of pesticide residues on black tea.

Applications of nDATA for screening, quantitation, and identification of pesticide residues in fruits and vegetables using UHPLC/ESI Q-Orbitrap all ion fragmentation and data independent acquisition.

High sample throughput and effective multiresidue methods for screening, quantitation, and identification are desired for the analysis of a large number of pesticides in routine monitoring programs for food safety. This study was designed to explore the use of an UHPLC/ESI Q-Orbitrap nontarget data acquisition for target analysis (nDATA) workflow for screening 655 pesticides and quantifying a small group of 46 most likely incurred pesticide residues in fruits and vegetables in a single analysis. High-resolution mass spectrometers such as the Q-Orbitrap offer unique applications for pesticide analysis using full MS scan with data independent acquisition (DIA) or all ion fragmentation (AIF) scan. The experiments were designed to achieve a balance between selectivity and cycle time by considering parameter settings such as mass resolution and the number of mass isolation windows or isolation window widths. Coupled with ultra-high performance liquid chromatography (UHPLC), both full MS/DIA and full MS/AIF nDATA workflows were evaluated for screening, quantification, and identification in a single analysis. In general, UHPLC/ESI full MS/vDIA detected more fragment ions per pesticide than AIF when one to four fragments were compared. UHPLC/ESI full MS/vDIA and AIF generated comparable quantitative results, but the latter provided slightly better repeatability likely due to its shorter cycle time and more scans across a chromatographic peak. UHPLC/ESI full MS/vDIA may be preferable for screening, quantitation and identification when the testing scope covers a few hundreds of pesticides in a single analysis.

Nondestructive identification of pesticide residues on the Hami melon surface using deep feature fusion by Vis/NIR spectroscopy and 1D‐CNN

AbstractNondestructive identification of pesticide residues remains a challenge in terms of fruit safety assessment. In this study, a novel method based on visible/near‐infrared (Vis/NIR) spectroscopy (348.45–1,141.34 nm) combined with deep feature fusion was proposed, achieving nondestructive identification of pesticide residues on the Hami melon surface. The spectra of Hami melons with clear water and three kinds of pesticide residues (chlorothalonil, imidacloprid, and pyraclostrobin) were collected in the diffuse reflectance mode. The one‐dimensional convolutional neural network (1D‐CNN), with increased width and depth through parallel convolution modules and concatenate layers, was presented to capture multiple deep features from Vis/NIR spectra and fuse them. This model had a better performance for four‐class identification as the accuracy of 95.83%, and outperformed other CNN models and conventional approaches (partial least squares discriminant analysis and support vector machine). Moreover, the proposed 1D‐CNN model could accurately differentiate whether there were pesticide residues with the identification accuracy as 99.17%. However, the prediction of imidacloprid and pyraclostrobin residues was not accurate due to the similar spectral features. The overall studies indicated that the 1D‐CNN model with deep feature fusion looked promising for nondestructive identification of pesticide residues on the Hami melon surface based on Vis/NIR spectroscopy.Practical applicationsVisible and near‐infrared (Vis/NIR) spectroscopy, as a nondestructive technique, looks promising for evaluation of fruit quality and safety. One‐dimensional convolutional neural network, with deep feature fusion structure to capture multi‐scale spectral information, has a better identification of pesticide residues on the Hami melon surface. Vis/NIR spectroscopy with deep feature fusion can be applied in research and development of a nondestructive detector for pesticide residues on the thick‐skinned fruit surface in the future.

Rapid on-site identification of pesticide residues in tea by one-dimensional convolutional neural network coupled with surface-enhanced Raman scattering.

In this study, a novel analytical approach is proposed for the identification of pesticide residues in tea by combining surface-enhanced Raman scattering (SERS) with a deep learning method one-dimensional convolutional neural network (1D CNN). First, a handheld Raman spectrometer was used for rapid on-site collection of SERS spectra. Second, the collected SERS spectra were augmented by a data augmentation strategy. Third, based on the augmented SERS spectra, the 1D CNN models were established on the cloud server, and then the trained 1D CNN models were used for subsequent pesticide residue identification analysis. In addition, to investigate the identification performance of the 1D CNN method, four conventional identification methods, including partial least square-discriminant analysis (PLS-DA), k-nearest neighbour (k-NN), support vector machine (SVM) and random forest (RF), were also developed on the basis of the augmented SERS spectra and applied for pesticide residue identification analysis. The comparative studies show that the 1D CNN method possesses better identification accuracy, stability and sensitivity than the other four conventional identification methods. In conclusion, the proposed novel analytical approach that exploits the advantages of SERS and a deep learning method (1D CNN) is a promising method for rapid on-site identification of pesticide residues in tea.

Identification of Pesticide Residues and Prediction of Their Fate in Agricultural Soil

Fourteen pesticides were screened and determined through quick, easy, cheap, effective, rugged, and safe (QuEChERS) extraction process combined with GC-MS/MS in arid agriculture soil. The aims of the current investigation were to account the occurrence of organochlorine (OCP) and organophosphates (OPP) pesticide residues as well as other groups of pyrethroids (PYRs), carbamates, and biopesticides using a combined of QuEChERS and GC-MS/MS techniques in agriculture soils at Al-Kharj region, Saudi Arabia, and to investigate correlation between pesticide losses in soils and some physicochemical characteristics of pesticides including an octanol-water coefficient partition (Kow) and the vapor pressure (Vp). Prediction of pesticide fate by considering both pesticide and soil physio-chemical properties will facilitate the management of pesticide application and minimize the hazards of environmental pollution. The fate of pesticide residue in soils is generally controlled by soil/air exchange, water interaction, and biodegradation. The results indicated that 14 pesticide residues were measured in collected samples of various soils, spinosad, chlorpyrifos methyl, dimethoate, chlorpyrifos, lindane (γ-HCH), permethrin, and methomyl which were the most abundant sources of contamination in the studied region. p,p-DDT, o,p-DDT, bifenthion, β-cyfluthrin, and methidathion were less commonly detected. Single parameter least squares regression equations (sp-LSRE) for Vp and Kow against the loss of each pesticide residue showed a significant change in concentration levels (p < 0.05) between the two seasons. The results showed that vapor pressure and octanol-water partition coefficient data are not enough to model pesticide residue losses in arid low organic carbon soil. More soil-related data is needed to describe the dissipation mechanisms of these pesticide residues in the region.

Qualitative Identification of Pesticide Residues in Pakchoi Based on Near Infrared Spectroscopy

This paper provided a new method for rapid and nondestructive classification and identification of vegetable residues. Near Infrared Spectroscopy (NIR) of two kinds of pakchoi were collected. One kind of pakchoi was non-pesticide. And the other was low concentration of pesticide residues . In this paper, wavelet soft threshold was used to pre-treat the spectral data. Then Principal Component Analysis (PCA) was run to reduce the dimensionality of spectral data. Next, Linear Discriminant Analysis (LDA) and K-Nearest Neighbor Classification and Recognition (KNN) was run to classify and discriminate. The experimental results show that the prediction rate is 95%. This method is accurate and effective.

Identification of pesticide residues in lettuce leaves based on near infrared transmission spectroscopy

AbstractTo explore the nondestructive and accurate qualitative detection method of pesticide residues in vegetables, lettuce leaves were taken as carrier and pesticides (fenvalerate and chlorpyrifos) were taken as research object. The near infrared spectral data of lettuce leaves was collected by using near infrared spectrometer NIRez (950–1,650 nm), then it was preprocessed by SNV algorithm and SG‐SNV combination, respectively. The successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), iteratively retaining informative variables (IRIV), and combination of two of them were used to select characteristic wavelengths from the preprocessed spectral data, respectively. In this study, support vector machine (SVM) was used to classify pesticide residues in lettuce leaves. Because the classification performance of SVM was influenced by parameters c (penalty coefficient) and g (kernel function parameter), so the parameters c and g of SVM were optimized by gravitational search algorithm (GSA). Finally, identification models were built on the full wavelengths and the selected characteristic wavelengths, respectively. Final result showed that CARS‐IRIV‐GSA‐SVM model had the best performance, and the classification accuracy of training set and predication set reached 100 and 98.33%. Therefore, near infrared transmission spectroscopy can be applied to the qualitative detection of pesticide residues in lettuce leaves.Practical applicationsLettuce leaves can be eaten raw, but pesticide residues in lettuce leaves are likely to do harm to human health. Near infrared transmission spectroscopy, a fast and nondestructive technology, can be used to detect pesticide residues in lettuce leaves. Furthermore, the small NIR spectrometer used in this study can also provide some idea for the production of portable pesticide residue detector. This study demonstrated that near infrared transmission spectroscopy can be applied to the qualitative detection of pesticide residues in lettuce leaves.

Classification and Identification of Pesticide Residues in Cucumber Based on Near Infrared Spectroscopy

To explore the feasibility of Near Infrared spectroscopy (NIR) for rapid and nondestructive qualitative identification of pesticide residues in vegetables, this paper presents a qualitative classification and discrimination method based on Support Vector Machine (SVM) with Gaussian Radial Basis Function (RBF). The cucumber with three kinds of pesticide residue levels (no pesticide, standard pesticide residue, severe excess) was used as the research object. The total reflectance NIR spectra of two groups of cucumber were collected after spraying 24 hours and 48 hours of pesticide respectively. First, Principal Component Analysis (PCA) was applied to dimensionality reduction of spectral data. Then normalize the spectrum. Next, the SVM training model based on RBF was established, and then SVM prediction was carried out. The correct recognition rate of the training set was 100%, and the correct prediction rate of the test set was 94.4444% and 95.5556%, respectively. Experiments show that this method is accurate and fast for qualitative classification and identification of pesticide residues in cucumbers with different concentrations, and provides a new idea for rapid non-destructive detection of vegetable pesticide residues.

A green, reusable SERS film with high sensitivity for in-situ detection of thiram in apple juice

We report a green and reusable surface-enhanced Raman scattering (SERS) film based on PMMA/Ag NPs/graphene. By using this Raman substrate, the SERS signals of R6G were significantly enhanced reaching a minimum detectable concentration of 5×10−8M, due to having lots of hot spots adhered backside to the exposed graphene. The SERS film can be used for in-situ monitoring of trace thiram in apple juice with a detection limit of 1×10−6M (0.24ppm), which is below the maximal residue limit (MRL) of 7ppm in fruit prescribed by the U.S. Environmental Protection Agency (EPA). Furthermore, reusability studies show that the SERS film can be used repeatedly. In addition, the graphene-enhanced SERS technique shows great potential applications for the in-situ detection and identification of pesticide residues in environmental water, fruits and vegetables.

Image processing based technique for classification of fish quality after cypermethrine exposure

The quality of fish is primarily dependent on its handling, processing, storage, exposure to contaminants and on climatic variability. Fishes nurtured at fresh and contaminated water exhibit marked differences in quality. Among different contaminants, pesticide is reported as a predominant non-specific menace to fish health and quality. Detection and identification of pesticide residues in fish is a challenging task and requires costly sophisticated instruments. This paper proposes an image processing based non-destructive technique for identifying quality differences between pesticide treated and untreated (control) fish. To evaluate the quality variability, rohu (Labeorohita) fishes were treated with mild dose of cypermethrin for seven days and bio-accumulation status was recorded through GC–MS at post-harvested condition followed by imaging at two days interval. Gill tissue was selected as focal tissue for image processing which was segmented and different features were extracted in wavelet domain using Haar filter. Features were selected up to the third level of decomposition in wavelet domain and analysed for discriminatory features. The discriminatory variations in the different features of images were related to the difference between pesticide treated and untreated fish using strategic image processing techniques. Supervised classification was performed on the extracted features using support vector machine (SVM) classifier. The experimental results indicate that the proposed method is efficient for identification of pesticide treated and untreated fish from the features of the images. The accuracy of identification is high and the computation time is faster enough to make this method efficient as a real time application.

Ag dendritic nanostructures for rapid detection of thiram based on surface-enhanced Raman scattering

We have developed a SERS-active substrate based on Ag dendritic nanostructures for sensitive Raman signal readout and fingerprint identification of pesticide residues in agricultural products and environments.

Determination of selected pesticides in water samples adjacent to agricultural fields and removal of organophosphorus insecticide chlorpyrifos using soil bacterial isolates

The use of pesticide for crops leads to serious environmental pollution, therefore, it is essential to monitor and develop approaches to remove pesticide from contaminated environment. In this study, water samples were collected to monitor pesticide residues, and degradation of chlorpyrifos was also performed using soil bacteria. Identification of pesticide residues and determination of their levels were performed by high-performance liquid chromatography with photodiode array detector. Among 12 samples, 10 samples were found contaminated with pesticides. Chlorpyrifos was detected in four tested samples and concentrations ranged from 3.27 to 9.31 μg/l whereas fenitrothion ranging from (Below Detection Limit, <0.1 μg/l) to 33.41 μg/l in the tested samples. Parathion was found in two tested samples at the concentration of 0.73 and 6.23 μg/l. None of the tested samples was found contaminated with Methoxychlor, DDT and Ethion. Three soil bacterial isolates, Pseudomonas peli BG1, Burkholderia caryophylli BG4 and Brevundimonas diminuta PD6 degraded chlorpyrifos completely in 8, 10 and 10 days, respectively, when 20 mg/l chlorpyrifos was supplied as sole source of carbon. Whereas, BG1, BG4 and PD6 took 14, 16 and 16 days, respectively, for complete removal of 50 mg/l chlorpyrifos. Chlorpyrifos degradation rates were found maximum by all three isolates at 2nd day of incubation for both tested concentrations. The results of the present study suggest the need for regular monitoring of pesticide residues in water, to protect the aquatic environment. Chlorpyrifos degrading bacterial isolates can be used to clean up environmental samples contaminated with the organophosphate pesticides.

Identification of pesticide residues in common fruits and vegetables by gas chromatography-quadrupole time-of-flight mass spectrometry

A new screening method was developed for the determination of 152 pesticide multi-residues in different chemical species with a Carbon NH2 column using solid-phase extraction (SPE) coupled with gas chromatography-quadrupole time-of-flight mass spectrometry (GC-QTOF MS). In the first stage (MS1) accurate mass database, up to three-five ions of the pesticides were monitored. The presence of at least three ions and the accomplishment of the intensity ratio (Q/q(i)) within the established tolerances were used as the confirmation of intensity criteria. The pesticides which have less characteristic ions or the peaks of the characteristic ions detected were up the tolerance were determined in the second stage (MS2) and the spectral difference was evaluated using MS2 library for the identified. Cabbage, tomato, pear were selected as typical fruits and vegetables to spike and detected all the 152 pesticides at two concentration levels of 5.0 and 10.0 microg/kg. The recoveries in the range of 70%-120% at two concentration levels were 91.45% and 94.08% for cabbage, 88.20% and 88.80% for tomato, 86.84% and 92.10% for pear respectively. Using the established 152 pesticide MS2 library some suspected pesticides were identified, and at the same time the analysis scope was expanded.

Identification of Pesticide Residues of Lettuce Leaves Based on LVQ Neural Network

In order to ensure the healthy safety of edible lettuce, an identification way of pesticide residues of lettuce leaves is studied. Soilless cultivation of lettuce sample was adopted. At tillering stage, various levels of fenvalerate were sprayed to different groups of lettuce, lettuce leaves accompanied by a collection of pesticide residues and lettuce leaves not sprayed pesticide residues were collected, Hyperspectral Information of each blade leaf were collected and lettuce leaves sample spectral library was set up. Randomly 90 samples were selected as training samples, and the classification models based on BP neural network and LVQ neural network were set up. The remaining samples were taken to forecast classification test. Results showed that, the prediction identification correct rate of LVQ neural network model is 98.3607%. The algorithm is suitable for pesticide residues diagnosis of lettuce leaves.

Shell Thickness-Dependent Raman Enhancement for Rapid Identification and Detection of Pesticide Residues at Fruit Peels

Here, we report the shell thickness-dependent Raman enhancement of silver-coated gold nanoparticles (Au@Ag NPs) for the identification and detection of pesticide residues at various fruit peels. The Raman enhancement of Au@Ag NPs to a large family of sulfur-containing pesticides is ~2 orders of magnitude stronger than those of bare Au and Ag NPs, and there is a strong dependence of the Raman enhancement on the Ag shell thickness. It has been shown for the first time that the huge Raman enhancement is contributed by individual Au@Ag NPs rather than aggregated Au@Ag NPs with "hot spots" among the neighboring NPs. Therefore, the Au@Ag NPs with excellent individual-particle enhancement can be exploited as stand-alone-particle Raman amplifiers for the surface identification and detection of pesticide residues at various peels of fruits, such as apple, grape, mango, pear, and peach. By casting the particle sensors onto fruit peels, several types of pesticide residues (e.g., thiocarbamate and organophosphorous compounds) have been reliably/rapidly detected, for example, 1.5 nanograms of thiram per square centimeter at apple peel under the current unoptimized condition. The surface-lifting spectroscopic technique offers great practical potentials for the on-site assessment and identification of pesticide residues in agricultural products.