Search

The Zhuhai-1 hyperspectral satellite can simultaneously obtain spectral information in 32 spectral bands and effectively obtain accurate information on land features through integrated hyperspectral observations of the atmosphere and land, while the presence of clouds can contaminate remote sensing images. To improve the utilization rate of hyperspectral images, this study investigates the cloud detection method for hyperspectral satellite data based on the transfer learning technique, which can obtain a model with high generalization capability with a small training sample size. In this study, for the acquired Level-1B products, the top-of-atmosphere reflectance data of each band are obtained by using the calibration coefficients and spectral response functions of the product packages. Meanwhile, to eliminate the data redundancy between hyperspectral bands, the data are downscaled using the principal component transformation method, and the top three principal components are extracted as the sample input data for model training. Then, the pretrained VGG16 and ResNet50 weight files are used as the backbone network of the encoder, and the model is updated and trained again using Orbita hyperspectral satellite (OHS) sample data to fine-tune the feature extraction parameters. Finally, the cloud detection model is obtained. To verify the accuracy of the method, the multi-view OHS images are visually interpreted, and the cloud pixels are sketched out as the baseline data. The experimental results show that the overall accuracy of the cloud detection model based on the Resnet50 backbone network can reach 91%, which can accurately distinguish clouds from clear sky and achieve high-accuracy cloud detection in hyperspectral remote sensing images.

In the food domain, text mining techniques are extensively employed to derive valuable insights from large volumes of text data, facilitating applications such as aiding food recalls, offering personalized recipes, and reinforcing food safety regulation. To provide researchers and practitioners with a comprehensive understanding of the latest technology and application scenarios of text mining in the food domain, the pertinent literature is reviewed and analyzed. Initially, the fundamental concepts, principles, and primary tasks of text mining, encompassing text categorization, sentiment analysis, and entity recognition, are elucidated. Subsequently, an analysis of diverse types of data sources within the food domain and the characteristics of text data mining is conducted, spanning social media, reviews, recipe websites, and food safety reports. Furthermore, the applications of text mining in the food domain are scrutinized from the perspective of various scenarios, including leveraging consumer food reviews and feedback to enhance product quality, providing personalized recipe recommendations based on user preferences and dietary requirements, and employing text mining for food safety and fraud monitoring. Lastly, the opportunities and challenges associated with the adoption of text mining techniques in the food domain are summarized and evaluated. In conclusion, text mining holds considerable potential for application in the food domain, thereby propelling the advancement of the food industry and upholding food safety standards. [ABSTRACT FROM AUTHOR]

In addition to the conventional situation of detecting a single disease on a single leaf in corn leaves, there is a complex phenomenon of multiple diseases overlapping on a single leaf (compound diseases). Current research on corn leaf disease detection predominantly focuses on single leaves with single diseases, with limited attention given to the detection of compound diseases on a single leaf. However, the occurrence of compound diseases complicates the accuracy of traditional deep learning algorithms for disease detection, necessitating the exploration of new models for the identification of compound diseases on corn leaves. To achieve rapid and accurate identification of compound diseases in corn fields, this study adopts the YOLOv5s model as the base network, chosen for its smaller size and faster detection speed. We propose a corn leaf compound disease recognition method, YOLOv5s-C3CBAM, based on an attention mechanism. To address the challenge of limited data for corn leaf compound diseases, a CycleGAN model is employed to generate synthetic images. The scarcity of real data is thereby mitigated, facilitating the training of deep learning models with sufficient data. The YOLOv5s model is selected as the base network, and an attention mechanism is introduced to enhance the network's focus on disease lesions while mitigating interference from compound diseases. This augmentation results in improved recognition accuracy. The YOLOv5s-C3CBAM compound disease recognition model, incorporating the attention mechanism, achieves an average precision of 83%, an F1 score of 81.98%, and a model size of 12.6 Mb. Compared to the baseline model, the average precision is improved by 3.1 percentage points. Furthermore, it outperforms Faster R-CNN and YOLOv7-tiny models by 27.57 and 2.7 percentage points, respectively. This recognition method demonstrates the ability to rapidly and accurately identify compound diseases on corn leaves, offering valuable insights for future research on precise identification of compound agricultural crop diseases in field conditions. [ABSTRACT FROM AUTHOR]

In order to address the significant prediction errors resulting from the substantial fluctuations in agricultural product prices and the non-linear features, this paper proposes a hybrid forecasting model based on variational mode decomposition (VMD), ensemble empirical mode decomposition (EEMD), and long short-term memory networks (LSTM). This combined model is referred to as the VMD–EEMD–LSTM model. Initially, the original time series of agricultural product prices undergoes decomposition using VMD to obtain a series of variational mode functions (VMFs) and a residual component with higher complexity. Subsequently, the residual component undergoes a secondary decomposition using EEMD. All components are then fed into an LSTM model for training to obtain predictions for each component. Finally, the predictions for each component are linearly combined to generate the ultimate price forecast. To validate the effectiveness of the VMD–EEMD–LSTM model, empirical analyses were conducted for one-step and multi-step forecasts using weekly price data for pork, Chinese chives, shiitake mushrooms, and cauliflower from China's wholesale agricultural markets. The results indicate that the composite model developed in this study provides enhanced forecasting accuracy. [ABSTRACT FROM AUTHOR]

Accurate and rapid estimation of leaf nitrogen content (LNC) in winter wheat using hyperspectral techniques is important for growth monitoring and accurate fertilization. Based on field experiments conducted over four years at three ecological sites with four different nitrogen (N) application treatments and four different N-efficient wheat varieties in Henan Province, the canopy spectra and LNC of winter wheat were obtained simultaneously in the main growth stages. The original spectrum was subjected to continuum removal (CR), the correlation between LNC and various vegetation indices was systematically analysed, and the optimal vegetation index estimation model for LNC was constructed. Simultaneously, discrete wavelet transform (DWT) was used to further compress and extract the CR spectrum. The model was combined with partial least squares regression (PLSR) and K-nearest neighbour (KNN) algorithms to estimate LNC in winter wheat. The results showed that the spectrum treated with CR was significantly improved in its correlation with LNC and that the model established based on normalized vegetation index NDVI (CR728, CR977) combined with the CR spectrum was better compared to existing vegetation indices. The calibration and validation coefficients of determination (R2) and root mean square error (RMSE) were 0.816 and 0.799, and 0.352% and 0.342%, respectively. DWT was used to transform the CR spectrum, and the results showed that a combination of the CR spectrum and a sym8 wavelet function with PLSR based on the approximation coefficients at decomposition level 2 predicted LNC most accurately. The coefficient of determination RC2, root mean square error RMSEC, and relative percent deviation (RPDC) of the calibration set were 0.884, 0.279%, and 2.932, respectively, and RV2, RMSEV, and RPDV of the validation set were 0.855, 0.291%, and 2.619, respectively, indicating that the model had good stability and predictive ability. Combination of CR and DWT improved the modelling accuracy of wheat LNC and showed better prediction results for multi-year and multi-point samples. The results of the study can provide a basis and reference for rapid monitoring of LNC in winter wheat. [ABSTRACT FROM AUTHOR]

Wheat take-all is a quarantine disease, which will lead to a disaster in wheat production without timely monitoring and management. Remote sensing technique, especially the field-based imaging spectrum technique, can achieve real-time monitoring of the disease development. For rapid extraction of take-all disease information, we try to monitor wheat take-all disease using imaging spectrometer. The experiment was carried out in Baisha village, Yuanyang County of China. We designed test of three concentration gradients and repeated three times, the experimental field was 30 m2. The wheat take-all white head rate was surveyed two weeks before harvest. The wheat's canopy spectrum was collected by two kinds of spectrometer, ASD Handheld non-imaging spectrometer (ASD Handheld, ASD Inc.) and Headwall imaging spectrometer (HyperSpec® VNIR, Headwall Photonics, Inc.). All data were collected between 10:00 to 13:00 in sunny days. In this study, based on gray association analysis (GAA) and support vector machine (SVM) classifier, a spectral feature extraction and classification method was proposed to separate the spectral features of the different take-all levels from spectral images. The field-based spectral images were acquired by Headwall imaging sensor. Meanwhile, the spectral data about different white head rate were collected by ASD HandHeld non-imaging sensor. Because of better accuracy and resolution, ASD spectral data had a better capacity to express the spectral features of take-all levels. These spectral features were extracted using kernel principle component analysis (K-PCA). Characteristic bands of the first four of principal component was mainly green band, red band and near infrared band, indicated in the spectrum curve, peak and valley phenomenon was the main distinguishing feature of white head rate and take-all disease grade. Then Jeffries-Matusita distances between feature bands were calculated, if Jeffries-Matusita distances between feature bands were greater than 1.8, the selected characteristic bands can distinguish different damage degree of wheat take-all disease. The spectral separability of take-all levels was tested and assessed by grey association analysis. Based on these significant features, some of Headwall imaging spectral data with different take-all levels were selected as the training data for the field-based spectral images. Through the SVM classifier based on RBF kernel function, a hyperspectral classification image of take-all was calculated. Results showed that the wheat take-all widely existed in the experimental zone, but its distribution had own specific characteristic with different disease levels. The slight disease wheat and the heavy disease wheat were mixture in the experimental zone. The distribution characteristics of serious take-all wheat disease (white head rate greater than 60%) were intensive and block. Slight wheat disease (white head rate between 10%-30%) were widely distributed in the middle of heavy wheat disease(white ear rate between 30%-60%), the proportion of slight wheat disease and heavy heat disease was 29.53% and 26.06%, respectively, very serious wheat take-all disease (white head rate between 60%-90%) and death of wheat disease showed regional distribution in the image, accounted for 10.73% and 19.91%.The overall accuracy of the classification was greater than 94% (Kappa>0.8). To further validate the classification accuracy, field experiment survey data was compared with the spectral classification, misclassification existed mainly in white head rate 30%~40%.These results proves the field-based imaging spectrum has the capacity to achieve the real-time monitoring and classification of wheat take-all condition, and to support the guidance on wheat production. [ABSTRACT FROM AUTHOR]

Soft computing is an important computational paradigm, and it provides the capability of flexible information processing to solve real world problems. Agricultural data classification is one of the important applications of computing technologies in agriculture, and it has become a hot topic because of the enormous growth of agricultural data available. Support vector machine is a powerful soft computing technique and it realizes the idea of structural risk minimization principle to find a partition hyperplane that can satisfy the class requirement. Rough set theory is another famous soft computing technique to deal with vague and uncertain data. Ensemble learning is an effective method to learn multiple learners and combine their decisions for achieving much higher prediction accuracy. In this study, the support vector machine, rough set and ensemble learning were incorporated to construct a hybrid soft computing approach to classify the agricultural data. An experimental evaluation of different methods was conducted on public agricultural datasets. The experimental results indicated that the proposed algorithm improves the performance of classification effectively. [ABSTRACT FROM AUTHOR]