Search

Diseases of tomato leaves can seriously damage crop yield and financial rewards. The timely and accurate detection of tomato diseases is a major challenge in agriculture. Hence, the early and accurate diagnosis of tomato diseases is crucial. The emergence of deep learning has dramatically helped in plant disease detection. However, the accuracy of deep learning models largely depends on the quantity and quality of training data. To solve the inter-class imbalance problem and improve the generalization ability of the classification model, this paper proposes a cycle-consistent generative-adversarial-network-based Transformer model to generate diseased tomato leaf images for data augmentation. In addition, this paper uses a Transformer model and densely connected CNN architecture to extract multilevel local features. The Transformer module is utilized to capture global dependencies and contextual information accurately to expand the sensory field of the model. Experiments show that the proposed model achieved 99.45% accuracy on the PlantVillage dataset. The 2018 Artificial Intelligence Challenger dataset and the private dataset attained accuracies of 98.30% and 95.4%, and the proposed classification model achieved a higher accuracy and smaller model size compared to previous deep learning models. The classification model is generalizable and robust and can provide a stable theoretical framework for crop disease prevention and control. [ABSTRACT FROM AUTHOR]

The tea industry, as one of the most globally important agricultural products, is characterized by pests and diseases that pose a serious threat to yield and quality. These diseases and pests often present different scales and morphologies, and some pest and disease target sizes can be tiny and difficult to detect. To solve these problems, we propose TeaViTNet, a multi-scale attention-based tea pest and disease detection model that combines CNNs and Transformers. First, MobileViT is used as the feature extraction backbone network. MobileViT captures and analyzes the tiny pest and disease features in the image via a self-attention mechanism and global feature extraction. Second, the EMA-PANet network is introduced to optimize the model's learning and attention to the Apolygus lucorum and leaf blight regions via an efficient multi-scale attention module with cross-space learning, which improves the model's ability to understand multi-scale information. In addition, RFBNet is embedded in the module to further expand the perceptual range and effectively capture the information of tiny features in tea leaf images. Finally, the ODCSPLayer convolutional block is introduced, aiming to focus on acquiring richer gradient flow information. The experimental results show that the TeaViTNet model proposed in this paper has an average accuracy of 89.1%, which is a significant improvement over the baseline network MobileViT and is capable of accurately detecting Apolygus lucorum and leaf blight of different scales and complexities. [ABSTRACT FROM AUTHOR]

Regenerated rice, characterized by single planting and double harvesting, saves labor and costs, significantly contributing to global food security. Hyperspectral imaging technology, which integrates image and spectral data, provides comprehensive, non-destructive, and pollution-free vegetation canopy analysis, making it highly effective for crop nutrient diagnosis. In this study, we selected two varieties of regenerated rice for field trials. Hyperspectral images were captured during key growth stages (flush, grouting, and ripening) of both the first and regenerated seasons. Utilizing a two-dimensional convolutional neural network (2D-CNN) as a deep feature extractor and a fully connected layer for nitrogen content prediction, we developed a robust model suitable for estimating nitrogen content in regenerated rice. The experimental results demonstrate that our method achieves a mean squared error (MSE) of 0.0008, significantly outperforming the back-propagation (BP) network and multiple linear regression by reducing the MSE by 0.0151 and 0.0247, respectively. It also surpasses the one-dimensional convolutional neural network (1D-CNN) by 0.003. This approach ensures accurate nitrogen content prediction throughout the growth cycle of regenerated rice, aiding in yield and economic benefit enhancement. [ABSTRACT FROM AUTHOR]

Conservation tillage, a crucial method for protecting soil fertility, depends heavily on maintaining adequate straw coverage. The current method of straw coverage detection relies primarily on manual measurement, which is both time-consuming and laborious. This paper introduces a novel straw coverage detection approach based on an improved mask regional convolutional neural network (Mask R-CNN) algorithm. Several images of wheat straw-covered fields were taken, and the dataset was augmented using techniques like image inversion, contrast enhancement, Gaussian noise addition, and translation after cropping the original images. These fields use a crop rotation cycle of wheat and corn. Subsequently, the straw images were annotated using the Labelme annotation tool to obtain the available straw instance segmentation dataset. The Mask R-CNN algorithm was improved by refining the mask generation network structure through a multi-feature fusion strategy, which interweaves features from both the encoder and the mask generation network, enhancing the model's ability to capture detailed and shape information of the straw. Lastly, using the mask information output by the improved Mask R-CNN algorithm, the straw coverage was calculated by counting the proportion of pixels within each segmented region. In the results, compared to the original Mask R-CNN algorithm, our improved Mask R-CNN algorithm achieved an average improvement of 7.8% in segmentation accuracy, indicating that the improved Mask R-CNN algorithm offers superior segmentation performance. Thus, the new algorithm can achieve straw coverage detection with higher accuracy and can provide a reference for other agricultural applications. [ABSTRACT FROM AUTHOR]

This paper presents a computational approach for quantifying soybean defects through seed classification using deep learning techniques. To differentiate between good and defective soybean seeds quickly and accurately, we introduce a lightweight soybean seed defect identification network (SSDINet). Initially, the labeled soybean seed dataset is developed and processed through the proposed seed contour detection (SCD) algorithm, which enhances the quality of soybean seed images and performs segmentation, followed by SSDINet. The classification network, SSDINet, consists of a convolutional neural network, depthwise convolution blocks, and squeeze-and-excitation blocks, making the network lightweight, faster, and more accurate than other state-of-the-art approaches. Experimental results demonstrate that SSDINet achieved the highest accuracy, of 98.64%, with 1.15 M parameters in 4.70 ms, surpassing existing state-of-the-art models. This research contributes to advancing deep learning techniques in agricultural applications and offers insights into the practical implementation of seed classification systems for quality control in the soybean industry. [ABSTRACT FROM AUTHOR]

Computer vision provides a real-time, non-destructive, and indirect way of horticultural crop yield estimation. Deep learning helps improve horticultural crop yield estimation accuracy. However, the accuracy of current estimation models based on RGB (red, green, blue) images does not meet the standard of a soft sensor. Through enriching more data and improving the RGB estimation model structure of convolutional neural networks (CNNs), this paper increased the coefficient of determination (R2) by 0.0284 and decreased the normalized root mean squared error (NRMSE) by 0.0575. After introducing a novel loss function mean squared percentage error (MSPE) that emphasizes the mean absolute percentage error (MAPE), the MAPE decreased by 7.58%. This paper develops a lettuce fresh weight estimation method through the multi-modal fusion of RGB and depth (RGB-D) images. With the multimodal fusion based on calibrated RGB and depth images, R2 increased by 0.0221, NRMSE decreased by 0.0427, and MAPE decreased by 3.99%. With the novel loss function, MAPE further decreased by 1.27%. A MAPE of 8.47% helps to develop a soft sensor for lettuce fresh weight estimation. [ABSTRACT FROM AUTHOR]

With the development and progress of uncrewed farming technology, uncrewed rice transplanters have gradually become an indispensable part of modern agricultural production; however, in the actual production, the working quality of uncrewed rice transplanters have not been effectively detected. In order to solve this problem, a detection method of uncrewed transplanter omission is proposed in this paper. In this study, the RGB images collected in the field were inputted into a convolutional neural network, and the bounding box center of the network output was used as the approximate coordinates of the rice seedlings, and the horizontal and vertical crop rows were fitted by the least square method, so as to detect the phenomenon of rice omission. By adding atrous spatial pyramid pooling and a convolutional block attention module to YOLOv5, the problem of image distortion caused by scaling and cropping is effectively solved, and the recognition accuracy is improved. The accuracy of this method is 95.8%, which is 5.6% higher than that of other methods, and the F1-score is 93.39%, which is 4.66% higher than that of the original YOLOv5. Moreover, the network structure is simple and easy to train, with the average training time being 0.284 h, which can meet the requirements of detection accuracy and speed in actual production. This study provides an effective theoretical basis for the construction of an uncrewed agricultural machinery system. [ABSTRACT FROM AUTHOR]

Plant diseases are a significant threat to global food security, impacting crop yields and economic growth. Accurate identification of plant diseases is crucial to minimize crop loses and optimize plant health. Traditionally, plant classification is performed manually, relying on the expertise of the classifier. However, recent advancements in deep learning techniques have enabled the creation of efficient crop classification systems using computer technology. In this context, this paper proposes an automatic plant identification process based on a synthetic neural network with the ability to detect images of plant leaves. The trained model EfficientNet-B3 was used to achieve a high success rate of 98.80% in identifying the corresponding combination of plant and disease. To make the system user-friendly, an Android application and website were developed, which allowed farmers and users to easily detect diseases from the leaves. In addition, the paper discusses the transfer method for studying various plant diseases, and images were captured using a drone or a smartphone camera. The ultimate goal is to create a user-friendly leaf disease product that can work with mobile and drone cameras. The proposed system provides a powerful tool for rapid and efficient plant disease identification, which can aid farmers of all levels of experience in making informed decisions about the use of chemical pesticides and optimizing plant health. [ABSTRACT FROM AUTHOR]

Continuing progress in machine learning (ML) has led to significant advancements in agricultural tasks. Due to its strong ability to extract high-dimensional features from fruit images, deep learning (DL) is widely used in fruit detection and automatic harvesting. Convolutional neural networks (CNN) in particular have demonstrated the ability to attain accuracy and speed levels comparable to those of humans in some fruit detection and automatic harvesting fields. This paper presents a comprehensive overview and review of fruit detection and recognition based on DL for automatic harvesting from 2018 up to now. We focus on the current challenges affecting fruit detection performance for automatic harvesting: the scarcity of high-quality fruit datasets, fruit detection of small targets, fruit detection in occluded and dense scenarios, fruit detection of multiple scales and multiple species, and lightweight fruit detection models. In response to these challenges, we propose feasible solutions and prospective future development trends. Future research should prioritize addressing these current challenges and improving the accuracy, speed, robustness, and generalization of fruit vision detection systems, while reducing the overall complexity and cost. This paper hopes to provide a reference for follow-up research in the field of fruit detection and recognition based on DL for automatic harvesting. [ABSTRACT FROM AUTHOR]

This paper proposes a method for recognizing the origin of Saposhnikovia divaricata using the IResNet model to achieve computer vision-based classification. Firstly, we created a small sample dataset and applied data augmentation techniques to enhance its diversity. After that, we introduced the hierarchical residual connection block in the early stage of the original model to expand the perceptual field of the neural network and enhance the extraction of scale features. Meanwhile, a depth-separable convolution operation was adopted in the later stage of the model to replace the conventional convolution operation and further reduce the time cost of the model. The experimental results demonstrate that the improved network model achieved a 5.03% improvement in accuracy compared to the original model while also significantly reducing the number of parameters required for the model. In our experiments, we compared the accuracy of the proposed model with several classical convolutional neural network models, including ResNet50, Resnest50, Res2net50, RepVggNet_B0, and ConvNext_T. The results showed that our proposed model achieved an accuracy of 93.72%, which outperformed ResNet50 (86.68%), Resnest50 (89.38%), Res2net50 (91.83%), RepVggNet_B0 (88.68%), and ConvNext_T (92.18%). Furthermore, our proposed model achieved the highest accuracy among the compared models, with a transmission frame rate of 158.9 fps and an inference time of only 6.29 ms. The research methodology employed in this study has demonstrated the ability to reduce potential errors caused by manual observation, effectively improving the recognition ability of Saposhnikovia divaricata based on existing data. Furthermore, the findings of this study provide valuable reference and support for future efforts to develop lightweight models in this area. [ABSTRACT FROM AUTHOR]

Strawberry (Fragaria × ananassa Duch.) has been widely accepted as the "Queen of Fruits". It has been identified as having high levels of vitamin C and antioxidants that are beneficial for maintaining cardiovascular health and maintaining blood sugar levels. The implementation of advanced techniques like precision agriculture (PA) is crucial for enhancing production compared to conventional farming methods. In recent years, the successful application of deep learning models was represented by convolutional neural networks (CNNs) in a variety of disciplines of computer vision (CV). Due to the dearth of a comprehensive and detailed discussion on the application of deep learning to strawberry cultivation, a particular review of recent technologies is needed. This paper provides an overview of recent advancements in strawberry cultivation utilizing Deep Learning (DL) techniques. It provides a comprehensive understanding of the most up-to-date techniques and methodologies used in this field by examining recent research. It also discusses the recent advanced variants of the DL model, along with a fundamental overview of CNN architecture. In addition, techniques for fine-tuning DL models have been covered. Besides, various strawberry-planting-related datasets were examined in the literature, and the limitations of using research models for real-time research have been discussed. [ABSTRACT FROM AUTHOR]

Accurate estimation of wheat leaf nitrogen concentration (LNC) is critical for characterizing ecosystem and plant physiological processes; it can further guide fertilization and other field management operations, and promote the sustainable development of agriculture. In this study, a wheat LNC test method based on multi-source spectral data and a convolutional neural network is proposed. First, interpolation reconstruction was performed on the wheat spectra data collected by different spectral instruments to ensure that the number of spectral channels and spectral range were consistent, and multi-source spectral data were constructed using interpolated, reconstructed imaging spectral data and non-imaging spectral data. Afterwards, the convolutional neural network DshNet and machine learning methods (PLSR, SVR, and RFR) were compared under various scenarios (non-imaging spectral data, imaging spectral data, and multi-source spectral data). Finally, the competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to optimize the LNC detection model. The results show that the model based on DshNet has the highest test accuracy. The CARS method is more suitable for DshNet model optimization than SPA. In the modeling scenario with non-imaging spectral, imaging spectral, and multi-source spectral, the optimized R2 is 0.86, 0.82, and 0.82, and the RMSE is 0.29, 0.31, and 0.31, respectively. The LNC visualization results show that DshNet modeling using multi-source spectral data is conducive to the visualization expansion of non-imaging spectral data. Therefore, the method presented in this paper provides new considerations for spectral data from different sources and is helpful for related research on the chemometric task of multi-source spectral data. [ABSTRACT FROM AUTHOR]

Phenotype analysis of leafy green vegetables in planting environment is the key technology of precision agriculture. In this paper, deep convolutional neural network is employed to conduct instance segmentation of leafy greens by weakly supervised learning based on box-level annotations and Excess Green (ExG) color similarity. Then, weeds are filtered based on area threshold, K-means clustering and time context constraint. Thirdly, leafy greens tracking is achieved by bipartite graph matching based on mask IoU measure. Under the framework of phenotype tracking, some time-context-dependent phenotype analysis tasks such as growth monitoring can be performed. Experiments show that the proposed method can achieve 0.95 F1-score and 76.3 sMOTSA (soft multi-object tracking and segmentation accuracy) by using weakly supervised annotation data. Compared with the fully supervised approach, the proposed method can effectively reduce the requirements for agricultural data annotation, which has more potential in practical applications. [ABSTRACT FROM AUTHOR]

The accurate identification of corn leaf diseases is crucial for preventing disease spread and improving corn yield. Plant leaf images are often affected by factors such as complex backgrounds, climate, light, and sample data imbalance. To address these issues, we propose a lightweight convolutional neural network, ICS-ResNet, based on ResNet50. This network incorporates improved spatial and channel attention modules as well as a deep separable residual structure to enhance recognition accuracy. (1) The residual connections in the ResNet network prevent gradient loss during deep network training. (2) The improved channel attention (ICA) and spatial attention (ISA) modules fully utilize semantic information from different feature layers to accurately localize key features of the network. (3) To reduce the number of parameters and lower computational costs, we replace traditional convolutional computation with a depth-separable residual structure. (4) We also employ cosine annealing to dynamically adjust the learning rate, enhancing the network's training stability, improving model convergence, and preventing local optima. Experiments on the corn dataset in Plant Village compare the proposed ICS-ResNet with eight popular networks: CSPNet, InceptionNet_v3, EfficientNet, ShuffleNet, MobileNet, ResNet50, ResNet101 and ResNet152. The results show that the ICS-ResNet achieves an accuracy of 98.87%, which is 5.03%, 3.18%, 1.13%, 1.81%, 1.13%, 0.68%, 0.44% and 0.60% higher than the other networks, respectively. Furthermore, the number of parameters and computations are reduced by 69.21% and 54.88%, respectively, compared to the original ResNet50 network, significantly improving the efficiency of corn leaf disease classification. The study provides strong technical support for sustainable agriculture and the promotion of agricultural science and technology innovation. [ABSTRACT FROM AUTHOR]

Early recognition of fruit body diseases in edible fungi can effectively improve the quality and yield of edible fungi. This study proposes a method based on improved ShuffleNetV2 for edible fungi fruit body disease recognition. First, the ShuffleNetV2+SE model is constructed by deeply integrating the SE module with the ShuffleNetV2 network to make the network pay more attention to the target area and improve the model's disease classification performance. Second, the network model is optimized and improved. To simplify the convolution operation, the 1 × 1 convolution layer after the 3 × 3 depth convolution layer is removed, and the ShuffleNetV2-Lite+SE model is established. The experimental results indicate that the accuracy, precision, recall, and Macro-F1 value of the ShuffleNetV2-Lite+SE model on the test set are, respectively, 96.19%, 96.43%, 96.07%, and 96.25%, which are 4.85, 4.89, 3.86, and 5.37 percent higher than those before improvement. Meanwhile, the number of model parameters and the average iteration time are 1.6 MB and 41 s, which is 0.2 MB higher and 4 s lower than that before the improvement, respectively. Compared with the common lightweight convolutional neural networks MobileNetV2, MobileNetV3, DenseNet, and EfficientNet, the proposed model achieves higher recognition accuracy, and its number of model parameters is significantly reduced. In addition, the average iteration time is reduced by 37.88%, 31.67%, 33.87%, and 42.25%, respectively. The ShuffleNetV2-Lite+SE model proposed in this paper has a good balance among performance, number of parameters, and real-time performance. It is suitable for deploying on resource-limited devices such as mobile terminals and helps in realization of real-time and accurate recognition of fruit body diseases of edible fungi. [ABSTRACT FROM AUTHOR]

Rice, the world's most extensively cultivated cereal crop, serves as a staple food and energy source for over half of the global population. A variety of abiotic and biotic factors such as weather conditions, soil quality, temperature, insects, pathogens, and viruses can greatly impact the quantity and quality of rice grains. Studies have established that plant infections have a significant impact on rice crops, resulting in substantial financial losses in agriculture. To accurately diagnose and manage the diseases affecting rice plants, plant pathologists are seeking efficient and reliable methods. Traditional disease detection techniques, employed by farmers, involve time-consuming visual inspections and result in inadequate farming practices. With advancements in agricultural technology, the identification of pathogenic organisms in rice plants has become significantly more manageable through techniques such as machine learning and deep learning, which are receiving significant attention in crop disease research. In this paper, we used the transfer learning approach on 15 pre-trained CNN models for the automatic identification of Rice leave diseases. Results showed that the InceptionV3 model is outperforming with an average accuracy of 99.64% with Precision, Recall, F1-Score, and Specificity as 98.23, 98.21, 98.20, and 99.80, and the AlexNet model resulted in poor performance with average accuracy of 97.35% among others. [ABSTRACT FROM AUTHOR]

Fruit quality is an important aspect in determining the consumer preference in the supply chain. Thermal imaging was used to determine different pineapple varieties according to the physicochemical changes of the fruit by means of the deep learning method. Deep learning has gained attention in fruit classification and recognition in unimodal processing. This paper proposes a multimodal data fusion framework for the determination of pineapple quality using deep learning methods based on the feature extraction acquired from thermal imaging. Feature extraction was selected from the thermal images that provided a correlation with the quality attributes of the fruit in developing the deep learning models. Three different types of deep learning architectures, including ResNet, VGG16, and InceptionV3, were built to develop the multimodal data fusion framework for the classification of pineapple varieties based on the concatenation of multiple features extracted by the robust networks. The multimodal data fusion coupled with powerful convolutional neural network architectures can remarkably distinguish different pineapple varieties. The proposed multimodal data fusion framework provides a reliable determination of fruit quality that can improve the recognition accuracy and the model performance up to 0.9687. The effectiveness of multimodal deep learning data fusion and thermal imaging has huge potential in monitoring the real-time determination of physicochemical changes of fruit. [ABSTRACT FROM AUTHOR]

The fruit quality and yield of sweet peppers can be effectively improved by accurately and efficiently controlling the growth conditions and taking timely corresponding measures to manage the planting process dynamically. The use of deep-learning-based image recognition technology to segment sweet pepper instances accurately is an important means of achieving the above goals. However, the accuracy of the existing instance segmentation algorithms is seriously affected by complex scenes such as changes in ambient light and shade, similarity between the pepper color and background, overlap, and leaf occlusion. Therefore, this paper proposes an instance segmentation algorithm that integrates the Swin Transformer attention mechanism into the backbone network of a Mask region-based convolutional neural network (Mask RCNN) to enhance the feature extraction ability of the algorithm. In addition, UNet3+ is used to improve the mask head and segmentation quality of the mask. The experimental results show that the proposed algorithm can effectively segment different categories of sweet peppers under conditions of extreme light, sweet pepper overlap, and leaf occlusion. The detection AP, AR, segmentation AP, and F1 score were 98.1%, 99.4%, 94.8%, and 98.8%, respectively. The average FPS value was 5, which can be satisfied with the requirement of dynamic monitoring of the growth status of sweet peppers. These findings provide important theoretical support for the intelligent management of greenhouse crops. [ABSTRACT FROM AUTHOR]

In order to select the light quality suitable for plant growth, a quantitative detection model of chlorophyll content in muskmelon leaves was established to monitor plant growth quickly and accurately. In the paper, muskmelon "Boyang 91" was used as the experimental material, and six different light proportion treatments were set up. Through measuring plant height, stem diameter, number of leaves, nodes, and other growth indicators, in addition to leaf chlorophyll content, the response difference of muskmelon to different light qualities was explored in a plant factory. The hyperspectral imaging technology was used to establish the prediction model for the chlorophyll content of muskmelon. The original spectrum was preprocessed and optimized by five pretreatments, and then the characteristic wavelengths were extracted by six methods. Partial least squares regression (PLSR), least squares support vector machine (LSSVM), and convolutional neural network (CNN) were established for optimal feature wavelength. The results showed that the plant height and stem diameter of the T3 treatment were higher than those of other treatments, and their values were 14.48 (cm) and 5.02 (mm), respectively. The chlorophyll content of the T3 treatment was the highest, and its value was 40.16 (mg/g), which was higher than that of other treatments. Through comprehensive analysis, the T3 treatment (light ratio: 6R/1B/2W, light quantum flux: 360 μmol/(m2·s), photoperiod: 12 h) was optimal. Meanwhile, the average spectral reflectance data of 216 leaf samples were extracted, and the S-G preprocessing method was selected to preprocess the original spectral data (Rc = 0.860, RMSEC = 1.806; Rcv = 0.790, RMSECV = 2.161). By comparing and analyzing the correlation coefficients and root mean square errors of six feature wavelength extraction methods, it was concluded that the variable combination population analysis (VCPA) method had the best model effect for feature wavelength extraction (RP = 0.824, RMSEP = 1.973). Ten characteristic wavelengths (396, 409, 457, 518, 532, 565, 687, 691, 701, and 705 nm) extracted by the VCPA method were used to establish the chlorophyll content prediction model, and the chlorophyll content prediction model of S-G-VCPA-CNN had the best performance (Rc = 0.9151, RMSEC = 1.445; Rp = 0.811, RMSEP = 2.055). The results of this study provide data support and a theoretical basis for screening the light ratio of other crops, and also present technical support for online monitoring of crop growth in plant factories. [ABSTRACT FROM AUTHOR]

Efficient identification of apple leaf diseases (ALDs) can reduce the use of pesticides and increase the quality of apple fruit, which is of significance to smart agriculture. However, existing research into identifying ALDs lacks models/methods that satisfy efficient identification in the wild environment, hindering the application of smart agriculture in the apple industry. Therefore, this paper explores an ACCURATE, LIGHTWEIGHT, and ROBUST convolutional neural network (CNN) called EfficientNet-MG, improving the conventional EfficientNet network by the multistage feature fusion (MSFF) method and gaussian error linear unit (GELU) activation function. The shallow and deep convolutional layers usually contain detailed and semantic information, respectively, but conventional EfficientNets do not fully utilize the different stage convolutional layers. Thus, MSFF was adopted to improve the semantic representation capacity of the last layer of features, and GELU was used to adapt to complicated tasks. Further, a comprehensive ALD dataset called AppleLeaf9 was constructed for the wild environment. The experimental results show that EfficientNet-MG achieves a higher accuracy (99.11%) and fewer parameters (8.42 M) than the five classical CNN models, thus proving that EfficientNet-MG achieves more competitive results on ALD identification. [ABSTRACT FROM AUTHOR]

This paper aims to evaluate whether an automatic analysis with deep learning convolutional neural networks techniques offer the ability to efficiently identify olive groves with different intensification patterns by using very high-resolution aerial orthophotographs. First, a sub-image crop classification was carried out. To standardize the size and increase the number of samples of the data training (DT), the crop images were divided into mini-crops (sub-images) using segmentation techniques, which used a different threshold and stride size to consider the mini-crop as suitable for the analysis. The four scenarios evaluated discriminated the sub-images efficiently (accuracies higher than 0.8), obtaining the largest sub-images (H = 120, W = 120) for the highest average accuracy (0.957). The super-intensive olive plantings were the easiest to classify for most of the sub-image sizes. Nevertheless, although traditional olive groves were discriminated accurately, too, the most difficult task was to distinguish between the intensive plantings and the traditional ones. A second phase of the proposed system was to predict the crop at farm-level based on the most frequent class detected in the sub-images of each crop. The results obtained at farm level were slightly lower than at the sub-images level, reaching the highest accuracy (0.826) with an intermediate size image (H = 80, W = 80). Thus, the convolutional neural networks proposed made it possible to automate the classification and discriminate accurately among traditional, intensive, and super-intensive planting systems. [ABSTRACT FROM AUTHOR]

Computer vision (CV) combined with a deep convolutional neural network (CNN) has emerged as a reliable analytical method to effectively characterize and quantify high-throughput phenotyping of different grain crops, including rice, wheat, corn, and soybean. In addition to the ability to rapidly obtain information on plant organs and abiotic stresses, and the ability to segment crops from weeds, such techniques have been used to detect pests and plant diseases and to identify grain varieties. The development of corresponding imaging systems to assess the phenotypic parameters, yield, and quality of crop plants will increase the confidence of stakeholders in grain crop cultivation, thereby bringing technical and economic benefits to advanced agriculture. Therefore, this paper provides a comprehensive review of CNNs in computer vision for grain crop phenotyping. It is meaningful to provide a review as a roadmap for future research in such a thriving research area. The CNN models (e.g., VGG, YOLO, and Faster R-CNN) used CV tasks including image classification, object detection, semantic segmentation, and instance segmentation, and the main results of recent studies on crop phenotype detection are discussed and summarized. Additionally, the challenges and future trends of the phenotyping techniques in grain crops are presented. [ABSTRACT FROM AUTHOR]

The agricultural sector plays a key role in supplying quality food and makes the greatest contribution to growing economies and populations. Plant disease may cause significant losses in food production and eradicate diversity in species. Early diagnosis of plant diseases using accurate or automatic detection techniques can enhance the quality of food production and minimize economic losses. In recent years, deep learning has brought tremendous improvements in the recognition accuracy of image classification and object detection systems. Hence, in this paper, we utilized convolutional neural network (CNN)-based pre-trained models for efficient plant disease identification. We focused on fine tuning the hyperparameters of popular pre-trained models, such as DenseNet-121, ResNet-50, VGG-16, and Inception V4. The experiments were carried out using the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 classes. The performance of the model was evaluated through classification accuracy, sensitivity, specificity, and F1 score. A comparative analysis was also performed with similar state-of-the-art studies. The experiments proved that DenseNet-121 achieved 99.81% higher classification accuracy, which was superior to state-of-the-art models. [ABSTRACT FROM AUTHOR]

Site-specific weed control offers a great potential for herbicide savings in agricultural crops without causing yield losses and additional weed management costs in the following years. Therefore, precision weed management is an efficient tool to meet the EU targets for pesticide reduction. This review summarizes different commercial technologies and prototypes for precision patch spraying and spot spraying. All the presented technologies have in common that they consist of three essential parts. (1) Sensors and classifiers for weed/crop detection, (2) Decision algorithms to decide whether weed control is needed and to determine a suitable type and rate of herbicide. Usually, decision algorithms are installed on a controller and (3) a precise sprayer with boom section control or single nozzle control. One point that differs between some of the techniques is the way the decision algorithms classify. They are based on different approaches. Green vegetation can be differentiated from soil and crop residues based on spectral information in the visible and near-infrared wavebands ("Green on Brown"). Those sensors can be applied for real-time on/off control of single nozzles to control weeds before sowing after conservation tillage and in the inter-row area of crops. More sophisticated imaging algorithms are used to classify weeds in crops ("Green on Green"). This paper will focus on Convolutional Neural Networks (CNN) for plant species identification. Alternatively, the position of each crop can be recorded during sowing/planting and afterward herbicides can be targeted to single weeds or larger patches of weeds if the economic weed threshold is exceeded. With a standardized protocol of data communication between sensor, controller and sprayer, the user can combine different sensors with different sprayers. In this review, an ISOBUS communication protocol is presented for a spot sprayer. Precision chemical weed control can be realized with tractor-mounted sprayers and autonomous robots. Commercial systems for both classes will be introduced and their economic and environmental benefits and limitations will be highlighted. Farmers ask for robust systems with less need for maintenance and flexible application in different crops. [ABSTRACT FROM AUTHOR]

To apply weed control treatments effectively, the weeds must be accurately detected. Deep learning (DL) has been quite successful in performing the weed identification task. However, various aspects of the DL have not been explored in previous studies. This research aimed to achieve a high average precision (AP) of eight classes of weeds and a negative (non-weed) class, using the DeepWeeds dataset. In this regard, a DL-based two-step methodology has been proposed. This article is the second stage of the research, while the first stage has already been published. The former phase presented a weed detection pipeline and consisted of the evaluation of various neural networks, image resizers, and weight optimization techniques. Although a significant improvement in the mean average precision (mAP) was attained. However, the Chinee apple weed did not reach a high average precision. This result provided a solid ground for the next stage of the study. Hence, this paper presents an in-depth analysis of the Faster Region-based Convolutional Neural Network (RCNN) with ResNet-101, the best-obtained model in the past step. The architectural details of the Faster RCNN model have been thoroughly studied to investigate each class of weeds. It was empirically found that the generation of anchor boxes affects the training and testing performance of the Faster RCNN model. An enhancement to the anchor box scales and aspect ratios has been attempted by various combinations. The final results, with the addition of 64 × 64 scale size, and aspect ratio of 1:3 and 3:1, produced the best classification and localization of all classes of weeds and a negative class. An enhancement of 24.95% AP was obtained in Chinee apple weed. Furthermore, the mAP was improved by 2.58%. The robustness of the approach has been shown by the stratified k-fold cross-validation technique and testing on an external dataset. [ABSTRACT FROM AUTHOR]

Maize small leaf spot (Bipolaris maydis) is one of the most important diseases of maize. The severity of the disease cannot be accurately identified, the cost of pesticide application increases every year, and the agricultural ecological environment is polluted. Therefore, in order to solve this problem, this study proposes a novel deep learning network DISE-Net. We designed a dilated-inception module instead of the traditional inception module for strengthening the performance of multi-scale feature extraction, then embedded the attention module to learn the importance of interchannel relationships for input features. In addition, a dense connection strategy is used in model building to strengthen channel feature propagation. In this paper, we constructed a data set of maize small leaf spot, including 1268 images of four disease grades and healthy leaves. Comparative experiments show that DISE-Net with a test accuracy of 97.12% outperforms the classical VGG16 (91.11%), ResNet50 (89.77%), InceptionV3 (90.97%), MobileNetv1 (92.51%), MobileNetv2 (92.17%) and DenseNet121 (94.25%). In addition, Grad-Cam network visualization also shows that DISE-Net is able to pay more attention to the key areas in making the decision. The results showed that the DISE-Net was suitable for the classification of maize small leaf spot in the field. [ABSTRACT FROM AUTHOR]

In Asia, rice is the most consumed grain by humans, serving as a staple food in India. The yield of rice paddies is easily affected by nutrient deficiencies and leaf diseases. To overcome this problem and improve the yield productivity of rice, nutrient deficiency and leaf disease identification are essential. The main nutrient elements in paddies are potassium, phosphorus, and nitrogen (PPN), the deficiency of any of which strongly affects the rice plants. When multiple nutrient elements are deficient, the leaf color of the rice plants is altered. To overcome this problem, optimal nutrient delivery is required. Hence, the present study proposes the use of Fuzzy C Means clustering (FCM) with Improved Tunicate Swarm Optimization (ITSO) to segment the lesions in rice plant leaves and identify the deficient nutrients. The proposed ITSO integrates the Tunicate Swarm Optimization (TSO) and Bacterial Foraging Optimization (BFO) approaches. The Hybrid Convolutional Neural Network (HCNN), a deep learning model, is used with ITSO to classify the rice leaf diseases, as well as nutrient deficiencies in the leaves. Two datasets, namely, a field work dataset and a Kaggle dataset, were used for the present study. The proposed HCNN-ITSO classified Bacterial Leaf Bright (BLB), Narrow Brown Leaf Spot (NBLS), Sheath Rot (SR), Brown Spot (BS), and Leaf Smut (LS) in the field work dataset. Furthermore, the potassium-, phosphorus-, and nitrogen-deficiency-presenting leaves were classified using the proposed HCNN-ITSO in the Kaggle dataset. The MATLAB platform was used for experimental analysis in the field work and Kaggle datasets in terms of various performance measures. When compared to previous methods, the proposed method achieved the best accuracies of 98.8% and 99.01% in the field work and Kaggle datasets, respectively. [ABSTRACT FROM AUTHOR]

Pest damage is a major factor in reducing crop yield and has negative impacts on the economy. However, the complex background, diversity of pests, and individual differences pose challenges for classification algorithms. In this study, we propose a patch-based neural network (PMLPNet) for multi-class pest classification. PMLPNet leverages spatial and channel contextual semantic features through meticulously designed token- and channel-mixing MLPs, respectively. This innovative structure enhances the model's ability to accurately classify complex multi-class pests by providing high-quality local and global pixel semantic features for the fully connected layer and activation function. We constructed a database of 4510 images spanning 40 types of plant pests across 4 crops. Experimental results demonstrate that PMLPNet outperforms existing CNN models, achieving an accuracy of 92.73%. Additionally, heat maps reveal distinctions among different pest images, while patch probability-based visualizations highlight heterogeneity within pest images. Validation on external datasets (IP102 and PlantDoc) confirms the robust generalization performance of PMLPNet. In summary, our research advances intelligent pest classification techniques, effectively identifying various pest types in diverse crop images. [ABSTRACT FROM AUTHOR]

Accurately recognizing apples in complex environments is essential for automating apple picking operations, particularly under challenging natural conditions such as cloudy, snowy, foggy, and rainy weather, as well as low-light situations. To overcome the challenges of reduced apple target detection accuracy due to branch occlusion, apple overlap, and variations between near and far field scales, we propose the Rep-ViG-Apple algorithm, an advanced version of the YOLO model. The Rep-ViG-Apple algorithm features a sophisticated architecture designed to enhance apple detection performance in difficult conditions. To improve feature extraction for occluded and overlapped apple targets, we developed the inverted residual multi-scale structural reparameterized feature extraction block (RepIRD Block) within the backbone network. We also integrated the sparse graph attention mechanism (SVGA) to capture global feature information, concentrate attention on apples, and reduce interference from complex environmental features. Moreover, we designed a feature extraction network with a CNN-GCN architecture, termed Rep-Vision-GCN. This network combines the local multi-scale feature extraction capabilities of a convolutional neural network (CNN) with the global modeling strengths of a graph convolutional network (GCN), enhancing the extraction of apple features. The RepConvsBlock module, embedded in the neck network, forms the Rep-FPN-PAN feature fusion network, which improves the recognition of apple targets across various scales, both near and far. Furthermore, we implemented a channel pruning algorithm based on LAMP scores to balance computational efficiency with model accuracy. Experimental results demonstrate that the Rep-ViG-Apple algorithm achieves precision, recall, and average accuracy of 92.5%, 85.0%, and 93.3%, respectively, marking improvements of 1.5%, 1.5%, and 2.0% over YOLOv8n. Additionally, the Rep-ViG-Apple model benefits from a 22% reduction in size, enhancing its efficiency and suitability for deployment in resource-constrained environments while maintaining high accuracy. [ABSTRACT FROM AUTHOR]

Water scarcity is one of the most significant environmental factors that inhibits photosynthesis and decreases the growth and productivity of plants. Using the deep learning convolutional neural network (CNN) model, this study evaluates the ability of spectroscopy to estimate leaf water content (LWC) in fruit trees. During midday, spectral data were acquired from leaf samples obtained from three distinct varieties of fruit trees, encompassing the spectral range spanning from 350 to 2500 nm. Then, for spectral preprocessing, the fractional order derivative (FOD) and continuous wavelet transform (CWT) algorithms were used to reduce the effects of scattering and noise on the collected spectra. Finally, the CNN model was developed to predict LWC in different fruit trees. The results showed that: (1) The spectra treated with CWT and FOD could improve the spectrum expression ability by improving the correlation between spectra and LWC. The correlation level of FOD treatment was higher than that of CWT treatment. (2) The CNN model was developed using FOD 1.2, and CWT 3 performed better than other traditional machine learning methods, such as RFR, SVR, and PLSR. (3) Further validation using additional samples demonstrated that the CNN model had good stability and quantitative prediction capability for the LWC of fruit trees (R2 > 0.95, root mean square error (RMSE) < 1.773%, and relative percentage difference (RPD) > 4.26). The results may provide an effective way to predict fruit LWC using a CNN-based model. [ABSTRACT FROM AUTHOR]

Agriculture is an area that currently benefits from the use of new technologies and techniques, such as artificial intelligence, to improve production in crop fields. Zacatecas is one of the states producing the most onions in the northeast region of Mexico. Identifying and determining vegetation, soil, and humidity zones could help solve problems such as irrigation demands or excesses, identify spaces with different levels of soil homogeneity, and estimate the yield or health of the crop. This study examines the application of artificial intelligence through the use of deep learning, specifically convolutional neural networks, to identify the patterns that can be found in a crop field, in this case, vegetation, soil, and humidity zones. To extract the mentioned patterns, the K-nearest neighbor algorithm was used to pre-process images taken using unmanned aerial vehicles and form a dataset composed of 3672 images of vegetation, soil, and humidity (1224 for each class). A total of six convolutional neural network models were used to identify and classify the patterns, namely Alexnet, DenseNet, VGG16, SqueezeNet, MobileNetV2, and Res-Net18. Each model was evaluated with the following validation metrics: accuracy, F1-score, precision, and recall. The results showed a variation in performance between 90% and almost 100%. Alexnet obtained the highest metrics with an accuracy of 99.92%, while MobileNetV2 had the lowest accuracy of 90.85%. Other models, such as DenseNet, VGG16, SqueezeNet, and ResNet18, showed an accuracy of between 92.02% and 98.78%. Furthermore, our study highlights the importance of adopting artificial intelligence in agriculture, particularly in the management of onion fields in Zacatecas, Mexico. The findings can help farmers and agronomists make more informed and efficient decisions, which can lead to greater production and sustainability in local agriculture. [ABSTRACT FROM AUTHOR]

Rapid and accurate grape leaf disease diagnosis is of great significance to its yield and quality of grape. In this paper, aiming at the identification of grape leaf diseases, a fast and accurate detection method based on fused deep features, extracted from a convolutional neural network (CNN), plus a support vector machine (SVM) is proposed. In the research, based on an open dataset, three types of state-of-the-art CNN networks, three kinds of deep feature fusion methods, seven species of deep feature layers, and a multi-class SVM classifier were studied. Firstly, images were resized to meet the input requirements of the CNN network; then, the deep features of the input images were extracted via the specific deep feature layer of the CNN network. Two kinds of deep features from different networks were then fused using different fusion methods to increase the effective classification feature information. Finally, a multi-class SVM classifier was trained with the fused deep features. The experimental results on the open dataset show that the fused deep features with any kind of fusion method can obtain a better classification performance than using a single type of deep feature. The direct concatenation of the Fc1000 deep feature extracted from ResNet50 and ResNet101 can achieve the best classification result compared with the other two fusion methods, and its F1 score is 99.81%. Furthermore, the SVM classifier trained using the proposed method can achieve a classification performance comparable to that of using the CNN model directly, but the training time is less than 1 s, which has an advantage over spending tens of minutes training a CNN model. The experimental results indicate that the method proposed in this paper can achieve fast and accurate identification of grape leaf diseases and meet the needs of actual agricultural production. [ABSTRACT FROM AUTHOR]

Non-destructive, fast, and accurate prediction of soil organic matter content in farmland is of great significance for soil fertility assessment and rational fertilization. In the process of soil organic matter prediction, it is important to give full play to the advantages of different prediction models and to integrate different prediction models to innovatively construct a combined prediction model of soil organic matter content so as to improve the prediction accuracy and generalization ability of the model. In this study, the soil organic matter content of agricultural soils was taken as the research object, and the visible near-infrared hyperspectral curves of soils were measured by the Starter Kit indoor mobile scanning platform (Headwall Photonics, Bolton, MA, USA), and the original spectral curves were firstly de-noised by Savitzky–Golay (S-G) smoothing. Secondly, the smoothed and denoised spectral data were subjected to a first-order differential transform, and the features were selected based on the first-order differential transformed spectral data using the L1-paradigm algorithm features. Then, secondly, eight algorithms based on the selected feature bands, such as LASSO Regression (LASSO) (Model 1), Multilayer Perceptron (MLP) (Model 2), Random Forest (RF) (Model 3), Gaussian Kernel Regression (GKR) (Model 4), Ridge Regression (Model 5), Long Short-Term Memory (LSTM) (Model 6), Convolutional Neural Networks (CNN) (Model 7), and Support Vector Regression (SVR) (Model 8), were applied to construct a single-prediction model of soil organic matter content. Finally, a superior linear combination-prediction model was proposed by the eight single-prediction models constructed, and the standard deviation-based prediction validity was added to test the model. The results showed the following: (1) the weights of the eight single-prediction models in the combined prediction model were ω 1 * = 0.099 , ω 2 * = 0.202 , ω 3 * = 0.000 , ω 4 * = 0.357 , ω 5 * = 0.088 , ω 6 * = 0.089 , ω 7 * = 0.000 , ω 8 * = 0.165 , respectively; (2) The average precision E of the predicted values of soil organic matter content constructed based on the eight single-prediction models was 0.856; the average standard deviation σ was 0.181, and the average prediction validity M was 0.702; (3) The accuracy E of the predicted value of soil organic matter content of the combined model was 0.893, which was 4.322% higher than the average accuracy of the single model; the standard deviation of the combined model was 0.129, which was 28.333% lower than the average standard deviation of the single model, and the prediction validity M of the combined model was 0.778, which was 10.826% higher than the average prediction validity of the single model. The combined model can be used for the effective estimation of soil organic matter content in farmland with visible near-infrared spectral data, which can provide a basis and reference for the rapid detection of soil organic matter content in farmland. [ABSTRACT FROM AUTHOR]

With the continuous growth of the global population and the increasing demand for crop yield, enhancing crop productivity has emerged as a crucial research objective on a global scale. Weeds, being one of the primary abiotic factors impacting crop yield, contribute to approximately 13.2% of annual food loss. In recent years, Unmanned Aerial Vehicle (UAV) technology has developed rapidly and its maturity has led to widespread utilization in improving crop productivity and reducing management costs. Concurrently, deep learning technology has become a prominent tool in image recognition. Convolutional Neural Networks (CNNs) has achieved remarkable outcomes in various domains, including agriculture, such as weed detection, pest identification, plant/fruit counting, maturity grading, etc. This study provides an overview of the development of UAV platforms, the classification of UAV platforms and their advantages and disadvantages, as well as the types and characteristics of data collected by common vision sensors used in agriculture, and discusses the application of deep learning technology in weed detection. The manuscript presents current advancements in UAV technology and CNNs in weed management tasks while emphasizing the existing limitations and future trends in its development process to assist researchers working on applying deep learning techniques to weed management. [ABSTRACT FROM AUTHOR]

The large-scale production of edible mushrooms typically requires the use of greenhouses, as the greenhouse environment significantly affects the growth of edible mushrooms. It is crucial to effectively predict the temperature, humidity, and carbon dioxide fluctuations within the mushroom greenhouse for determining the environmental stress and pre-regulation of edible mushrooms. To address the nonlinearity, temporal dynamics, and strong coupling of the edible mushroom greenhouse environment, a temperature, humidity, and carbon dioxide prediction model based on the combination of the attention mechanism, the convolutional neural network, and the long short-term memory neural network (A-CNN-LSTM) is proposed. Experimental data were collected from both the inside and outside of the greenhouse, including environmental data and the on–off data of environmental control devices. After completing missing data using linear interpolation, denoising with Kalman filtering, and normalization, the recurrent neural network (RNN) model, long short-term memory (LSTM) model, and A-CNN-LSTM model were trained and tested on the time series data. These models were used to predict the environmental changes in temperature, humidity, and carbon dioxide inside the greenhouse. The results indicate that the A-CNN-LSTM model outperforms the other two models in terms of denoising, non-denoising, and different prediction time steps. The proposed method accurately predicts temperature, humidity, and carbon dioxide levels with errors of 0.17 °C (R2 = 0.974), 2.06% (R2 = 0.804), and 8.367 ppm (R2 = 0.993), respectively. These results indicate improved prediction accuracy for temperature, humidity, and carbon dioxide values inside the edible mushroom greenhouse. The findings provide a decision basis for the precise control of the greenhouse environment. [ABSTRACT FROM AUTHOR]

The accurate measurement of soil moisture content emerges as a critical parameter within the ambit of agricultural irrigation management, wherein the precise prediction of this variable plays an instrumental role in enhancing the efficiency and conservation of agricultural water resources. This study introduces an innovative, cutting-edge hybrid model that ingeniously integrates Gated Recirculation Unit (GRU) and Transformer technologies, meticulously crafted to amplify the precision and reliability of soil moisture content forecasts. Leveraging meteorological and soil moisture datasets amassed from eight monitoring stations in Hebei Province, China, over the period from 2011 to 2018, this investigation thoroughly assesses the model's efficacy against a diverse array of input variables and forecast durations. This assessment is concurrently contrasted with a range of conventional machine learning and deep learning frameworks. The results demonstrate that (1) the GRU–Transformer model exhibits remarkable superiority across various aspects, particularly in short-term projections (1- to 2-day latency). The model's mean square error (MSE) for a 1-day forecast is notably low at 5.22%, reducing further to a significant 2.71%, while the mean coefficient of determination (R2) reaches a high of 89.92%. Despite a gradual increase in predictive error over extended forecast periods, the model consistently maintains robust performance. Moreover, the model shows exceptional versatility in managing different soil depths, notably excelling in predicting moisture levels at greater depths, thereby surpassing its performance in shallower soils. (2) The model's predictive error inversely correlates with the reduction in parameters. Remarkably, with a streamlined set of just six soil moisture content parameters, the model predicts an average MSE of 0.59% and an R2 of 98.86% for a three-day forecast, highlighting its resilience to varied parameter configurations. (3) In juxtaposition with prevalent models such as Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Gradient Boosting Decision Tree (GBDT), XGBoost, Random Forest, and deep learning models like Deep Neural Network (DNN), Convolutional Neural Network (CNN), and standalone GRU-branch and Transformer-branch models, the GRU–Transformer framework demonstrates a significant advantage in predicting soil moisture content with enhanced precision for a five-day forecast. This underscores its exceptional capacity to navigate the intricacies of soil moisture data. This research not only provides a potent decision-support tool for agricultural irrigation planning but also makes a substantial contribution to the field of water resource conservation and optimization in agriculture, while concurrently imparting novel insights into the application of deep learning techniques in the spheres of agricultural and environmental sciences. [ABSTRACT FROM AUTHOR]

Timely forecasting of aboveground vegetation biomass is crucial for effective management and ensuring food security. However, research on predicting aboveground biomass remains scarce. Artificial intelligence (AI) methods could bridge this research gap and provide early warning to planners and stakeholders. This study evaluates the effectiveness of deep learning (DL) algorithms in predicting aboveground vegetation biomass with limited-size data. It employs an iterative forecasting procedure for four target horizons, comparing the performance of DL models—multi-layer perceptron (MLP), long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), and CNN-LSTM—against the traditional seasonal autoregressive integrated moving average (SARIMA) model, serving as a benchmark. Five limited-size vegetation biomass time series from Kenyan grasslands with values at 15-day intervals over a 20-year period were chosen for this purpose. Comparing the outcomes of these models revealed significant differences (p < 0.05); however, none of the models proved superior among the five time series and the four horizons evaluated. The SARIMA, CNN, and CNN-LSTM models performed best, with the statistical model slightly outperforming the other two. Additionally, the accuracy of all five models varied significantly according to the prediction horizon (p < 0.05). As expected, the accuracy of the models decreased as the prediction horizon increased, although this relationship was not strictly monotonic. Finally, this study indicated that, in limited-size aboveground vegetation biomass time series, there is no guarantee that deep learning methods will outperform traditional statistical methods. [ABSTRACT FROM AUTHOR]

Crown diameter is one of the crucial indicators for evaluating the adaptability, growth quality, and ornamental value of garden chrysanthemums. To accurately obtain crown diameter, this study employed an unmanned aerial vehicle (UAV) equipped with a RGB camera to capture orthorectified canopy images of 64 varieties of garden chrysanthemums at different growth stages. Three methods, namely RGB color space, hue-saturation-value (HSV) color space, and the mask region-based convolutional neural network (Mask R-CNN), were employed to estimate the crown diameter of garden chrysanthemums. The results revealed that the Mask R-CNN exhibited the best performance in crown diameter estimation (sample number = 2409, R2 = 0.9629, RMSE = 2.2949 cm). Following closely, the HSV color space-based model exhibited strong performance (sample number = 2409, R2 = 0.9465, RMSE = 3.4073 cm). Both of the first two methods were efficient in estimating crown diameter throughout the entire growth stage. In contrast, the RGB color space-based model exhibited slightly lower performance (sample number = 1065, R2 = 0.9011, RMSE = 3.3418 cm) and was only applicable during periods when the entire plant was predominantly green. These findings provide theoretical and technical support for utilizing UAV-based imagery to estimate the crown diameter of garden chrysanthemums. [ABSTRACT FROM AUTHOR]

Invasive plant species pose significant biodiversity and ecosystem threats. Real-time identification of invasive plants is a crucial prerequisite for early and timely prevention. While deep learning has shown promising results in plant recognition, the use of deep learning models often involve a large number of parameters and high data requirements for training. Unfortunately, the available data for various invasive plant species are often limited. To address this challenge, this study proposes a lightweight deep learning model called IPMCNet for the identification of multiple invasive plant species. IPMCNet attains high recognition accuracy even with limited data and exhibits strong generalizability. Simultaneously, by employing depth-wise separable convolutional kernels, splitting channels, and eliminating fully connected layer, the model's parameter count is lower than that of some existing lightweight models. Additionally, the study explores the impact of different loss functions, and the insertion of various attention modules on the model's accuracy. The experimental results reveal that, compared with eight other existing neural network models, IPMCNet achieves the highest classification accuracy of 94.52%. Furthermore, the findings suggest that focal loss is the most effective loss function. The performance of the six attention modules is suboptimal, and their insertion leads to a decrease in model accuracy. [ABSTRACT FROM AUTHOR]

Existing maize production is grappling with the hurdles of not applying nitrogen fertilizer accurately due to subpar detection accuracy and responsiveness. This situation presents a significant challenge, as it has the potential to impact the optimal yield of maize and ultimately, the profit margins associated with its cultivation. In this study, an automatic modeling prediction method for nitrogen content in maize leaves was proposed based on machine vision and convolutional neural network. We developed a program designed to streamline the image preprocessing workflow. This program can process multiple images in batches, automatically carrying out the necessary preprocessing steps. Additionally, it integrates an automated training and modeling system that correlates the images with nitrogen content values. The primary objective of this program is to enhance the accuracy of the models by leveraging a larger dataset of image samples. Secondly, the fully connected layer of the convolutional neural network was reconstructed to transform the optimization goal from classification based on 0–1 tags into regression prediction, so that the model can output numerical values of nitrogen content. Furthermore, the prediction model of nitrogen content in maize leaves was gained by training many samples, and samples were collected in three key additional fertilizing stages throughout the growth period of maize (i.e., jointing stage, bell mouth stage, and tasseling stage). In addition, the proposed method was compared with the spectral detection method under full-wave band and characteristic wavelengths. It was verified that our machine vision and CNN (Convolutional Neural Network)-based method offers a high prediction accuracy rate that is not only consistently better—by approximately 5% to 45%—than spectral detection approaches but also features the benefits of easy operation and low cost. This technology can significantly contribute to the implementation of more precise fertilization practices in maize production, leading to potential yield optimization and increased profitability. [ABSTRACT FROM AUTHOR]

Yield prediction is a crucial activity in scheduling agronomic operations and in informing the management and financial decisions of a wide range of stakeholders of the organic durum wheat supply chain. This research aims to develop a yield forecasting system by combining vegetation index time-series data from Sentinel-2 L2A time-series data, field-measured yields, and deep learning techniques. Remotely sensed data over a season could be, in general, noisy and characterized by a variable density due to weather conditions. This problem was mitigated using Functional Principal Component Analysis (FPCA). We obtained a functional representation of acquired data, and starting from this, we tried to apply deep learning to predict the crop yield. We used a Convolutional Neural Network (CNN) approach, starting from images that embed temporal and spectral dimensions. This representation does not require one to a priori select a vegetation index that, typically, is task-dependent. The results have been also compared with classical approaches as Partial Least Squares (PLS) on the main reference vegetation indexes such as the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red Edge index (NDRE), considering both in-season and end-season scenarios. The obtained results show that the image-based representation of multi-spectral time series could be an effective method to estimate the yield, also, in the middle stage of cropping with R2 values greater than 0.83. The developed model could be used to estimate yield the neighbor fields characterized by similar setups in terms of the crop, variety, soil, and, of course, management. [ABSTRACT FROM AUTHOR]

Terrestrial ecosystems depend heavily on their vegetation; it is possible to forecast future growth trends of regional vegetation by keeping an eye on changes in vegetation dynamics. To circumvent the potential reduction in prediction accuracy caused by the non-stationarity of meteorological changes, we analyzed the characteristics of NDVI (Normalized Difference Vegetation Index) spatial and temporal changes and the influencing factors over the past 20 years in the Maowusu Sandland of China via attribution analysis. We also constructed a comprehensive analysis system for vegetation pre-restoration. Moreover, we combined meteorological data from 2000 to 2018 and presented a deep-learning NDVI-Informer prediction model with a self-attentive mechanism. We also used distillation operation and fusion convolutional neural network for NDVI prediction. Incorporating a probsparse self-attention method successfully overcomes Transformer weaknesses by lowering the memory use and complexity of large time series. It significantly accelerates the inference speed of long time series prediction and works well with non-smooth data. The primary findings were: (1) the Maowusu Sandland's 20-year average showed a consistent increasing trend in the NDVI at 0.0034 a−1, which was mostly caused by climate change, with a relative contribution rate of 55.47%; (2) The Informer-based model accurately forecasted the NDVI in the research region based on meteorological elements and conducted a thorough analysis of the MAPE (mean absolute percentage error) (2.24%). This suggests that it can effectively lower the data's volatility and increase prediction accuracy. The anticipated outcomes indicate that the trend will stabilize during the following ten years. To attain more sustainable and efficient agricultural production, the results of this study may be used to accurately estimate future crop yields and NDVI using previous data. [ABSTRACT FROM AUTHOR]

Deep learning excels in the identification of specific plant diseases. However, dealing with multi-domain datasets, which encompass a variety of categories, presents challenges due to limited data availability. (1) Background: In real-world scenarios, data distribution is uneven, the scale continues to grow, new categories emerge, and a phenomenon known as 'catastrophic forgetting' occurs. Models rely on a substantial amount of data for labeling and training. (2) Methods: We introduce a two-stage approach. The first stage is the scalable feature learning phase, where the previous feature representation is fixed. Through a new feature extractor, incoming and stored data are trained to expand features. In the second stage, by introducing an auxiliary loss to determine whether key parameters are retained, we reduce the instability of weight parameters. This maintains the separability of old features and encourages the model to learn new concepts, diversity, and discriminative features. (3) Results: Our findings indicate that when the data landscape shifts, recognition accuracy in multi-task continual learning, leveraging the simultaneous availability of datasets, significantly outperforms single convolutional networks and multi-task learning models. (4) Conclusions: Our method advances continual learning towards practical applications. It is particularly effective in mitigating catastrophic forgetting in multi-domain datasets and enhancing the robustness of deep-learning models. [ABSTRACT FROM AUTHOR]

The Montado ecosystem is an important agri-forestry system in Portugal, occupying about 8% of the total area of the country. However, this biodiverse ecosystem is threatened due to factors such as shrub encroachment. In this context, the development of tools for characterizing and monitoring Montado areas is crucial for their conservation. In this study, we developed a deep convolutional neural network algorithm based on the U-net architecture to identify regions with trees, shrubs, grass, bare soil, or other areas in Montado areas using high-resolution RGB and near-infrared orthophotos (with a spatial resolution of 25 cm) from seven experimental sites in the Alentejo region of Portugal (six used for training/validation and one for testing). To optimize the model's performance, we performed hyperparameter tuning, which included adjusting the number of filters, dropout rate, and batch size. The best model achieved an overall classification performance of 0.88 and a mean intersection of the union of 0.81 on the test set, indicating high accuracy and reliability of the model in identifying and delineating land cover classes in the Montado ecosystem. The developed model is a powerful tool for identifying the status of the Montado ecosystem regarding shrub encroachment and facilitating better future management. [ABSTRACT FROM AUTHOR]

Over the last few years, several Convolutional Neural Networks for object detection have been proposed, characterised by different accuracy and speed. In viticulture, yield estimation and prediction is used for efficient crop management, taking advantage of precision viticulture techniques. Convolutional Neural Networks for object detection represent an alternative methodology for grape yield estimation, which usually relies on manual harvesting of sample plants. In this paper, six versions of the You Only Look Once (YOLO) object detection algorithm (YOLOv3, YOLOv3-tiny, YOLOv4, YOLOv4-tiny, YOLOv5x, and YOLOv5s) were evaluated for real-time bunch detection and counting in grapes. White grape varieties were chosen for this study, as the identification of white berries on a leaf background is trickier than red berries. YOLO models were trained using a heterogeneous dataset populated by images retrieved from open datasets and acquired on the field in several illumination conditions, background, and growth stages. Results have shown that YOLOv5x and YOLOv4 achieved an F1-score of 0.76 and 0.77, respectively, with a detection speed of 31 and 32 FPS. Differently, YOLO5s and YOLOv4-tiny achieved an F1-score of 0.76 and 0.69, respectively, with a detection speed of 61 and 196 FPS. The final YOLOv5x model for bunch number, obtained considering bunch occlusion, was able to estimate the number of bunches per plant with an average error of 13.3% per vine. The best combination of accuracy and speed was achieved by YOLOv4-tiny, which should be considered for real-time grape yield estimation, while YOLOv3 was affected by a False Positive–False Negative compensation, which decreased the RMSE. [ABSTRACT FROM AUTHOR]

The accurate acquisition of safflower filament information is the prerequisite for robotic picking operations. To detect safflower filaments accurately in different illumination, branch and leaf occlusion, and weather conditions, an improved Faster R-CNN model for filaments was proposed. Due to the characteristics of safflower filaments being dense and small in the safflower images, the model selected ResNeSt-101 with residual network structure as the backbone feature extraction network to enhance the expressive power of extracted features. Then, using Region of Interest (ROI) Align improved ROI Pooling to reduce the feature errors caused by double quantization. In addition, employing the partitioning around medoids (PAM) clustering was chosen to optimize the scale and number of initial anchors of the network to improve the detection accuracy of small-sized safflower filaments. The test results showed that the mean Average Precision (mAP) of the improved Faster R-CNN reached 91.49%. Comparing with Faster R-CNN, YOLOv3, YOLOv4, YOLOv5, and YOLOv6, the improved Faster R-CNN increased the mAP by 9.52%, 2.49%, 5.95%, 3.56%, and 1.47%, respectively. The mAP of safflower filaments detection was higher than 91% on a sunny, cloudy, and overcast day, in sunlight, backlight, branch and leaf occlusion, and dense occlusion. The improved Faster R-CNN can accurately realize the detection of safflower filaments in natural environments. It can provide technical support for the recognition of small-sized crops. [ABSTRACT FROM AUTHOR]

Cluster 3 (blue circles) is defined by 193 keywords, with keywords including "Internet of Things" contributing 4.416 TLS or 6.39%, "smart agricultures" contributing 1.542 TLS or 2.23%, "smart agriculture" contributing 1.465 TLS or 2.12%, "IoT" contributing 1.441 TLS or 2.09%, and "Internet of Things (IoT)" contributing 1.163 TLS or 1.68%. Cluster 3 (blue circles) is defined by 213 keywords, with keywords including "agriculture" contributing 27.225 TLS or 6.89%, "artificial intelligence" contributing 12.658 TLS or 3.02%, "agricultural robots" contributing 8.964 TLS or 2.27%, "Internet of Things" contributing 7.893 TLS or 1.20%, and "precision agriculture" contributing 6.743 TLS or 1.71%. In detail, the co-keyword network visualization was: "Agriculture" AND "Sustainable" AND "Smart technologies" (Figure 1), "Agriculture" AND "Sustainable" AND "Artificial intelligence" (Figure 2), "Agriculture" AND "Sustainable" AND "Robotics" (Figure 3), and "Agriculture" AND "Sustainable" AND "Internet of Things" (Figure 4). Cluster 3 (blue circles) is defined by 198 keywords, with keywords including "agricultural robots", which contributed 7.713 TLS or 3.31%, "smart agriculture", which contributed 5.223 TLS or 2.24%, "Internet of Things (IoT)", which contributed 4.841 TLS or 2.08%, "smart agriculture" contributed 4.179 TLS or 1.79%, and "artificial intelligence" contributed 4.082 TLS or 1.75%. [Extracted from the article]

Buckwheat plant height is an important indicator for producers. Due to the decline in agricultural labor, the automatic and real-time acquisition of crop growth information will become a prominent issue for farms in the future. To address this problem, we focused on stereo vision and a regression convolutional neural network (CNN) in order to estimate buckwheat plant height. MobileNet V3 Small, NasNet Mobile, RegNet Y002, EfficientNet V2 B0, MobileNet V3 Large, NasNet Large, RegNet Y008, and EfficientNet V2 L were modified into regression CNNs. Through a five-fold cross-validation of the modeling data, the modified RegNet Y008 was selected as the optimal estimation model. Based on the depth and contour information of buckwheat depth image, the mean absolute error (MAE), root mean square error (RMSE), mean square error (MSE), and mean relative error (MRE) when estimating plant height were 0.56 cm, 0.73 cm, 0.54 cm, and 1.7%, respectively. The coefficient of determination (R2) value between the estimated and measured results was 0.9994. Combined with the LabVIEW software development platform, this method can estimate buckwheat accurately, quickly, and automatically. This work contributes to the automatic management of farms. [ABSTRACT FROM AUTHOR]

Aiming at difficult image acquisition and low recognition accuracy of two rice canopy pests, rice stem borer and rice leaf roller, we constructed a GA-Mask R-CNN (Generative Adversarial Based Mask Region Convolutional Neural Network) intelligent recognition model for rice stem borer and rice leaf roller, and we combined it with field monitoring equipment for them. Firstly, based on the biological habits of rice canopy pests, a variety of rice pest collection methods were used to obtain the images of rice stem borer and rice leaf roller pests. Based on different segmentation algorithms, the rice pest images were segmented to extract single pest samples. Secondly, the bug generator based on a generative adversarial network strategy improves the sensitivity of the classification network to the bug information, generates the pest information images in the real environment, and obtains the sample dataset for deep learning through multi-way augmentation. Then, through adding channel attention ECA module in Mask R-CNN and improving the connection of residual blocks in the backbone network ResNet101, the recognition accuracy of the model is improved. Finally, the GA-Mask R-CNN model was tested on a multi-source dataset with an average precision (AP) of 92.71%, recall (R) of 89.28% and a balanced score F1 of 90.96%. The average precision, recall, and balanced score F1 are improved by 7.07, 7.65, and 8.83%, respectively, compared to the original Mask R-CNN. The results show that the GA-Mask R-CNN model performance indexes are all better than the Mask R-CNN, the Faster R-CNN, the SSD, the YOLOv5, and other network models, which can provide technical support for remote intelligent monitoring of rice pests. [ABSTRACT FROM AUTHOR]

Sunscald in kiwifruit, an environmental stress caused by solar radiation during the summer, reduces fruit quality and yields and causes economic losses. The efficient and timely detection of sunscald and similar diseases is a challenging task but helps to implement measures to control stress. This study provides high-precision detection models and relevant spectral information on kiwifruit physiology for similar statuses, including early-stage sunscald, late-stage sunscald, anthracnose, and healthy. Primarily, in the laboratory, 429 groups of spectral reflectance data for leaves of four statuses were collected and analyzed using a hyperspectral reflection acquisition system. Then, multiple modeling approaches, including combined preprocessing methods, feature extraction algorithms, and classification algorithms, were designed to extract bands and evaluate the performance of the models to detect the statuses of kiwifruit. Finally, the detection of different stages of kiwifruit sunscald under anthracnose interference was accomplished. As influential bands, 694–713 nm, 758–777 nm, 780–799 nm, and 1303–1322 nm were extracted. The overall accuracy, precision, recall, and F1-score values of the models reached 100%, demonstrating an ability to detect all statuses with 100% accuracy. It was concluded that the combined processing of moving average and standard normal variable transformations (MS) could significantly improve the data; the near-infrared support vector machine and visible convolutional neural network with MS (NIR-MS-SVM and VIS-MS-CNN) were established as high-precision detection techniques for the classification of similar kiwifruit statuses, demonstrating 25.58% higher accuracy than the single support vector machine. The VIS-MS-CNN model reached convergence with a stable cross-entropy loss of 0.75 in training and 0.77 in validation. The techniques developed in this study will improve orchard management efficiency and yields and increase researchers' understanding of kiwifruit physiology. [ABSTRACT FROM AUTHOR]