“Smart Agriculture” Information Technology and Agriculture Cross-Discipline Research and Development

A special issue of Agronomy (ISSN 2073-4395). This special issue belongs to the section "Precision and Digital Agriculture".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 43559

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors


E-Mail Website1 Website2
Guest Editor
1. Department of Biology, University of British Columbia, Okanagan, Kelowna, BC V1V 1V7, Canada
2. Faculty of Agronomy, Jilin Agricultural University, Changchun 131018, China
Interests: digital agriculture; bioinformatics; genomics; plant phenomics; indoor breeding
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Centre for Machine Learning, Department of Computer Science, University of Alberta, Edmonton, AB T6G 2R3, Canada
Interests: foundations of AI and machine learning; applications in health, law and agronomy

E-Mail Website
Guest Editor
Faculty of Agronomy, Jilin Agricultural University, Changchun 131018, China
Interests: smart agriculture; precision agriculture; rice cultivation; rice dry farming

Special Issue Information

Dear Colleagues,

Our goal is to explore and support the evolution of emerging digital technology applications in agriculture and biology, including but not limited to agriculture, data collection, data mining, bioinformatics, genomics and phenomics, as well as applications of machine learning and artificial intelligence.

The development of a community to support this goal requires the cross linking and integration of multiple sources of agricultural research across 3S technologies (remote sensing—RS, geographic information systems—GIS, global positioning systems—GPS). This provides a basis for the detection of crop pathogens, weeds and pests (insects) using multi-spectrum techniques and the exploitation of remote sensing technology to create and analyze multiple heterogeneous-structured data sets, which enables effective cross-linking and phenomic classification. It is essential to study growth models of plants/crops and utilize expert support to develop production and smart management decision systems to achieve real-time, quantified, and precise decisions.

Topics of high interest include the capture and curation of biological “big data,”  research on multi-spectrum analysis, the assembly of complex genetic sequencing fragments, and structural gene predictions coupled with intermediate structures to predict phenotypes. In this context, novel data structures are required to capture predictive structures in the path from genome type to phenotype, together with new techniques to capture identify the regularity of biological data.

Finally, multiple-sources-based monitoring and decision making for plants, water, and nutrients are required, with a research focus on the utilization of remote sensing and drone sensing to compute and predict plant water usage. This will lead to the development of precision models of crop water/nutrient management systems and form the foundation for the digitalization of agricultural water/nutrient applications.

Prof. Dr. Jian Zhang
Prof. Dr. Randy G. Goebel
Prof. Dr. Zhihai Wu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Agronomy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • information technology
  • agriculture
  • bioinformatics
  • genetics
  • machine learning
  • sensors
  • imaging
  • satellites
  • geographic information technology

Published Papers (21 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research, Review

4 pages, 180 KiB  
Editorial
“Smart Agriculture” Information Technology and Agriculture Cross-Discipline Research and Development
by Jian Zhang, Randy G. Goebel and Zhihai Wu
Agronomy 2023, 13(10), 2536; https://doi.org/10.3390/agronomy13102536 - 30 Sep 2023
Viewed by 1133
Abstract
Digital technology applications in agriculture and biology are a dynamic area of research interest, with topics including, but not limited to, agriculture, data collection, data mining, bioinformatics, genomics and phenomics, as well as applications of machine learning and artificial intelligence [...] Full article

Research

Jump to: Editorial, Review

15 pages, 2888 KiB  
Article
A Comprehensive Approach to Assessing Yield Map Quality in Smart Agriculture: Void Detection and Spatial Error Mapping
by John Byabazaire, Gregory M. P. O’Hare, Rem Collier, Chamil Kulatunga and Declan Delaney
Agronomy 2023, 13(7), 1943; https://doi.org/10.3390/agronomy13071943 - 22 Jul 2023
Cited by 2 | Viewed by 1232
Abstract
Smart agriculture relies on accurate yield maps as a crucial tool for decision-making. Many yield maps, however, suffer from spatial errors that can compromise the quality of their data, while several approaches have been proposed to address some of these errors, detecting voids [...] Read more.
Smart agriculture relies on accurate yield maps as a crucial tool for decision-making. Many yield maps, however, suffer from spatial errors that can compromise the quality of their data, while several approaches have been proposed to address some of these errors, detecting voids or holes in the maps remains challenging. Additionally, the quality of yield datasets is typically evaluated based on root mean squared errors after interpolation. This evaluation method relies on weighbridge data, which can occasionally be inaccurate, impacting the quality of decisions made using the datasets. This paper introduces a novel algorithm designed to identify voids in yield maps. Furthermore, it maps three types of spatial errors (GPS errors, yield surges, and voids) to two standard data quality dimensions (accuracy and completeness). Doing so provides a quality score that can be utilized to assess the quality of yield datasets, eliminating the need for weighbridge data. The paper carries out three types of evaluations: (1) evaluating the algorithm’s efficacy by applying it to a dataset containing fields with and without voids; (2) assessing the benefits of integrating void detection and other spatial error identification techniques into the yield data processing chain; and (3) examining the correlation between root mean squared error and the proposed quality score before and after filtering out spatial errors. The results of the evaluations demonstrate that the proposed algorithm achieves a 100% sensitivity, 91% specificity, and 82% accuracy in identifying yield maps with voids. Additionally, there is a decrease in the root mean squared error when various spatial errors, including voids after applying the proposed data pre-processing chain. The inverse correlation observed between the root mean squared error and the proposed quality score (−0.577 and −0.793, before and after filtering spatial errors, respectively) indicates that the quality score can effectively assess the quality of yield datasets. This assessment enables seamless integration into real-time big data quality assessment solutions based on various data quality dimensions. Full article
Show Figures

Figure 1

16 pages, 4125 KiB  
Article
Recognition of Edible Fungi Fruit Body Diseases Based on Improved ShuffleNetV2
by Xingmei Xu, Yuqi Zhang, Hongcheng Cao, Dawei Yang, Lei Zhou and Helong Yu
Agronomy 2023, 13(6), 1530; https://doi.org/10.3390/agronomy13061530 - 31 May 2023
Cited by 4 | Viewed by 1357
Abstract
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 [...] Read more.
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. Full article
Show Figures

Figure 1

18 pages, 7462 KiB  
Article
Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage
by Shuolin Kong, Jian Li, Yuting Zhai, Zhiyuan Gao, Yang Zhou and Yanlei Xu
Agronomy 2023, 13(6), 1503; https://doi.org/10.3390/agronomy13061503 - 30 May 2023
Cited by 5 | Viewed by 1369
Abstract
Crop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed [...] Read more.
Crop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed as an alternative to conventional labeling approaches to improve the detection accuracy for dense planting crops. Second, a seedling detection network based on YOLOv5 and a transformer mechanism was proposed, and the effects of three features (query, key and value) in the transformer mechanism on the detection accuracy were explored in detail. Finally, the seedling detection network was optimized into a lightweight network. The experimental results show that application of the single leaf labeling method could improve the mAP0.5 of the model by 1.2% and effectively solve the problem of missed detection. By adding the transformer mechanism module, the mAP0.5 was improved by 1.5%, enhancing the detection capability of the model for dense and obscured targets. In the end, this study found that query features had the least impact on the transformer mechanism, and the optimized model improved the computation speed by 23 ms·frame−1 on the intelligent computing platform Jetson TX2, providing a theoretical basis and technical support for real-time seedling management. Full article
Show Figures

Figure 1

17 pages, 6199 KiB  
Article
Detection and Counting of Small Target Apples under Complicated Environments by Using Improved YOLOv7-tiny
by Li Ma, Liya Zhao, Zixuan Wang, Jian Zhang and Guifen Chen
Agronomy 2023, 13(5), 1419; https://doi.org/10.3390/agronomy13051419 - 20 May 2023
Cited by 14 | Viewed by 2540
Abstract
Weather disturbances, difficult backgrounds, the shading of fruit and foliage, and other elements can significantly affect automated yield estimation and picking in small target apple orchards in natural settings. This study uses the MinneApple public dataset, which is processed to construct a dataset [...] Read more.
Weather disturbances, difficult backgrounds, the shading of fruit and foliage, and other elements can significantly affect automated yield estimation and picking in small target apple orchards in natural settings. This study uses the MinneApple public dataset, which is processed to construct a dataset of 829 images with complex weather, including 232 images of fog scenarios and 236 images of rain scenarios, and proposes a lightweight detection algorithm based on the upgraded YOLOv7-tiny. In this study, a backbone network was constructed by adding skip connections to shallow features, using P2BiFPN for multi-scale feature fusion and feature reuse at the neck, and incorporating a lightweight ULSAM attention mechanism to reduce the loss of small target features, focusing on the correct target and discard redundant features, thereby improving detection accuracy. The experimental results demonstrate that the model has an mAP of 80.4% and a loss rate of 0.0316. The mAP is 5.5% higher than the original model, and the model size is reduced by 15.81%, reducing the requirement for equipment; In terms of counts, the MAE and RMSE are 2.737 and 4.220, respectively, which are 5.69% and 8.97% lower than the original model. Because of its improved performance and stronger robustness, this experimental model offers fresh perspectives on hardware deployment and orchard yield estimation. Full article
Show Figures

Figure 1

14 pages, 3840 KiB  
Article
Maize (Zea mays L.) Stem Target Region Extraction and Stem Diameter Measurement Based on an Internal Gradient Algorithm in Field Conditions
by Jing Zhou, Mingren Cui, Yushan Wu, Yudi Gao, Yijia Tang, Zhiyi Chen, Lixin Hou and Haijuan Tian
Agronomy 2023, 13(5), 1185; https://doi.org/10.3390/agronomy13051185 - 22 Apr 2023
Cited by 2 | Viewed by 1731
Abstract
The target region and diameter of maize stems are important phenotyping parameters for evaluating crop vitality and estimating crop biomass. To address the issue that the target region and diameter of maize stems obtained after transplantation may not accurately reflect the true growth [...] Read more.
The target region and diameter of maize stems are important phenotyping parameters for evaluating crop vitality and estimating crop biomass. To address the issue that the target region and diameter of maize stems obtained after transplantation may not accurately reflect the true growth conditions of maize, a phenotyping monitoring technology based on an internal gradient algorithm is proposed for acquiring the target region and diameter of maize stems. Observations were conducted during the small bell stage of maize. First, color images of maize plants were captured by an Intel RealSense D435i camera. The color information in the color image was extracted by the hue saturation value (HSV) color space model. The maximum between-class variance (Otsu) algorithm was applied for image threshold segmentation to obtain the main stem of maize. Median filtering, image binarization, and morphological opening operations were then utilized to remove noise from the images. Subsequently, the morphological gradient algorithm was applied to acquire the target region of maize stems. The similarity between the three types of gradient images and the manually segmented image was evaluated by pixel ratio extraction and image quality assessment indicators. Evaluation results indicated that the internal gradient algorithm could more accurately obtain the target region of maize stems. Finally, a checkerboard was employed as a reference for measurement assistance, and the stem diameter of maize was calculated by the pinhole imaging principle. The mean absolute error of stem diameter was 1.92 mm, the mean absolute percentage error (MAPE) was 5.16%, and the root mean square error (RMSE) was 2.25 mm. The R² value was 0.79. With an R² greater than 0.7 and a MAPE within 6%, the phenotyping monitoring technology based on the internal gradient algorithm was proven to accurately measure the diameter of maize stems. The application of phenotyping monitoring technology based on the internal gradient algorithm in field conditions provides technological support for smart agriculture. Full article
Show Figures

Figure 1

16 pages, 6361 KiB  
Communication
Hybrid CNN-SVM Classifier Approaches to Process Semi-Structured Data in Sugarcane Yield Forecasting Production
by Debnath Bhattacharyya, Eali Stephen Neal Joshua, N. Thirupathi Rao and Tai-hoon Kim
Agronomy 2023, 13(4), 1169; https://doi.org/10.3390/agronomy13041169 - 20 Apr 2023
Cited by 4 | Viewed by 1881
Abstract
Information communication technology (ICT) breakthroughs have boosted global social and economic progress. Most rural Indians rely on agriculture for income. The growing population requires modern agricultural practices. ICT is crucial for educating farmers on how to be environmentally friendly. It helps them create [...] Read more.
Information communication technology (ICT) breakthroughs have boosted global social and economic progress. Most rural Indians rely on agriculture for income. The growing population requires modern agricultural practices. ICT is crucial for educating farmers on how to be environmentally friendly. It helps them create more food by solving a variety of challenges. India’s sugarcane crop is popular and lucrative. Long-term crops that require water do not need specific soil. They need water; the ground should always have adequate water due to the link between cane growth and evaporation. This research focuses on forecasting soil moisture and classifying sugarcane output; sugarcane has so many applications that it must be categorized. This research examines these claims: The first phase model predicts soil moisture using two-level ensemble classifiers. Secondly, to boost performance, the proposed ensemble model integrates the Gaussian probabilistic method (GPM), the convolutional neural network (CNN), and support vector machines (SVM). The suggested approach aims to correctly anticipate future soil moisture measurements affecting crop growth and cultivation. The proposed model is 89.53% more accurate than conventional neural network classifiers. The recommended models’ outcomes will assist farmers and agricultural authorities in boosting production. Full article
Show Figures

Figure 1

17 pages, 3285 KiB  
Article
Hyperspectral Non-Imaging Measurements and Perceptron Neural Network for Pre-Harvesting Assessment of Damage Degree Caused by Septoria/Stagonospora Blotch Diseases of Wheat
by Sofia V. Zhelezova, Elena V. Pakholkova, Vladislav E. Veller, Mikhail A. Voronov, Eugenia V. Stepanova, Alena D. Zhelezova, Anton V. Sonyushkin, Timur S. Zhuk and Alexey P. Glinushkin
Agronomy 2023, 13(4), 1045; https://doi.org/10.3390/agronomy13041045 - 1 Apr 2023
Cited by 2 | Viewed by 1695
Abstract
The detection and identification of plant diseases is a fundamental task for sustainable crop production. Septoria tritici and Stagonospora nodorum blotch (STB and SNB) are two of the most common diseases of cereal crops that cause significant economic damage. Both pathogens are difficult [...] Read more.
The detection and identification of plant diseases is a fundamental task for sustainable crop production. Septoria tritici and Stagonospora nodorum blotch (STB and SNB) are two of the most common diseases of cereal crops that cause significant economic damage. Both pathogens are difficult to identify at early stages of infection. Determining the degree of the disease at a late infection stage is useful for assessing cereal crops before harvesting, as it allows the assessment of potential yield losses. Hyperspectral sensing could allow for automatic recognition of Septoria harmfulness on wheat in field conditions. In this research, we aimed to collect information on the hyperspectral data on wheat plants with different lesion degrees of STB&SNB and to create and train a neural network for the detection of lesions on leaves and ears caused by STB&SNB infection at the late stage of disease development. Spring wheat was artificially infected twice with Septoria pathogens in the stem elongation stage and in the heading stage. Hyperspectral reflections and brightness measurements were collected in the field on wheat leaves and ears on the 37th day after STB and the 30th day after SNB pathogen inoculation using an Ocean Insight “Flame” VIS-NIR hyperspectrometer. Obtained non-imaging data were pre-treated, and the perceptron model neural network (PNN) was created and trained based on a pairwise comparison of datasets for healthy and diseased plants. Both statistical and neural network approaches showed the high quality of the differentiation between healthy and damaged wheat plants by the hyperspectral signature. A comparison of the results of visual recognition and automatic STB&SNB estimation showed that the neural network was equally effective in the quality of the disease definition. The PNN, based on a neuron model of hyperspectral signature with a spectral step of 6 nm and 2000–4000 value datasets, showed a high quality of detection of the STB&SNB severity. There were 0.99 accuracy, 0.94 precision, 0.89 recall and 0.91 F-score metrics of the PNN model after 10,000 learning epochs. The estimation accuracy of diseased/healthy leaves ranged from 88.1 to 97.7% for different datasets. The accuracy of detection of a light and medium degree of disease was lower (38–66%). This method of non-imaging hyperspectral signature classification could be useful for the identification of the STB and SNB lesion degree identification in field conditions for pre-harvesting crop estimation. Full article
Show Figures

Figure 1

17 pages, 75879 KiB  
Article
Citrus Disease Image Generation and Classification Based on Improved FastGAN and EfficientNet-B5
by Qiufang Dai, Yuanhang Guo, Zhen Li, Shuran Song, Shilei Lyu, Daozong Sun, Yuan Wang and Ziwei Chen
Agronomy 2023, 13(4), 988; https://doi.org/10.3390/agronomy13040988 - 27 Mar 2023
Cited by 6 | Viewed by 3166
Abstract
The rapid and accurate identification of citrus leaf diseases is crucial for the sustainable development of the citrus industry. Because citrus leaf disease samples are small, unevenly distributed, and difficult to collect, we redesigned the generator structure of FastGAN and added small batch [...] Read more.
The rapid and accurate identification of citrus leaf diseases is crucial for the sustainable development of the citrus industry. Because citrus leaf disease samples are small, unevenly distributed, and difficult to collect, we redesigned the generator structure of FastGAN and added small batch standard deviations to the discriminator to produce an enhanced model called FastGAN2, which was used for generating citrus disease and nutritional deficiency (zinc and magnesium deficiency) images. The performance of the existing model degrades significantly when the training and test data exhibit large differences in appearance or originate from different regions. To solve this problem, we propose an EfficientNet-B5 network incorporating adaptive angular margin (Arcface) loss with the adversarial weight perturbation mechanism, and we call it EfficientNet-B5-pro. The FastGAN2 network can be trained using only 50 images. The Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) are improved by 31.8% and 59.86%, respectively, compared to the original FastGAN network; 8000 images were generated using the FastGAN2 network (2000 black star disease, 2000 canker disease, 2000 healthy, 2000 deficiency). Only images generated by the FastGAN2 network were used as the training set to train the ten classification networks. Real images, which were not used to train the FastGAN2 network, were used as the test set. The average accuracy rates of the ten classification networks exceeded 93%. The accuracy, precision, recall, and F1 scores achieved by EfficientNet-B5-pro were 97.04%, 97.32%, 96.96%, and 97.09%, respectively, and they were 2.26%, 1.19%, 1.98%, and 1.86% higher than those of EfficientNet-B5, respectively. The classification network model can be successfully trained using only the images generated by FastGAN2, and EfficientNet-B5-pro has good generalization and robustness. The method used in this study can be an effective tool for citrus disease and nutritional deficiency image classification using a small number of samples. Full article
Show Figures

Figure 1

12 pages, 2933 KiB  
Communication
Evaluation of a Real-Time Monitoring and Management System of Soybean Precision Seed Metering Devices
by Jicheng Zhang, Yinghui Hou, Wenyi Ji, Ping Zheng, Shichao Yan, Shouyin Hou and Changqing Cai
Agronomy 2023, 13(2), 541; https://doi.org/10.3390/agronomy13020541 - 14 Feb 2023
Cited by 2 | Viewed by 1963
Abstract
Aiming at precise evaluation of the performance of soybean seed metering devices, a photoelectric sensor-based real-time monitoring system was designed. The proposed system mainly included a photoelectric sensor module for seeding signal collecting, Hall sensors speeding module, microcontroller unit (MCU), light and sound [...] Read more.
Aiming at precise evaluation of the performance of soybean seed metering devices, a photoelectric sensor-based real-time monitoring system was designed. The proposed system mainly included a photoelectric sensor module for seeding signal collecting, Hall sensors speeding module, microcontroller unit (MCU), light and sound alarm module, human–machine interface (HMI), and other parts. The indexes of miss, multiples, flow rate, and application rate were estimated on the basis of seeder speed, seed metering disk rotation rate, photoelectric sensor signals, and clock signals. These real-time statistics of the seeding process were recorded by seeding management system. The laboratory results showed that the detection errors of seeding quantity of both big- and small-diameter soybeans were less than 2.0%. Miss and multiples index estimated by this system were 0.4% and 0.5% than that of seeding image monitoring platform (SIMP), respectively. In field tests, miss and multiples index can be used to evaluate the performance of seed metering device, and big-diameter seeds can be detected more precisely than small ones by these photoelectric sensors. This system can provide support for evaluation of working performance of seed metering devices and have a positive effect on seeding monitoring technology. Full article
Show Figures

Figure 1

17 pages, 3493 KiB  
Article
Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism
by Li Ma, Qiwen Yu, Helong Yu and Jian Zhang
Agronomy 2023, 13(2), 521; https://doi.org/10.3390/agronomy13020521 - 11 Feb 2023
Cited by 12 | Viewed by 1887
Abstract
Maize diseases are reported to occur often, and are complicated and difficult to control, which seriously affects the yield and quality of maize. This paper proposes an improved YOLOv5n model incorporating a CA (Coordinate Attention) mechanism and STR (Swin Transformer) detection head, CTR_YOLOv5n, [...] Read more.
Maize diseases are reported to occur often, and are complicated and difficult to control, which seriously affects the yield and quality of maize. This paper proposes an improved YOLOv5n model incorporating a CA (Coordinate Attention) mechanism and STR (Swin Transformer) detection head, CTR_YOLOv5n, to identify common maize leaf spot, gray spot, and rust diseases in mobile applications. Based on the lightweight model YOLOv5n, the accuracy of the model is improved by adding a CA attention module, and the global information acquisition capability is enhanced by using TR2 as the detection head. The average recognition accuracy of the algorithm model can reach 95.2%, which is 2.8 percent higher than the original model, and the memory size is reduced to 5.1MB compared to 92.9MB of YOLOv5l, which is 94.5% smaller and meets the requirement of being light weight. Compared with SE, CBAM, and ECA, which are the mainstream attention mechanisms, the recognition effect we used is better and the accuracy is higher, achieving fast and accurate recognition of maize leaf diseases with fewer computational resources, providing new ideas and methods for real-time recognition of maize and other crop spots in mobile applications. Full article
Show Figures

Figure 1

14 pages, 3303 KiB  
Article
Based on FCN and DenseNet Framework for the Research of Rice Pest Identification Methods
by He Gong, Tonghe Liu, Tianye Luo, Jie Guo, Ruilong Feng, Ji Li, Xiaodan Ma, Ye Mu, Tianli Hu, Yu Sun, Shijun Li, Qinglan Wang and Ying Guo
Agronomy 2023, 13(2), 410; https://doi.org/10.3390/agronomy13020410 - 30 Jan 2023
Cited by 12 | Viewed by 1741
Abstract
One of the most important food crops is rice. For this reason, the accurate identification of rice pests is a critical foundation for rice pest control. In this study, we propose an algorithm for automatic rice pest identification and classification based on fully [...] Read more.
One of the most important food crops is rice. For this reason, the accurate identification of rice pests is a critical foundation for rice pest control. In this study, we propose an algorithm for automatic rice pest identification and classification based on fully convolutional networks (FCNs) and select 10 rice pests for experiments. First, we introduce a new encoder–decoder in the FCN and a series of sub-networks connected by jump paths that combine long jumps and shortcut connections for accurate and fine-grained insect boundary detection. Secondly, the network also integrates a conditional random field (CRF) module for insect contour refinement and boundary localization, and finally, a novel DenseNet framework that introduces an attention mechanism (ECA) is proposed to focus on extracting insect edge features for effective rice pest classification. The proposed model was tested on the data set collected in this paper, and the final recognition accuracy was 98.28%. Compared with the other four models in the paper, the proposed model in this paper is more accurate, faster, and has good robustness; meanwhile, it can be demonstrated from our results that effective segmentation of insect images before classification can improve the detection performance of deep-learning-based classification systems. Full article
Show Figures

Figure 1

12 pages, 1775 KiB  
Article
Real-Time Measurement of Atmospheric CO2, CH4 and N2O above Rice Fields Based on Laser Heterodyne Radiometers (LHR)
by Jun Li, Zhengyue Xue, Yue Li, Guangyu Bo, Fengjiao Shen, Xiaoming Gao, Jian Zhang and Tu Tan
Agronomy 2023, 13(2), 373; https://doi.org/10.3390/agronomy13020373 - 27 Jan 2023
Cited by 4 | Viewed by 1632
Abstract
High-precision observations provide an efficient way to calculate greenhouse gas emissions from agricultural fields and their spatial and temporal distributions. Two high-resolution laser heterodyne radiometers (LHRs) were deployed in the suburb of Hefei (31.9°N 117.16°E) for the remote sensing of atmospheric CO2 [...] Read more.
High-precision observations provide an efficient way to calculate greenhouse gas emissions from agricultural fields and their spatial and temporal distributions. Two high-resolution laser heterodyne radiometers (LHRs) were deployed in the suburb of Hefei (31.9°N 117.16°E) for the remote sensing of atmospheric CO2, CH4 and N2O above rice paddy fields. The atmospheric transmittance spectra of CO2, CH4 and N2O were measured simultaneously in real time, and the atmospheric total column abundance was retrieved from the measured data based on the optimal estimation algorithm, with errors of 0.7 ppm, 4 ppb and 2 ppb, respectively. From July to October, the abundance of CO2 in the atmospheric column that was influenced by emissions from rice fields increased by 0.7 ppm CH4 by 30 ppb, and by 4 ppb N2O. During the rice growth season, rice paddy fields play a role in carbon sequestration. CH4 and N2O emissions from paddy fields are negatively correlated. The method of baking rice paddy fields reduces CH4 emissions from rice fields, but N2O emissions from rice fields are usually subsequently increased. The measurement results showed that LHRs are highly accurate in monitoring atmospheric concentrations and have promising applications in monitoring emissions from rice paddy fields. In the observation period, rice paddy fields can sequester carbon, and CH4 and N2O emissions from rice fields are negatively correlated. The LHRs have strong application prospects for monitoring emissions from agricultural fields. Full article
Show Figures

Figure 1

16 pages, 14024 KiB  
Article
Rapid and Accurate Prediction of Soil Texture Using an Image-Based Deep Learning Autoencoder Convolutional Neural Network Random Forest (DLAC-CNN-RF) Algorithm
by Zhuan Zhao, Wenkang Feng, Jinrui Xiao, Xiaochu Liu, Shusheng Pan and Zhongwei Liang
Agronomy 2022, 12(12), 3063; https://doi.org/10.3390/agronomy12123063 - 3 Dec 2022
Cited by 4 | Viewed by 2209
Abstract
Soil determines the degree of water infiltration, crop nutrient absorption, and germination, which in turn affects crop yield and quality. For the efficient planting of agricultural products, the accurate identification of soil texture is necessary. This study proposed a flexible smartphone-based machine vision [...] Read more.
Soil determines the degree of water infiltration, crop nutrient absorption, and germination, which in turn affects crop yield and quality. For the efficient planting of agricultural products, the accurate identification of soil texture is necessary. This study proposed a flexible smartphone-based machine vision system using a deep learning autoencoder convolutional neural network random forest (DLAC-CNN-RF) model for soil texture identification. Different image features (color, particle, and texture) were extracted and randomly combined to predict sand, clay, and silt content via RF and DLAC-CNN-RF algorithms. The results show that the proposed DLAC-CNN-RF model has good performance. When the full features were extracted, a very high prediction accuracy for sand (R2 = 0.99), clay (R2 = 0.98), and silt (R2 = 0.98) was realized, which was higher than those frequently obtained by the KNN and VGG16-RF models. The possible mechanism was further discussed. Finally, a graphical user interface was designed and used to accurately predict soil types. This investigation showed that the proposed DLAC-CNN-RF model could be a promising solution to costly and time-consuming laboratory methods. Full article
Show Figures

Figure 1

8 pages, 2140 KiB  
Communication
Smart Automation for Production of Panchagavya Natural Fertilizer
by Sumathi V. and Mohamed Abdullah J.
Agronomy 2022, 12(12), 3044; https://doi.org/10.3390/agronomy12123044 - 1 Dec 2022
Cited by 1 | Viewed by 2183
Abstract
Modern agricultural farming techniques employ the usage of chemical supplements to improve crop yield in terms of quantity and quality. This practice has brought down the fertility of the soil and has led to secondary impacts and necessitates a significant financial investment. Awareness [...] Read more.
Modern agricultural farming techniques employ the usage of chemical supplements to improve crop yield in terms of quantity and quality. This practice has brought down the fertility of the soil and has led to secondary impacts and necessitates a significant financial investment. Awareness of the side effects of artificially enriched food has made people move towards organically grown food, and the consumption has also increased significantly. One of the ancient organic fertilizers used in India is panchagavya. As the name implies, pancha means five and gavya means cow. The five products of the cow are combined as per the compositions and procedure described in the literature, to provide economical and meaningful value to organic farming. The objective of this work is to design, develop, and implement an automated system to manufacture panchagavya with reduced operator assistance. The system implements an ATmega 328 microcontroller to automate the entire process by interfacing sensors such as pH, moisture, temperature, and pressure. The system is also provided with a SIM900A GSM modem to provide information to the user regarding the status of the process. The developed pilot scale design discussed in this work has several advantages in the world of farming technologies in terms of enriching the soil, thereby improving the crop yield. This technology will benefit the farmers as this natural fertilizer can be mass-produced and turn them into entrepreneurs, which benefits society at large. Full article
Show Figures

Figure 1

15 pages, 3603 KiB  
Article
A Grading Method of Ginseng (Panax ginseng C. A. Meyer) Appearance Quality Based on an Improved ResNet50 Model
by Dongming Li, Xinru Piao, Yu Lei, Wei Li, Lijuan Zhang and Li Ma
Agronomy 2022, 12(12), 2925; https://doi.org/10.3390/agronomy12122925 - 23 Nov 2022
Cited by 3 | Viewed by 1648
Abstract
In the academic world, ginseng (Panax ginseng C. A. Meyer) has received much attention as the most representative element of Chinese medicine. To address the lack of traditional algorithms in the identification of ginseng appearance quality and further improve the manual [...] Read more.
In the academic world, ginseng (Panax ginseng C. A. Meyer) has received much attention as the most representative element of Chinese medicine. To address the lack of traditional algorithms in the identification of ginseng appearance quality and further improve the manual identification on ginseng, we propose a grading method of ginseng appearance quality based on deep learning, taking advantage of the benefits of deep learning in the image identification. Firstly, we substituted LeakyReLU for the conventional activation function ReLU to enhance the predictive power of the model. Secondly, we added an ECA module to the residual block, which allowed attention to be focused on the input object to capture more precise and detailed features. Thirdly, we used the focal loss function to solve the problem of an imbalanced dataset. Then, the self-constructed dataset was processed with data enhancement and divided into four different classes of ginseng. The dataset was trained on a model with transfer learning to finally obtain the best model applicable to the identification of ginseng appearance quality. The experiments showed that, compared with the classical convolutional neural network models VGG16, GoogLeNet, ResNet50 and Densenet121, the proposed model reported the best performance, its accuracy in the test set was as high as 97.39%, and the loss value was 0.035. This method can efficiently classify the appearance quality of ginseng, and has a significant value in the field of ginseng appearance quality identification. Full article
Show Figures

Figure 1

15 pages, 8590 KiB  
Article
Development of Weed Detection Method in Soybean Fields Utilizing Improved DeepLabv3+ Platform
by Helong Yu, Minghang Che, Han Yu and Jian Zhang
Agronomy 2022, 12(11), 2889; https://doi.org/10.3390/agronomy12112889 - 18 Nov 2022
Cited by 11 | Viewed by 1999
Abstract
Accurately identifying weeds in crop fields is key to achieving selective herbicide spraying. Weed identification is made difficult by the dense distribution of weeds and crops, which makes boundary segmentation at the overlap inaccurate, and thus pixels cannot be correctly classified. To solve [...] Read more.
Accurately identifying weeds in crop fields is key to achieving selective herbicide spraying. Weed identification is made difficult by the dense distribution of weeds and crops, which makes boundary segmentation at the overlap inaccurate, and thus pixels cannot be correctly classified. To solve this problem, this study proposes a soybean field weed recognition model based on an improved DeepLabv3+ model, which uses a Swin transformer as the feature extraction backbone to enhance the model’s utilization of global information relationships, fuses feature maps of different sizes in the decoding section to enhance the utilization of features of different dimensions, and adds a convolution block attention module (CBAM) after each feature fusion to enhance the model’s utilization of focused information in the feature maps, resulting in a new weed recognition model, Swin-DeepLab. Using this model to identify a dataset containing a large number of densely distributed weedy soybean seedlings, the average intersection ratio reached 91.53%, the accuracy improved by 2.94% compared with that before the improvement with only a 48 ms increase in recognition time, and the accuracy was superior to those of other classical semantic segmentation models. The results showed that the Swin-DeepLab network proposed in this paper can successfully solve the problems of incorrect boundary contour recognition when weeds are densely distributed with crops and incorrect classification when recognition targets overlap, providing a direction for the further application of transformers in weed recognition. Full article
Show Figures

Figure 1

12 pages, 4804 KiB  
Article
A Faster R-CNN-Based Model for the Identification of Weed Seedling
by Ye Mu, Ruilong Feng, Ruiwen Ni, Ji Li, Tianye Luo, Tonghe Liu, Xue Li, He Gong, Ying Guo, Yu Sun, Yu Bao, Shijun Li, Yingkai Wang and Tianli Hu
Agronomy 2022, 12(11), 2867; https://doi.org/10.3390/agronomy12112867 - 16 Nov 2022
Cited by 14 | Viewed by 1986
Abstract
The accurate and rapid acquisition of crop and weed information is an important prerequisite for automated weeding operations. This paper proposes the application of a network model based on Faster R-CNN for weed identification in images of cropping areas. The feature pyramid network [...] Read more.
The accurate and rapid acquisition of crop and weed information is an important prerequisite for automated weeding operations. This paper proposes the application of a network model based on Faster R-CNN for weed identification in images of cropping areas. The feature pyramid network (FPN) algorithm is integrated into the Faster R-CNN network to improve recognition accuracy. The Faster R-CNN deep learning network model is used to share convolution features, and the ResNeXt network is fused with FPN for feature extractions. Tests using >3000 images for training and >1000 images for testing demonstrate a recognition accuracy of >95%. The proposed method can effectively detect weeds in images with complex backgrounds taken in the field, thereby facilitating accurate automated weed control systems. Full article
Show Figures

Figure 1

15 pages, 3765 KiB  
Article
Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+
by Changqing Cai, Jianwen Tan, Peisen Zhang, Yuxin Ye and Jian Zhang
Agronomy 2022, 12(8), 1875; https://doi.org/10.3390/agronomy12081875 - 9 Aug 2022
Cited by 10 | Viewed by 2222
Abstract
Aiming to determine the inaccurate image segmentation of strawberries with varying maturity levels due to fruit adhesion and stacking, this study proposed a strawberry image segmentation method based on the improved DeepLabV3+ model. The technique introduced the attention mechanism into the backbone network [...] Read more.
Aiming to determine the inaccurate image segmentation of strawberries with varying maturity levels due to fruit adhesion and stacking, this study proposed a strawberry image segmentation method based on the improved DeepLabV3+ model. The technique introduced the attention mechanism into the backbone network and the atrous spatial pyramid pooling module of the DeepLabV3+ network, adjusted the weights of feature channels in the neural network propagation process through the attention mechanism to enhance the feature information of strawberry images, reduced the interference of environmental factors, and improved the accuracy of strawberry image segmentation. The experimental results showed that the proposed method can accurately segment images of strawberries with different maturities; the mean pixel accuracy and mean intersection over union of the model were 90.9% and 83.05%, respectively, and the frames per second (FPS) was 7.67. The method can effectively reduce the influence of environmental factors on strawberry image segmentation and provide an effective approach for accurate operation of strawberry picking robots. Full article
Show Figures

Figure 1

20 pages, 5528 KiB  
Article
Development of Deep Learning Methodology for Maize Seed Variety Recognition Based on Improved Swin Transformer
by Chunguang Bi, Nan Hu, Yiqiang Zou, Shuo Zhang, Suzhen Xu and Helong Yu
Agronomy 2022, 12(8), 1843; https://doi.org/10.3390/agronomy12081843 - 4 Aug 2022
Cited by 24 | Viewed by 2979
Abstract
In order to solve the problems of high subjectivity, frequent error occurrence and easy damage of traditional corn seed identification methods, this paper combines deep learning with machine vision and the utilization of the basis of the Swin Transformer to improve maize seed [...] Read more.
In order to solve the problems of high subjectivity, frequent error occurrence and easy damage of traditional corn seed identification methods, this paper combines deep learning with machine vision and the utilization of the basis of the Swin Transformer to improve maize seed recognition. The study was focused on feature attention and multi-scale feature fusion learning. Firstly, input the seed image into the network to obtain shallow features and deep features; secondly, a feature attention layer was introduced to give weights to different stages of features to strengthen and suppress; and finally, the shallow features and deep features were fused to construct multi-scale fusion features of corn seed images, and the seed images are divided into 19 varieties through a classifier. The experimental results showed that the average precision, recall and F1 values of the MFSwin Transformer model on the test set were 96.53%, 96.46%, and 96.47%, respectively, and the parameter memory is 12.83 M. Compared to other models, the MFSwin Transformer model achieved the highest classification accuracy results. Therefore, the neural network proposed in this paper can classify corn seeds accurately and efficiently, could meet the high-precision classification requirements of corn seed images, and provide a reference tool for seed identification. Full article
Show Figures

Figure 1

Review

Jump to: Editorial, Research

16 pages, 970 KiB  
Review
Current Optical Sensing Applications in Seeds Vigor Determination
by Jian Zhang, Weikai Fang, Chidong Xu, Aisheng Xiong, Michael Zhang, Randy Goebel and Guangyu Bo
Agronomy 2023, 13(4), 1167; https://doi.org/10.3390/agronomy13041167 - 20 Apr 2023
Cited by 1 | Viewed by 2041
Abstract
Advances in optical sensing technology have led to new approaches to monitoring and determining crop seed vigor. In order to improve crop performance to secure reliable yield and food supply, calibrating seed vigor, purity, germination rate, and clarity is very critical to the [...] Read more.
Advances in optical sensing technology have led to new approaches to monitoring and determining crop seed vigor. In order to improve crop performance to secure reliable yield and food supply, calibrating seed vigor, purity, germination rate, and clarity is very critical to the future of the agriculture/horticulture industry. Traditional methods of seed vigor determination are lengthy in process, labor intensive, and sometimes inaccurate, which can lead to false yield prediction and faulty decision-making. Optical sensing technology offers rapid, accurate, and non-destructive calibration methods to help the industry develop accurate decisions for seed usage and agronomic evaluation. In this review, we hope to provide a summary of current research in the optical sensing technology used in seed vigor assessments. Full article
Show Figures

Figure 1

Back to TopTop