Intelligent Agriculture Research Articles

Residual swin transformer for classifying the types of cotton pests in complex background.

Cotton pests have a major impact on cotton quality and yield during cotton production and cultivation. With the rapid development of agricultural intelligence, the accurate classification of cotton pests is a key factor in realizing the precise application of medicines by utilize unmanned aerial vehicles (UAVs), large application devices and other equipment. In this study, a cotton insect pest classification model based on improved Swin Transformer is proposed. The model introduces the residual module, skip connection, into Swin Transformer to improve the problem that pest features are easily confused in complex backgrounds leading to poor classification accuracy, and to enhance the recognition of cotton pests. In this study, 2705 leaf images of cotton insect pests (including three insect pests, cotton aphids, cotton mirids and cotton leaf mites) were collected in the field, and after image preprocessing and data augmentation operations, model training was performed. The test results proved that the accuracy of the improved model compared to the original model increased from 94.6% to 97.4%, and the prediction time for a single image was 0.00434s. The improved Swin Transformer model was compared with seven kinds of classification models (VGG11, VGG11-bn, Resnet18, MobilenetV2, VIT, Swin Transformer small, and Swin Transformer base), and the model accuracy was increased respectively by 0.5%, 4.7%, 2.2%, 2.5%, 6.3%, 7.9%, 8.0%. Therefore, this study demonstrates that the improved Swin Transformer model significantly improves the accuracy and efficiency of cotton pest detection compared with other classification models, and can be deployed on edge devices such as utilize unmanned aerial vehicles (UAVs), thus providing an important technological support and theoretical basis for cotton pest control and precision drug application.

Research on Corn Leaf and Stalk Recognition and Ranging Technology Based on LiDAR and Camera Fusion.

Corn, as one of the three major grain crops in China, plays a crucial role in ensuring national food security through its yield and quality. With the advancement of agricultural intelligence, agricultural robot technology has gained significant attention. High-precision navigation is the basis for realizing various operations of agricultural robots in corn fields and is closely related to the quality of operations. Corn leaf and stalk recognition and ranging are the prerequisites for achieving high-precision navigation and have attracted much attention. This paper proposes a corn leaf and stalk recognition and ranging algorithm based on multi-sensor fusion. First, YOLOv8 is used to identify corn leaves and stalks. Considering the large differences in leaf morphology and the large changes in field illumination that lead to discontinuous identification, an equidistant expansion polygon algorithm is proposed to post-process the leaves, thereby increasing the average recognition completeness of the leaves to 86.4%. Secondly, after eliminating redundant point clouds, the IMU data are used to calculate the confidence of the LiDAR and depth camera ranging point clouds, and point cloud fusion is performed based on this to achieve high-precision ranging of corn leaves. The average ranging error is 2.9 cm, which is lower than the measurement error of a single sensor. Finally, the stalk point cloud is processed and clustered using the FILL-DBSCAN algorithm to identify and measure the distance of the same corn stalk. The algorithm combines recognition accuracy and ranging accuracy to meet the needs of robot navigation or phenotypic measurement in corn fields, ensuring the stable and efficient operation of the robot in the corn field.

Automatic Face Detection of Farm Images Based on an Enhanced Lightweight Deep Learning Model

In the realm of precise management, artificial intelligence has garnered significant attention and adoption, particularly within the domain of smart agriculture. In modern animal husbandry, animal face detection is conducive to individual identification, expression detection and behavior analysis of animals, and this technological advancement holds immense importance in fostering the advancement of intelligent farming practices. In order to solve the challenge of face detection caused by similar appearance features (color, texture, etc.) and no obvious feature differences between the solid-color goats and sheep in the natural environment, this research introduces a novel approach for face detection by combining the capabilities of YOLOv5 and a convolutional block attention module (CBAM). First, datasets of goats and sheep with different angles, scales and densities were constructed. Second, the basic framework of YOLOv5 was used for object detection. To address the obstacle posed by the limited presence of distinguishing features on the faces of goats and sheep, this study aims to overcome the challenge of extracting informative facial characteristics. The CBAM block was introduced to construct the YOLOv5-CBAM model to improve the feature extraction ability. Finally, 2412 images were selected and divided into training set and verification set according to 8:1. The experimental results of this dataset show that the proposed YOLOv5-CBAM model yielded remarkable results with a precision rate of 0.970, a recall rate of 0.890, a mAP@0.5 score of 0.935, an frames per second (FPS) of 140.845, and a model size of 14.680[Formula: see text]MB. In comparison to other approaches such as Faster R-CNN, SSD, YOLOv3, and YOLOv5, the proposed model demonstrated superior performance in some aspects. In addition, it excelled in both lightweight design and overall effectiveness, and it is well-suited for real-time detection of animal faces in real-world farming settings, ensuring efficient identification and monitoring of animals within practical agricultural environments.

Applications of Hyperspectral Remote Sensing, GIS, and Artificial Intelligence in Agriculture

Applications of Hyperspectral Remote Sensing, GIS, and Artificial Intelligence in Agriculture

A Highly Accurate Detection Platform for Potato Seedling Canopy in Intelligent Agriculture Based on Phased Array LiDAR Technology

A Highly Accurate Detection Platform for Potato Seedling Canopy in Intelligent Agriculture Based on Phased Array LiDAR Technology

A new dataset for video-based cow behavior recognition

A new video based multi behavior dataset for cows, CBVD-5, is introduced in this paper. The dataset includes five cow behaviors: standing, lying down, foraging,rumination and drinking. The dataset comprises 107 cows from the entire barn, maintaining an 80% stocking density. Monitoring occurred over 96 h for these 20-month-old cows, considering varying light conditions and nighttime data to ensure standardization and inclusivity.The dataset consists of ranch monitoring footage collected by seven cameras, including 687 video segment samples and 206,100 image samples, covering five daily behaviors of cows. The data collection process entailed the deployment of cameras, hard drives, software, and servers for storage. Data annotation was conducted using the VIA web tool, leveraging the video expertise of pertinent professionals. The annotation coordinates and category labels of each individual cow in the image, as well as the generated configuration file, are also saved in the dataset. With this dataset,we propose a slowfast cow multi behavior recognition model based on video sequences as the baseline evaluation model. The experimental results show that the model can effectively learn corresponding category labels from the behavior type data of the dataset, with an error rate of 21.28% on the test set. In addition to cow behavior recognition, the dataset can also be used for cow target detection, and so on.The CBVD-5 dataset significantly influences dairy cow behavior recognition, advancing research, enriching data resources, standardizing datasets, enhancing dairy cow health and welfare monitoring, and fostering agricultural intelligence development. Additionally, it serves educational and training needs, supporting research and practical applications in related fields. The dataset will be made freely available to researchers world-wide.

The Implementation of “Smart” Technologies in the Agricultural Sector: A Review

The growing global population demands an increase in agricultural production and the promotion of sustainable practices. Smart agriculture, driven by advanced technologies, is crucial to achieving these goals. These technologies provide real-time information for crop monitoring, yield prediction, and essential farming functions. However, adopting intelligent farming systems poses challenges, including learning new systems and dealing with installation costs. Robust support is crucial for integrating smart farming into practices. Understanding the current state of agriculture, technology trends, and the challenges in technology acceptance is essential for a smooth transition to Agriculture 4.0. This work reports on the pivotal synergy of IoT technology with other research trends, such as weather forecasting and robotics. It also presents the applications of smart agriculture worldwide, with an emphasis on government initiatives to support farmers and promote global adoption. The aim of this work is to provide a comprehensive review of smart technologies for precision agriculture and especially of their adoption level and results on the global scale; to this end, this review examines three important areas of smart agriculture, namely field, greenhouse, and livestock monitoring.

Research on Intelligent Agriculture Based on Artificial Intelligence and Embedded Perception Algorithms

Research on Intelligent Agriculture Based on Artificial Intelligence and Embedded Perception Algorithms

Exploration of the application of artificial intelligence in modern agricultural production Take orchard management as an example

In the context of increasing global agricultural challenges, the application of artificial intelligence technology in the agricultural field is increasingly a trend, especially in the production of agricultural products, intelligent identification technology has shown the potential to significantly improve production efficiency and optimize yield and quality. By the mid-21st century, demand for food production is expected to reach 50 percent, and there will be enormous pressure to achieve this goal with traditional agricultural technologies, which could be achieved through the application of artificial intelligence. The application of artificial intelligence technology in modern agricultural production will be analyzed in detail in this paper, the guidance of future research fields will be proposed, and the existing challenges and technical problems will be identified and discussed in order to promote the deepening and wide application of intelligent agriculture. This paper specifically discusses examples of applications in orchard management, pest detection, and automated harvesting and summarizes the effectiveness and obstacles of these techniques.

Assessing the Attitude of Farmers towards Artificial Intelligence in Agriculture

Digital technology innovations, particularly in artificial intelligence (AI), have the potential to significantly benefit agriculture. Agriculture is increasingly being held accountable for ensuring food security and safety while also taking into account environmental concerns. AI in the agricultural sector has the potential to feed a continuously growing global population while also contributing to achieving the UN's Sustainable Development Goals (SDGs). This was the right time to analyse and explore the artificial intelligence in agriculture. The present study was conducted in Dindigul district of Tamil Nadu. The findings indicated that farmers had moderately favourable level of attitude towards AI in agriculture. Farmers had positive attitude towards AI in agriculture because AI-enabled systems make weather predictions, monitor agricultural sustainability, and assess farms for the presence of diseases or pests and undernourished plants using data like temperature, precipitation, wind speed, and sun radiation in conjunction with photographs taken by satellites and drones.

Smart wearable flexible sensor based on laser-induced graphene/gold nanoparticles/black phosphorus nanosheets for in situ quercetin detection

In situ detection of metabolic substances in plants is necessary for the development of smart agriculture. However, there is a mechanical mismatch between the traditional rigid sensing interfaces and the softness surface of plant leaves, which can reduce the reliability and accuracy of sensor. Stretchable and flexible sensors provide new solutions to this problem. Herein, using quercetin (Que) as a model, we developed a flexible electrochemical sensor for in situ monitoring of metabolite in plants. A light and thin laser-induced graphene (LIG) electrodes with good flexibility were obtained after polydimethylsiloxane (PDMS) transfer. Gold nanoparticles (AuNPs) and two-dimensional black phosphorus (BP) nanosheets were fabricated on the electrode to further improve the electrochemical performance. The sensor can detect Que concentrations in the range of 1–100 μM with a detection limit of 0.65 μM (S/N=3). The sensor can adapt well to the soft plant leaf surfaces, thus realizing the application of in situ and in vivo detection in the field. This innovative plant wearable biosensor is expected to be a next-generation electronic candidate for intelligent agriculture, paving the way for in-situ and in vivo detection, and facilitating the intelligentsias of modern agriculture.

One-Year-Old Precocious Chinese Mitten Crab Identification Algorithm Based on Task Alignment.

The cultivation of the Chinese mitten crab (Eriocheir sinensis) is an important component of China's aquaculture industry and also a field of concern worldwide. It focuses on the selection of high-quality, disease-free juvenile crabs. However, the early maturity rate of more than 18.2% and the mortality rate of more than 60% make it difficult to select suitable juveniles for adult culture. The juveniles exhibit subtle distinguishing features, and the methods for differentiating between sexes vary significantly; without training from professional breeders, it is challenging for laypersons to identify and select the appropriate juveniles. Therefore, we propose a task-aligned detection algorithm for identifying one-year-old precocious Chinese mitten crabs, named R-TNET. Initially, the required images were obtained by capturing key frames, and then they were annotated and preprocessed by professionals to build a training dataset. Subsequently, the ResNeXt network was selected as the backbone feature extraction network, with Convolutional Block Attention Modules (CBAMs) and a Deformable Convolution Network (DCN) embedded in its residual blocks to enhance its capability to extract complex features. Adaptive spatial feature fusion (ASFF) was then integrated into the feature fusion network to preserve the detailed features of small targets such as one-year-old precocious Chinese mitten crab juveniles. Finally, based on the detection head proposed by task-aligned one-stage object detection, the parameters of its anchor alignment metric were adjusted to detect, locate, and classify the crab juveniles. The experimental results showed that this method achieves a mean average precision (mAP) of 88.78% and an F1-score of 97.89%. This exceeded the best-performing mainstream object detection algorithm, YOLOv7, by 4.17% in mAP and 1.77% in the F1-score. Ultimately, in practical application scenarios, the algorithm effectively identified one-year-old precocious Chinese mitten crabs, providing technical support for the automated selection of high-quality crab juveniles in the cultivation process, thereby promoting the rapid development of aquaculture and agricultural intelligence in China.

An Effective Soil Analysis and Crop Yield Prediction Based on Optimised Light GBM in Smart Agriculture

ABSTRACTIn the agricultural sector, crop yield prediction plays an important role as it helps farmers make decisions about the growing season and type of crops to get better yield. The main goal in the agricultural sector is to reduce operating costs and pollution by improving crop yields and quality. This paper proposes an effective method for soil analysis and crop yield prediction for intelligent agriculture. The collected data are preprocessed using missing value interpolation and data normalisation techniques. Feature selection is performed on the preprocessed data using the Aquila‐based adaptive optimisation algorithm, which selects the best trait subset for yield prediction. An improved lightweight gradient‐boosting machine based on the Battle Royale Optimisation technique is used for classification. The performance of the proposed system is evaluated using mean absolute error, root mean square error, R‐squared, mean square error, mean square logarithmic error and mean absolute percentage error, and the proposed system achieved an accuracy of 97%. The proposed system accurately predicts crop yields, improving crop production and quality.

Research on an Adaptive Active Suspension Leveling Control Method for Special Vehicles

Adaptive active suspension systems, integral to specialized vehicles, hold significance for their stability and safety. This study introduces a novel adaptive active suspension system featuring four independently controlled wheels employing wheel-hub motors, hydraulic cylinders, pump motor power, controllers, and sensors. A rapid and, within a certain range, leveling and height adjustment control strategy is proposed for this system, utilizing the Kalman filter algorithm. Additionally, the paper examines the front-wheel Ackermann steering model and four-wheel reverse Ackermann transition model to enhance the suspension’s stability. Subsequently, experiments on leveling and height adjustment are conducted, demonstrating the system’s capability to swiftly and accurately rectify the vehicle’s deviation angle within the specified threshold. Following adjustments made by the leveling and height control algorithm, the vehicle body promptly returns to the preset level state and designated height. The leveling control system holds broad applicability in intelligent agriculture, logistics handling, off-road equipment, and other domains, presenting significant practical utility.

A review of lysimeters from the perspective of measurement performance and intelligent development in China

AbstractLysimeters are critical instruments for studying infiltration, runoff and evapotranspiration processes in the hydrological cycle and play a critical role in promoting efficient water‐saving irrigation. This paper provides a systematic review of the development process and research status of lysimeters, progressing from simple to complex designs, from single instruments to clusters, and from manual measurement to intelligent monitoring. The working principles of various types of lysimeter were first described based on Chinese lysimeter patents over the past 20 years. Second, this paper analyses the measurement performance and application scope of different lysimeters and further studies the weighting stability of various weighing lysimeters. Third, by analysing sources of measurement error, the reliability improvement methods of lysimeters are analysed from the aspects of environment control and sensor compensation. Fourth, this paper reviews typical research on the automation and informatization of lysimeters and discusses future intelligent developments and application prospects for lysimeters in complex environments. Finally, the measurement performance of different lysimeters is analysed based on experimental data sets. This paper puts forward some suggestions for developing lysimeters with high performance, high efficiency and high reliability, hoping to promote the development of intelligent agriculture.

Research on the Training and Application Methods of a Lightweight Agricultural Domain-Specific Large Language Model Supporting Mandarin Chinese and Uyghur

In the field of Natural Language Processing (NLP), the lack of support for minority languages, especially Uyghur, the scarcity of Uyghur language corpora in the agricultural domain, and the lightweight nature of large language models remain prominent issues. This study proposes a method for constructing a bilingual (Uyghur and Chinese) lightweight specialized large language model for the agricultural domain. By utilizing a mixed training approach of Uyghur and Chinese, we extracted Chinese corpus text from agricultural-themed books in PDF format using OCR (Optical Character Recognition) technology, converted the Chinese text corpus into a Uyghur corpus using a rapid translation API, and constructed a bilingual mixed vocabulary. We applied the parameterized Transformer model algorithm to train the model for the agricultural domain in both Chinese and Uyghur. Furthermore, we introduced a context detection and fail-safe mechanism for the generated text. The constructed model possesses the ability to support bilingual reasoning in Uyghur and Chinese in the agricultural domain, with higher accuracy and a smaller size that requires less hardware. It (our work) addresses issues such as the scarcity of Uyghur corpora in the agricultural domain, mixed word segmentation and word vector modeling in Uyghur for widespread agricultural languages, model lightweighting and deployment, and the fragmentation of non-relevant texts during knowledge extraction from small-scale corpora. The lightweight design of the model reduces hardware requirements, facilitating deployment in resource-constrained environments. This advancement promotes agricultural intelligence, aids in the development of specific applications and minority languages (such as agriculture and Uyghur), and contributes to rural revitalization.

Artificial intelligence: prototype of an automated irrigation system for the cultivation of roses in Cotopaxi

Implementing artificial intelligence in agriculture can improve efficiency, reduce pollution, and promote more effective agricultural production. Efficient irrigation management avoids wasting water and ensures that plants receive the right amount of water at the right time. The purpose of this research is to present an intelligent irrigation system based on neural networks and fuzzy logic, to avoid the presence of pests due to excess relative humidity in rose crops in Cotopaxi. A mixed methodology was used. The SCRUM methodology, Android Studio as an integrated development environment, a relational database management system and the Mobile-D method were used as software elements. For the prototype construction, the main hardware element that was used was the Arduino Board. The system for irrigating automated water using fuzzy logic took less time than manual irrigation. Training actions were proposed for employers and employees in the use and maintenance of the automated irrigation system, to maintain continuous improvement in the process

High-precision object detection network for automate pear picking

To address the urgent need for agricultural intelligence in the face of increasing agricultural output and a shortage of personnel, this paper proposes a high precision object detection network for automated pear picking tasks. The current object detection method using deep learning does not fully consider the redundant background information of the pear detection scene and the mutual occlusion characteristics of multiple pears, so that the detection accuracy is low and cannot meet the needs of complex automated pear picking detection tasks. The proposed, High-level deformation-perception Network with multi-object search NMS(HDMNet), is based on YOLOv8 and utilizes a high-level Semantic focused attention mechanism module to eliminate irrelevant background information and a deformation-perception feature pyramid network to improve accuracy of long-distance and small scale fruit. A multi-object search non-maximum suppression is also proposed to choose the anchor frame in a combined search method suitable for multiple pears. The experimental results show that the HDMNet parameter amount is as low as 12.9 M, the GFLOPs is 41.1, the mAP is 75.7%, the mAP50 reaches 93.6%, the mAP75 reaches 70.2%, and the FPS reaches 73.0. Compared with other SOTA object detection methods, it has the transcend of real-time detection, low parameter amount, low calculation amount, high precision, and accurate positioning.

Exploring the Chinese public's affective attitudes towards digital transformation in agriculture: A social media-based analysis.

This study utilizes natural language processing techniques and panel vector autoregression methodology, to delve into the perceived attitudes of social media users towards the digital transformation of agriculture, and to assess its impact on total agricultural output and agricultural science and technology inputs. Data related to agricultural digital transformation were collected from Sina Weibo using web crawlers. The SnowNLP model was employed to infer users' attitudes, encompassing both positive and negative aspects. Furthermore, the study delves into the specific themes capturing users' positive attitudes and explores regional variations in focus. The findings reveal a sustained increase in users' interest in agricultural digital transformation since 2013. Positive attitudes primarily center around green development, agricultural intelligence, and global cooperation and innovation. Moreover, the study establishes a significant positive impact of users' positive attitudes on both total agricultural output value and agricultural science and technology investment, highlighting the constructive influence of user support on the agricultural industry's development.

YOLOv8-CML: a lightweight target detection method for color-changing melon ripening in intelligent agriculture

Color-changing melon is an ornamental and edible fruit. Aiming at the problems of slow detection speed and high deployment cost for Color-changing melon in intelligent agriculture equipment, this study proposes a lightweight detection model YOLOv8-CML.Firstly, a lightweight Faster-Block is introduced to reduce the number of memory accesses while reducing redundant computation, and a lighter C2f structure is obtained. Then, the lightweight C2f module fusing EMA module is constructed in Backbone to collect multi-scale spatial information more efficiently and reduce the interference of complex background on the recognition effect. Next, the idea of shared parameters is utilized to redesign the detection head to simplify the model further. Finally, the α-IoU loss function is adopted better to measure the overlap between the predicted and real frames using the α hyperparameter, improving the recognition accuracy. The experimental results show that compared to the YOLOv8n model, the parametric and computational ratios of the improved YOLOv8-CML model decreased by 42.9% and 51.8%, respectively. In addition, the model size is only 3.7 MB, and the inference speed is improved by 6.9%, while mAP@0.5, accuracy, and FPS are also improved. Our proposed model provides a vital reference for deploying Color-changing melon picking robots.