Smart agricultural technology最新文献

Mastitis is a significant disease on dairy farms and can have serious negative animal performance and economic consequences if not controlled. While clinical mastitis is often easily identified due to visibly abnormal milk, subclinical mastitis presents a more insidious challenge. Somatic cell count (SCC) is commonly used to monitor and detect subclinical mastitis, however, SCC is not available at a high sampling frequency rate at the cow level on most farms due to the manual effort involved in collecting it. With the rise of precision dairy farming technologies such as milk meters, however, there is increasing interest in using data-driven approaches (especially approaches using machine learning) for detecting subclinical mastitis based on indicators more easily collected by modern sensors. In this article we introduce milk flow profiles, a new, easy-to-collect data type that can replace more difficult-to-collect data sources (e.g., those that require laboratory tests or manual measurements) in precision dairy farming. The results of our experiments demonstrate that milk flow profiles, combined with other easily accessible milking machine data, can be employed to train machine learning models that accurately detect subclinical mastitis (as evidenced by high SCC measurements), with an AUC of 0.793. Moreover, these models perform better than models trained using features from milk characteristic data that are expensive to collect and are only collected at low frequency on commercial farms. Our experiments used data from 16 weeks of milking events from 285 cows on Irish farms, and their results demonstrate the value of milk flow profiles as an easily accessible and valuable data source for precision dairy farming applications.

Technological advancements have revolutionized livestock farming, notably in health monitoring. Traditional methods, which have been criticized for subjectivity and treatment delays, can be replaced with efficient health monitoring systems, thereby reducing costs and workload. Implementing cow behavior recognition allows for effective dairy cow health monitoring. In this research, we propose an integrated system using inertial measurement unit (IMU) devices and machine learning techniques for dairy cow behavior recognition. Six main dairy cow behaviors were studied: lying, standing, walking, drinking, feeding, and ruminating. All behavior types were manually labeled into the IMU data by reviewing the recorded footage. The labeled IMU data underwent four processing steps: selecting different window sizes, feature extraction, feature selection, and normalization. These processed data were then used to build the behavior recognition model. Various model structures, including SVM, Random Forest, and XGBoost, were tested. The top-performing model, XGBoost, with its proposed 58 features achieved an F1-score of 0.87, with specific scores of 0.93 for lying, 0.85 for walking, 0.94 for ruminating, 0.89 for feeding, 0.86 for standing, 0.93 for drinking, and 0.59 for other activities. During our online testing, we observed similar patterns for each healthy cow. The cumulative time spent on each behavior also matched the statistics from previous surveys. Additionally, our backend optimization approach resulted in a final overall percentage error of 1.55 % per day during online testing. In conclusion, our study presents an IMU-based system capable of accurately recognizing dairy cow behavior. Feature design and appropriate models are proposed herein. A functional optimization method was introduced indicating that our system has the potential with applications for estrus detection and other reproductive management practices in the dairy industry.

Observing poultry activity is crucial for assessing their health status; however, the inspection process is often time-consuming and labor-intensive, particularly in cases involving large numbers of chickens. Inexperienced breeders may also misjudge their activity levels, potentially missing opportunities for prevention and treatment. This study integrates traditional video surveillance with an advanced monitoring system to identify various broiler behaviors in a breeding environment. A two-stage deep learning approach is employed: in the first stage, the broilers are detected, and in the second stage, five key body points (head, abdomen, two legs, and tail) are identified. A skeleton-based model is then developed centered around the abdomen, with six angles calculated using trigonometric methods. These angles are analyzed by a long short-term memory network to estimate behaviors such as “Standing”, “Walking”, “Resting”, “Eating”, “Preening”, and “Flapping”, selecting the behavior with the highest probability. Dual-layer fuzzy logic inference systems were used to evaluate the proportion of time broilers spent in static versus dynamic states, providing a robust determination of their activity levels. Validated in a mixed-sex breeding environment, the proposed system achieved accuracies of at least 85.2% for identifying broiler type, 79.2% for identifying body parts, and 50.8% for identifying behaviors. The activity level evaluation results were consistent with those conducted by experienced poultry experts.

The implementation of a machine-vision system for real-time precision weed management is a crucial step towards the development of smart spraying robotic vehicles. The intelligent machine-vision system, constructed using deep learning object detection models, has the potential to accurately detect weeds and crops from images. Both data-centric and model-centric approaches of deep learning model development offer advantages depending on environment and non-environment factors. To assess the performance of weed detection in real-field conditions for eight crop species, the Yolov8, Yolov9, and customized Yolov9 deep learning models were trained and evaluated using RGB images from four locations (Casselton, Fargo, and Carrington) over a two-year period in the Great Plains region of the U.S. The experiment encompassed eight crop species—dry bean, canola, corn, field pea, flax, lentil, soybean, and sugar beet—and five weed species—horseweed, kochia, redroot pigweed, common ragweed, and water hemp. Six Yolov8 and eight Yolov9 model variants were trained using annotated weed and crop images gathered from four different sites including combined dataset from four sites. The Yolov8 and Yolov9 models’ performance in weed detection were assessed based on mean average precision (mAP50) metrics for five datasets, eight crop species, and five weed species. The results of the weed and crop detection evaluation showed high mAP50 values of 86.2 %. The mAP50 values for individual weed and crop species detection ranged from 80.8 % to 98 %. The results demonstrated that the performance of the model varied by model type (model-centric), location due to environment (data-centric), data size (data-centric), data quality (data-centric), and object size in the image (data-centric). Nevertheless, the Yolov9 customized lightweight model has the potential to play a significant role in building a real time machine-vision-based precision weed management system.

This paper presents the development of a robotic sprayer that combines artificial intelligence with robotics for optimal spray application on citrus nursery plants grown in an indoor environment. The robotic platform is integrated with an embedded firmware of MobileNetV2 model to identify and classify the plant samples with a classification accuracy of 100 % which is used to dispense variable rate spraying of pesticide based on the health status of the plant foliage. The disease detection model was developed through the edge impulse platform and deployed on Raspberry Pi 4. The robot navigates through an array of plants, stops beside each plant, and captures an image of the citrus plants. It feeds the image into the deployed embedded model to generate a disease inference that informs the variable rate application of spray during real-time actuation. To test the spraying performance of the prototype within the growing environment, water sensitive cards were placed in each plant's canopy. After spraying, the samples of water sensitive cards were collected and quantified using a smart spray app to determine the classification accuracy as well as the extent of spray coverage on the citrus samples. The robot spray coverage results show an average spray coverage of 87 % on lemon foliage when compared with 67 % for navel orange, during the spray performance test of the robot.

Hyperspectral measurements can help with rapid decision-making and collecting data across multiple locations. However, there are multiple data processing methods (Savisky-Golay [SG], first derivative [FD], and normalization) and analyses (partial least squares regression [PLS], weighted k-nearest neighbor [KKNN], support vector machine [SVM], and random forest [RF]) that can be used to determine the best relationship between physical measurements and hyperspectral data. In the current study, FD was the best method for data processing and SVM was the best model for predicting average cotton (Gossypium spp. Malvaceae) height and nodes. However, the combination of FD and RF were best at predicting cotton leaf area index, canopy cover, and chlorophyll content across the growing season. Additionally, results from models developed by both SVM and RF were closely related to pseudo-CHIME satellite wavebands, where in-situ hyperspectral data were matched to the spectral resolutions of a future hyperspectral satellite. The information and results presented will aid producers and other members of the cotton industry to make rapid and meaningful decisions that could result in greater yield and sustainable intensification.

Optimizing cannabis crop yield and quality necessitates accurate, automated leaf disease classi-fication systems for timely detection and intervention. Existing automated solutions, however, are insufficiently tailored to the specific challenges of cannabis disease identification, struggling with robustness across varied environmental conditions and plant growth stages. This paper introduces a novel Hybrid Adaptive Multi-Intelligence System for Deep Learning Ensembles (HyAMIS-DLE), utilizing a comprehensive dataset reflective of the diversity in cannabis leaf diseases and their progression. Our approach combines non-population-based decision fusion in image prepro-cessing with population-based decision fusion in classification, employing multiple CNN archi-tectures. This integration facilitates a significant improvement in performance metrics: Hy-AMIS-DLE achieves an accuracy of 99.58 %, outperforming conventional models by up to 4.16 %, and exhibits superior robustness and an enhanced Area Under the Curve (AUC) score, effectively distinguishing between healthy and diseased leaves. The successful deployment of HyAMIS-DLE within our Automated Cannabis Leaf Disease Classification System (A-CLDC-S) demonstrates its practical value, contributing to increased crop yields, reduced losses, and the promotion of sus-tainable agricultural practices.

Agriculture sustains the livelihoods of a significant portion of India's rural population, yet challenges persist in manual practices and disease management. To address these issues, this paper presents an automated plant leaf damage detection and disease identification system leveraging advanced deep learning techniques. The proposed method consists of six stages: first, utilizing YOLOv8 for region of interest identification from drone images; second, employing DeepLabV3+ for background removal and facilitating disease classification; third, implementing a CNN model for accurate disease classification achieving high training and validation accuracies (96.97 % and 92.89 %, respectively); fourth, utilizing UNet semantic segmentation for precise damage detection at a pixel level with an evaluation accuracy of 99 %; fifth, evaluating disease severity; and sixth, suggesting tailored remedies based on disease type and damage state. Experimental analysis using the Plant Village dataset demonstrates the effectiveness of the proposed method in detecting various defects in plants such as apple, tomato, and corn. This automated approach holds promise for enhancing agricultural productivity and disease management in India and beyond.

Ensuring food security, fostering agricultural sustainability, and driving economic development. However, existing prediction models often overlook the unique characteristics of paddy productivity distribution, which varies between areas, skewed, and bounded within a certain minimum and maximum range, following a four-parameter beta distribution. Consequently, these models yield less accurate and potentially misleading predictions. Additionally, most approaches fail to capture the complex interrelationships among variables that often occur when we incorporate satellite data alongside survey data that has been recognized as a key approach for improving prediction accuracy and optimizing farming practices. To address these shortcomings, this study introduces a four-parameter beta Generalized Linear Mixed Model (GLMM) augmented within a four-parameter beta Generalized Mixed Effect Tree (GMET). The four-parameter beta GMET, an extension of the four-parameter beta GLMM model integrated with a regression tree, offers enhanced flexibility in modeling complex relationships. Application of this methodology to an empirical study in Central Kalimantan and Karawang reveals notable improvements over previous methods, as evidenced by substantially lower AIC and RRMSE values. Notably, the analysis identifies lagged values of band 4, band 8, and NDVI from Sentinel-2A satellite data as significant predictors of paddy productivity, overriding the importance of farmer survey variables. This underscores the potential of satellite data to be utilized in paddy productivity predictions, offering a more efficient and cost-effective alternative to farmer survey-based methods. By enhancing satellite technology, future efforts in paddy productivity prediction can achieve higher efficiency and accuracy, contributing to informed decision-making in agricultural management.

Rice blast (RB) and Brown spot (BS) are economically important diseases in rice that cause greater yield losses annually. Both share the same host and produce quite similar lesions, which leads to confusion in identification by farmers. Proper identification is essential for better management of the diseases. Visual identification needs trained experts and the laboratory-based experiments using molecular techniques are costly and time-consuming even though they are accurate. This study investigated the differentiation of the lesions from these two diseases based on proximally sensed digital RGB images and derived colour indices. Digital images of lesions were acquired using a smartphone camera. Thirty-six colour indices were evaluated by k-means clustering to distinguish the diseases using three colour channel components; RGB, HSV, and La*b*. Briefly, the background of the images was masked to target the leaf spot lesion, and colour indices were derived as features from the centre region across the lesion, coinciding with the common identification practice of plant pathologists. The results revealed that 36 indices delineated both diseases with 84.3 % accuracy. However, it was also found that the accuracy was mostly governed by indices associated with the R, G and B profiles, excluding the others. G/R, NGRDI, (R + G + B)/R, VARI, (G + B)/R, R/G, Nor_r, G-R, Mean_A, and Logsig indices were identified to contribute more in distinguishing the diseases. Therefore, these RGB-based colour indices can be used to distinguish blast and brown spot diseases using the k-means algorithm. The results from this study present an alternative, and non-destructive, objective method for identifying RB and BS disease symptoms. Based on the findings, a mobile application, Blast O spot is developed to differentiate the diseases in fields.