Artificial Intelligence in Agriculture最新文献

Plant-parasitic nematodes cause various diseases that can be fatal to the infected plants. It causes losses to the agricultural industry, such as crop failure and poor crop quality. Developing an accurate nematode classification system is vital for pest identification and control. Deep learning classification techniques can help speed up Nematode identification as it can perform tasks directly from images. In the present study, four state-of-the-art deep learning models (ResNet101v2, CoAtNet-0, Effi- cientNetV2B0, and EfficientNetV2M) were evaluated in plant-parasitic nematode classification from microscopic image. The models were trained using a combination of three different optimizers (Adam, SGD, dan RMSProp) and several data augmentation with image transformations, such as image flip, blurring, noise addition, brightness, and contrast adjustment. The performance of the trained models was varied. Regarding test accuracy, EfficientNetV2B0 and EfficientNetV2M using RMSProp and brightness augmentation give the best result of 97.94% However, the overall performance of EfficientNetV2M was superior, with 98.66% mean class accuracy, 97.99%F1 score, 98.26% average precision, and 97.94% average recall.

Agricultural Internet of Things (IoT) has brought new changes to agricultural production. It not only increases agricultural output but can also effectively improve the quality of agricultural products, reduce labor costs, increase farmers' income, and truly realize agricultural modernization and intelligence. This paper systematically summarizes the research status of agricultural IoT. Firstly, the current situation of agricultural IoT is illustrated and its system architecture is summarized. Then, the five key technologies of agricultural IoT are discussed in detail. Next, applications of agricultural IoT in five representative fields are introduced. Finally, the problems existing in agricultural IoT are analyzed and a forecast is given of the future development of agricultural IoT.

Rapid socio-economic changes in China, such as land conversion and urbanization, are creating new scopes for the application of precision agriculture (PA).An experiment to assess the economic benefits of two precision agriculture methods was applied for one year – precision seeding and precision seeding with land leveling. Whilst the results for this were positive, of itself it did not provide evidence of longer terms gains. The costs of land leveling are accrued in a single year but the benefits could carry over into subsequent years. Thus, in this case if the PA method provides carry over benefits to future years, the economic assessment would incorrectly assign all the costs to a single year of benefits i.e.the benefit-cost ratio would be underestimated. To gauge whether there was carry over benefits in future years we looked at NDVI and GUI as proxies for future year benefits. For the single year experiment, our results showed that: (1) Winter wheat yield was increased 23.2% through the integration of precision seeding and laser leveling technologies.(2) Both the single technology and the integrated technologies significant reduced the concentration of soil ammonium nitrogen at the depths of 60 cm; (3) The benefit/cost ratio's of the treatments exceeded that of the baseline by approximately 10% which translated to an increase of several hundred US$ per hectare. The NDVI analysis showed that the effect of laser land leveling could last to the next two years. When considering the multi-year impact of land leveling, the benefit/cost ratio of PSLL will increase to 23.5% and 22.9% with and without laser land leveling subsidies. Making clear the economic benefits of using PA technologies will likely promote application of the technologies in the region.

With the recent trends in urban agriculture and climate change, there is an emerging need for alternative plant culture techniques where dependence on soil can be eliminated. Hydroponic and aquaponic growth techniques have proven to be viable alternatives, but the lack of efficient and optimal practices for irrigation and nutrient supply limits its applications on a large-scale commercial basis. The main purpose of this research was to develop statistical methods and Machine Learning algorithms to regulate nutrient concentrations in aquaponic irrigation water based on plant needs, for achieving optimal plant growth and promoting broader adoption of aquaponic culture on a commercial scale. One of the key challenges to developing these algorithms is the sparsity of data which requires the use of Bolstered error estimation approaches. In this paper, several linear and non-linear algorithms trained on relatively small datasets using Bolstered error estimation techniques were evaluated, for selecting the best method in making decisions regarding the regulation of nutrients in hydroponic environments. After repeated tests on the dataset, it was decided that Semi-Bolstered Resubstitution Error estimation technique works best in our case using Linear Support Vector Machine as the classifier with the value of penalty parameter set to one. A set of recommended rules have been prescribed as a Decision Support System, using the output of the Machine Learning algorithm, which have been tested against the results of the baseline model. Further, the positive impact of the recommended nutrient concentrationson plant growth in aquaponic environments has been elaborately discussed.

Increased biosecurity and food safety requirements may increase demand for efficient traceability and identification systems of livestock in the supply chain. The advanced technologies of machine learning and computer vision have been applied in precision livestock management, including critical disease detection, vaccination, production management, tracking, and health monitoring. This paper offers a systematic literature review (SLR) of vision-based cattle identification. More specifically, this SLR is to identify and analyse the research related to cattle identification using Machine Learning (ML) and Deep Learning (DL). This study retrieved 731 studies from four online scholarly databases. Fifty-five articles were subsequently selected and investigated in depth. For the two main applications of cattle detection and cattle identification, all the ML based papers only solve cattle identification problems. However, both detection and identification problems were studied in the DL based papers. Based on our survey report, the most used ML models for cattle identification were support vector machine (SVM), k-nearest neighbour (KNN), and artificial neural network (ANN). Convolutional neural network (CNN), residual network (ResNet), Inception, You Only Look Once (YOLO), and Faster R-CNN were popular DL models in the selected papers. Among these papers, the most distinguishing features were the muzzle prints and coat patterns of cattle. Local binary pattern (LBP), speeded up robust features (SURF), scale-invariant feature transform (SIFT), and Inception or CNN were identified as the most used feature extraction methods. This paper details important factors to consider when choosing a technique or method. We also identified major challenges in cattle identification. There are few publicly available datasets, and the quality of those datasets are affected by the wild environment and movement while collecting data. The processing time is a critical factor for a real-time cattle identification system. Finally, a recommendation is given that more publicly available benchmark datasets will improve research progress in the future.

Physical land suitability assessment is a prerequisite for enhancing yield production and enables the agricultural communities to use the right place for the right crops. Maize is one of stable one food crops of Ethiopia and cultivated in three agroecological zones: highland, midland and lowlands. Despite these facts, maize yield is very low due to a lack of knowledge and information gaps on land suitability. Physical land suitability for maize cultivation is essential to minimize the problem of food security. The present study aims to identify the potential land suitability for maize production in the Didessa watershed, Western Ethiopia using Multi-Criteria Evaluation (MCE) and geospatial technologies. Land use land cover (LULC) change, climate, topography, soil, and infrastructure facilities were considered for maize land suitability assessment. The MCE based pairwise comparison matrix was applied to estimate land suitability for maize crop cultivation. The results showed that, about 977.7 km² (14.1%) is highly suitable, 4794.9 km²(69.1%) is moderately suitable while 1118.8 km² (16.1%), and 51.5 km² (0.7%) of the study area were categorized under marginally and not suitable for maize production, respectively. This research provides crucial information for decision making organs and the farming community to utilize potential areas for maize cultivation.

In recent times, the use of artificial intelligence (AI) in agriculture has become the most important. The technology adoption in agriculture if creatively approached. Controlling on the diseased leaves during the growing stages of crops is a crucial step. The disease detection, classification, and analysis of diseased leaves at an early stage, as well as possible solutions, are always helpful in agricultural progress. The disease detection and classification of different crops, especially tomatoes and grapes, is a major emphasis of our proposed research. The important objective is to forecast the sort of illness that would affect grapes and tomato leaves at an early stage. The Convolutional Neural Network (CNN) methods are used for detecting Multi-Crops Leaf Disease (MCLD). The features extraction of images using a deep learning-based model classified the sick and healthy leaves. The CNN based Visual Geometry Group (VGG) model is used for improved performance measures. The crops leaves images dataset is considered for training and testing the model. The performance measure parameters, i.e., accuracy, sensitivity, specificity precision, recall and F1-score were calculated and monitored. The main objective of research with the proposed model is to make on-going improvements in the performance. The designed model classifies disease-affected leaves with greater accuracy. In the experiment proposed research has achieved an accuracy of 98.40% of grapes and 95.71% of tomatoes. The proposed research directly supports increasing food production in agriculture.

The agriculture sector is no exception to the widespread usage of deep learning tools and techniques. In this paper, an automated detection method on the basis of pre-trained Convolutional Neural Network (CNN) models is proposed to identify and classify paddy crop biotic stresses from the field images. The proposed work also provides the empirical comparison among the leading CNN models with transfer learning from the ImageNet weights namely, Inception-V3, VGG-16, ResNet-50, DenseNet-121 and MobileNet-28. Brown spot, hispa, and leaf blast, three of the most common and destructive paddy crop biotic stresses that occur during the flowering and ripening growth stages are considered for the experimentation. The experimental results reveal that the ResNet-50 model achieves the highest average paddy crop stress classification accuracy of 92.61% outperforming the other considered CNN models. The study explores the feasibility of CNN models for the paddy crop stress identification as well as the applicability of automated methods to non-experts.

The use of biomass is increasing because it is a form of renewable energy that provides high heating value. Rapid measurements could be used to check the quality of biomass pellets during production. This research aims to apply a near-infrared (NIR) hyperspectral imaging system for the evaluation of the true density of individual biomass pellets during the production process. Real-time measurement of the true density could be beneficial for the operation settings, such as the ratio of the binding agent to the raw material, the temperature of operation, the production rate, and the mixing ratio. The true density could also be used for rough measurement of the bulk density, which is a necessary parameter in commercial production. Therefore, knowledge of the true density is required during production in order to maintain the pellet quality as well as operation conditions. A prediction model was developed using partial least squares (PLS) regression across different wavelengths selected using different spectral pre-treatment methods and variable selection methods. After model development, the performance of the models was compared. The best model for predicting the true density of individual pellets was developed with first-derivative spectra (D1) and variables selected by the genetic algorithm (GA) method, and the number of variables was reduced from 256 to 53 wavelengths. The model gave R²_cal, R²_val, SEC, SEP, and RPD values of 0.88, 0.89, 0.08 g/cm³, 0.07 g/cm³, and 3.04, respectively. The optimal prediction model was applied to construct distribution maps of the true density of individual biomass pellets, with the level of the predicted values displayed in colour bars. This imaging technique could be used to check visually the true density of biomass pellets during the production process for warnings to quality control equipment.

The ability to characterize rapidly and repeatedly exchangeable potassium (K_ex) content in the soil is essential for optimizing remediation of radiocaesium contamination in agriculture. In this paper, we show how this can be now achieved using a Convolutional Neural Network (CNN) model trained on a large Mid-Infrared (MIR) soil spectral library (40,000 samples with K_ex determined with 1 M NH₄OAc, pH 7), compiled by the National Soil Survey Center of the United States Department of Agriculture. Using Partial Least Squares Regression as a baseline, we found that our implemented CNN leads to a significantly higher prediction performance of K_ex when a large amount of data is available (10000), increasing the coefficient of determination from 0.64 to 0.79, and reducing the Mean Absolute Percentage Error from 135% to 31%. Furthermore, in order to provide end-users with required interpretive keys, we implemented the GradientShap algorithm to identify the spectral regions considered important by the model for predicting K_ex. Used in the context of the implemented CNN on various Soil Taxonomy Orders, it allowed (i) to relate the important spectral features to domain knowledge and (ii) to demonstrate that including all Soil Taxonomy Orders in CNN-based modeling is beneficial as spectral features learned can be reused across different, sometimes underrepresented orders.