Smart agricultural technology最新文献

Mango is a highly significant fruit crop that thrives in a variety of agro-ecologies around the world. Mangoes are rich in vitamins and minerals. However, its yield is currently severely constrained due to disease and pest infestations. Thus, in order to improve mango fruit quality and productivity, illnesses and insect pests must be detected early on. In this study, we conceived and constructed a mango leaf disease detection mechanism utilizing an ensemble convolutional neural network approach. Healthy and diseased mango leaf images were manually obtained from main producing locations in Amhara Region for Merawi fruit and vegetable research identification. To improve the datasets, several pre-processing procedures (such as image resizing, noise reduction, and image augmentation) were used. To improve classification performance and meet the study's purpose, various segmentation approaches such as k means and Mask R-CNN were applied. Furthermore, following pre-processing and segmentation, features of mango leaf images were retrieved using CNN to obtain important features. The classification model was then constructed using fully-connected layer classifiers on the retrieved features of mango leaf images. The ensemble proposed GoogLeNet and VGG16 based CNN model in the study encompasses various operations, including dataset collection, image preprocessing, noise removal, segmentation, data augmentation, feature extraction, and classification. Upon testing, the model demonstrated impressive performance with 99.87 % training classification accuracy, 99.72 % validation accuracy, and 99.21 % testing accuracy. This indicates the effectiveness of the ensemble approach in achieving high accuracy in image classification tasks.

The promotion of sustainable tourism models in mountain areas represents a critical success factor for the territory and the environment. In political and economic literature there has been much debate in the attempt to interpret the phenomenon of growth and development with the changing socio-economic environment. Today the topic remains at the center of the debate of many economic policy authorities due to the exodus phenomena occurring in internal areas. In this study, we examined how the resources of mountain areas can create income opportunities as a function of the diffusion of sustainable income. On the one hand, in mountain environments, we have natural resources that represent common goods that must be maintained precisely according to the opportunities they create for sustainable tourism where they represent its essential feature. The complexity of the economic phenomena, which on the one hand leads to an exodus from these environments, determines the need to create new management structures, that can satisfy the needs of the local community and guarantee appropriate management of natural resources. In this study, we analyzed the relationships between sustainable tourism models and natural resource management considering the case of the Ficuzza Forest and applying new digital technologies such as mobile apps that allow you to make hotel reservations, read reviews about the best restaurant in the area, and buy museum tickets to avoid the queue. Starting from the theoretical framework, and subsequently analyzing the empirical case, we highlighted the utility flows that descend from the Bosco. The resulting results have considerable relevance for the planning of mountain territories. The study highlights that the interconnection between public and private management models can guarantee the growth and development of mountain territories.

An unmanned rice seeder (URS) with WiFi based wireless communication system was developed to reduce surface seed dispersion, drudgery, human involvement, Occupational health hazards and environmental pollution. An android mobile phone with WIFI connectivity acts as wireless communication system to control the developed URS with operating range of 144.6 m which was surplus for small farms in hilly terrains of Sikkim. The factors of URS are found to be forward speed (F_s) and hopper fill level (H_L) w.r.t responses of co-efficient of variation of number of seeds per hill (C_v), Seed rate (S_r), hill spacing uniformity (U_s,), missing hill index (MI) and mean hill span (H_s). The optimum results of soil bin study are of F_s and H_L of 2.4 km.h⁻¹ and 75% w.r.t responses of C_v, S_r, MI, U_s, H_s are 0.28, 18.5 kg. ha⁻¹, 7.3%, 91.7%, and 6.4 cm. Test results showed that the seeding performance of developed seeder was similar to manual drum seeder. But, due to higher speed of operation in developed seeder showed better results in field operation. The results from the field evaluation revealed that URS has increase in field capacity of 41%, reduces labor requirement of 50% than manual rice seeder. In economic evaluation URS has reduced cost of operation (₹ ha⁻¹) of 90% and increase net benefit (₹ year⁻¹), Payback period of 61% and 91% over manual rice seeder (MRS). The operator's workload was decreased by up to 95% due to the machine's mobile operation as compared to the manual operation.

Recent advancements in artificial intelligence and big data analytics introduce new tools that can enhance the packing efficiency of sweetpotatoes (Ipomoea batatas) (SPs). In this study, we focused on the quantification of inventory as early in the packing process as possible to allow for effective storage planning, smarter inventory selection to fulfill orders, and ultimately reduce the need for refrigeration of excess packed SPs. We built and implemented two scanners to quantify phenotype distributions at different stages of the post-harvest pipeline. Testing and validation were conducted through a collaboration with an industry-partner's packing facility in North Carolina, gaining access to their packing methods, warehouse data, and resources. The first scanner imaged all SPs during the conveyance stage, immediately after they are washed but before they are sorted. The second scanner, positioned to view the top bins after harvest, scanned the top layer of bins on harvesting trucks as they entered the storage warehouse for receiving. We compared the output of our first scanner to the output of a commercial optical sorter under a controlled packing simulation, and then compared our two developed scanners against each other in an observational commercial packing operation. We evaluated millions of SPs, assessing length, width, length-to-width ratio (LW ratio), and weight. We computed a pairwise t-test for each phenotype across scanner pairs and evaluated the Cohen's d effect size to interpret our results. We observed no significant differences in the grade distributions across the scanners, except for the “Giant” weight class, which showed variation between the top bin and eliminator table scanners. In summary, both systems demonstrated promising outcomes, suggesting a potential enhancement in packing efficiency through the timely delivery of comprehensive inventory data.

Current remote sensing technologies employing Unmanned Aerial Vehicles (UAVs) for farm monitoring have shown promise in characterizing the environment through diverse sensor systems, including hyperspectral cameras, LiDAR, thermal cameras, and RGB sensors. However, these solutions often specialize in either activity recognition or crop monitoring, but not both. To address this limitation and enhance efficacy, we propose a multi-vision monitoring (MVM) framework capable of simultaneously recognizing farm activities and assessing crop health. Our approach involves computer vision techniques that transform aerial videos into sequential images to extract essential environmental features. Central to our framework are two pivotal components: the Farmer Activity Recognition (FAR) algorithm and the Crop Image Analysis (CIA). The FAR algorithm introduces a novel feature extraction method capturing motion across various maps, enabling distinct feature sets for each activity. Meanwhile, the CIA component utilizes the normalized Triangular Greenness Index (nTGI) to estimate leave chlorophyll levels, an important indicator for crop health. By unifying these components, we achieve dual functionality—activity recognition and crop health estimation—using identical input data, thereby enhancing efficiency and versatility in farm monitoring. Our framework employs a diverse range of machine learning models, demonstrating the potential of our extracted features to address the defined problem effectively in unison.

Hyperspectral images provide rich spectral/spatial data and have shown remarkable performance in precision viticulture. Standardized data-processing methods are necessary to reduce the dimensionality and to identify powerful wavelengths. Toward this goal, we evaluated and compared the performance and novel-wavelength-identification ability of five renowned machine learning models: the linear models Ridge and LASSO, a 1D + 2D convolutional neural network (1D +2D CNN) non-linear model, a gradient boosting decision tree (GBDT) using XGBoost as an ensemble model, and an explainable boosting machine (EBM) followed by support vector regression (SVR) as a hybrid model. The model evaluations were conducted using leave-one-out cross-validation (LOOCV) as we sought to clarify the best-fitted machine learning model. Our results demonstrated that Ridge, LASSO, showed better performance with relatively high accuracy but were weak as a wavelength identifier. GDBT-XGBoost showed considerable prediction power and wavelength identification. EBM-SVM emerged as the most powerful model, demonstrating exceptional stability and clear wavelength classification even for destructive measurements under varying environmental stresses across Rondo's growth stages. The combined approach of 1D + 2D CNN algorithms was advantageous to handle the dynamic shapes of spectral curve and horizontal shift of the wavelengths obtained from outdoor data acquisition, and notably, it showed the highest accuracy to predict the brix and pH of wine grapes for both indoor and outdoor sensings. But the combined effects of 1D and 2D CNN algorithms were difficult to clarify the importance of spectral features for the brix and pH prediction. The integrated machine learning models with dimensionality reduction, and proper image acquisition can increase the model's accuracy. The common absorption peaks were observed in the near-infrared region of 700 nm and 900 nm. Those wavelengths should be considered for the development of low-cost sensing platforms with fewer bands. Wavelengths over 900 nm are also important to develop outdoor sensing platforms.

Deep learning networks, more specifically convolutional neural networks, have shown a notable distinction when it comes to computer vision problems. Their versatility spans various domains, where they are applied for tasks such as classification and regression, contingent primarily on the availability of a representative dataset. This work explores the feasibility of employing this approach in the domain of agriculture, particularly within the context of olive growing. The objective is to enhance and facilitate cultivar identification techniques by using images of olive tree leaves. To achieve this, a comparative analysis involving ten distinct convolutional networks (VGG16, VGG19, ResNet50, ResNet152-V2, Inception V3, Inception ResNetV2, XCeption, MobileNet, MobileNetV2, EfficientNetB7) was conducted, all initiated with transfer learning as a common starting point. Also, the impact of adjusting network hyperparameters and structural elements was explored. For the training and evaluation of the networks, a dedicated dataset was created and made available, consisting of approximately 4200 images from the four most representative categories of the region. The findings of this study provide compelling evidence that the majority of the examined methods offer a robust foundation for cultivar identification, ensuring a high level of accuracy. Notably, the first nine methods consistently attain accuracy rates surpassing 95%, with the top three methods achieving an impressive 98% accuracy (ResNet50, EfficientNetB7). In practical terms, out of approximately 2016 images, 1976 were accurately classified. These results signify a substantial advancement in olive cultivar identification through computer vision techniques.

Effective defect detection of blueberries is important to ensuring supplies of high-quality products to the fresh market. In this study, hyperspectral reflectance imaging with machine learning was evaluated for discriminating between defective and normal blueberries. Fresh blueberries hand-harvested were scanned in the wavelength range of 400–1000 nm. An image analysis pipeline was developed to segment individual blueberries and extract mean spectra and spatial features. Defective blueberries were found to have lower near-infrared reflectance than sound samples, and spectral features produced a better separation between defective and sound samples than the spatial features in the scattering plots of their first two principal components. Nine types of machine learning models were built for classifying defective and sound samples using the spectral and spatial features separately as well as their concatenation. The regularized linear discriminant analysis (RLDA) model trained on the spectral features achieved the best overall accuracy of 95.7 %, as opposed to the best accuracy of 85.3 % based on spatial features, which was obtained by LDA. Simply concatenating spectral and spatial features did not improve over modeling using spectral or spatial features alone. A model ensemble strategy integrating the spectral features-based RLDA and the spatial features-based LDA resulted in a statistically significant improvement in the overall accuracy to 96.6 %. Model-level feature integration offers an effective means for improving the discrimination between defective and normal blueberries. Both the hyperspectral data¹ and the software programs² of this study are made publicly available.

In Bangladesh, where agriculture forms the backbone of the economy, efficient grain storage is crucial, particularly for paddy storage. Traditional methods like gunny bags and plastic containers are common, but the recent introduction of hermetic storage technologies, such as GrainPro bags and hermetic cocoons, have significantly reduced postharvest losses paddy. However, most research focuses on oxygen (O₂) and carbon dioxide (CO₂) levels in those open storage systems. This study introduces an innovative, cost-effective remote monitoring system for hermetically sealed grain storage, designed using locally sourced components, including a Digital Hygrometer, WiFi Mini IP Camera, and a Remote Controller unit. Tested over a 125-day period at Advanced Storage Lab, Bangladesh Agricultural University, the system effectively monitored the internal environment of the storage units. Key findings show that the internal temperature of the storage bags varied between 16.7°C and 29.2°C, demonstrating lesser fluctuation compared to the ambient temperature range of 16.1°C to 33.5°C. The relative humidity inside the storage units remained stable between 45 % and 54 %, in contrast to the external humidity range of 45 % to 81.2 %. Additionally, using the Steffe and Singh equation, an increase of 0.512 % in Equilibrium Moisture Content (EMC) of paddy was recorded. Notably, there was no evidence of insect or mold growth after 125 days of storage. This study's remote monitoring system not only marks a significant advancement in hermetic grain storage technology but also contributes to sustainable agricultural practices. It provides a practical, real-time solution to monitor and manage key environmental parameters, ensuring the preservation of grain quality over time.

Assessing soil moisture content (SMC) is necessary for managing water at a spatial scale. Remote sensing technologies provide a robust approach for detecting the spatial-temporal fluctuations of SMC. The aim of this study was to estimate SMC at different soil depths using very high-resolution unmanned aerial vehicle (UAV)-based multispectral (MS) images and machine learning algorithms and generate spatial maps of SMC using the best-performed machine learning (ML) algorithm. The UAV-based multispectral images of bare soil were captured at 40 m altitude with a very high spatial resolution (2.89 cm) during the rabi 2021/22 season. At the same time, the soil samples were collected from different soil depths, and the gravimetric SMC was measured. Five machine-learning algorithms (Linear Regression (LR), K-Nearest Neighbors (KNN), Random Forest (RF), Decision Tree (DT), and Support Vector Regression (SVR)) were used to train the model between SMC and MS data (MS band reflectance and vegetation indices). The soil with high SMC has low spectral reflectance and soil with low SMC shows high spectral reflectance. For the prediction of surface SMC, the linear regression (R² = 0.89; RMSE = 2.80 %) and 5 cm depth SMC, the SVR (R² = 0.64; RMSE = 3.03 %) were performed well compared to other ML algorithms. For surface SMC, blue band reflectance, and 5 cm depth SMC, the Ratio Vegetation Index (RVI) correlated well compared to others. All models failed to predict the SMC at the deeper soil depths. The spatial SMC mapping described the visual color variations in SMC within the field. Crop irrigation scheduling can be significantly improved through the insights this spatial SMC estimation approach provides, making it a valuable tool for farmers and irrigation planners.