Search

Pollination is a crucial reproductive process that underpins crop yield and quality as well as sustains other ecosystem services essential for our planet's life. Insects are the largest group of pollinators, particularly bees, handling the pollination of 71 of the 100 crops that contribute to 90% of the world's food supply. Nevertheless, both biotic and abiotic factors exert considerable influence on bee behaviour, which in turn affects the pollination process. Moreover, the alarming decline in bee populations and other essential insect pollinators presents a major challenge to natural pollination. This work focuses on Actinidia, a dioecious plant, i.e., with female and male flowers on separate plants, which introduces entropy into the pollination phase. In this plant, the number of pollinated seeds directly influences the size of Actinidia fruits (kiwi), so the success of the pollination phase is fundamental. However, natural pollination in Actinidia is mainly entomophilic, i.e., by insects. Hence, the exploration of alternative approaches becomes essential. To address this need, there has been a growing interest in robotic solutions for pollination, which include several tools to perform pollination. This research investigates the existing technologies for conducting artificial pollination procedures. It involves a comprehensive examination of various methods outlined in the literature, thoroughly analysing their strengths and weaknesses. The ultimate objective is to provide valuable insights and guidance to enhance the efficacy of artificial pollination processes [ABSTRACT FROM AUTHOR]

Sustainable and efficient agricultural production is a growing priority in modern society. Viticulture, an important agricultural and food sector, also faces this challenge. Precision Viticulture (PV) has gained prominence as it aims to foster high-quality, efficient, and environmentally sustainable practices. The Soluble Solids Content (SSC) is essential for assessing grape ripeness and quality in the winemaking process. Conventional methods for determining SSC values (expressed in °Brix) are invasive, expensive, and labour-intensive, necessitating sample preparation, making large-scale analysis impractical. In response to these limitations, this study presents an innovative approach within the field of Precision Viticulture. It focuses on the non-invasive prediction of SSC using low-cost proximal hyperspectral optical sensors. These sensors rely on spectral reflectance measurements in the range of 340–850 nm. This study was conducted in a commercial vineyard in the Demarcated Douro Region, Cima-Corgo sub-region, Portugal, over six weeks during ripening. In total, 169 grape berries from Touriga Nacional vines were analysed under three irrigation regimes (no irrigation, 30% ETc, and 60% ETc). After organising and preprocessing the data, machine learning algorithms, namely Partial Least Squares Regression (PLS), Random Forest (RF), and the Generalised Linear Model (GLM), were applied to predict SSC values. These models' performance was thoroughly evaluated using cross-validation techniques. The performance of different models was evaluated, showing significant differences according to the metrics used (R2, RMSE, and MAPE). The RF model demonstrated effectiveness and precision. A high R² value of 0.9312, coupled with low RMSE (0.9199 °Brix) and MAPE (3.88%), signifies a strong fit to the data and accurate predictive capabilities. The results of this benchmarking study on predictive models of SSC provide valuable insights into the performance of various models, aiding winegrowers and winemakers in decision making. [ABSTRACT FROM AUTHOR]

Predawn leaf water potential (Ψpd) is the main parameter to determine plant water status, and it has been broadly used to support irrigation management. However, the Scholander pressure chamber methodology is laborious, time-consuming and invasive. This study examined a low-cost hyperspectral proximal sensor to estimate the Ψpd in grapevine (Vitis vinifera L.). For this, both the Ψpd and spectral reflectance (340–850 nm) were accessed in grapevines in a commercial vineyard located in the Douro Wine Region, northeast Portugal. A machine-learning algorithm was tested and validated to assess grapevine's water status. The experiment was performed in a randomized design with 12 grapevines (cv. Touriga Nacional) per irrigation treatment: non-irrigated, 30% crop evapotranspiration (Etc), and 60% Etc. The dataset was analyzed using Principal Component Analysis (PCA), and the machine-learning regression algorithm applied was Extreme Gradient Boosting (Xgboost). Results from the validation dataset (n = 108) for the Xgboost tested exhibited a root mean square error (RMSE) of 0.23 MPa, a mean absolute error (MAPE) of 16.57% and an R² value of 0.95. These results demonstrate that the hyperspectral sensor and Xgboost algorithm show potential for predicting the Ψpd in vineyards, regardless of a plant's water status. [ABSTRACT FROM AUTHOR]

With the rising impact of climate change on agriculture, insect-borne diseases are proliferating. There is a need to monitor the appearance of new vectors to take preventive actions that allow us to reduce the use of chemical pesticides and treatment costs. Thus, agriculture requires advanced monitoring tools for early pest and disease detection. This work presents a new concept design for a scalable, interoperable and cost-effective smart trap that can digitize daily images of crop-damaging insects and send them to the cloud server. However, this procedure can consume approximately twenty megabytes of data per day, which can increase the network infrastructure costs and requires a large bandwidth. Thus, a two-stage system is also proposed to locally detect and count insects. In the first stage, a lightweight approach based on the SVM model and a visual descriptor is used to classify and detect all regions of interest (ROIs) in the images that contain the insects. Instead of the full image, only the ROIs are then sent to a second stage in the pest monitoring system, where they will be classified. This approach can reduce, by almost 99%, the amount of data sent to the cloud server. Additionally, the classifier will identify unclassified insects in each ROI, which can be sent to the cloud for further training. This approach reduces the internet bandwidth usage and helps to identify unclassified insects and new threats. In addition, the classifier can be trained with supervised data on the cloud and then sent to each smart trap. The proposed approach is a promising new method for early pest and disease detection. [ABSTRACT FROM AUTHOR]

Plant-soil sensing devices coupled with Artificial Intelligence autonomously collect and process in situ plant phenotypic data. A challenge of this approach is the limited incorporation of phenotype data into decision support systems designed to harness agricultural practices and forecast plant behavior within the intricate context of genotype, environment, and management interactions (G × E × M). To enhance the role of digital phenotyping in supporting Precision Agriculture, this paper proposes a sensing network based on the Internet of Things. The developed system comprises three modules: data collection, communication, and a cloud server. Several processes co-occur in the server, namely data visualization to confirm the correct sensors and data stream functioning. In addition, a crop growth model (CGM) runs on the server, which is powered by the collected data. The simulations generated by the model will support agricultural decisions, obtaining, in advance, insights about plant behavior considering several G × E × M scenarios. To assess the performance of the proposed network to provide reliable data to the model, a greenhouse was equipped with several sensors that collect plant, environment, and soil data (e.g., leaf numbers, air temperature, soil moisture). The proposed network can provide real-time causal support for advanced agricultural practices, evolving from a data-driven approach to an integrative framework where context (G × E × M) drives decision making. [ABSTRACT FROM AUTHOR]

Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. Traditionally, this task is carried out through manual and destructive sampling of production components and their accurate assessment is expensive, time-consuming, and error-prone, resulting in erroneous projections. The number of inflorescences and flowers per vine is one of the main components and serves as an early predictor. The adoption of new non-invasive technologies can automate this task and drive viticulture yield forecasting to higher levels of accuracy. In this study, different Single Stage Instance Segmentation models from the state-of-the-art You Only Look Once (YOLO) family, such as YOLOv5 and YOLOv8, were benchmarked on a dataset of RGB images for grapevine inflorescence detection and segmentation, with the aim of validating and subsequently implementing the solution for counting the number of inflorescences and flowers. All models obtained promising results, with the YOLOv8s and the YOLOv5s models standing out with an F1-Score of 95.1% and 97.7% for the detection and segmentation tasks, respectively. Moreover, the low inference times obtained demonstrate the models' ability to be deployed in real-time applications, allowing for non-destructive predictions in uncontrolled environments. [ABSTRACT FROM AUTHOR]