Precision Agriculture最新文献

Through targeted spray applications, precision agriculture can provide not only environmental benefits but also lower production costs, improving farm competitiveness. Nevertheless, few studies have focused on the cost-effectiveness of precision agriculture sprayers in vineyards, which are among the most widespread specialty crops. Therefore, this is the first study that aims to evaluate the cost-effectiveness of variable rate technology (VRT) and unmanned aerial vehicle (UAV) sprayers compared to a conventional sprayer in a hypothetical and representative vineyard area of southern Italy. The economic analysis, based on technological parameters in the literature, enabled the identification of the minimum farm size (break-even point) for introducing precision agriculture sprayers (PAS), considering the annual cost of the pesticide treatments (equipment and pesticide costs). Our findings revealed that the UAV sprayer—if permitted by law—could be the most convenient option for farms larger than 2.27 ha, whereas the VRT sprayer should be chosen by farms over 17.02 ha. However, public subsidies, such as those provided by the Italian Recovery Plan, make adopting VRT sprayers also economically viable for areas as small as 3.03 ha. Finally, the sensitivity analysis confirmed that the purchase price and pesticide cost are the most sensitive parameters affecting the break-even points. Our findings shed light on the economic sustainability of these innovative sprayers, a key driver for their adoption by farmers and for setting future strategies for facing the current agricultural crisis.

Purpose

Creating spatial weed distribution maps as the basis for site-specific weed management (SSWM) requires determining the occurrence and densities of weeds at georeferenced grid points. To achieve a field-wide distribution map, the weed distribution between the sampling points needs to be predicted. The aim of this study was to determine the best combination of grid sampling design and spatial interpolation technique to improve prediction accuracy. Gaussian copula as alternative method was tested to overcome challenges associated with interpolating weed densities such as smoothing effects.

Methods

The quality of weed distribution maps created using combinations of different sampling grids and interpolation methods was assessed: Inverse Distance Weighting, different geostatistical approaches, and Nearest Neighbor Interpolation. For this comparison, the weed distribution and densities in four fields were assessed using three sampling grids with different resolutions and arrangements: Random vs. regular arrangement of 40 grid points, and a combination of both grid types (fine grid).

Results

The best prediction of weed distribution was achieved with the Kriging interpolation models based on weed data sampled on the fine grid. In contrast, the lowest performance was observed using the regular grid and the Nearest Neighbor Interpolation. A patchy distribution of weeds did not affect the prediction quality.

Conclusion

Using the Gaussian copula kriging did not result in a reduction of the smoothing effect, which still represents a challenge when employing spatial interpolation methods for SSWM. However, using a randomly distributed raster with a fine resolution could further optimize the precision of weed distribution maps.

Spring dead spot is a disease of bermudagrass (Cynodon dactylon L. Pers) caused by Ophiosphaerella spp., of fungi which infect the below ground structures of plants, causing damage to the turf canopy. Previous research suggests that precision management strategies based on manually identified disease within unmanned aerial vehicle (UAV) imagery using GIS software and global navigation satellite systems (GNSS)-equipped sprayers can reduce the fungicide required for spring dead spot management. However, this methodology is time consuming and impractical for golf course superintendents. This paper introduces a novel approach to spring dead spot identification utilizing a custom Python script, the Simple Ophiosphaerella Damage Detector (SODD), to identify and record locations of spring dead spot from UAV imagery using basic feature extraction techniques. Initial tests comparing the outputs from SODD to spring dead spot manually identified by researchers on four fairways, comparisons of K-means cluster maps showed similarities ranging between 71 and 88% although incidence counts were inconsistent. Precision treatment methods based on SODD were evaluated across 16 golf course fairways at three locations in Virginia organized as a randomized complete-block design with four replications and four treatment methods; spot and zonal treatments based on SODD identified incidence and density, respectively, compared against full-coverage and non-treated controls. Applications were made with a Toro Multipro5800 with GeoLink GNSS-equipped sprayer in Fall of 2021. Spot and zonal treatment strategies showed similar control to full-coverage applications (p≤0.001) while reducing the percentage of the fairways treated by 48% and 52%, respectively (p≤0.001). These results highlight the capabilities for SODD as a tool for disease map generation.

Counting soybean plants is a crucial strategy for assessing sowing quality and supporting high production. Despite its importance, the laborious nature of traditional assessment methods makes them unreliable and not scalable. Additionally, innovative image-based solutions have demonstrated limitations in detecting dense crops such as soybeans. Therefore, in this study, we developed neural network models to analyze a set of RGB and multispectral images and perform plant classification in a comprehensive dataset, which included data collected at three vegetative stages of soybean (VC, V1, and V2). Our results demonstrated high accuracy in classifying plants using either RGB (98%) or multispectral images (92%). A significant strength of this study is the ability to classify highly dense plants, without a trend for misclassification. Clearly, our findings provide stakeholders with a timely and effective approach to counting soybean plants, reducing labor and time, while increasing reliability.

Precision Agriculture relies significantly on yield data obtained from combine harvesters, which constitutes a pivotal tool for optimizing crop productivity. Despite its potential, challenges in data accuracy persist, necessitating the development of novel automated postprocessing protocols for yield data refinement. In this paper, different automatic postprocessing protocols were evaluated using remote sensing data, specifically Sentinel-2 satellite imagery. Various automatic postprocessing protocols were applied to a dataset spanning 946 hectares over a four-year period. Commercial sensors on combine harvesters acquired the yield data. The analysis included global (field-level) adjustments and local adjustments at a finer scale (40 × 40 m² level), employing interval mean ± n·(standard deviation) calculations. Three n values (1, 1.5, and 2.5) were tested, resulting in thirteen distinct postprocessing variations. Finally, a mean filter was also applied. The results demonstrated that the yield correlation with satellite data increased with the reduction of yield variability at the pixel level (10 m). The best results were obtained using n = 1 with a 3 × 3 mean filter, where Sentinel-2 pixels remained unaffected, and the average Root Mean Square Error (RMSE) during validation was 0.572 t·ha⁻¹. In addition, the geostatistical parameters (coefficient of variation, semivariance, and range within a 10 m pixel) reached optimal values. Finally, the postprocessing uncertainty was determined to be 0.200 t·ha⁻¹. These results validate the efficacy of a novel postprocessing protocol for refining yield data in rice crops. The integration of pixel-level data from combine harvesters with Sentinel-2 imagery emerges as a promising approach for optimizing crop management, offering valuable insights for the advancement of Precision Agriculture.

Accurate estimation and spatial allocation of economic optimum nitrogen (N) rates (EONR) can support sustainable crop production systems by reducing chemical compounds to be applied to the ground while preserving the optimum yield and profitability Smart Farming (SF) techniques such as historical precision agriculture (PA) machinery data, satellite multispectral imagery, and on-machine nitrogen adjustment sensors can bring together state-of-the-art precision in determining EONR. The novelty of this study is in introducing an efficient optimization framework using SF technology to enable real-time and prescription based EONR application execution. An optimization strategy called response surface modelling (RSM) was implemented to support decision making by fusing multiple sources of information while keeping the underlying computation simple and interpretable. Here, a field of winter wheat with an area of 7 ha was used to prove the proposed concept of determining EONR for each location in the field using auxiliary variables called multispectral indices (MSIs) derived from Sentinel 2. Three different image acquisition dates before the actual N application were considered to find the best time combination of MSIs along with the best MSIs to model yield. The best MSIs were filtered out through three phases of feature selection using analysis of variance (ANOVA), Lasso regression, and model reduction of RSM. For the date 2020.03.25, 14 out of 21 MSIs exhibited a significant interaction with the N applied as determined through an on-machine N sensor. For dates 2020.03.30 and 2020.04.04, the numbers of significant indices were identified as 6 and 10, respectively. Some of the MSIs were no longer significant after five days of the growth period (5-day interval between Sentinel 2 revisits). The best model demonstrated an average prediction error of 14.5%. Utilizing the model’s coefficients, the EONR was computed to be between 43 kg/ha and 75 kg/ha for the target field. By incorporating MSIs into the fitted model for a given N range, it was demonstrated that the shape of the yield-N relation (RSM) varied due to field heterogeneity. The proposed analytical approach integrates farmer engagement by participatory annual post-mortem analysis. Using the determined RSM approach, retrospective assessment compares economically optimal N input, based on observed MSIs values to each location, with the actual applied rates.

The ability to reduce sampling distance or time is crucial for growers to monitor vineyard nutrients more frequently. Extension specialists often recommend collecting large random samples, but this is frequently overlooked, leading to inaccurate fertilizer recommendations. A novel, one-location square grid area-based sampling method called “box” sampling was developed to capture the overall nutrient distribution within a block, providing guidance for growers on sample collection in vineyards for nutrient monitoring. Box sampling was compared with random and stratified sampling methods at both bloom and veraison for grapevine foliar nitrogen (N%), phosphorus (P%), potassium (K%), magnesium (Mg%), and calcium (Ca%). Box and stratified sampling locations were determined based on Synthetic Aperture Radar (SAR) from Sentinel-1 and Sentinel-2 Normalized Difference Vegetation Index (NDVI) images. SAR and NDVI images were stratified into three variability zones using the k-means + + algorithm. Representative pixels from each zone were sampled using the stratified method, while the junction of these variability zones (30mx30m sampling window) was sampled using the new box method. In 2021 and 2022, these methods were compared against nutrient population parameters in two vineyard blocks. Both methods showed marginal differences in mean, median, and standard deviation, with box sampling consistently capturing a broader range of variations. This was evidenced by the Bhattacharya coefficient, which indicates the overlap between two probability distributions (with values closer to 1 for greater overlap). The coefficient was > 0.80 for N%, P%, and Mg%, and > 0.60 for K% and Ca% at both bloom and veraison. For 14 different commercial vineyards in 2022 and 2023, box sampling accurately captured random nutrient variability for N%, P% and Mg% at both bloom and veraison. However, for K% (at veraison) and Ca% box sampling performed poorly due to high spatial variability. Box sampling reduced the sampling distance and time by 75% compared to random sampling.

Evaluated Sentinel-2, SuperDove, and Dove-R consistency for wheat field monitoring.

Hierarchical evaluation on surface reflectance, VIs, and LAI.

VI and LAI consistencies of Sentinel-2 and PlanetScope exceed surface reflectance.

Sentinel-2 and PlanetScope’s optimal synergy interval at VI or LAI is 2 days.

Nitrogen (N) is a key factor affecting corn yield. Remote sensing of spectral reflectance from plant canopies offers an efficient way to assess N status. High spatial and temporal resolution imagery from unmanned aerial vehicles (UAVs) provides additional advantages. This study aimed to (1) develop and validate a model to predict top-dressing N requirements at the V5 stage using vegetation indices (VIs), N rates, and/or leaf N content (LNC), and (2) correlate VIs with LNC and yield at V6, V11, and R1 stages. Two experiments were conducted in Goiás state, Brazil. The first tested N rates from 0 to 300 kg ha⁻¹ applied at V5, with imagery and LNC collected at V6, V11, and R1 stages. VIs such as GNDVI (R² = 0.55–0.74), GN (R² = 0.70–0.75), and TCARI (R² = 0.62–0.63) showed strong correlations with N sources and LNC. Linear, linear-plateau, and quadratic-plateau models best fit the data. The validation trial confirmed the effectiveness of these VIs in optimizing N applications without reducing yield. GNDVI presented more benefits of reducing the amount of top-dressed N regardless of the variable used (N rate or LNC). The reduction of N inputs ranged from 6.6 to 35% compared to traditional methods. Additionally, VIs such as SAVI, GSAVI, and RVI accurately predicted yield, especially at the V6 stage, where correlations were highest (R² ≥ 0.70). This approach demonstrates the potential of UAV-based VIs for optimizing N management and improving grain yield predictions.

Mechanical weeding is an important part of integrated weed management. It destroys weeds between (interrow) and in (intrarow) crop rows. Preventing crop damage requires precise detection and tracking of the plants. In this work, a detection and tracking algorithm was developed and integrated on an intrarow hoeing prototype. The algorithm was developed and validated on 12 rows of 950 cauliflower plants. Therefore, a methodology was provided to automatically generate a label based on the crop plants’ Global Navigation Satellite System (GNSS) position during data collection with a robot platform. A CenterNet architecture was adjusted for plant centre detection by comparing different encoder networks and selecting the optimal hyperparameters. The monocular camera projection error of the plant centre detections in pixel to 3D coordinates was evaluated and used in a position- and velocity-based tracking algorithm to determine the timing for intrarow hoeing knife actuation. A dataset of 53k labelled images was created. The best CenterNet model resulted in an F1 score on the test set of 0.986 for detecting cauliflower centres. The position tracking had an average variation of 1.62 cm. Velocity tracking had a standard deviation of 0.008 (mathrm {m,,s^{-1}}) with respect to the robot’s operational target velocity. Overall, the entire integration showed effective actuation of the prototype in field conditions. Only one false positive detection occurred during operation in two test rows of 135 cauliflowers.