Precision Agriculture最新文献

The monitoring of the tassel number and tasseling time reflects the maize growth and is necessary for crop management. However, it mainly depends on field observations, which is very labor intensive and may be biased by human errors. Tassel detection remains challenging due to the varying appearance of tassels across maize varieties, tasseling stages, and spatial resolutions. Moreover, the capability of the deep learning model for monitoring tassel number change and the time of entering tasseling stage has not been explored. In this study, we propose a novel approach for fast tassel detection using PConv (Partial Convolution) within YoloV8 series, named PConv-YoloV8 series. Compared to seven state-of-the-art deep learning methods, PConv-YoloV8 × 6 best trades off detection accuracy with the number of parameters (Parameters = 52.50 MB, AP = 0.950, R² = 0.92, rRMSE = 9.08%). The potential of PConv-YoloV8 × 6 to provide an accurate detection of tassels in complex situations from near-ground and UAV images were comprehensively studied. PConv-YoloV8 × 6 maintained an excellent detection accuracy for maize at different tasseling stages (AP = 0.826–0.972, R² = 0.83–0.92, RMSE = 1.94–3.01, rRMSE = 21.06%-7.09%), for different varieties (AP = 0.901–0.978, R² = 0.77–0.97, RMSE = 1.39–3.16, rRMSE = 11.72%-5.06%), at different resolutions (AP = 0.921–0.956, R² = 0.84–0.93, rRMSE = 8.72%-17.71%), and on UAV images with different resolutions (AP = 0.918–0.968, R² = 0.98–0.99, rRMSE = 6.43%-12.76%), which proved the robustness of the model. The tasseling number and the time of entering tasseling stage detected from images were basically consistent with the trends observed in the manually labeled results. This study provides an effective method to monitor the tassel number and the time of entering the tasseling stage. A new maize tassel detection dataset (18260 tassels in 729 near-ground images and 20835 tassels in 144 UAV images) is created. Future studies will focus on making more lightweight models and achieving real-time detection capabilities.

Given the high costs of soil sampling, low and extra-low sampling densities are still being used. Low-density soil sampling usually does not allow the computation of experimental variograms reliable enough to fit models and perform interpolation. In the absence of geostatistical tools, deterministic methods such as inverse distance weighting (IDW) are recommended but they are susceptible to the “bull’s eye” effect, which creates non-smooth surfaces. This study aims to develop and assess interpolation methods or approaches to produce soil test maps that are robust and maximize the information value contained in sparse soil sampling data. Eleven interpolation procedures, including traditional methods, a newly proposed methodology, and a kriging-based approach, were evaluated using grid soil samples from four fields located in Central Alberta, Canada. In addition to the original 0.4 ha⋅sample⁻¹ sampling scheme, two sampling design densities of 0.8 and 3.5 ha⋅sample⁻¹ were considered. Among the many outcomes of this study, it was found that the field average never emerged as the basis for the best approach. Also, none of the evaluated interpolation procedures appeared to be the best across all fields, soil properties, and sampling densities. In terms of robustness, the proposed kriging-based approach, in which the nugget effect estimate is set to the value of the semi-variance at the smallest sampling distance, and the sill estimate to the sample variance, and the IDW with the power parameter value of 1.0 provided the best approaches as they rarely yielded errors worse than those obtained with the field average.

This study describes a new method for satellite-based remote sensing analysis of plant-specific biomass yield patterns for precision farming applications. The relative biomass potential (rel. BMP) serves as an indicator for multiyear stable and homogeneous yield zones. The rel. BMP is derived from satellite data corresponding to specific growth stages and the normalized difference vegetation index (NDVI) to analyze crop-specific yield patterns. The development of this methodology is based on data from arable fields of two research farms; the validation was conducted on arable fields of commercial farms in southern Germany. Close relationships (up to r > 0.9) were found between the rel. BMP of different crop types and study years, indicating stable yield patterns in arable fields. The relative BMP showed moderate correlations (up to r = 0.64) with the yields determined by the combine harvester, strong correlations with the vegetation index red edge inflection point (REIP) (up to r = 0.88, determined by a tractor-mounted sensor system) and moderate correlations with the yield determined by biomass sampling (up to r = 0.57). The study investigated the relationship between the rel. BMP and key soil parameters. There was a consistently strong correlation between multiyear rel. BMP and soil organic carbon (SOC) and total nitrogen (TN) contents (r = 0.62 to 0.73), demonstrating that the methodology effectively reflects the impact of these key soil properties on crop yield. The approach is well suited for deriving yield zones, with extensive application potential in agriculture.

There is growing interest in using canopy temperature (Tc), including crop water Stress index (CWSI), for irrigation management. However, Tc varies greatly in one day, while soil water content (SWC) varies little, which may lead to different conclusions on whether irrigation is needed based on CWSI at different times. For this end, Tc of winter wheat was continuously monitored, and the data of such environmental factors as atmospheric temperature and soil water content (SWC) were simultaneously collected. CWSI was calculated based on empirical formulation and Tc and CWSI were generalized based on the normalization formulation. The correlation SWC between Tc and CWSI before and after generalization was compared and error analysis was based on SWC theoretical formula. The results showed: (1) the accuracy of SWC retrieval by Tc and CWSI increased firstly and then decreased with time during the day. The optimal time for Tc monitoring SWC was between 10:00 ~ 16:00 (R² > 0.72) and the optimal time for CWSI monitoring SWC was between 9:00 ~ 18:00 (R² > 0.69). (2) CWSI and Tc were mapped based on the relationship between crop water stress and soil water deficit and normalized canopy temperature expressions characterized the relationship between crop water stress and soil water deficit. (3) The accuracy of inversion of SWC by mapping Tc from 18:00 ~ 8:00 is increased from 0.5 ~ 0.6 to 0.7 ~ 0.8; the accuracy of soil water content inversion by mapping CWSI from 18:00 ~ 8:00 was improved from 0.2 ~ 0.4 to 0.4 ~ 0.6. (4) The theoretical expression of SWC deduced based on CWSI also proves that considering the relationship between crop water stress and soil water deficit change can effectively reduce the relative error from 30 to 5% in the morning and evening. This study contributes to the understanding of the reason why the correlation between Tc and SWC varies greatly during the day and solves the time-limited problem of thermal infrared remote sensing monitoring of crop water stress.

Fruit size is crucial for growers as it influences consumer willingness to buy and the price of the fruit. Fruit size and growth along the seasons are two parameters that can lead to more precise orchard management favoring production sustainability. In this study, a Python-based computer vision system (CVS) for sizing apples directly on the tree was developed to ease fruit sizing tasks. The system is made of a consumer-grade depth camera and was tested at two distances among 17 timings throughout the season, in a Fuji apple orchard. The CVS exploited a specifically trained YOLOv5 detection algorithm, a circle detection algorithm, and a trigonometric approach based on depth information to size the fruits. Comparisons with standard-trained YOLOv5 models and with spherical objects were carried out. The algorithm showed good fruit detection and circle detection performance, with a sizing rate of 92%. Good correlations (r > 0.8) between estimated and actual fruit size were found. The sizing performance showed an overall mean error (mE) and RMSE of + 5.7 mm (9%) and 10 mm (15%). The best results of mE were always found at 1.0 m, compared to 1.5 m. Key factors for the presented methodology were: the fruit detectors customization; the HoughCircle parameters adaptability to object size, camera distance, and color; and the issue of field natural illumination. The study also highlighted the uncertainty of human operators in the reference data collection (5–6%) and the effect of random subsampling on the statistical analysis of fruit size estimation. Despite the high error values, the CVS shows potential for fruit sizing at the orchard scale. Future research will focus on improving and testing the CVS on a large scale, as well as investigating other image analysis methods and the ability to estimate fruit growth.

Peanut is a significant oilseed crop that is often affected by peanut southern blight, a disease that greatly reduces crop yield and quality. Therefore, accurate and timely monitoring of this disease is crucial to ensure crop safety and minimize the need for pesticides. Spectral features combined with texture features have been widely applied in plant disease monitoring. However, previous studies have mostly used original texture features, and its combination form has been rarely considered. This study presents a novel approach for monitoring peanut southern blight, integrating multiple spectral indices and textural indices (TIs). Firstly, a total of 20 vegetation indices (VIs) were extracted from the unmanned aerial vehicle multispectral images, while three TIs were constructed based on original textural features. Subsequently, Otsu-CIgreen algorithm was used to find the optimal threshold to eliminate the complex background of the image. Lastly, monitoring models for peanut southern blight were constructed using three machine learning models based on the screened VIs, VIs combined with TIs. Among these models, the K-nearest neighbor model using VIs combined with TIs demonstrates the best performance, with accuracy and F1 score on the test set reaching 91.89% and 91.39% respectively. The results indicate that the monitoring models utilizing VIs and TIs were more effective compared to models using only VIs. This approach provides valuable insights for non-destructive and accurate monitoring of peanut southern blight.

Recognition of the importance of soil moisture information to the optimisation of water-limited dryland cereal production has led to Australian growers being encouraged to make use of soil moisture sensors. However, irrespective of the merits of different sensing technologies, only a small soil volume is sensed, raising questions as to the utility of such sensors in broadacre cropping, especially given spatial variability in soil water holding capacity. Here, using data collected from contrasting sites in South Australia and Western Australia over two seasons, during which either wheat or barley were grown, we describe a method for extrapolating soil moisture information away from the location of a probe using freely-available NDVI time series and weather data as covariates. Relationships between soil moisture probe data, cumulative NDVI (ΣNDVI), cumulative net precipitation (ΣNP) and seasonal growing degree days (GDD) were significant (P < 0.0001). In turn, these could be used to predict soil moisture status for any location within a field on any date following crop emergence. However, differences in ΣNDVI between different within-field zones did not fully explain differences in the soil moisture from multiple sensors located in these zones, resulting in different calibrations being required for each sensor or zone and a relatively low accuracy of prediction of measured soil moisture (R²_adj ~ 0.4–0.7) which may not be sufficient to support targeted agronomic decision-making. The results also suggest that at any location within a field, the range of variation in soil moisture status down the soil profile on any given date will present as greater than the spatial variation in soil moisture across the field on that date. Accordingly, we conclude that, in dryland cereal cropping, the major value in soil moisture sensors arises from an enhanced ability to compare seasons and to relate similarities and differences between seasons as a guide to decision-making.

The use of soil residual herbicides, along with other practices that diversify weed management strategies, have been recommended to improve weed management and deter the progression of herbicide resistance. Although soil characteristics influence recommended application rates for these herbicides, the common practice is to apply a uniform dose of soil residual herbicides across fields with variable soil characteristics. Mapping fields for soil characteristics that dictate the optimal dose of soil residual herbicides could improve the efficiency and effectiveness of these herbicides, as well as improve environmental stewardship. The objectives of this research were to develop and quantify the accuracy of management zone classifications for variable-rate residual herbicide applications using multiple soil data sources and soil sampling intensities. The maps were created from soil data that included (i) Soil Survey Geographic database (SSURGO), (ii) soil samples (SS), (iii) soil samples regressed onto soil electrical conductivity (EC) measurements (SSEC), (iv) soil samples with organic matter (OM) data from SmartFirmer® (SF) sensors (SSSF), and (v) soil samples regressed onto EC measurements plus OM data from SmartFirmer® sensor (SSECSF). A modified Monte Carlo cross validation method was used on ten commercial Indiana fields to generate 36,000 maps across all sources of spatial soil data, sampling density, and three representative herbicides (pyroxasulfone, s-metolachlor, and metribuzin). Maps developed from SSEC data were most frequently ranked with the highest management zone classification accuracy compared to maps developed from SS data. However, SS and SSEC maps concurrently had the highest management zone classification accuracy of 34% among maps developed across all fields, herbicides, and sampling intensities. One soil sample per hectare was the most reliable sampling intensity to generate herbicide application management zones compared to one soil sample for every 2 or 4 hectares. In conclusion, soil sampling with EC_a data should be used for defining the management zones for variable-rate (VR) residual herbicide applications.

Unmanned aerial vehicles (UAVs) equipped with high-resolution imaging sensors have shown great potential for plant phenotyping in agricultural research. This study aimed to explore the potential of UAV-derived red–green–blue (RGB) and multispectral imaging data for estimating classical phenotyping measures such as plant height and predicting yield and chlorophyll content (indicated by SPAD values) in a field trial of 38 faba bean (Vicia faba L.) cultivars grown at four replicates in south-eastern Norway. To predict yield and SPAD values, Support Vector Regression (SVR) and Random Forest (RF) models were utilized. Two feature selection methods, namely the Pearson correlation coefficient (PCC) and sequential forward feature selection (SFS), were applied to identify the most relevant features for prediction. The models incorporated various combinations of multispectral bands, indices, and UAV-based plant height values at four different faba bean development stages. The correlation between manual and UAV-based plant height measurements revealed a strong agreement with a correlation coefficient (R²) of 0.97. The best prediction of SPAD value was achieved at BBCH 50 (flower bud present) with an R² of 0.38 and RMSE of 1.14. For yield prediction, BBCH 60 (first flower open) was identified as the optimal stage, using spectral indices yielding an R² of 0.83 and RMSE of 0.53 tons/ha. This development stage presents an opportunity to implement targeted management practices to enhance yield. The integration of UAVs equipped with RGB and multispectral cameras, along with machine learning algorithms, proved to be an accurate approach for estimating agronomically important traits in faba bean. This methodology offers a practical solution for rapid and efficient high-throughput phenotyping in faba bean breeding programs.

The crop water stress index (CWSI) is widely used for assessing water status in vineyards, but its accuracy can be compromised by various factors. Despite its known limitations, the question remains whether it is inferior to the current practice of direct measurements of Ψ_stem of a few representative vines. This study aimed to address three key knowledge gaps: (1) determining whether Ψ_stem (measured in few vines) or CWSI (providing greater spatial representation) better represents vineyard water status; (2) identifying the optimal scale for using CWSI for precision irrigation; and (3) understanding the seasonal impact on the CWSI-Ψ_stem relationship and establishing a reliable Ψ_stem prediction model based on CWSI and meteorological parameters. The analysis, conducted at five spatial scales in a single vineyard from 2017 to 2020, demonstrated that the performance of the CWSI- Ψ_stem model improved with increasing scale and when meteorological variables were integrated. This integration helped mitigate apparent seasonal effects on the CWSI-Ψ_stem relationship. R² were 0.36 and 0.57 at the vine and the vineyard scales, respectively. These values rose to 0.51 and 0.85, respectively, with the incorporation of meteorological variables. Additionally, a CWSI-based model, enhanced by meteorological variables, outperformed current water status monitoring at both vineyard (2.5 ha) and management cell (MC) scales (0.09 ha). Despite reduced accuracy at smaller scales, water status evaluation at the management cell scale produced significantly lower Ψ_stem errors compared to whole vineyard evaluation. This is anticipated to enable more effective irrigation decision-making for small-scale management zones in vineyards implementing precision irrigation.