Precision Agriculture最新文献

The digitization of agriculture is widely discussed today. But despite proven benefits, its acceptance in agricultural practice remains low. In small-structured areas, this trend is even more pronounced. There are even known cases where farmers initially purchased and used technology, but then stopped using it due to lack of profitability or other reasons. Interestingly, despite extensive research on precision agriculture technologies (PATs), the processes of adoption and phase-out with their associated economic impacts have never been studied. This paper provides a methodological framework for evaluating the economics of PAT deployment, taking into account changes during the period of use; the framework provides decision rules for determining the appropriate time to phase out technology. Using a selected PAT, a farm model, and defined entry and exit scenarios, it was shown that farms with outdated technology and farms with retrofittable technology are at a significant economic disadvantage during implementation compared to farms already using technology suitable for site-specific fertilization or farms relying on the use of a contractor. And even in the event of a phase-out, the two disadvantaged starting conditions face significantly greater uncertainties and costs. Moreover, the decision to phase out in time is difficult, as making an informed and fact-based decision is not possible after the first year of use. Therefore, it is advisable that farmers are not only accompanied before and during phase-in, but also receive professional support during use.

Soil acidification is an issue for agriculture that requires effective management, typically in the form of lime (calcium carbonate, CaCO₃), application. Mid infrared (MIR) spectroscopy methods offer an alternative to conventional laboratory methods, that may enable cost-effective and improved measurement of soil acidity and responses to liming, including detection of small–scale heterogeneity through the profile. Properties of an acidic soil following lime application were measured using both MIR spectroscopy with Partial Least Squares Regression (MIR-PLSR) and laboratory measurements to (a) compare the ability of each method to detect lime treatment effects on acidic soil, and (b) assess effects of the different treatments on selected soil properties. Soil properties including soil pH (in H₂O and CaCl₂), Aluminium (Al, exchangeable and extractable), cation exchange capacity (CEC) and organic carbon (OC) were measured at a single field trial receiving lime treatments differing in rate, source and incorporation. Model performance of MIR-PLSR prediction of the soil properties ranged from R² = 0.582, RMSE = 2.023, RPIQ = 2.921 for Al (extractable) to R² = 0.881, RMSE = 0.192, RPIQ = 5.729 for OC. MIR-PLSR predictions for pH (in H₂O and CaCl₂) were R² = 0.739, RMSE = 0.287, RPIQ = 2.230 and R² = 0.788, RMSE = 0.311, RPIQ = 1.897 respectively, and could detect a similar treatment effect compared to laboratory measurements. Treatment effects were not detected for MIR-PLSR-predicted values of CEC and both exchangeable and extractable Al. Findings support MIR-PLSR as a method of measuring soil pH to monitor effects of liming treatments on acidic soil to help inform precision agricultural management strategies, but suggests that some nuance and important information about treatment effects of lime on CEC and Al may be lost. Improvements to prediction model performance should be made to realise the full potential of this approach.

Rice stands as the paramount food crop worldwide, catering to more than half of the global populace as staple sustenance. Accurately and non-destructively predicting rice yield on a large scale assumes paramount importance for assessing rice growth, market planning and food security monitoring. Nonetheless, the pivotal factors that influence the final yield remain inadequately understood. In this study, we evaluated the variation patterns of Normalized Difference Vegetation Index, Enhanced Vegetation Index, Ratio Vegetation Index, Red Edge Ratio Vegetation Index and Normalized Difference Red Edge during crucial growth stages of long, medium and short-grain rice cultivars (YX054, DF018 and LF203) from 2019 to 2021. We investigated the correlation between vegetation index (VI) combinations at different growth stages and rice yield for these three cultivars. To establish predictive models, we deployed multi-seasonal VIs from multi-year dataset and three regression algorithms: partial least squares regression (PLSR), random forest regression (RFR) and support vector regression (SVR). The outcomes evinced a lack of significant correlation between single-season VIs and rice yield. The PLSR algorithm was deemed optimal for YX054, while the RFR was adjudged most suitable for DF018 and LF203. Moreover, the triple-growth and quadruple-growth period VIs models evinced superior robustness compared to the penta-growth period VIs models for all three cultivars, attaining the highest R² value of 0.86 and the lowest RMSE of 88.17 kg/ha. This paper underscores the criticality of multi-seasonal VIs in bolstering the performance of rice yield prediction.

Graphical abstract

Due to the fact that the color of mango peel is similar to that of leaf, and there are many fruits on one stem, it is difficult to locate the picking point when using robots to pick fresh mango in the natural environment. A multi-task learning method named YOLOMS was proposed for mango recognition and rapid location of main stem picking points. Firstly, the backbone network of YOLOv5s was optimized and improved by using the RepVGG structure. The loss function of original YOLOv5s was improved by introducing the loss function of Focal-EIoU. The improved model could accurately identify mango and fruit stem in complex environment without decreasing reasoning speed. Secondly, the subtask of mango stem segmentation was added to the improved YOLOv5s model, and the YOLOMS multi-task model was constructed to obtain the location and semantic information of the fruit stem. Finally, the strategies of main fruit stem recognition and picking point location were put forward to realize the picking point location of the whole cluster mango. The images of mangoes on trees in natural environment were collected to test the performance of the YOLOMS model. The test results showed that the mAP and Recall of mango fruit and stem target detection by YOLOMS model were 82.42% and 85.64%, respectively, and the MIoU of stem semantic segmentation reached to 82.26%. The recognition accuracy of mangoes was 92.19%, the success rate of stem picking location was 89.84%, and the average location time was 58.4 ms. Compared with the target detection models of Yolov4, Yolov5s, Yolov7-tiny and the target segmentation models of U-net, PSPNet and DeepLab_v3+, the improved YOLOMS model had significantly better performance, which could quickly and accurately locate the picking point. This research provides technical support for mango picking robot to recognize the fruit and locate the picking point.

Finding economic optimum fertilizer rate with good accuracy is essential for optimal crop yield, efficient resource utilization, and environmental well-being. However, the prevailing incomplete understanding of input-output relationships leads to imprecise crop yield response functions, such as those for winter wheat, and potentially biased fertilizer choices. From a statistical point of view, there is uncertainity with regards to which model is most suitable to estimate the economic optimum fertilizer rate. This complexity is amplified when considering site-specific nitrogen fertilization, which factors into elements like soil attributes, topography, and crop variations within a field, as opposed to uniform application. This study undertakes a comparative analysis to evaluate biases, variance, mean squared errors and confidence intervals in Economic Optimum Nitrogen Rate (EONR) estimations across different functional forms. The goal is to uncover performance discrepancies among these forms and explore potential advantages of adopting model averaging for optimizing nitrogen use in crop cultivation. The results of simulations reveal noteworthy biases when comparing diverse yield functions with the averaged model, particularly evident in the Linear-Plateau and Mitscherlich models. Moreover, analysis of empirical data indicates that confidence intervals for the averaged model overlap with the projected ranges of all functions. This implies that the averaged model could be suitable for determining EONR and effectively address the problem of model specification without focusing on one specific functional form. The effectiveness of model averaging hinges on incorporating models that well approximate the true model. However, even if the true model is not known, the average model can provide reasonable information for determining the EONR, provided that similar model specifications are considered. This has implications for modelling of yield response for various applications and can contribute to unbiased estimations of yield response.

Canopy Chlorophyll Content (CCC) is an important physiological indicator that reflects the growth stage of trees. Accurate estimation of CCC facilitates dynamic monitoring and efficient forest management. In this study, we used high-resolution remote sensing images obtained by uncrewed aerial vehicles (UAVs) equipped with multispectral sensors (red, green, blue, near-infrared, and red-edge) to estimate CCC of lodgepole pine (Pinus elliottii). Our aim was to determine the optimal machine learning model between support vector regression (SVR) and random forest regression (RFR) for predicting CCC and to evaluate the effectiveness of multispectral bands along with 21 vegetation indices (VIs) in the estimation process. Individual tree boundaries were derived from the canopy height model (CHM) based on three-dimensional (3D) point clouds generated using structure from motion. These images, combined with continuous field measurements from January to December, provided comprehensive data for our analysis. The results showed that the SVR method outperformed the RFR method in estimating leaf chlorophyll content (LCC), with fitting R² values up to 0.692 and RMSE values up to 0.168 mg⋅g⁻¹. Overall, the study highlights the potential of UAV-based remote sensing for multitemporal forest monitoring, offering advances in precision forestry and tree breeding.

On-farm experiments are increasingly being used as their costs have decreased with technological advances in collecting, storing, and processing geospatial data. A question that has not been well addressed is what spatial experimental design is best for on-farm experiments when the goal is to estimate a spatially varying coefficients (SVC) model. The focus here is determining the optimal location of treatments to obtain a nearly D-optimal experimental design when estimating a linear plateau model. A pseudo-Bayesian approach is taken here because the field’s site-specific optimal nitrogen value is unknown. Optimal designs are generated, assuming a fixed number of replications for each treatment level. The resulting designs are more efficient than classic Latin square, strip plot, and completely randomized designs. The method consistently produces designs that have 95% efficiency or higher. Random designs had efficiencies varying from 41 to 64% with Latin squares having higher efficiencies and strip plots lower.

Abstract

Site-specific nitrogen management has been proposed as a tool to increase crop yield while decreasing nutrient losses to the environment. Many reports can be found on sensing technologies to quantify the variability within a field and the definition of management zones based on the observed variability. However, fewer studies have been dedicated to the selection of the most suitable N fertilizer management scenario: should more or less nutrients be applied in the zones with a lower crop productivity potential? To address this knowledge gap, nine Flemish maize fields were selected as potential candidates for precision fertilization based on the soil maps and historical vegetation index patterns. Within each field, two management zones were identified based on historical vegetation index patterns and electrical conductivity maps, and different fertilization strategies were tested in each zone. The field trial results in terms of yield and soil residual nitrate showed that site-specific N management outperforms the conventional practice only in the fields with temporally stable management zones. In the fields having differences in the physical soil properties (e.g. presence of stones or clay particles), affecting water availability, lower fertilization in zones with a poor soil productivity potential could be recommended. In the fields where the performance of the management zones changes from year to year mainly due to annual variation in precipitation, a risk of incorrect implementation of the precision fertilization concept was identified. Historical NDVI time series serve a good basis to delineate the temporally stable management zones.