Precision Agriculture最新文献

Accurate localization of picking points in non-structural environments is crucial for intelligent picking of ripe citrus with a harvesting robot. However, citrus pedicels are too small and resemble other background objects in color, making it challenging to detect and localize the picking point of citrus fruits. This work presents a novel approach for detecting and localizing citrus picking points using binocular vision. First, the convolutional block attention module (CBAM) attention model is integrated into the backbone network of Mask R-CNN to increase the feature extraction for citrus pedicels, and the soft-non maximum suppression (Soft-NMS) strategy is used in the region proposal network to enhance the detection performance of citrus pedicel. Second, to accurately associate the citrus fruit with the best detected pedicel, a maximum discrimination criterion is proposed by integrating the confidence score of the detected pedicel and the degree of positional connectivity between the pedicel and the fruit. Finally, to reduce matching errors and improve computational efficiency, a rapid and robust matching method based on the normalized cross-correlation was applied to search the picking point within the line segment between the left and right images. The experimental results show that the precision, recall and F1-score for pedicel detection are 95.04%, 88.11%, and 91.44%, respectively, which are improvement of 13.00%, 7.84%, and 10.30% compared to the original Mask R-CNN. The mean absolute error (MAE) for the localizing the citrus picking point is 8.63 mm and the mean relative error (MRE) is 2.76%. The MRE was significantly reduced by at least 1.2% compared to the stereo matching methods belief-propagation (BP), semi-global block matching (SGBM), and block matching (BM), respectively. This study provides an effective method for the precise detection and localization of citrus picking point for a harvesting robot.

Mapping the spatial variability of crops is critical for precision agriculture. In this sense, remote sensing is a key technology generally dependent on the result of vegetation indices (VIs). Therefore, investigating the sensitivity of VIs and their contribution toward explaining crop variability and assisting in predicting yield is one of the pathways scientific research needs to explore. In this study, we evaluated 12 VIs with different acquisition principles in four soybean-producing fields. Using these VIs proved to be interesting to increase the performance of yield prediction models using the Randon Forest algorithm. However, simply adding VIs to the model is not enough; these VIs must aggregate information on crop variability. Some VIs are calculated based on the variation of the scene under study, and these can be an interesting option to complement the information provided by more traditional VIs, such as NDVI, assisting in predictive models, even if their direct correlation with crop yield is low in some situations. We found that using VIs groups with the same acquisition principle in isolation did not allow reaching performance of models that contained more than one principle simultaneously. In this study, the CI and TC2 indices stood out. Thus, associating VIs with different acquisition principles and, consequently, capturing different responses to variability in vegetation vigor and canopy structure is more important than the number of predictor variables itself.

In the present era of agricultural digitalization, documenting on-farm operations is critical. These records contextualize other layers of data and underpin economic analysis and informed decision-making. On-farm recordkeeping is rooted in an ancient tradition and has evolved from pen and paper to digital means integrating diverse tools and methods. These tools vary widely in mode of data recording and this presents challenges in achieving complete, accurate and interoperable data. Assessing this diversity of existing recordkeeping systems is a key step toward the improvement in recordkeeping systems that enhance data quality and interoperability. Despite the importance, as of present, comprehensive studies addressing this challenge are lacking. A systematic review of existing on-farm recordkeeping systems was carried out to address their advantages and weaknesses and to analyze their features and traits, focusing on interoperability and adherence to efficient and comprehensive on-farm recordkeeping. Paper-based recordkeeping, a longstanding and reliable method, is gradually being replaced by digital platforms. Many universities and agencies have released farm management spreadsheets and interactive database forms representing the initial step toward intuitive recordkeeping. Furthermore, farm management software, web apps, and user-friendly smartphone apps are increasingly crucial for handling agricultural big data. Notably, among the surveyed software packages and apps, most of them are not free and only a few support data interoperability. The survey also indicates a scope for further development in open-source tools with automation in recordkeeping. Adopting digital on-farm recordkeeping tools can positively impact both on and off the farm, fostering data interoperability, controlled yet flexible data access, completeness, and appropriate accuracy.

Strawberry (Fragraria x ananassa) is a crop affected by various soil-borne fungal pathogens with mostly non-specific foliar symptoms and often requiring laboratory isolation for correct diagnosis. Moreover, these nonspecific foliar symptoms, appreciated by the human eye, appear after some time following infection by the pathogen. Early detection of plant diseases is one of the primary objectives in agriculture because it may contribute to identifying more tolerant cultivars in breeding programs and optimise pesticide use in agricultural production with earlier applications in emerging disease foci. New technologies, such as remote sensing and machine learning (ML) algorithms, have arisen as potential tools to improve the ability to detect and classify different crop diseases. The combined use of hyperspectral imagery and ML algorithms were investigated to detect and classify the physiological stress caused by early infections of Fusarium wilt in strawberry plants. Six ML models, namely artificial neural network, decision tree, K-nearest neighbour, support vector machine, multinomial logistic regression and Naïve Bayes were developed to estimate physiological stress associated with Fusarium wilt disease. The results showed that stomatal conductance (g_s) and photosynthesis (A) declined even without visual symptoms of the disease. Among the six ML models evaluated, the artificial neural network model showed the highest classification performance with an overall accuracy of 81%, regardless of the physiological parameter utilized for model training. Moreover, the artificial neural network accurately predicted the absolute values of both physiological parameters (g_s and A) based on the complete spectral signature from visually healthy foliar tissue, achieving coefficients of determination of 84% and 81%, respectively. Consequently, ML models utilizing physiological response data and hyperspectral imaging exhibited remarkable robustness, facilitating the estimation of Fusarium wilt severity in strawberry plants even without visual symptoms.

Purpose

This study examines the willingness of Spanish and Lithuanian grain farmers to adopt a combined approach of preventive site-specific spraying (PSSS) and selective harvesting (SH), two precision agricultural technologies (below referred to as PSSS-SH) aimed at mitigating the risk of mycotoxin contamination in barley and wheat.

Methods

Data were collected from 190 commercial grain farmers using a choice experimental survey. The empirical analysis relied on the estimation of mixed logit and integrated latent class models.

Results

The surveyed farmers were heterogeneous in their preference for the PSSS-SH technology, with a majority (81%) reporting that they were willing to adopt and pay for the PSSS-SH technology. Furthermore, the farmers’ willingness to adopt PSSS-SH technology was influenced by the trade-offs between the potential production, economic and environmental changes.

Conclusion

Profit maximization is not the only motivation for a farmer’s decision to adopt PSSS-SH, there are also important non-financial benefits that align with the observed choices. Furthermore, the perceived usefulness of the technology, the willingness and readiness to use the technology, and the farmer characteristics (e.g. cooperative membership, employment status, share of household income from grain production and past experience with precision farming technology) were positively associated with uptake of the PSSS-SH technology. Therefore, extension programmes should have a special focus on the perceived usefulness of the technology, the willingness and readiness of farmers to use it, and its unique characteristics.

Automated technologies in precision agriculture enable unmanned systems to precisely target areas with chemicals through controlled nozzle movements. Quantitative assessment of these sprayers can enhance spraying strategies, catering to different canopy sizes, row spacing and coverage objectives. This research assessed an unmanned sprayer equipped with pan-tilt nozzles for targeted area control and spray coverage adjustment. The spray cloud path on the canopy, as the nozzles moved vertically and the sprayer advanced, was simulated mathematically. A model was developed to determine the swing angle based on orchard/vineyard geometrical parameters. This model was then applied in field tests in a vineyard and an apple orchard. Various nozzle-heading angles, driving speeds, and flow rates were experimented with, using average coverage and droplet density as the evaluation criterion. The findings showed that the developed model offered an effective method for determining the swing angles. Lowering driving speeds and increasing flow rates were found to notably enhance coverage. A 45º nozzle-heading angle proved more effective in vineyards, whereas a 90º angle yielded better results in apple orchards, reflecting the variations in canopy size and row spacing. The unmanned sprayer demonstrated great potential for autonomous spraying in vineyards and orchards.

Purpose and Methods

Crop identification using remotely sensed imagery provides useful information to make management decisions about land use and crop health. This research used phonecams to acquire the Normalized Difference Vegetation Index (NDVI) of various crops for three crop seasons. NDVI time series from Sentinel (L121-L192) images was also acquired using Google Earth Engine (GEE) for the same period. The resolution of satellite data is low therefore gap filling and smoothening filters were applied to the time series data. The comparison of data from satellite images and phenocam provides useful insight into crop phenology. The results show that NDVI is generally underestimated when compared to phenocam data. The Savitzky-Golay (SG) and some other gap filling and smoothening methods are applied to NDVI time series based on satellite images. The smoothened NDVI curves are statistically compared with daily NDVI series based on phenocam images as a reference.

Results

The SG method has performed better than other methods like moving average. Furthermore, polynomial order has been found to be the most sensitive parameter in applying SG filter in GEE. Sentinel (L121-L192) image was used to identify wheat during the year 2022–2023 in Sargodha district where experimental fields were located. The Random Forest Machine Leaning algorithm was used in GEE as a classifier.

Conclusion

The classification accuracy has been found 97% using this algorithm which suggests its usefulness in applying to other areas with similar agro-climatic characteristics.

Crop establishment is one of the major rice production operations that strongly affects rice production, productivity, and environmental impacts. This research introduced a new technology and provided scientific evidence for the benefits of mechanized wet direct seeding (mDSR) of rice as compared with the other crop establishment practices commonly applied by farmers for wet direct seeded rice in Mekong River Delta in Vietnam, such as seeding in line using drum-seeder (dDSR) and broadcast seeding (bDSR). The experiment was implemented across two consecutive rice cropping seasons that are Winter-Spring season and Summer-Autumn season in 2020–2021. Treatments included (1–3) mDSR with seeding rates of 30, 50, and 70 kg ha^− 1, (4) dDSR with 80 kg ha^− 1 seed rate, and (5) bDSR as current farmer practice with seeding rate of 180 kg ha^− 1. The fertilizer application was adjusted as per seeding rate with 80:40:30 kg ha^− 1 N: P₂O₅: K₂O with lower seed rate 30 and 50 kg ha^− 1 in mDSR; 90:40:30 kg ha^− 1 N: P₂O₅: K₂O with medium seed rate of 70 to 80 kg ha^− 1; and 115:55:40 kg ha^− 1 N: P₂O₅: K₂O with high seed rate of 180 kg ha^− 1 in bDSR. Mechanized wet direct seeding rice with a lower seed rate of 30 to 70 kg ha^− 1 and fertilizer rate by 22–30% reduced variation in seedling density by 40–80% and in yield by 0.1 to 0.3 t ha^− 1 and had similar yield to bDSR. In consequence, N productivity was 27 and 32% higher in mDSR as compared to bDSR during the Winter-Spring season and Summer-Autumn seasons, respectively. The use of lower seed rate and fertilizer in mDSR also led to higher income and lower carbon footprint (GHGe per kg of paddy grains) of rice production than the currently used practices of bDSR. Net income of mDSR was comparable to that of dDSR and higher by 145–220 and 171–248 $US than that of bDSR in Winter-Spring season and Summer-Autumn, respectively. The carbon footprint of mDSR rice production compared to bDSR was lower by 22–25% and 12–20% during the Winter-Spring and Summer-Autumn seasons, respectively. Given the above benefits of farming efficiency, higher income, and low emission, mDSR would be a technology package that strongly supports sustainable rice cultivation transformation for the Mekong River Delta of Vietnam.

This study assesses the potential of using multispectral images collected by an unmanned aerial system (UAS) on machine learning (ML) frameworks to estimate cereal rye (Secale cereal L.) biomass. Multispectral images and ground-truth cereal rye biomass data were collected from 15 farmers’ fields up to three times between March and May in northwest Ohio. Images were processed to derive 13 vegetation indices (VIs). Out of 13 VIs, six optimal sets of VIs, including excess green (ExG), normalized green red difference index (NGRDI), soil adjusted vegetation index (SAVI), blue green ratio (B_G_ratio), red-edge triangular vegetation index (RTVI), and normalized difference red-edge (NDRE) were selected using the variance inflation factor (VIF) based feature selection approach. Six regression models including a multiple linear regression (MLR), elastic net (ENET), multivariate adaptive regression splines (MARS), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGB) were investigated for estimation of cereal rye biomass based on the VIs. For most of the models, the six selected VIs performed better than or similar to the full set of 13 VIs with R² ranging from 0.24 to 0.59 and RMSE ranging from 83.13 to 91.89 g/m² during 10-fold cross-validation. During independent accuracy assessment with the selected set of VIs, XGB exhibited the highest R² (0.67) and lowest RMSE (83.13 g/m²) and MAE (48.13 g/m²) followed by RF and ENET. For all the models, the agreement between observed and predicted biomass was high for biomass less than or equal to 200 g/m² but decreased for biomass greater than 200 g/m². When field-collected structural features were integrated with the selected VIs, the models showed improved performance, with R² and RMSE of the models reaching up to 0.82 and 61.67 g/m² respectively. Among the six VIs, SAVI showed the strongest impact on the model prediction for the best-performing RF and XGB regression models. The findings of this study demonstrate the potential of precisely estimating and mapping cereal rye biomass based on UAS-captured multispectral images. Timely information on cover crop growth can facilitate numerous decision-making processes, including planning the planting operations, and management of nutrients, weeds, and soil moisture to improve agronomic and environmental outcomes.

Purpose

A generalised approach to downscale areal observations of crop production data is illustrated using cotton yield and fibre quality (length and micronaire) data which is measured as a module (areal/block) average.

Methods

Two features of the downscaling algorithm are; (i) to estimate spatial trends in yield and quality using regression with fine resolution predictors such as remote sensing imagery, and (ii) use area-to-point kriging (A2PK) to downscale either the observations in the absence of a useful spatial trend model or the residuals from the trend model (if useful) from areal averages.

Results

Correlations with remote sensing covariates were stronger for cotton fibre yield than for cotton fibre micronaire, and much stronger compared to those for cotton fibre length. Spatial trends in cotton fibre yield and micronaire could be estimated with good model quality using regression with remote sensing covariates with or without A2PK in almost all fields. Conversely, model quality was poorer for cotton fibre length and there was only a small difference in model performance between the null and trend models. When the downscaling approach was tested using fine-resolution yield observations, model performance was poorer at a fine-resolution compared to the module-resolution, which was to be expected.

Conclusion

This approach enables the creation of high-resolution raster maps of variables of interest with a much finer spatial resolution compared to the areal observations, and can be applied for any areal averaged crop production data in a range of broadacre and horticultural industries (e.g. sugarcane, apples, citrus). The finer spatial resolution may allow growers or agronomists to better understand the drivers of variability within fields, assess management implications, and create management plans at a higher resolution.