Precision Agriculture最新文献

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.

Purpose

This research aims to develop a meta-machine learning model to optimize soil and nitrogen management for durum wheat in Italy. It addresses the challenges of increased food production on limited land amidst rising input costs, geopolitical changes, and climate change. The goal is to aid decision-makers in achieving maximum crop yield and income margins through effective agronomic strategies.

Methods

The study developed a meta-machine learning model, integrating classification and regression models, and tested it at four sites in Marche and Basilicata, Italy, over several years. The model incorporated data from remote sensing, crop phenology, soil chemical properties, weather data, soil management, and nitrogen levels. A Random Forest model was used to classify crop phenology, while a Neural Network model predicted yield. Eleven nitrogen levels were compared across these sites.

Results

The Random Forest model achieved an accuracy of 0.98, kappa of 0.96, and recall of 0.98 for predicting crop phenology. The Neural Network model for yield prediction had an R squared of 0.90 and a Root Mean Square Error of 0.59 t ha-1. Key factors identified for model accuracy were temperature, precipitation, NDVI, and nitrogen input. Simulations of 30 soil management and fertilization combinations revealed that no-tillage management increased grain yield. The Marginal Fertilizer Yield Index determined optimal nitrogen application.

Conclusions

The meta-machine learning model accurately predicted durum wheat yield and identified effective agronomic strategies, demonstrating the potential for broader application in field conditions. The model offers a promising approach to sustainable agriculture and climate change mitigation by utilising publicly available spatial datasets.

Graphical abstract

Plant disease forecasting models, driven by concurrent data and advanced technologies, are reliable tools for accurate prediction of disease outbreaks in achieving sustainable and productive agricultural systems. Optimal integration of Internet of Things (IoTs), machine learning (ML) techniques and artificial intelligence (AI), further augment the capabilities of these models in empowering farmers with proactive disease control measures towards modern agriculture manifested by efficient resource management, reduced diseases and higher crop yields. This article summarizes the role of disease forecasting models in crop management, emphasizing the advancements and applications of AI and ML in disease prediction, challenges and future directions in the field via (a) The technological foundations and need for validation testing of models, (b) The advancements in disease forecasting with the importance of high-quality publicly available data and (c) The challenges and future directions for the development of transparent and interpretable open-source AI models. Further improvement of these models needs investment in continuous innovative research with collaboration and data sharing among agricultural stakeholders.

Precision Agriculture Technologies (PATs) are providing a great potential in alleviating adverse impacts arising from climate change. This study evaluates the decision-making process of farmers regarding the adoption and implementation of PATs in potato agricultural cooperative in Northern Greece. For this purpose, a bio-economic model utilizing mathematical programming techniques was designed and applied to three different farms producing Protected Geographical Indication (PGI) potato of Kato Nevrokopi. The proposed model aims to incorporate the existing management methods of farming systems and their associated characteristics. Its objective is to analyse the aspirations of farmers to adopt new practices, considering agronomic, environmental, and policy limitations. Special focus was paid to two distinct scenarios: (a) subsiding PATs adopters or (b) penalizing the non-adopters. Results indicated that subsidy provision 594–650€/ha would have a greater impact on PATs profitability. Lastly, based on the results, further explanations of incentives towards promoting the adoption of novel practices, ensuring the long-term viability of agricultural systems, are proposed.

Purpose

Understanding spatial and temporal variability of absolute and relative profit within fields provides a basis for site-specific management of limited agricultural inputs such as water. The objectives of this study were to evaluate the pattern of spatial and temporal variation of cotton profitability and to assess the stability of profit in management zones (MZs) created based on soil properties and topography.

Methods

This study analyzed profitability patterns in eight commercially managed fields in the Southern High Plains from 2000 to 2003. Each field was divided into 30 m grids and soil physical properties, topography, and lint yield were collected for each grid. Based on the input cost and output prices, profit was also calculated for each grid. Clusters or MZs based on soil and topographic properties were created for each field using the partitioning around medoids (PAM) clustering algorithm. ANOVA and Least Significant Difference tests were conducted to determine the difference in profit among the clusters over multiple years.

Results

In four of the eight fields, the spatial pattern of profit was consistent across multiple years, indicating the potential of using MZs for site-specific input management. For the rest of the fields, the profit pattern in clusters was inconsistent across multiple years, indicating the need for within-season dynamic MZs.

Conclusion

The variability in soil and topographic properties influenced the profitability of management zones within a field across multiple years. Hence, this study indicates that understanding the variability in profit patterns in management zones can help to determine the best strategy for field-specific and year-specific precision input management. 

Precision agriculture technologies (PATs) are believed to be able to ensure the sustainability of rice production. However, the adoption of PATs in developing countries is much lower than in developed countries. The basic question of our research is how Indonesian rice farmers are ready to adopt precision agriculture since they are smallholder farmers. Data was collected from 521 rice farmers in five Indonesian provinces, i.e. North Sumatra, West Java, Yogyakarta, South Sulawesi, and East Nusa Tenggara, in 2023. Farmers were interviewed face to face using structured questionnaires. The data were analysed using Partial Least Squares-Structural Equation Modelling (PLS-SEM) through the Python software. The results showed that Indonesian rice farmers have a moderate level of readiness. The mean value of the capabilities and opportunities indicators were 2.54 to 3.8, while the range for the opportunity’s indicator is 3.23 to 4.11, larger than the capabilities indicators. The level of precision agriculture implementation on Indonesian rice farmers was significant influenced by management (β = 0.42, t = 7.11, p < 0.05), environment (β = 0.17, t = 3.63, p < 0.05), readiness (β = 0.14, t = 2.51, p < 0.05), and technology (β = 0.10, t = 2.12, p < 0.05), economy (β = 0.09, t = 3.63, p < 0.05), and technology² (β = -0.072, t = 3.5, p < 0.05). Meanwhile, farmer readiness was significantly influenced by opportunity (β = 0.39, t = 6.64, p < 0.05) and capabilities (β = 0.43, t = 6.82, p < 0.05). This research provides information on the status of human resource capacity in exploiting opportunities for implementing precision agriculture and technical policy advice. The Indonesian government should improve farmers’ skills in information technology, Global Positioning Systems (GPS), and sensor technology in agricultural sectors, and facilitate access to technology and resources in order to increase rice farmers’ readiness to adopt PATs. For opportunity indicators, however, further research is needed to determine which components require immediate attention for construction or development.

Introduction

Service robotics is recently enhancing precision agriculture enabling many automated processes based on efficient autonomous navigation solutions. However, data generation and in-field validation campaigns hinder the progress of large-scale autonomous platforms. Simulated environments and deep visual perception are spreading as successful tools to speed up the development of robust navigation with low-cost RGB-D cameras.

Materials and methods

In this context, the contribution of this work resides in a complete framework to fully exploit synthetic data for a robust visual control of mobile robots. A wide realistic multi-crops dataset is accurately generated to train deep semantic segmentation networks and enabling robust performance in challenging real-world conditions. An automatic parametric approach enables an easy customization of virtual field geometry and features for a fast reliable evaluation of navigation algorithms.

Results and conclusion

The high quality of the generated synthetic dataset is demonstrated by an extensive experimentation with real crops images and benchmarking the resulting robot navigation both in virtual and real fields with relevant metrics.

In the context of increasing global food demand and the urgent need for production processes optimization, plant protection products play a key role in safeguarding crops from insects, pests, and fungi, responsible of plant diseases proliferation and yield losses. Despite the inaccurate distribution of conventional aerial spraying performed by airplanes and helicopters, Unmanned Aerial Spraying Systems (UASSs) offer low health risks and operational cost solutions, preserving crops and soil from physical damage. This study explores the impact of UASS flight height (2 m and 2.5 m above ground level), speed (1 m s⁻¹ and 1.5 m s⁻¹), and position (over the canopy and the inter-row) on vineyard aerial spraying efficiency by analysing Water Sensitive Papers droplet coverage, density, and Number Median Diameter using a MATLAB script. Flight position factor, more than others, influenced the application results. The specific configuration of 2 m altitude, 1.5 m s⁻¹ cruising speed, and inter-row positioning yielded the best results in terms of canopy coverage, minimizing off-target and ground dispersion, and represented the best setting to facilitate droplets penetration, reaching the lowest parts generally more affected from disease. Further research is needed to assess UASS aerial PPP distribution effectiveness and environmental impact in agriculture, crucial for technology implementation, especially in countries where aerial treatments are not yet permitted.