This study investigated the potential of in-season airborne hyperspectral imaging for the calibration of robust forage yield and quality estimation models. An unmanned aerial vehicle (UAV) and a hyperspectral imager were used to capture canopy reflections of a grass-legume mixture in the range of 450 nm to 800 nm. Measurements were performed over two years at two locations in Southeast and Central Norway. All images were subject to radiometric and geometric corrections before being processed to ortho-images, carrying canopy reflectance information. The data (n = 707) was split in two, using half the data for model calibration and the remaining half for validation. Several powered partial least squares regression (PPLSR) models were fitted to the reflectance data to estimate fresh (FM) and dry matter (DM) yields, as well as crude protein (CP), dry matter digestibility (DMD), neutral detergent fibre (NDF), and indigestible neutral detergent fibre (iNDF) content. Prediction performance of these models was compared with the prediction performance of simple linear regression (SLR) models, which were based on selected vegetation indices and plant height. The highest prediction accuracies for general models, based on the pooled data, were achieved by means of PPLSR, with relative root-mean-square errors of validation of 14.2% (2550 kg FM ha⁻¹), 15.2% (555 kg DM ha⁻¹), 11.7% (1.32 g CP 100 g⁻¹ DM), 2.4% (1.71 g DMD 100 g⁻¹ DM), 4.8% (2.72 g NDF 100 g⁻¹ DM), and 12.8% (1.32 g iNDF 100 g⁻¹ DM) for the prediction of FM, DM, CP, DMD, NDF, and iNDF content, respectively. None of the tested SLR models achieved acceptable prediction accuracies.

Weeds affect crop yield and quality due to competition for resources. In order to reduce the risk of yield losses due to weeds, herbicides or non-chemical measures are applied. Weeds, especially creeping perennial species, are generally distributed in patches within arable fields. Hence, instead of applying control measures uniformly, precision weeding or site-specific weed management (SSWM) is highly recommended. Unmanned aerial vehicle (UAV) imaging is known for wide area coverage and flexible operation frequency, making it a potential solution to generate weed maps at a reasonable cost. Efficient weed mapping algorithms need to be developed together with UAV imagery to facilitate SSWM. Different machine learning (ML) approaches have been developed for image-based weed mapping, either classical ML models or the more up-to-date deep learning (DL) models taking full advantage of parallel computation on a GPU (graphics processing unit). Attention-based transformer DL models, which have seen a recent boom, are expected to overtake classical convolutional neural network (CNN) DL models. This inspired us to develop a transformer DL model for segmenting weeds, cereal crops, and ‘other’ in low-resolution RGB UAV imagery (about 33 mm ground sampling distance, g.s.d.) captured after the cereal crop had turned yellow. Images were acquired during three years in 15 fields with three cereal species (Triticum aestivum, Hordeum vulgare, and Avena sativa) and various weed flora dominated by creeping perennials (mainly Cirsium arvense and Elymus repens). The performance of our transformer model, 1Dtransformer, was evaluated through comparison with a classical DL model, 1DCNN, and two classical ML methods, i.e., random forest (RF) and k-nearest neighbor (KNN). The transformer model showed the best performance with an overall accuracy of 98.694% on pixels set aside for validation. It also agreed best and relatively well with ground reference data on total weed coverage, R2 = 0.598. In this study, we showed the outstanding performance and robustness of a 1Dtransformer model for weed mapping based on UAV imagery for the first time. The model can be used to obtain weed maps in cereals fields known to be infested by perennial weeds. These maps can be used as basis for the generation of prescription maps for SSWM, either pre-harvest, post-harvest, or in the next crop, by applying herbicides or non-chemical measures.

The remote sensing of the biophysical and biochemical parameters of crops facilitates the preparation of application maps for variable-rate nitrogen fertilization. According to comparative studies of machine learning algorithms, Gaussian process regression (GPR) can outperform more popular methods in the prediction of crop status from hyperspectral data. The present study evaluates GPR model accuracy in the context of spring wheat dry matter, nitrogen content, and nitrogen uptake estimation. Models with the squared exponential covariance function were trained on images from two hyperspectral cameras (a frenchFabry–Pérot interferometer camera and a push-broom scanner). The most accurate predictions were obtained for nitrogen uptake (${\mathrm{R}}^2=0.75–0.85$, ${\mathrm{RPD}}_{\mathrm{P}}=2.0–2.6$). Modifications of the basic workflow were then evaluated: the removal of soil pixels from the images prior to the training, data fusion with apparent soil electrical conductivity measurements, and replacing the Euclidean distance in the GPR covariance function with the spectral angle distance. Of these, the data fusion improved the performance while predicting nitrogen uptake and nitrogen content. The estimation accuracy of the latter parameter varied considerably across the two hyperspectral cameras. Satisfactory nitrogen content predictions (${\mathrm{R}}^2>0.8$, ${\mathrm{RPD}}_{\mathrm{P}}>2.4$) were obtained only in the data-fusion scenario, and only with a high spectral resolution push-broom device capable of capturing longer wavelengths, up to 1000 $\mathrm{n}$$\mathrm{m}$, while the full-frame camera spectral limit was 790 $\mathrm{n}$$\mathrm{m}$. The prediction performance and uncertainty metrics indicated the suitability of the models for precision agriculture applications. Moreover, the spatial patterns that emerged in the generated crop parameter maps accurately reflected the fertilization levels applied across the experimental area as well as the background variation of the abiotic growth conditions, further corroborating this conclusion.

The ageing population, climate change, and labour shortages in the agricultural sector are driving the need to reevaluate current farming practices. To address these challenges, the deployment of robot systems can help reduce environmental footprints and increase productivity. However, convincing farmers to adopt new technologies poses difficulties, considering economic viability and ease of use. In this paper, we introduce a management system based on the Robot Operating System (ROS) that integrates heterogeneous vehicles (conventional tractors and mobile robots). The goal of the proposed work is to ease the adoption of mobile robots in an agricultural context by providing to the farmer the initial tools needed to include them alongside the conventional machinery. We provide a comprehensive overview of the system’s architecture, the control laws implemented for fleet navigation within the field, the development of a user-friendly Graphical User Interface, and the charging infrastructure for the deployed vehicles. Additionally, field tests are conducted to demonstrate the effectiveness of the proposed framework.