COVID-19 and the restrictive measures towards containing the spread of its infections have seriously affected the agricultural workforce and jeopardized food security. The present study aims at assessing the COVID-19 pandemic impacts on agricultural labor and suggesting strategies to mitigate them. To this end, after an introduction to the pandemic background, the negative consequences on agriculture and the existing mitigation policies, risks to the agricultural workers were benchmarked across the United States’ Standard Occupational Classification system. The individual tasks associated with each occupation in agricultural production were evaluated on the basis of potential COVID-19 infection risk. As criteria, the most prevalent virus transmission mechanisms were considered, namely the possibility of touching contaminated surfaces and the close proximity of workers. The higher risk occupations within the sector were identified, which facilitates the allocation of worker protection resources to the occupations where they are most needed. In particular, the results demonstrated that 50% of the agricultural workforce and 54% of the workers’ annual income are at moderate to high risk. As a consequence, a series of control measures need to be adopted so as to enhance the resilience and sustainability of the sector as well as protect farmers including physical distancing, hygiene practices, and personal protection equipment.

Robotics and computerization have drastically changed the agricultural production sector and thus moved it into a new automation era. Robots have historically been used for carrying out routine tasks that require physical strength, accuracy, and repeatability, whereas humans are used to engage with more value-added tasks that need reasoning and decision-making skills. On the other hand, robots are also increasingly exploited in several non-routine tasks that require cognitive skills. This technological evolution will create a fundamental and an unavoidable transformation of the agricultural occupations landscape with a high social and economic impact in terms of jobs creation and jobs destruction. To that effect, the aim of the present work is two-fold: (a) to map agricultural occupations in terms of their cognitive/manual and routine/non-routine characteristics and (b) to assess the susceptibility of each agricultural occupation to robotization. Seventeen (17) agricultural occupations were reviewed in relation to the characteristics of each individual task they entail and mapped onto a two-dimensional space representing the manual versus cognitive nature and the routine versus non-routine nature of an occupation. Subsequently, the potential for robotization was investigated, again concerning each task individually, and resulted in a weighted average potential adoption rate for each one of the agricultural occupations. It can be concluded that most of the occupations entail manual tasks that need to be performed in a standardised manner. Considering also that almost 81% of the agricultural work force is involved with these activities, it turns out that there is strong evidence for possible robotization of 70% of the agricultural domain, which, in turn, could affect 56% of the total annual budget dedicated to agricultural occupations. The presented work silhouettes the expected transformation of occupational landscape in agricultural production as an effort for a subsequent identification of social threats in terms of unemployment and job and wages polarization, among others, but also of opportunities in terms of emerged skills and training requirements for a social sustainable development of agricultural domain.

This paper conducts an in-depth exploration of carbon farming at the confluence of advanced technology and EU policy, particularly within the context of the European Green Deal. Emphasizing technologies at technology readiness levels (TRL) 6–9, the study critically analyzes and synthesizes their practical implementation potential in the agricultural sector. Methodologically, the paper integrates a review of current technologies with an analysis of EU policy frameworks, focusing on the practical application of these technologies in alignment with policy directives. The results demonstrate a symbiotic relationship between emerging carbon farming technologies and evolving EU policies, highlighting how technological advancements can be effectively integrated within existing and proposed legal structures. This alignment is crucial for fostering practical, market-ready, and sustainable agricultural practices. Significantly, this study underscores the importance of bridging theoretical research with commercialization. It proposes a pathway for transitioning current research insights into innovative, market-responsive products, thereby contributing to sustainable agricultural practices. This approach not only aligns with the European Green Deal but also addresses market demands and environmental policy evolution. In conclusion, the paper serves as a critical link between theoretical advancements and practical applications in sustainable carbon farming. It offers a comprehensive understanding of both the technological and policy landscapes, aiming to propel practical, sustainable solutions in step with dynamic environmental policy goals.

Accurate crop yield prediction is vital towards optimizing agricultural productivity. Machine Learning (ML) has shown promise in this field; however, its application to legume crops, especially to lupin, remains limited, while many models lack interpretability, hindering real-world adoption. To bridge this literature gap, an interpretable ML framework was developed for predicting lupin yield using Sentinel-2 remote sensing data integrated with georeferenced yield measurements. Data preprocessing involved computing vegetation indices, removing outliers, addressing multicollinearity, normalizing feature scales, and applying data augmentation techniques to correct target imbalance. Subsequently, six ML models were evaluated representing different algorithmic strategies. Among them, XGBoost showed the best performance ($R^2$ = 0.8756) and low error values across $MAE$, $MSE$, and $RMSE$ metrics. To enhance model transparency, SHapley Additive exPlanations (SHAP) values were applied to interpret the feature contributions of the XGBoost model. The Enhanced Vegetation Index ($EVI$) and Normalized Difference Vegetation Index ($NDVI$) were found to be key predictors of crop yield, both showing a positive correlation with higher values reflecting greater vegetation vigor and corresponding to increased yield. These were followed by $B03$ (green) and $B12$ (short-wave infrared), which captured key reflectance properties associated with chlorophyll activity and water content, respectively. Both of them substantially influence photosynthetic efficiency and plant health, ultimately affecting yield potential.

Agriculture is being transformed through automation and robotics to improve efficiency and reduce production costs. However, this transformation poses risks of job loss, particularly for low-skilled workers, as automation decreases the need for human labor. To adapt, the workforce must acquire new qualifications to collaborate with automated systems or shift to roles that leverage their unique human abilities. In this study, 15 agricultural occupations were methodically mapped in a cognitive/manual versus routine/non-routine two-dimensional space. Subsequently, each occupation’s susceptibility to robotization was assessed based on the readiness level of existing technologies that can automate specific tasks and the relative importance of these tasks in the occupation’s execution. The qualifications required for occupations less impacted by robotization were summarized, detailing the specific knowledge, skills, and work styles required to effectively integrate the emerging technologies. It was deduced that occupations involving primary manual routine tasks exhibited the highest susceptibility rate, whereas occupations with non-routine tasks showed lower susceptibility. To thrive in this evolving landscape, a strategic combination of STEM (science, technology, engineering, and mathematics) skills with essential management, soft skills, and interdisciplinary competences is imperative. Finally, this research stresses the importance of strategic preparation by policymakers and educational systems to cultivate key competencies, including digital literacy, that foster resilience, inclusivity, and sustainability in the sector.

Understanding the impact of robotization on the workforce dynamics has become increasingly urgent. While expert assessments provide valuable insights, they are often time-consuming and resource-intensive. Large language models (LLMs) offer a scalable alternative; however, their accuracy and reliability in evaluating workforce robotization potential remain uncertain. This study systematically compares general-purpose LLM-generated assessments with expert evaluations to assess their effectiveness in the agricultural sector by considering human judgments as the ground truth. Using ChatGPT, Copilot, and Gemini, the LLMs followed a three-step evaluation process focusing on (a) task importance, (b) potential for task robotization, and (c) task attribute indexing of 15 agricultural occupations, mirroring the methodology used by human assessors. The findings indicate a significant tendency for LLMs to overestimate robotization potential, with most of the errors falling within the range of 0.229 ± 0.174. This can be attributed primarily to LLM reliance on grey literature and idealized technological scenarios, as well as their limited capacity, to account for the complexities of agricultural work. Future research should focus on integrating expert knowledge into LLM training and improving bias detection and mitigation in agricultural datasets, as well as expanding the range of LLMs studied to enhance assessment reliability.