Food and Agriculture Organization (FAO) The Food and Agriculture Organization (FAO), established in 1945, is a UN specialized agency that provides global data and expertise on agri culture and nutrition, fisheries, forestry, and other food and agriculture– related issues. FAO is the UN system’s largest autonomous agency, with headquarters in Rome, 78 country offices and 15 regional, sub–regional, and liaison offices, including one located in Washington, D.C. FAO’s highest policy–making body, the biennial General Conference, comprises all 183 FAO member countries plus the European Commission. The General Conference determines FAO policy and approves FAO’s reg ular program of work and budget. The 31st Conference, meeting in November 1999, re–elected Director–General Jacques Diouf (Senegal) to a second six–year term through December 2005. Each biennial Confer ence elects a 49–member Council that meets semi–annually to make rec ommendations to the General Conference on budget and policy issues. The North America region, which comprises the United States and Can ada, is allocated two seats on the Council and one seat each on FAO’s Program, Finance, and Constitutional and Legal Matters (CCLM) Com mittees. The United States holds the North American seats on the Finance and Joint Staff Pension Committees through December 2003. Canada holds the North American seat on the CCLM and Program Committees through December 2003. The United States participated at the World Food Summit: Five Years Later meeting held at FAO headquarters June 10–13, 2002, to discuss progress towards attaining the 1996 World Food Summit target of reduc ing the world’s number of hungry and malnourished by half by 2015. The United States presented new initiatives to improve agriculture productivity as a significant contribution toward meeting that goal. U.S. Secretary of Agriculture Ann Veneman, leading the U.S. delegation, joined other min isters and heads of state and government in adopting a Declaration, “The International Alliance Against Hunger,” which reiterated the goals of the 1996 World Food Summit and stated, inter alia, “we are committed to
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.
Stephane Ngnepiepaye Wembe, Vincent Rousseau, Johann Laconte
et al.
Robots are increasingly being deployed in agriculture to support sustainable practices and improve productivity. They offer strong potential to enable precise, efficient, and environmentally friendly operations. However, most existing path-following controllers focus solely on the robot's center of motion and neglect the spatial footprint and dynamics of attached implements. In practice, implements such as mechanical weeders or spring-tine cultivators are often large, rigidly mounted, and directly interacting with crops and soil; ignoring their position can degrade tracking performance and increase the risk of crop damage. To address this limitation, we propose a closed-form predictive control strategy extending the approach introduced in [1]. The method is developed specifically for Ackermann-type agricultural vehicles and explicitly models the implement as a rigid offset point, while accounting for lateral slip and lever-arm effects. The approach is benchmarked against state-of-the-art baseline controllers, including a reactive geometric method, a reactive backstepping method, and a model-based predictive scheme. Real-world agricultural experiments with two different implements show that the proposed method reduces the median tracking error by 24% to 56%, and decreases peak errors during curvature transitions by up to 70%. These improvements translate into enhanced operational safety, particularly in scenarios where the implement operates in close proximity to crop rows.
Abhiraam Eranti, Yogesh Tewari, Rafael Palacios
et al.
Deep-learning methods have boosted the analytical power of Raman spectroscopy, yet they still require large, task-specific, labeled datasets and often fail to transfer across application domains. The study explores pre-trained encoders as a solution. Pre-trained encoders have significantly impacted Natural Language Processing and Computer Vision with their ability to learn transferable representations that can be applied to a variety of datasets, significantly reducing the amount of time and data required to create capable models. The following work puts forward a new approach that applies these benefits to Raman Spectroscopy. The proposed approach, RSPTE (Raman Spectroscopy Pre-Trained Encoder), is designed to learn generalizable spectral representations without labels. RSPTE employs a novel domain adaptation strategy using unsupervised Barlow Twins decorrelation objectives to learn fundamental spectral patterns from multi-domain Raman Spectroscopy datasets containing samples from medicine, biology, and mineralogy. Transferability is demonstrated through evaluation on several models created by fine-tuning RSPTE for different application domains: Medicine (detection of Melanoma and COVID), Biology (Pathogen Identification), and Agriculture. As an example, using only 20% of the dataset, models trained with RSPTE achieve accuracies ranging 50%–86% (depending on the dataset used) while without RSPTE the range is 9%–57%. Using the full dataset, accuracies with RSPTE range 81%–97%, and without pre-training 51%–97%. Current methods and state-of-the-art models in Raman Spectroscopy are compared to RSPTE for context, and RSPTE exhibits competitive results, especially with less data as well. These results provide evidence that the proposed RSPTE model can effectively learn and transfer generalizable spectral features across different domains, achieving accurate results with less data in less time (both data collection time and training time).
From slow, non-uniform germination to pre-harvest sprouting (PHS), both extremes of seed dormancy have posed challenges for plant breeders. Because this trait needs to be genetically tuned in relation to environmental cues, controlling the problem of pre-harvest sprouting can only be realized through a better understanding of the biological mechanisms of seed dormancy. Yet studying seed dormancy poses challenges, because of its complexity in the different modes of regulation (physical, chemical, developmental, physiological and genetic) in interaction with environmental cues (light, temperature, water and nutrients) and lack of natural variation in the commercial crop genetic resources. Building information from model systems can help guide our research efforts. While phylogenetically distant from temperate cereals, the available information for Arabidopsis is much more elaborate and can, to a certain extent, be translated. We therefore provide a comprehensive comparison of the mechanisms and pathways and indicate similarities, differences and knowledge gaps. While knowledge from Arabidopsis is highly valuable to guide seed dormancy studies in temperate cereals, effective knowledge translation that includes functional validation will often require the use of the more closely related “model system” Brachypodium. This model will also allow us to unravel derived or unique mechanisms in temperate cereals. As an indication of such derived mechanisms, we also discuss the genetic factors involved in seed dormancy control discovered in cereals, often through natural variation studies.
The objective of this study was to provide a comprehensive overview of the recent advancements in the use of deep learning (DL) in the agricultural sector. The author conducted a review of studies published between 2016 and 2022 to highlight the various applications of DL in agriculture, which include counting fruits, managing water, crop management, soil management, weed detection, seed classification, yield prediction, disease detection, and harvesting. The author found that DL’s ability to learn from large datasets has great promise for the transformation of the agriculture industry, but there are challenges, such as the difficulty of compiling datasets, the cost of computational power, and the shortage of DL experts. The author aimed to address these challenges by presenting his survey as a resource for future research and development regarding the use of DL in agriculture.