Agricultural Extension Disk5, File 05230 Agricultural Extension: The Training and Visit System Disk 4, File 05-127 AgroForestrySystems for the HumidTropics East of the Andes Disk4, File 05-128 An Agromedical Approach to Pesticide Management Disk 5, File 05-231 Alternative AgricultureDisk 7, File 05-277 Animal Husbandryin the Tropics Disk 5, File 05-232 Approved Practices in Soil Conservation Disk 4, File 05-130 The Art of the Informal Agricultural SurveyDisk 7, File 05-284 As You Sow Disk 4, File 05-131 Backyard Composting Disk 4, File 05-134 The Basic Bookof Organic Gardening Disk4, File 05135 Basic Soil Improvement for Everyone Disk4, File 05-136 The Complete Better Farming Series Disk 4, Files 05-137 through05162 The Book of Geese Disk 5, File 05-234 China: Recycling of Organic Wastes in Agriculture Disk4, File 05-163 Code of Practice for Safe Use of Pesticides Disk 5, File 05-235 Composting for the Tropics Disk 4, File 05-164 Composting in Tropical Agriculture Disk 4, File 05-165 Composting: SanitaryDisposal and Reclamation of Organic Wastes Disk4, File 05-166 Conservation Farming for Small Farmers in the Humid Tropics Disk4, File 05167 The Design and Optimization of Irrigation Distribution Networks Disk 7, File 05-274 EnvironmentallySound Small Scale Agricultural Projects Disk4, File 05-170 Farm Management Research for Small Farmer Development Disk 7, File 05-280 The Farmer's Guide Disk 4, File 05-171 A Farmer's Primer on Growing Rice Disk 5, File 05-236 Fields and Pastures in Deserts Disk4, File 05174 Friends of the Rice Farmer Disk 7, File 05-275 Gardening for Better Nutrition Disk 4, File 05-179 Gardening with the Seasons Disk4, File 05-180 Goat Health HandbookDisk 6, File 05-237 Growing Garden Seeds Disk4, File 05-182 Guayule Disk4, File 05-183 Guide for Field Crops in the Tropics and Subtropics Disk 4, File 05-184 Guide for Small Holder Coffee Farmers Disk7, File 05281 Guidelines for Watershed Management Disk 7, File 05-282 GullyControl and Reclamation Disk6, File 05-260 Handbookof Tropical and Subtropical HorticultureDisk 4, File 05-185 The Homesteader's Handbookfor Raising Small Livestock Disk 6, File 05-261 How to Grow More Vegetables Disk4, File 05186 How to Make Fertilizer Disk4, File 05187 How to Perform an Agricultural Experiment Disk 4, File 05-188 Hydroponics Disk4, File 05189 Illustrated Guide to Integrated Pest Management in Rice in Tropical AsiaDisk 6, File 05-269 Insights of Outstanding Farmers Disk6, File 05238 Integrated Farm Management Disk 7, File 05-286 Integrated Pest Management: A Catalogue of Training and Extension Materials Disk 7, File 05-276 Integrated Pest Management Disk6, File 05239 Intensive Gardening for Profit and Self Sufficiency Disk4, File 05-191
Large Language Models show promise for agricultural advisory, yet vanilla models exhibit unsupported recommendations, generic advice lacking specific, actionable detail, and communication styles misaligned with smallholder farmer needs. In high stakes agricultural contexts, where recommendation accuracy has direct consequences for farmer outcomes, these limitations pose challenges for responsible deployment. We present a hybrid LLM architecture that decouples factual retrieval from conversational delivery: supervised fine-tuning with LoRA on expert-curated GOLDEN FACTS (atomic, verified units of agricultural knowledge) optimizes fact recall, while a separate stitching layer transforms retrieved facts into culturally appropriate, safety-aware responses. Our evaluation framework, DG-EVAL, performs atomic fact verification (measuring recall, precision, and contradiction detection) against expert-curated ground truth rather than Wikipedia or retrieved documents. Experiments across multiple model configurations on crops and queries from Bihar, India show that fine-tuning on curated data substantially improves fact recall and F1, while maintaining high relevance. Using a fine-tuned smaller model achieves comparable or better factual quality at a fraction of the cost of frontier models. A stitching layer further improves safety subscores while maintaining high conversational quality. We release the farmerchat-prompts library to enable reproducible development of domain-specific agricultural AI.
Community Supported Agriculture (CSA) has been recognized globally as a promising framework that embeds agriculture within social relations, yet its diffusion remains limited in contexts such as Japan. Existing studies have largely focused on either consumer or producer participation in isolation, offering fragmented insights and leaving unexplored how their reciprocal processes jointly shape CSA communities. This study addresses this gap by integrating the trajectories of both groups into a comprehensive account of CSA community formation. Drawing on semi-structured interviews with ten CSA producers and ten consumers, we employed the Modified Grounded Theory Approach (M-GTA) to inductively theorize processes of participation and practice. The analysis showed that producers advance CSA through internal adjustments and sense-making to cope with uncertainties, while consumers are guided by life events, practical skills, and prior purchasing experiences toward participation. Synthesizing these insights, we propose a six-phase model of CSA community formation, dispersed interest, awareness, interest formation, motivation, practice, and co-creative continuation, that demonstrates how producers, consumers, and intermediaries interact across stages. The model highlights the pivotal role of key players in sustaining engagement and provides a new perspective for institutionalizing CSA as a durable component of sustainable food systems.
The innovative agriculture system is revolutionizing how we farm, making it one of the most critical innovations of our time! Yet it faces significant connectivity challenges, particularly with the sensors that power this technology. An efficient sensor deployment solution is still required to maximize the network's detection capabilities and efficiency while minimizing resource consumption and operational costs. This paper introduces an innovative sensor allocation optimization method that employs a Gradient-Based Iteration with Lagrange. The proposed method enhances coverage by utilizing a hybrid approach while minimizing the number of sensor nodes required under grid-based allocation. The proposed sensor distribution outperformed the classic deterministic deployment across coverage, number of sensors, cost, and power consumption. Furthermore, scalability is enhanced by extending sensing coverage to the remaining area via Bluetooth, which has a shorter communication range. Moreover, the proposed algorithm achieved 98.5% wireless sensor coverage, compared with 95% for the particle swarm distribution.
High-resolution rainfall estimates from satellite and reanalysis sources (SRE) could play a major role in improving climate services for agriculture. This is particularly relevant in regions that rely on rain-fed farming but lack a dense network of ground-based measurements to provide localised historical climate information, as in most of the Global South. However, there is a need for a framework which practitioners can use to determine the suitability of these estimated data for specific agricultural applications. This paper presents a comprehensive methodology for evaluating the ability of SRE to provide historical rainfall information for agricultural applications, primarily through comparison with ground-based measurements. The methodology comprises five main steps: data selection and pre-processing, spatial and temporal consistency checks, quantitative SRE-gauge comparisons, bias correction, and application specific summaries. The methodology makes use of graphical summaries, standard comparison metrics, and Markov chain models. We describe how users can apply this methodology to evaluate rainfall estimates for specific applications, complementing existing validation studies. Evaluation cases are presented to demonstrate the methodology using five widely used satellite and reanalysis rainfall products and ground-based measurements from 12 stations in Africa and the Caribbean. The case studies demonstrate how the methodology can be applied to examine multiple aspects of the rainfall estimates. While previous validation studies ask "Does the SRE estimate the true rainfall well?", this methodology provides means of establishing "To what extent can an SRE be used for this specific purpose?" and a comprehensive framework for this. This meets a major need for location specific rainfall information to improve climate information services for millions of small-holder farming households.
Umair Nawaz, Muhammad Zaigham Zaheer, Fahad Shahbaz Khan
et al.
Crops, fisheries and livestock form the backbone of global food production, essential to feed the ever-growing global population. However, these sectors face considerable challenges, including climate variability, resource limitations, and the need for sustainable management. Addressing these issues requires efficient, accurate, and scalable technological solutions, highlighting the importance of artificial intelligence (AI). This survey presents a systematic and thorough review of more than 200 research works covering conventional machine learning approaches, advanced deep learning techniques (e.g., vision transformers), and recent vision-language foundation models (e.g., CLIP) in the agriculture domain, focusing on diverse tasks such as crop disease detection, livestock health management, and aquatic species monitoring. We further cover major implementation challenges such as data variability and experimental aspects: datasets, performance evaluation metrics, and geographical focus. We finish the survey by discussing potential open research directions emphasizing the need for multimodal data integration, efficient edge-device deployment, and domain-adaptable AI models for diverse farming environments. Rapid growth of evolving developments in this field can be actively tracked on our project page: https://github.com/umair1221/AI-in-Agriculture
Agricultural robotic agents have been becoming useful helpers in a wide range of agricultural tasks. However, they still heavily rely on manual operations or fixed railways for movement. To address this limitation, the AgriVLN method and the A2A benchmark pioneeringly extend Vision-and-Language Navigation (VLN) to the agricultural domain, enabling agents to navigate to the target positions following the natural language instructions. We observe that AgriVLN can effectively understands the simple instructions, but often misunderstands the complex ones. To bridge this gap, we propose the T-araVLN method, in which we build the instruction translator module to translate noisy and mistaken instructions into refined and precise representations. When evaluated on A2A, our T-araVLN successfully improves Success Rate (SR) from 0.47 to 0.63 and reduces Navigation Error (NE) from 2.91m to 2.28m, demonstrating the state-of-the-art performance in the agricultural VLN domain. Code: https://github.com/AlexTraveling/T-araVLN.
Vaibhava Srivastava, Jason R. Rohr, Rana D. Parshad
The Paradox of Enrichment (PoE) predicts that increasing resources, such as nutrient inputs like fertilizers or food availability, should destabilize ecological systems, such as crop-pest dynamics, leading to population cycles that can increase the risk of crop failure during environmental shocks. Yet, since the Green Revolution, fertilizer use has surged without widespread evidence of yield instability, challenging the PoE's relevance to modern agriculture. Here, we propose and test a novel resolution: that insecticides, frequently co-applied with fertilizers, act as stabilizing agents that counterbalance enrichment-induced instability. Using a modified PoE model with empirically grounded parameters for three major crop-pest systems-soybean-aphid, wheat-aphid, and cabbage-diamondback moth-we find that fertilizer increases yields, but destabilizes dynamics, whereas insecticides restore stability and ensure more predictable harvests. These findings reveal that insecticides may suppress pests but also play a critical role in stabilizing crop yields in nutrient-enriched agroecosystems, with implications for ecosystem management, eutrophication, conservation biology, and pesticide policy.
Soybean is a vital crop globally and a key source of food, feed, and biofuel. With advancements in high-throughput technologies, soybeans have become a key target for genetic improvement. This comprehensive review explores advances in multi-omics, artificial intelligence, and economic sustainability to enhance soybean resilience and productivity. Genomics revolution, including marker-assisted selection (MAS), genomic selection (GS), genome-wide association studies (GWAS), QTL mapping, GBS, and CRISPR-Cas9, metagenomics, and metabolomics have boosted the growth and development by creating stress-resilient soybean varieties. The artificial intelligence (AI) and machine learning approaches are improving genetic trait discovery associated with nutritional quality, stresses, and adaptation of soybeans. Additionally, AI-driven technologies like IoT-based disease detection and deep learning are revolutionizing soybean monitoring, early disease identification, yield prediction, disease prevention, and precision farming. Additionally, the economic viability and environmental sustainability of soybean-derived biofuels are critically evaluated, focusing on trade-offs and policy implications. Finally, the potential impact of climate change on soybean growth and productivity is explored through predictive modeling and adaptive strategies. Thus, this study highlights the transformative potential of multidisciplinary approaches in advancing soybean resilience and global utility.
Cassandra Upton, Gerhard Prinsloo, Paul Anton Steenkamp
et al.
IntroductionSea cucumbers are ecologically and economically significant marine invertebrates, yet the metabolic diversity and bioactive potential of noncommercialized, endemic species remains poorly understood.MethodsThis study presents the first intra-species metabolomic analysis of Pseudocnella sykion, a species endemic to the Eastern coast of Southern Africa, using untargeted 1HNMR metabolomics and full-scan UPLC-QTOF-HR-MS.ResultsThe analysis revealed a diverse array of metabolites associated with protein synthesis, tissue growth, osmoregulation, and energy utilization, with distinct tissue-specific patterns across the body wall, gonad, and gut/mesentery. The gut/mesentery tissue showed higher levels of amino acids and energy-related compounds. UPLCQTOF-HR-MS tentatively identified several metabolites, including triterpene glycosides and rosmarinic acid, a phenolic compound typically associated with plants. Online resources, including the Dictionary of Marine Natural Products, contained no previously recorded compounds for P. sykion.DiscussionThese findings underscore the untapped potential of P. sykion as a source of novel metabolites and demonstrate the utility of untargeted metabolomics in generating baseline profiles for underexplored marine species. The results offer a foundation for future research into bioactivity, environmental monitoring, and cultivation strategies. While this study provides critical baseline data, challenges in metabolite identification and extraction underscore the need for further targeted analyses. Overall, this research enhances our understanding of the metabolic dynamics of sea cucumbers and advocates for continued exploration of lesser-known species to support conservation, bioprospecting, and sustainable aquaculture. It represents a pioneering effort in metabolomic profiling of Southern African sea cucumber species and lays the groundwork for future investigations into their metabolic pathways and potential bioactivities.
Science, General. Including nature conservation, geographical distribution
ZHANG Lei, YU Ying, ZHAO Yixuan, CHEN Qiang, YANG Ruxing
This study aimed to evaluate the dynamic changes of non-volatile metabolites during green tea processing from the albino tea variety ‘Fuhuang 1’. Green tea was made from one bud with two leaves through three steps: natural drying, fixation and rolling. A total of 2 654 non-volatile metabolites were detected by ultra-high performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) in the raw material, intermediate products and final product. The total content of non-volatile metabolites showed an upward trend during tea processing. Our analysis showed that fixation was crucial for the conversion of non-volatile metabolites in green tea processing. A total of 292 important differential metabolites were selected before and after fixation, including amino acids and their derivatives (40), flavonoids (37), lipids (101), nucleotides and their derivatives (28), and phenolic acids (21). These metabolites were significantly enriched in pathways such as the biosynthesis of secondary metabolites, carbon metabolism, cysteine and methionine metabolism, arginine biosynthesis, alanine, aspartic acid and glutamic acid metabolism. They were categorized into three clusters by K-Means analysis. The metabolites in the first cluster accumulated significantly during fixation. The metabolites in the second cluster accumulated significantly during fixation and also accumulated during drying, but to a lesser extent. However, the metabolites in the third cluster significantly decreased during fixation. Amino acids and their derivatives accumulated significantly during fixation, especially reduced glutathione, which might be a signature compound of ‘Fuhuang 1’ green tea. Lipids were the most active compounds during green tea processing; their relative contents significantly increased, with lysophosphatidylethanolamine showing the greatest accumulation. Some flavonoids, nucleotides and their derivatives accumulated only during fixation, whereas others accumulated during both fixation and drying. This study provides a theoretical basis for the innovative utilization of tea albino mutants.
In this paper, a joint sensing and communication system is presented for smart agriculture. The system integrates an Ultra-compact Soil Moisture Sensor (UCSMS) for precise sensing, along with a Pattern Reconfigurable Antenna (PRA) for efficient transmission of information to the base station. A multiturn complementary spiral resonator (MCSR) is etched onto the ground plane of a microstrip transmission line to achieve miniaturization. The UCSMS operates at 180 MHz with a 3-turn complementary spiral resonator (3-CSR), at 102 MHz with a 4- turn complementary spiral resonator (4-CSR), and at 86 MHz with a 5-turn complementary spiral resonator (5-CSR). Due to its low resonance frequency, the proposed UCSMS is insensitive to variations in the Volume Under Test (VUT) of soil. A probe-fed circular patch antenna is designed in the Wireless Local Area Network (WLAN) band (2.45 GHz) with a maximum measured gain of 5.63 dBi. Additionally, four varactor diodes are integrated across the slots on the bottom side of the substrate to achieve pattern reconfiguration. Six different radiation patterns have been achieved by using different bias conditions of the diodes. In standby mode, PRA can serve as a means for Wireless Power Transfer (WPT) or Energy Harvesting (EH) to store power in a battery. This stored power can then be utilized to bias the varactor diodes. The combination of UCSMS and PRA enables the realization of a joint sensing and communication system. The proposed system's planar and simple geometry, along with its high sensitivity of 2.05 %, makes it suitable for smart agriculture applications. Moreover, the sensor is adaptive and capable of measuring the permittivity of various Material Under Test (MUT) within the range of 1 to 23.
The integration of artificial intelligence into agricultural practices, specifically through Consultation on Intelligent Agricultural Machinery Management (CIAMM), has the potential to revolutionize efficiency and sustainability in farming. This paper introduces a novel approach that leverages large language models (LLMs), particularly GPT-4, combined with multi-round prompt engineering to enhance decision-making processes in agricultural machinery management. We systematically developed and refined prompts to guide the LLMs in generating precise and contextually relevant outputs. Our approach was evaluated using a manually curated dataset from various online sources, and performance was assessed with accuracy and GPT-4 Scores. Comparative experiments were conducted using LLama-2-70B, ChatGPT, and GPT-4 models, alongside baseline and state-of-the-art methods such as Chain of Thought (CoT) and Thought of Thought (ThoT). The results demonstrate that our method significantly outperforms these approaches, achieving higher accuracy and relevance in generated responses. This paper highlights the potential of advanced prompt engineering techniques in improving the robustness and applicability of AI in agricultural contexts.
Mycorrhizal fungi form vast subterranean networks that are critical for plant nutrient uptake, carbon sequestration, and ecosystem resilience. Despite their ecological importance, optimizing these networks for precision agriculture, forestry,and carbon sequestration remains an open challenge, particularly when it comes to understanding the complex molecular and quantum-scale processes that govern nutrient exchange. In this paper, we propose a novel experimental framework using mycoponics, a controlled, soil-less environment for the study of plant fungal symbiosis integrated with isotopic labeling and quantum dots to track real-time nutrient transfer.