Hasil untuk "Agriculture"

A. Wezel, M. Casagrande, F. Celette et al.

T. D. Ponti, B. Rijk, M. Ittersum

C. Boryan, Zhengwei Yang, R. Mueller et al.

C. Atzberger

Many remote sensing applications are devoted to the agricultural sector. Representative case studies are presented in the special issue "Advances in Remote Sensing of Agriculture". To complement the examples published within the special issue, a few main applications with regional to global focus were selected for this review, where remote sensing contributions are traditionally strong. The selected applications are put in the context of the global challenges the agricultural sector is facing: minimizing the environmental impact, while increasing production and productivity. Five different applications have been selected, which are illustrated and described: (1) biomass and yield estimation, (2) vegetation vigor and drought stress monitoring, (3) assessment of crop phenological development, (4) crop acreage estimation and cropland mapping and (5) mapping of disturbances and land use/land cover (LULC) changes. Many other applications exist, such as precision agriculture and irrigation management (see other special issues of this journal), but were not included to keep the paper concise. The paper starts with an overview of the main agricultural challenges. This section is followed by a brief overview of existing operational monitoring systems. Finally, in the main part of the paper, the mentioned applications are described and illustrated. The review concludes with some key recommendations.

J. Craigie

L. P. Koh, D. Wilcove

D. Molden

J. Roumasset, J. B. Hardeker, R. Huirne et al.

Leo Horrigan, R. Lawrence, Polly Walker

The industrial agriculture system consumes fossil fuel, water, and topsoil at unsustainable rates. It contributes to numerous forms of environmental degradation, including air and water pollution, soil depletion, diminishing biodiversity, and fish die-offs. Meat production contributes disproportionately to these problems, in part because feeding grain to livestock to produce meat--instead of feeding it directly to humans--involves a large energy loss, making animal agriculture more resource intensive than other forms of food production. The proliferation of factory-style animal agriculture creates environmental and public health concerns, including pollution from the high concentration of animal wastes and the extensive use of antibiotics, which may compromise their effectiveness in medical use. At the consumption end, animal fat is implicated in many of the chronic degenerative diseases that afflict industrial and newly industrializing societies, particularly cardiovascular disease and some cancers. In terms of human health, both affluent and poor countries could benefit from policies that more equitably distribute high-protein foods. The pesticides used heavily in industrial agriculture are associated with elevated cancer risks for workers and consumers and are coming under greater scrutiny for their links to endocrine disruption and reproductive dysfunction. In this article we outline the environmental and human health problems associated with current food production practices and discuss how these systems could be made more sustainable.

R. Mendelsohn, W. Nordhaus, D. Shaw

A. Rehman, A. Z. Abbasi, Noman Islam et al.

P. Tittonell

D. Crowder, J. Reganold

Significance Some recognize organic agriculture as being important for future global food security, whereas others project it to become irrelevant. Although organic agriculture is rapidly growing, it currently occupies only 1% of global cropland. Whether organic agriculture can continue to expand will likely be determined by whether it is economically competitive with conventional agriculture. Accordingly, we analyzed the financial performance of organic and conventional agriculture from 40 y of studies covering 55 crops grown on five continents. We found that, in spite of lower yields, organic agriculture was significantly more profitable than conventional agriculture and has room to expand globally. Moreover, with its environmental benefits, organic agriculture can contribute a larger share in sustainably feeding the world. To promote global food and ecosystem security, several innovative farming systems have been identified that better balance multiple sustainability goals. The most rapidly growing and contentious of these systems is organic agriculture. Whether organic agriculture can continue to expand will likely be determined by whether it is economically competitive with conventional agriculture. Here, we examined the financial performance of organic and conventional agriculture by conducting a meta-analysis of a global dataset spanning 55 crops grown on five continents. When organic premiums were not applied, benefit/cost ratios (−8 to −7%) and net present values (−27 to −23%) of organic agriculture were significantly lower than conventional agriculture. However, when actual premiums were applied, organic agriculture was significantly more profitable (22–35%) and had higher benefit/cost ratios (20–24%) than conventional agriculture. Although premiums were 29–32%, breakeven premiums necessary for organic profits to match conventional profits were only 5–7%, even with organic yields being 10–18% lower. Total costs were not significantly different, but labor costs were significantly higher (7–13%) with organic farming practices. Studies in our meta-analysis accounted for neither environmental costs (negative externalities) nor ecosystem services from good farming practices, which likely favor organic agriculture. With only 1% of the global agricultural land in organic production, our findings suggest that organic agriculture can continue to expand even if premiums decline. Furthermore, with their multiple sustainability benefits, organic farming systems can contribute a larger share in feeding the world.

Yongchao Liang, M. Nikolić, R. Bélanger et al.

K. Giller, J. Andersson, M. Corbeels et al.

Global support for Conservation Agriculture (CA) as a pathway to Sustainable Intensification is strong. CA revolves around three principles: no-till (or minimal soil disturbance), soil cover, and crop rotation. The benefits arising from the ease of crop management, energy/cost/time savings, and soil and water conservation led to widespread adoption of CA, particularly on large farms in the Americas and Australia, where farmers harness the tools of modern science: highly-sophisticated machines, potent agrochemicals, and biotechnology. Over the past 10 years CA has been promoted among smallholder farmers in the (sub-) tropics, often with disappointing results. Growing evidence challenges the claims that CA increases crop yields and builds-up soil carbon although increased stability of crop yields in dry climates is evident. Our analyses suggest pragmatic adoption on larger mechanized farms, and limited uptake of CA by smallholder farmers in developing countries. We propose a rigorous, context-sensitive approach based on Systems Agronomy to analyze and explore sustainable intensification options, including the potential of CA. There is an urgent need to move beyond dogma and prescriptive approaches to provide soil and crop management options for farmers to enable the Sustainable Intensification of agriculture.

Bo Yang, Yu Zhang, Yunkui Chen et al.

Intelligent agent systems in real-world agricultural scenarios must handle diverse tasks under multimodal inputs, ranging from lightweight information understanding to complex multi-step execution. However, most existing approaches rely on a unified execution paradigm, which struggles to accommodate large variations in task complexity and incomplete tool availability commonly observed in agricultural environments. To address this challenge, we propose AgriAgent, a two-level agent framework for real-world agriculture. AgriAgent adopts a hierarchical execution strategy based on task complexity: simple tasks are handled through direct reasoning by modality-specific agents, while complex tasks trigger a contract-driven planning mechanism that formulates tasks as capability requirements and performs capability-aware tool orchestration and dynamic tool generation, enabling multi-step and verifiable execution with failure recovery. Experimental results show that AgriAgent achieves higher execution success rates and robustness on complex tasks compared to existing tool-centric agent baselines that rely on unified execution paradigms. All code, data will be released at after our work be accepted to promote reproducible research.

Quanxi Zhou, Wencan Mao, Yilei Liang et al.

The widespread application of wireless communication technology has promoted the development of smart agriculture, where unmanned aerial vehicles (UAVs) play a multifunctional role. We target a multi-UAV smart agriculture system where UAVs cooperatively perform data collection, image acquisition, and communication tasks. In this context, we model a Markov decision process to solve the multi-UAV trajectory planning problem. Moreover, we propose a novel Elite Imitation Actor-Shared Ensemble Critic (EIA-SEC) framework, where agents adaptively learn from the elite agent to reduce trial-and-error costs, and a shared ensemble critic collaborates with each agent's local critic to ensure unbiased objective value estimates and prevent overestimation. Experimental results demonstrate that EIA-SEC outperforms state-of-the-art baselines in terms of reward performance, training stability, and convergence speed.

Hossein Zaremehrjerdi, Shreyan Ganguly, Ashlyn Rairdin et al.

Agricultural decision-making involves complex, context-specific reasoning, where choices about crops, practices, and interventions depend heavily on geographic, climatic, and economic conditions. Traditional large language models (LLMs) often fall short in navigating this nuanced problem due to limited reasoning capacity. We hypothesize that recent advances in large reasoning models (LRMs) can better handle such structured, domain-specific inference. To investigate this, we introduce AgReason, the first expert-curated open-ended science benchmark with 100 questions for agricultural reasoning. Evaluations across thirteen open-source and proprietary models reveal that LRMs outperform conventional ones, though notable challenges persist, with the strongest Gemini-based baseline achieving 36% accuracy. We also present AgThoughts, a large-scale dataset of 44.6K question-answer pairs generated with human oversight and equipped with synthetically generated reasoning traces. Using AgThoughts, we develop AgThinker, a suite of small reasoning models that can be run on consumer-grade GPUs, and show that our dataset can be effective in unlocking agricultural reasoning abilities in LLMs. Our project page is here: https://baskargroup.github.io/Ag_reasoning/

Yue Shi, Liangxiu Han, Xin Zhang et al.

Process-based models (PBMs) and deep learning (DL) are two key approaches in agricultural modelling, each offering distinct advantages and limitations. PBMs provide mechanistic insights based on physical and biological principles, ensuring interpretability and scientific rigour. However, they often struggle with scalability, parameterisation, and adaptation to heterogeneous environments. In contrast, DL models excel at capturing complex, nonlinear patterns from large datasets but may suffer from limited interpretability, high computational demands, and overfitting in data-scarce scenarios. This study presents a systematic review of PBMs, DL models, and hybrid PBM-DL frameworks, highlighting their applications in agricultural and environmental modelling. We classify hybrid PBM-DL approaches into DL-informed PBMs, where neural networks refine process-based models, and PBM-informed DL, where physical constraints guide deep learning predictions. Additionally, we conduct a case study on crop dry biomass prediction, comparing hybrid models against standalone PBMs and DL models under varying data quality, sample sizes, and spatial conditions. The results demonstrate that hybrid models consistently outperform traditional PBMs and DL models, offering greater robustness to noisy data and improved generalisation across unseen locations. Finally, we discuss key challenges, including model interpretability, scalability, and data requirements, alongside actionable recommendations for advancing hybrid modelling in agriculture. By integrating domain knowledge with AI-driven approaches, this study contributes to the development of scalable, interpretable, and reproducible agricultural models that support data-driven decision-making for sustainable agriculture.

Tamim Ahmed, Monowar Hasan

By offering a dynamic, real-time virtual representation of physical systems, digital twin technology can enhance data-driven decision-making in digital agriculture. Our research shows how digital twins are useful for detecting inconsistencies in agricultural weather data measurements, which are key attributes for various agricultural decision-making and automation tasks. We develop a modular framework named Cerealia that allows end-users to check for data inconsistencies when perfect weather feeds are unavailable. Cerealia uses neural network models to check anomalies and aids end-users in informed decision-making. We develop a prototype of Cerealia using the NVIDIA Jetson Orin platform and test it with an operational weather network established in a commercial orchard as well as publicly available weather datasets.