Adaptive AI in precision agriculture: A review: Investigating the use of self-learning algorithms in optimizing farm operations based on real-time data

Open Access Research Journal of Multidisciplinary Studies, Год журнала: 2024, Номер 7(2), С. 016 - 030

Опубликована: Апрель 7, 2024

This study investigates the transformative impact of adaptive Artificial Intelligence (AI) on precision agriculture, focusing optimizing farm operations through real-time data analysis. The primary objective was to assess how AI technologies enhance efficiency, productivity, and sustainability agricultural practices. Employing a systematic literature review content analysis, methodology involved scrutinizing peer-reviewed articles grey from key databases, applying stringent inclusion exclusion criteria ensure relevance quality. Key findings reveal that significantly improves by enabling precise monitoring management crops, soil, environmental conditions. integration IoT devices machine learning algorithms facilitates leading optimized resource use, reduced impact, increased crop yields. Economic benefits include cost savings efficient management, while advantages encompass minimized chemical use enhanced sustainability. Challenges identified high implementation costs, technical complexity, privacy concerns. However, solutions such as policy support, technological advancements, stakeholder collaboration are proposed overcome these barriers. Lastly, holds potential revolutionize agriculture making it more efficient, sustainable, productive. Future research should focus developing accessible, robust fostering an environment conducive adoption. underscores need for continued innovation support fully realize in agriculture.

Язык: Английский

---

Building trust: A systematic review of the drivers and barriers of agricultural data sharing

Smart Agricultural Technology, Год журнала: 2024, Номер 8, С. 100477 - 100477

Опубликована: Май 25, 2024

Smart farming practices offer decision-making support as farmers navigate economic, social, and environmental challenges. However, smart adoption remains low in many contexts due to the perceived cost skills required, hesitancies about sharing agricultural data. Numerous studies have reviewed factors that influence within different scenarios, but best our knowledge, none specifically motivators obstacles of agri-data farming. The objective this research was identify classify most prominent drivers barriers for across stakeholders, by examining existing literature. A Systematic Literature Review conducted using PRISMA 2020 methodology. query initially identified 491 papers from Scopus Web Science, after screening final number assessment 59. Factors affecting willingness capability engage data were categorised socio-economic, systemic, technical, legal categories. systemic which discussed 58% 57% papers, respectively. Technical prevalent barriers, 68% Perceived knowledge gain leading improved decision-making, collaboration agri-value chain, technologies, clarity around sovereignty key enablers Lack purpose benefit data, mistrust "who will my data", privacy security, lack on ownership rights use concerns. findings paper help inform on-the-ground social science EU focused feasible options promoting benefits sharing.

Язык: Английский

---

Data Analytics in Agriculture: Enhancing Decision-Making for Crop Yield Optimization and Sustainable Practices

Sustainability, Год журнала: 2024, Номер 16(17), С. 7331 - 7331

Опубликована: Авг. 26, 2024

Collaboration across the agriculture supply chain is essential to address high-yield demand and sustainable practices amid global overpopulation. Limited resources, such as soil water, are compromised by excessive chemical agents nutrient use. The Internet of Things (IoT) smart farming offer solutions optimizing agent applications, data analysis, farm monitoring. Evidence from numerous studies indicates that collaboration in chain, including farmers, can improve efficiency productivity, reduce costs, enhance crop quality. This paper investigates transformation traditional into through integration IoT technology community partnerships. It presents a case study focused on educating owners about advanced technologies decision-making, yields, promote sustainability. Additionally, highlights role analytics agriculture. Farmers southern region Zagreb, Croatia, were trained use sensors yield Small farms face challenges improving yields due limited capacity lack entrepreneurial experience. DMAIC methodology was employed these issues measure relevant parameters. also discusses consistent patterns between electrical conductivity (EC) measurements potassium levels soil. explains potential estimating concentrations based EC readings, or vice versa. Leveraging proxy for could cost-effective means assessing fertility dynamics. Principal Component Analysis (PCA) biplot analysis presented, showing pH values behaved independently. Understanding dynamics enhances knowledge variability informs management practices.

Язык: Английский

---

AI for Data-Driven Decision-Making in Smart Agriculture: From Field to Farm Management

Опубликована: Янв. 1, 2024

Язык: Английский

---

Investigating the barriers to drone implementation in sustainable agriculture: A hybrid fuzzy-DEMATEL-MMDE-ISM-based approach

Journal of Environmental Management, Год журнала: 2024, Номер 371, С. 123299 - 123299

Опубликована: Ноя. 12, 2024

Язык: Английский

---

Agroecological innovation to scale livestock agriculture for positive economic, environmental, and social outcomes

Deleted Journal, Год журнала: 2024, Номер 1(1), С. 013001 - 013001

Опубликована: Март 27, 2024

Abstract Livestock agriculture must change to meet demand for food production while building soil, reducing flooding, retaining nutrients, enhancing biodiversity, and supporting thriving communities. Technological innovations, including those in digital precision agriculture, are unlikely by themselves create the magnitude directionality of transformation livestock systems that needed. We begin comparing technological, ecological social innovations feedlot-finished pasture-finished cattle propose what is required a more integrative ‘agroecological innovation’ process intentionally weaves these three forms innovation transition be genuinely regenerative multifunctional. This integrated system emphasizes as essential components because their capacity address influence context into which technological occur. In particular, regional place-making can especially useful an interactive designing identities people engage with one another environments define landscape futures related standards normalize particular land management practices. Intentionally developing help communities relational processes desired outcomes agricultural landscapes develop ways collaborate towards achieving them, creation novel supply chains support systems. As norms evolve through they individual behaviors practices on ground offer pathway rapid scaling agriculture. Regional also ‘meta’ engaging public private institutions responsible natural resources, systems, good, further accelerating process. Emerging agroecological designed governed ensure diverse compatible contexts, approaches technologies consistent values goals region.

Язык: Английский

---

Development of an Improved GWO Algorithm for Solving Optimal Paths in Complex Vertical Farms with Multi-Robot Multi-Tasking

Agriculture, Год журнала: 2024, Номер 14(8), С. 1372 - 1372

Опубликована: Авг. 15, 2024

As the global population grows, achieving Zero Hunger by 2030 presents a significant challenge. Vertical farming technology offers potential solution, making path planning of agricultural robots in vertical farms research priority. This study introduces Farming System Multi-Robot Trajectory Planning (VFSMRTP) model. To optimize this model, we propose Elitist Preservation Differential Evolution Grey Wolf Optimizer (EPDE-GWO), an enhanced version (GWO) incorporating elite preservation and differential evolution. The EPDE-GWO algorithm is compared with Genetic Algorithm (GA), Simulated Annealing (SA), Dung Beetle (DBO), Particle Swarm Optimization (PSO). experimental results demonstrate that reduces length 24.6%, prevents premature convergence, exhibits strong search capabilities. Thanks to DE EP strategies, requires fewer iterations reach optimal stability robustness, consistently finds solution at high frequency. These attributes are particularly context farming, where optimizing robotic essential for maximizing operational efficiency, reducing energy consumption, improving scalability operations.

Язык: Английский

---

Optimal Sensor Placement and Multimodal Fusion for Human Activity Recognition in Agricultural Tasks

Applied Sciences, Год журнала: 2024, Номер 14(18), С. 8520 - 8520

Опубликована: Сен. 21, 2024

This study examines the impact of sensor placement and multimodal fusion on performance a Long Short-Term Memory (LSTM)-based model for human activity classification taking place in an agricultural harvesting scenario involving human-robot collaboration. Data were collected from twenty participants performing six distinct activities using five wearable inertial measurement units placed at various anatomical locations. The signals sensors first processed to eliminate noise then input into LSTM neural network recognizing features sequential time-dependent data. Results indicated that chest-mounted provided highest F1-score 0.939, representing superior over other placements combinations them. Moreover, magnetometer surpassed accelerometer gyroscope, highlighting its ability capture crucial orientation motion data related investigated activities. However, accelerometer, showed benefit integrating different types improve accuracy. emphasizes effectiveness strategic optimizing recognition, thus minimizing requirements computational expenses, resulting cost-optimal system configuration. Overall, this research contributes development more intelligent, safe, cost-effective adaptive synergistic systems can be integrated variety applications.

Язык: Английский

---

Lab to farm: mapping knowledge transfer channels and determinants from researchers’ perspective – A systematic literature review

Journal of Innovation & Knowledge, Год журнала: 2025, Номер 10(1), С. 100650 - 100650

Опубликована: Янв. 1, 2025

Язык: Английский

---

Review of Methods and Models for Potato Yield Prediction

Agriculture, Год журнала: 2025, Номер 15(4), С. 367 - 367

Опубликована: Фев. 9, 2025

This article provides a comprehensive overview of the development and application statistical methods, process-based models, machine learning, deep learning techniques in potato yield forecasting. It emphasizes importance integrating diverse data sources, including meteorological, phenotypic, remote sensing data. Advances computer technology have enabled creation more sophisticated such as mixed, geostatistical, Bayesian models. Special attention is given to techniques, particularly convolutional neural networks, which significantly enhance forecast accuracy by analyzing complex patterns. The also discusses effectiveness other algorithms, Random Forest Support Vector Machines, capturing nonlinear relationships affecting yields. According standards adopted agricultural research, Mean Absolute Percentage Error (MAPE) implementation prediction issues should generally not exceed 15%. Contemporary research indicates that, through use advanced accurate value this error can reach levels even less than 10 per cent, increasing efficiency Key challenges field include climatic variability difficulties obtaining on soil properties agronomic practices. Despite these challenges, technological advancements present new opportunities for Future focus leveraging Internet Things (IoT) real-time collection impact biological variables yield. An interdisciplinary approach, insights from ecology meteorology, recommended develop innovative predictive exploration methods has potential advance knowledge forecasting support sustainable

Язык: Английский

---