Computers and Electronics in Agriculture, Год журнала: 2025, Номер 231, С. 109917 - 109917
Опубликована: Янв. 22, 2025
Язык: Английский
Machines, Год журнала: 2023, Номер 11(8), С. 774 - 774
Опубликована: Июль 25, 2023
Agriculture 5.0 refers to the next phase of agricultural development, building upon previous digital revolution in agrarian sector and aiming transform industry be smarter, more effective, ecologically conscious. Farming processes have already started becoming efficient due development technologies, including big data, artificial intelligence (AI), robotics, Internet Things (IoT), virtual augmented reality. Farmers can make most resources at their disposal thanks this data-driven approach, allowing them effectively cultivate sustain crops on arable land. The European Union (EU) aims food systems fair, healthy, environmentally sustainable through Green Deal its farm-to-fork, soil, biodiversity strategies, zero pollution action plan, upcoming use pesticides regulation. Many historical synthetic are not currently registered EU market. In addition, continuous a limited number active ingredients with same mode scales up pests/pathogens/weed resistance potential. Increasing plant protection challenges as well having fewer chemical apply require innovation smart solutions for crop production. Biopesticides tend pose risks human health environment, efficacy depends various factors that cannot controlled traditional application strategies. This paper disclose contribution robotic ecosystems, highlighting both limitations technology. Specifically, work documents current threats agriculture (climate change, invasive pests, diseases, costs) how robotics AI act countermeasures deal such threats. Finally, specific case studies intelligent analyzed, architecture our decision system is proposed.
Язык: Английский
Процитировано
99
IEEE Access, Год журнала: 2023, Номер 11, С. 145813 - 145852
Опубликована: Янв. 1, 2023
The increasing food scarcity necessitates sustainable agriculture achieved through automation to meet the growing demand. Integrating Internet of Things (IoT) and Wireless Sensor Networks (WSNs) is crucial in enhancing production across various agricultural domains, encompassing irrigation, soil moisture monitoring, fertilizer optimization control, early-stage pest crop disease management, energy conservation. application protocols such as ZigBee, WiFi, SigFox, LoRaWAN are commonly employed collect real-time data for monitoring purposes. Embracing advanced technology imperative ensure efficient annual production. Therefore, this study emphasizes a comprehensive, future-oriented approach, delving into IoT-WSNs, wireless network protocols, their applications since 2019. It thoroughly discusses overview IoT WSNs, architectures summarization protocols. Furthermore, addresses recent issues challenges related IoT-WSNs proposes mitigation strategies. provides clear recommendations future, emphasizing integration aiming contribute future development smart systems.
Язык: Английский
Процитировано
69
Smart Agricultural Technology, Год журнала: 2024, Номер 7, С. 100416 - 100416
Опубликована: Фев. 17, 2024
In general, agriculture plays a crucial role in human survival as primary source of food, alongside other sources such fishing. Unfortunately, global warming and environmental issues, particularly less privileged nations, hamper the Agricultural sector. It is estimated that range 720 to 811 million individuals experienced food insecurity. Today's faced significant difficulties obstacles, do surveillance monitoring systems (climate, energy, water, fields, works, cost, fertilizers, diseases, etc.). The COVID-19 pandemic has exacerbated susceptibilities insufficiencies inherent worldwide systems. Current agricultural practices tend prioritize productivity profitability over conservation long-term sustainability. To establish sustainable capable meeting needs projected ten billion people next 30 years, substantial structural automation changes are required. However, these obstacles can be overcome by employing smart technologies advancing Artificial Intelligence (AI) operations. AI believed contribute sustainability goals multiple sectors, incorporation renewable energy. anticipated will revitalize both existing new fields retrofitting, installing integrating automatic devices instruments. This paper presents comprehensive review most promising novel applications industry. Furthermore, transition precision investigated.
Язык: Английский
Процитировано
66
Neural Computing and Applications, Год журнала: 2024, Номер 36(11), С. 5695 - 5714
Опубликована: Янв. 11, 2024
Abstract Crop Recommendation Systems are invaluable tools for farmers, assisting them in making informed decisions about crop selection to optimize yields. These systems leverage a wealth of data, including soil characteristics, historical performance, and prevailing weather patterns, provide personalized recommendations. In response the growing demand transparency interpretability agricultural decision-making, this study introduces XAI-CROP an innovative algorithm that harnesses eXplainable artificial intelligence (XAI) principles. The fundamental objective is empower farmers with comprehensible insights into recommendation process, surpassing opaque nature conventional machine learning models. rigorously compares prominent models, Gradient Boosting (GB), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), Multimodal (MNB). Performance evaluation employs three essential metrics: Mean Squared Error (MSE), Absolute (MAE), R-squared (R2). empirical results unequivocally establish superior performance XAI-CROP. It achieves impressively low MSE 0.9412, indicating highly accurate yield predictions. Moreover, MAE 0.9874, consistently maintains errors below critical threshold 1, reinforcing its reliability. robust R 2 value 0.94152 underscores XAI-CROP's ability explain 94.15% data's variability, highlighting explanatory power.
Язык: Английский
Процитировано
39
Food Packaging and Shelf Life, Год журнала: 2024, Номер 43, С. 101287 - 101287
Опубликована: Апрель 22, 2024
Язык: Английский
Процитировано
25
Computers and Electronics in Agriculture, Год журнала: 2024, Номер 224, С. 109229 - 109229
Опубликована: Июль 10, 2024
Язык: Английский
Процитировано
24
Expert Systems, Год журнала: 2023, Номер unknown
Опубликована: Июнь 25, 2023
Abstract Recently, the global food supply chain has become increasingly complex, and its scalability grown. From farm to fork, performance of food‐producing systems is influenced by significant changes in environment, population economy. These may cause an increase fraud safety hazards hence, harm human health. Adopting artificial intelligence (AI) technology one strategy reduce these hazards. Although use AI been rising numerous industries, such as precision nutrition, self‐driving cars, agriculture, medicine safety, much what do a black box due poor explainability. This study covers cases risk prediction using explainable (XAI) techniques, LIME, SHAP WIT. We aimed interpret predictions machine learning model with aid technologies. The case was performed on dataset adulteration/fraud notifications retrieved from Rapid Alert System for Food Feed system economically motivated adulteration database. A deep built based this XAI tools have investigated proposed model. Both features shortcomings current area presented.
Язык: Английский
Процитировано
35
Smart Agricultural Technology, Год журнала: 2023, Номер 6, С. 100350 - 100350
Опубликована: Ноя. 1, 2023
Food safety hazards can be discovered and avoided using XAI blockchain technology. The immutable transparent ledger of technology used to maintain track perishable food items, allowing for more rapid precise detection contamination immediate removal from shelves. Using technology, smart agriculture streamline the supply chain by connecting farmers directly with their customers. As a result, community members may confident in meeting own dietary needs. Combining XAI, blockchain, has far-reaching societal economic implications. More efficiency, openness, sustainability might benefit farmers, consumers, world. This study provides detailed bibliometric overview visualization integrating two prominent promising technologies, explainable AI Blockchain, into Smart Agriculture. In this study, author implemented analysis four phases, each phase, chose different strings, which provided results. 2479 articles are taken "smart agriculture", 103 "Smart blockchain", 37 "blockchain explainable," finally, seven AI". mapping program VOSviewer is Network analysis. uses co-occurrence, co-citation, bibliographic coupling employed uncover significant focus areas authors publications. By variety publications, research was conducted on vital topics integration; as consequence, influence collaborations began take place, ultimately leading development.
Язык: Английский
Процитировано
33
Computational Intelligence, Год журнала: 2024, Номер 40(1)
Опубликована: Янв. 14, 2024
Abstract Agriculture serves as the predominant driver of a country's economy, constituting largest share nation's manpower. Most farmers are facing problem in choosing most appropriate crop that can yield better based on environmental conditions and make profits for them. As consequence this, there will be notable decline their overall productivity. Precision agriculture has effectively resolved issues encountered by farmers. Today's may benefit from what's known precision agriculture. This method takes into account local climate, soil type, past yields to determine which varieties provide best results. The explainable artificial intelligence (XAI) technique is used with radial basis functions neural network spider monkey optimization classify suitable crops underlying conditions. XAI technology would assets transparency prediction model deciding farms, taking variety geographical operational criteria. proposed assessed using standard metrics like precision, recall, accuracy, F1‐score. In contrast other cutting‐edge approaches discussed this study, shown fair performance approximately 12% accuracy than models considered current study. Similarly, improvised 10%, recall 11%, F1‐score 10%.
Язык: Английский
Процитировано
16
Agriculture, Год журнала: 2024, Номер 14(3), С. 481 - 481
Опубликована: Март 16, 2024
The interplay of machine learning (ML) and deep (DL) within the agroclimatic domain is pivotal for addressing multifaceted challenges posed by climate change on agriculture. This paper embarks a systematic review to dissect current utilization ML DL in agricultural research, with pronounced emphasis impacts adaptation strategies. Our investigation reveals dominant reliance conventional models uncovers critical gap documentation methodologies. constrains replicability, scalability, adaptability these technologies research. In response challenges, we advocate strategic pivot toward Automated Machine Learning (AutoML) frameworks. AutoML not only simplifies standardizes model development process but also democratizes expertise, thereby catalyzing advancement incorporation stands significantly enhance research adaptability, overall performance, ushering new era innovation practices tailored mitigate adapt change. underscores untapped potential revolutionizing propelling forward sustainable efficient solutions that are responsive evolving dynamics.
Язык: Английский
Процитировано
14