The integration of artificial intelligence (AI) and machine learning (ML) into crop management is transforming modern agriculture by enhancing efficiency, sustainability, and resilience. This review explores the multifaceted applications of AI and ML in key areas such as precision farming, pest and disease management, and harvest optimization. The use of AI-driven predictive analytics allows for more accurate forecasting of crop yields, pest outbreaks, and weather conditions, enabling farmers to make data-driven decisions that optimize resource use and reduce environmental impacts. A significant advancement is the integration of AI and ML with the Internet of Things (IoT) and autonomous farming equipment. These technologies enable real-time monitoring and precise interventions, enhancing productivity and minimizing labor costs. In crop breeding and genomics, AI accelerates the development of resilient crop varieties, which is crucial for adapting to climate change and increasing food demands. Despite the many benefits, challenges such as data quality, infrastructure limitations, and high implementation costs remain. The adoption of AI technologies is uneven, with small-scale farmers in developing regions facing barriers due to limited access to data and resources. Ethical concerns related to data privacy and the digital divide must also be addressed to ensure equitable access to these technologies. The future of AI and ML in agriculture lies in the development of more advanced predictive models, enhanced integration with the IoT, and the widespread use of autonomous farming systems.
Keywords
artificial intelligence
machine learning techniques
crop
data
Author information
Introduction
Agriculture stands as one of the oldest and most crucial sectors of the global economy, serving as the foundation for food, fiber, and fuel production for the world’s population. It employs a significant portion of the global workforce and makes a substantial contribution to economic development. However, the sector is increasingly challenged by issues such as climate change, water scarcity, soil degradation, and the prevalence of pests and diseases. These challenges have led to declining crop yields and heightened food insecurity. The integration of technology offers a promising avenue to revolutionize agricultural practices and address these pressing challenges. Among the most transformative technologies are artificial intelligence (AI) and machine learning (ML). Artificial intelligence, the simulation of human intelligence by machines and computers, encompasses capabilities such as reasoning, learning, and self-correction. Machine learning, a subset of AI, involves the development of algorithms and statistical models that enable machines to perform specific tasks without being explicitly programmed. Artificial intelligence is increasingly integral to daily life, expanding our capacity to modify the environment [1, 2, 3]. In agriculture, AI and ML techniques are instrumental in processing vast amounts of data to extract actionable insights. These insights can optimize the use of resources like fertilizers, water, and pesticides, ultimately reducing costs and enhancing crop yields.
In countries like India, where agriculture accounts for 18% of GDP and employs 50% of the workforce, advancements in the agricultural sector are pivotal. They not only foster rural development but also catalyze structural transformation, leading to broader socio-economic progress [4, 5].
This chapter explores the advancements in agricultural technology and the practical application of these innovations through AI and ML in crop management. It also examines the gaps in the current technological framework that need to be addressed to enhance the overall agricultural system.
Key features of machine learning and artificial learning in crop management
Effective crop management is essential for maintaining healthy crops and maximizing yields, encompassing activities such as soil preparation, planting, irrigation, fertilization, pest and disease control, and harvest. Each of these activities requires careful planning, monitoring, and adjustment to ensure optimal crop growth and productivity. The integration of AI and ML into crop management leverages advanced technologies to optimize resource use, reduce costs, and enhance yields. By adopting these technologies, farmers can not only ensure food security and economic sustainability but also contribute to the global effort to mitigate climate change and environmental degradation.
Predictive analysis
One of the most significant advantages of AI and ML in crop management is their capacity for predictive analytics. The AI algorithms can analyze historical weather data, soil conditions, and crop characteristics to forecast future crop yields and nutrient deficiencies. This predictive capability enables farmers to make informed decisions regarding planting times, irrigation levels, and fertilizer application. Moreover, predictive analytics can identify specific field areas that require additional attention and resources, thereby enhancing overall efficiency and productivity [6, 7]. Crop management relies heavily on accurate weather forecasting, as predictions regarding temperature, rainfall and other weather variables guide decisions on irrigation and fertilization. The integration of AI and ML has the potential to significantly enhance the precision of these forecasts, leading to more effective crop management strategies. By analyzing extensive datasets of weather information, AI and ML algorithms can detect patterns and predict future conditions with greater accuracy. These algorithms consider variables such as temperature, humidity, wind speed, and rainfall, providing more reliable forecasts than traditional methods.
One of the major benefits of employing AI and ML in weather forecasting is the capability to deliver timely updates. This allows farmers to adjust their management practices in response to changing weather conditions, such as irrigating before a predicted drought or postponing planting due to anticipated heavy rainfall. Moreover, AI and ML can offer more localized forecasts, enabling farmers to make precise interventions at the level of individual fields or even plants, which is particularly valuable for managing areas experiencing drought stress.
However, the use of AI and ML in weather forecasting is not without challenges. Data availability remains a significant hurdle. Despite the abundance of weather data from sources like satellite imagery and weather stations, inconsistencies and gaps in coverage can affect the accuracy of the forecasts provided by these technologies [8, 9].
Disease detection
Artificial intelligence and machine learning have revolutionized disease detection in crop management, offering farmers powerful tools to identify and manage plant diseases with greater precision and efficiency. These technologies use a combination of image processing, pattern recognition, and predictive analytics to detect diseases early, often before symptoms become visually apparent to the human eye. The AI and ML models can analyze images of crops captured by drones, satellites, or smartphones to identify disease symptoms. These models are trained on large datasets of images that contain various stages and types of plant diseases. Convolutional neural networks are particularly effective in recognizing patterns associated with specific diseases, such as leaf spots, blights, and rusts. This allows for rapid and accurate disease identification across large fields [10]. Artificial intelligence and machine learning can also predict the likelihood of disease outbreaks by analyzing environmental data such as temperature, humidity, and soil moisture. These predictions help farmers take preventive measures, such as adjusting irrigation practices or applying fungicides at optimal times, thus reducing crop losses. The ML models can predict the spread of diseases like late blight in potatoes by analyzing weather patterns and historical disease data [11]. Artificial intelligence and machine learning are increasingly being integrated with Internet of Things (IoT) devices, such as sensors and cameras, to monitor crop health in real time. These devices collect vast amounts of data that can be processed by AI algorithms to detect diseases at an early stage and recommend specific interventions. This real-time monitoring helps in reducing the need for broad-spectrum pesticides, promoting more sustainable agricultural practices [12]. Despite their potential, AI and ML applications in disease detection face challenges, including the need for extensive training data and the difficulty of distinguishing between similar disease symptoms caused by different pathogens. Furthermore, the effectiveness of these technologies can be limited by the quality of the input data, such as images with varying lighting conditions or angles.
Precision farming
Precision farming is an advanced agricultural practice that involves the use of technology to manage variations in the field accurately, thereby optimizing the use of inputs like water, fertilizer, and pesticides. Artificial intelligence and machine learning play pivotal roles in enhancing precision farming by enabling more accurate decision-making and resource management in crop production. The AI and ML algorithms analyze large datasets from various sources such as soil sensors, satellite imagery, weather stations, and historical crop data to provide insights that help farmers make informed decisions. These algorithms can process complex data to identify patterns and correlations that would be difficult for humans to detect, leading to optimized planting schedules, irrigation levels, and fertilization strategies. Machine learning models can predict the best times to plant or harvest based on weather forecasts and soil conditions [13]. Artificial intelligence and machine learning are integral to variable-rate technologies, which allow farmers to apply inputs like fertilizers and pesticides at variable rates across a field rather than uniformly. This is based on the specific needs of different areas within the field as determined by AI analysis of soil fertility, crop health, and pest presence. By applying resources where they are most needed, farmers can increase yields while reducing waste and environmental impact [14]. AI-driven predictive maintenance helps in the efficient operation of farm machinery by predicting potential failures and optimizing performance. Machine learning algorithms analyze data from sensors embedded in agricultural equipment to predict when maintenance is needed, thereby minimizing downtime and reducing repair costs. This ensures that machinery operates at optimal efficiency, contributing to better overall farm management [15]. Artificial intelligence and machine learning facilitate continuous monitoring of crops through the integration of drones, satellite imagery, and IoT devices. These technologies provide real-time data on crop health, growth rates, and environmental conditions. The AI algorithms process this data to predict yields and suggest timely interventions to maximize productivity. The AI models can detect early signs of stress in crops due to factors like water deficiency or disease, allowing for rapid corrective actions [16]. By optimizing input use and reducing waste, AI and ML contribute to more sustainable farming practices. Precision farming techniques driven by AI help in minimizing the environmental footprint of agriculture by reducing runoff, lowering greenhouse gas emissions, and conserving water. This is particularly important in the context of climate change, where efficient resource use is crucial for maintaining agricultural productivity [17].
Pest management is a critical aspect of crop management, directly impacting crop yields and quality. Traditional methods of pest control often involve the extensive use of chemical pesticides, which can have detrimental effects on the environment and human health. Artificial intelligence and machine learning offer innovative solutions for more sustainable and effective pest management by enabling early detection, precise targeting, and optimized control strategies. The AI and ML algorithms can analyze data from various sources, such as satellite images, drones, and sensors, to detect early signs of pest infestations. By identifying patterns and anomalies in crop health, these technologies can pinpoint the presence of pests before they cause significant damage. Image recognition algorithms can analyze leaf images to detect signs of pest attacks, such as spots or discoloration, allowing for early intervention [18]. The ML models can predict potential pest outbreaks by analyzing historical data on weather conditions, crop health, and pest behavior. These predictions enable farmers to implement preventive measures, such as adjusting planting schedules or applying biological controls, reducing the need for chemical pesticides. Predictive models have been used to forecast locust swarms, enabling timely action to prevent large-scale crop destruction [19]. AI-driven systems can optimize the application of pesticides, ensuring that they are used only where and when necessary. This precision reduces the overall quantity of chemicals used, minimizing environmental impact and costs. Autonomous drones equipped with AI can target specific areas of a field where pests are detected, applying pesticides in a focused manner rather than blanket coverage. This approach not only conserves resources but also reduces the risk of pesticide resistance [20]. Artificial intelligence and machine learning are key components in the implementation of integrated pest management strategies, which combine biological, cultural, mechanical, and chemical methods to manage pests. By providing real-time data and insights, AI helps farmers make informed decisions on the most effective and sustainable pest control methods. This integration leads to more resilient crop management systems that are less reliant on chemical inputs and more adaptive to changing pest dynamics [17]. Although AI and ML offer significant benefits in pest management, challenges remain, particularly in the availability and quality of data. Accurate pest detection and prediction require extensive and high-quality datasets, which can be difficult to obtain in some regions. Additionally, the deployment of AI technologies requires technical expertise and infrastructure, which may not be readily available to all farmers, especially in developing countries. Future research and development should focus on making these technologies more accessible and user-friendly.
Harvest optimization
Harvest optimization is a critical aspect of crop management, where the timing and method of harvest can significantly impact crop yield and quality. Artificial intelligence and machine learning are increasingly being utilized to optimize the harvesting process, ensuring that crops are harvested at the right time and in the most efficient manner possible. The AI and ML algorithms can analyze a wide range of data inputs, including weather patterns, soil conditions, crop growth stages, and historical yield data, to predict the optimal time for harvesting. This helps farmers maximize yield and quality by harvesting crops when they are at their peak. Machine learning models can predict the best harvest time for fruits like grapes and apples, considering factors such as sugar content and ripeness, which are crucial for the quality of the final product [21]. AI-powered robotics and machinery are being developed to automate the harvesting process, especially for labor-intensive crops like fruits and vegetables. These systems use computer vision and deep learning algorithms to identify and pick ripe produce, reducing the need for manual labor and increasing the speed and efficiency of the harvest. AI-driven robots equipped with cameras and sensors can distinguish between ripe and unripe fruits and selectively harvest only those that meet the desired criteria [22]. Artificial intelligence and machine learning are also used to predict crop yields accurately, which is essential for planning harvest logistics, including labor and transportation. By analyzing factors like plant health, growth rates, and environmental conditions, ML models can provide reliable yield estimates, allowing farmers to plan their harvest operations more effectively. This includes optimizing the allocation of resources such as harvesting equipment and labor, ensuring that crops are harvested at the right time and transported efficiently [23]. Artificial intelligence and machine learning play a role in optimizing post-harvest processes, such as sorting, grading, and storage. Artificial intelligence systems can analyze the quality of harvested produce and automatically sort it based on parameters like size, color, and ripeness. This helps in maintaining the quality of the produce and reducing waste. Additionally, ML models can optimize storage conditions, such as temperature and humidity, to extend the shelf life of perishable crops [24]. Although AI and ML offer significant benefits in harvest optimization, challenges remain, including the high cost of technology adoption and the need for extensive training data to develop accurate models. However, ongoing advancements in AI, coupled with increasing accessibility of technology, are expected to overcome these challenges, making harvest optimization more efficient and sustainable in the future.
Integration of sensors and drones with AI and ML for crop management
The integration of sensors and drones with AI and ML is revolutionizing crop management by providing farmers with real-time, precise, and actionable insights. This technological synergy enhances various aspects of crop management, including monitoring, analysis, and decision-making processes. Sensors placed in fields collect data on various environmental factors such as soil moisture, temperature, humidity, and nutrient levels. Drones equipped with multispectral, hyperspectral, and thermal imaging cameras capture detailed aerial images of crops. The AI and ML algorithms analyze this data in real time to monitor crop health, detect anomalies, and identify areas requiring attention. Sensors can detect water stress in plants, while drones can spot early signs of disease or pest infestation, allowing for timely intervention [25, 26]. Artificial intelligence and machine learning enable precision agriculture by analyzing data from sensors and drones to optimize input use. This includes the precise application of water, fertilizers, and pesticides, which reduces waste and minimizes environmental impact. Variable-rate technology guided by AI can adjust the application of inputs based on the specific needs of different areas within a field, improving efficiency and crop yields [27]. The data collected by sensors and drones are fed into AI and ML models that predict future crop performance, pest outbreaks, and weather conditions. This predictive capability helps farmers make informed decisions about planting, irrigation, and harvesting schedules. The ML models can predict when a particular area of a field is likely to be affected by pests, enabling farmers to apply preventive measures before the infestation occurs [28]. Drones equipped with AI-powered image recognition algorithms can automatically assess crop conditions across large areas, identifying issues such as nutrient deficiencies, water stress, and disease symptoms. This automation reduces the need for manual scouting, saving time and labor while increasing the accuracy of assessments. Drones can map crop biomass and identify areas with lower productivity, enabling targeted interventions [29]. By optimizing resource use and reducing the need for chemical inputs, the integration of sensors, drones, and AI/ML contributes to more sustainable agricultural practices. This approach not only improves productivity but also reduces the environmental footprint of farming, which is crucial in the context of climate change and resource scarcity [30].
Challenges of AI and ML in crop management
Although AI and ML offer promising solutions for improving crop management, several challenges need to be addressed to fully harness their potential. These challenges span technical, economic, and social dimensions, which are critical for the successful integration of AI and ML into agriculture. The AI and ML algorithms rely heavily on large datasets for training and accurate predictions. However, in agriculture, data collection can be inconsistent, especially in regions with limited technological infrastructure. The quality of data can also vary significantly, leading to biases in models. Moreover, integrating data from multiple sources (e.g., weather data, soil sensors, drone imagery) can be complex due to differences in data formats and scales [31, 32]. The implementation of AI and ML in crop management requires specialized knowledge in both agriculture and data science. Farmers and agronomists often lack the necessary technical expertise to deploy and maintain these systems effectively. Additionally, the complexity of AI models, such as deep learning, can make them difficult to interpret and trust, which is crucial for decision-making in agriculture [33]. The adoption of AI and ML technologies in agriculture involves significant upfront investment in hardware (e.g., sensors, drones) and software. For small-scale farmers, the costs can be prohibitive, limiting the widespread adoption of these technologies. Additionally, ongoing maintenance and updates can add to the financial burden, making it challenging for farmers in developing countries to access these tools [34]. In many rural areas, particularly in developing countries, the lack of infrastructure such as reliable internet connectivity, electricity, and technical support poses a significant barrier to the adoption of AI and ML. Without the necessary infrastructure, farmers cannot effectively implement or benefit from AI-driven crop management solutions [35]. The use of AI and ML in agriculture raises ethical concerns related to data privacy, job displacement, and the digital divide. Farmers may be reluctant to share data due to concerns about privacy and data ownership. Additionally, the automation of tasks traditionally performed by laborers could lead to job losses, particularly in regions where agriculture is a major source of employment. The digital divide also exacerbates inequalities, with wealthier farmers being able to access advanced technologies while others are left behind [36]. The AI and ML models often need to be customized for specific crops, regions, and farming practices. This requirement makes scaling these technologies across different agricultural systems challenging. Moreover, the heterogeneity of agricultural practices globally means that a solution effective in one context may not work in another, necessitating extensive localization efforts [37].
Future directions of AI and ML in crop management
The future of AI and ML in crop management is promising, with potential advancements poised to revolutionize agriculture by enhancing efficiency, sustainability, and productivity. Several key areas are likely to shape the future of AI and ML in this field. The future will likely see more sophisticated predictive models that can accurately forecast crop yields, pest outbreaks, and weather conditions with greater precision. These models will leverage vast datasets, including genomic, phenotypic, and environmental data, to provide more reliable and granular predictions. Improved AI algorithms will help farmers make more informed decisions, reducing risks associated with climate variability and market fluctuations [38]. The integration of AI and ML with the IoT will continue to expand, leading to the development of fully automated smart farming systems. These systems will utilize real-time data from connected sensors and devices to monitor crop health, soil conditions, and environmental factors. AI-driven analytics will enable real-time decision-making, optimizing inputs like water, fertilizers, and pesticides, and enhancing the overall efficiency of farming operations [37, 39]. Artificial intelligence and machine learning will play a crucial role in the development of autonomous farming equipment, such as drones and robots, capable of performing tasks like planting, weeding, and harvesting with minimal human intervention. These machines will use AI to navigate fields, identify crops, and perform precise agricultural tasks, thereby reducing labor costs and increasing productivity. Advances in computer vision and deep learning will further enhance the capabilities of these autonomous systems [22, 40]. Artificial intelligence and machine learning will increasingly be used in crop breeding programs to accelerate the development of high-yielding, climate-resilient, and disease-resistant crop varieties. By analyzing large datasets from genomic studies, AI can identify desirable traits and predict the performance of new hybrids, significantly speeding up the breeding process. This will be particularly important in addressing the challenges posed by climate change and the need for sustainable agricultural practices [41, 42]. Artificial intelligence and machine learning will be pivotal in developing sustainable agricultural practices that reduce the environmental footprint of farming. Future AI-driven systems will focus on optimizing resource use, minimizing waste, and promoting regenerative practices. Precision agriculture techniques enabled by AI can reduce the overuse of fertilizers and pesticides, leading to more sustainable crop production and less environmental degradation [30, 43]. As AI and ML technologies evolve, they will enable more personalized farming solutions tailored to the specific needs of individual farms. These solutions will consider unique factors such as local soil conditions, climate, and crop types to provide customized recommendations for each farmer. This level of personalization will help small and medium-sized farms to optimize their operations and compete with larger agricultural enterprises. The development of ethical AI frameworks will be crucial to ensure that the benefits of AI and ML in crop management are distributed equitably. Future research will likely focus on addressing issues such as data privacy, algorithmic transparency, and the digital divide, ensuring that AI technologies are accessible and beneficial to all farmers, regardless of their scale or location [36].
Conclusion
The integration of AI and ML into crop management has ushered in a new era of precision agriculture, offering significant potential to enhance productivity, sustainability, and resilience in the face of growing challenges such as climate change and food security. Through advancements in predictive analytics, AI and ML have enabled more accurate forecasting of crop yields, pest outbreaks, and weather patterns, thereby allowing farmers to make informed decisions and optimize resource use. The synergy among AI, ML, and emerging technologies such as the IoT and autonomous farming equipment promises to further revolutionize agriculture. These technologies facilitate real-time monitoring and decision-making, automate labor-intensive tasks, and personalize farming solutions to the specific needs of individual farms. Moreover, the application of AI and ML in crop breeding and genomics is accelerating the development of resilient crop varieties, contributing to the long-term sustainability of agricultural practices.
However, the widespread adoption of AI and ML in crop management is not without its challenges. Issues such as data quality and availability, technical complexity, high costs, and infrastructure limitations pose significant barriers, particularly for small-scale farmers in developing regions. In addition, ethical considerations related to data privacy, job displacement, and the digital divide must be addressed to ensure that the benefits of AI and ML are equitably distributed.
Looking ahead, the future of AI and ML in crop management is likely to be shaped by ongoing advancements in technology, the development of ethical AI frameworks, and the creation of scalable solutions that are accessible to all farmers. By overcoming the existing challenges and leveraging the full potential of AI and ML, the agricultural sector can achieve greater efficiency, sustainability, and resilience, ultimately contributing to global food security and environmental conservation.
Acknowledgments
The support and help provided by Dr. M. Muzamil (Assistant Professor) is highly appreciated and duly acknowledged. The authors also acknowledge the use of QuillBot for language polishing of the manuscript.
This research did not receive external funding from any agencies.
Ethical statement
Not Applicable.
Data availability statement
Source data is not available for this article.
Conflict of interest
The authors declare no conflict of interest.
References
1.
KundaliaK, PatelY and ShahM. Multi-label movie genre detection from a movie poster using knowledge transfer learning. Augmented Human Research. 2020;5:1–9.
2.
GandhiM, KamdarJ and ShahM. Preprocessing of non-symmetrical images for edge detection. Augmented Human Research. 2020;5(1):10.
3.
AhirK, GovaniK, GajeraR and ShahM. Application on virtual reality for enhanced education learning, military training and sports. Augmented Human Research. 2020;5:1–9.
4.
MogiliUR and DeepakBBVL. Review on application of drone systems in precision agriculture. Procedia Computer Science. 2018;133:502–509
5.
ShahG, ShahA and ShahM. Panacea of challenges in real-world application of big data analytics in healthcare sector. Journal of Data, Information and Management. 2019;1:107–116
6.
BaliN, SinglaA. Emerging trends in machine learning to predict crop yield and study its influential factors: A survey. Arch Comput Methods Eng. 2022;29(1):95–112.
7.
BoseS, BanerjeeS, KumarS, SahaA, NandyD, HazraS. Review of applications of artificial intelligence (AI) methods in crop research. J Appl Genet. 2024;65(2):225–240.
8.
da Rocha MirandaJ, de Carvalho AlvesM, PozzaEA, NetoHS. Detection of coffee berry necrosis by digital image processing of landsat 8 oli satellite imagery. Int J Appl Earth Obs Geoinf. 2020;85: 101983.
9.
SambasivamG., OpiyoGD. A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks. Egypt Inform J. 2021;22(1):27–34.
10.
FerentinosKP. Deep learning models for plant disease detection and diagnosis. Comput Electron Agric. 2018;145: 311–318.
11.
MahleinAK. Plant disease detection by imaging sensors–parallels and specific demands for precision agriculture and plant phenotyping. Plant Dis. 2016;100(2):241–251.
12.
JafarA, BibiN, NaqviRA, Sadeghi-NiarakiA, JeongD. Revolutionizing agriculture with artificial intelligence: plant disease detection methods, applications, and their limitations. Front Plant Sci. 2024;15: 1356260.
13.
LingwalS, BhatiaKK, SinghM. A novel machine learning approach for rice yield estimation. J Exp Theor Artif Intell. 2024;36(3):337–356.
14.
SinghS, JainP. Applications of artificial intelligence for the development of sustainable agriculture. In: Agro-biodiversity and agri-ecosystem management. Singapore: Springer Nature Singapore; 2022. p. 303–322.
15.
KistenM, EzugwuAE, OlusanyaMS. Explainable artificial intelligence model for predictive maintenance in smart agricultural facilities. IEEE Access. 2024;12: 24348–24367.
16.
LiakosKG, BusatoP, MoshouD, PearsonS, BochtisD. Machine learning in agriculture: A review. Sensors. 2018;18(8):2674.
17.
JhaK, DoshiA, PatelP, ShahM. A comprehensive review on automation in agriculture using artificial intelligence. Artif Intell Agric. 2019;2: 1–12.
18.
KamilarisA and Prenafeta-BolduFX. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture. 2018;147:70–90
19.
RahmanSM, RaviG. Role of artificial intelligence in pest management. Current Topics Agric Sci. 2022;7: 64–81.
20.
DominguesT, BrandãoT, FerreiraJC. Machine learning for detection and prediction of crop diseases and pests: A comprehensive survey. Agriculture. 2022;12(9):1350.
21.
KoiralaA, WalshKB, WangZ, McCarthyC. Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ‘MangoYOLO’. Precis Agric. 2019;20(6):1107–1135.
22.
BacCW, Van HentenEJ, HemmingJ, EdanY. Harvesting robots for high-value crops: State-of-the-art review and challenges ahead. J Field Robot. 2014;31(6):888–911.
23.
ZhengX, GongT, LiX, LuX. Generalized scene classification from small-scale datasets with multitask learning. IEEE Trans Geosci Remote Sens. 2021;60: 1–11.
24.
VasconezJP, KantorGA, CheeinFAA. Human–robot interaction in agriculture: A survey and current challenges. Biosyst Eng. 2019;179: 35–48.
25.
ZhangC, KovacsJM. The application of small unmanned aerial systems for precision agriculture: a review. Precis Agric. 2012;13: 693–712.
26.
WahabI, HallO, JirströmM. Remote sensing of yields: Application of UAV imagery-derived NDVI for estimating maize vigor and yields in complex farming systems in sub-Saharan Africa. Drones. 2018;2(3):28.
27.
ShamshiriR, KalantariF, TingKC, ThorpKR, HameedIA, WeltzienC, Advances in greenhouse automation and controlled environment agriculture: A transition to plant factories and urban agriculture. Int J Agric Biol Eng. 2018;11(1):1–22.
28.
JinX, LiuS, BaretF, HemerléM, ComarA. Estimates of plant density of wheat crops at emergence from very low altitude UAV imagery. Remote Sens Environ. 2017;198: 105–114.
29.
SishodiaRP, RayRL, SinghSK. Applications of remote sensing in precision agriculture: A review. Remote Sens. 2020;12(19):3136.
30.
TsourosDC, BibiS, SarigiannidisPG. A review on UAV-based applications for precision agriculture. Information. 2019;10(11):349.
31.
KamilarisA, Prenafeta-BolduFX. Deep learning in agriculture: A survey. Comput Electron Agric. 2018;147: 70–90.
32.
BhatSA, HuangNF. Big data and AI revolution in precision agriculture: Survey and challenges. IEEE Access. 2021;9: 110209–110222.
33.
Van EsH, WoodardJ. Innovation in agriculture and food systems in the digital age. In: The global innovation index. Ithaca, NY: Cornell University; 2017.
34.
OliveiraRCD, SilvaRDDSE. Artificial intelligence in agriculture: benefits, challenges, and trends. Appl Sci. 2023;13(13):7405.
35.
KumariS, JebleS, PatilYB. Barriers to technology adoption in agriculture-based industry and its integration into technology acceptance model. Int J Agric Res Governance Ecology. 2018;14(4):338–351.
36.
BronsonK. Looking through a responsible innovation lens at uneven engagements with digital farming. NJAS-Wageningen J Life Sci. 2019;90: 100294.
37.
WolfertS, GeL, VerdouwC, BogaardtMJ. Big data in smart farming–A review. Agric Syst. 2017;153: 69–80.
38.
AdliHK, RemliMA, Wan Salihin WongKNS, IsmailNA, González-BrionesA, CorchadoJM, Recent advancements and challenges of AIoT application in smart agriculture: A review. Sensors. 2023;23(7):3752.
39.
TzounisA, KatsoulasN, BartzanasT, KittasC. Internet of things in agriculture, recent advances and future challenges. Biosyst Eng. 2017;164: 31–48.
40.
Lowenberg-DeBoerJ, HuangIY, GrigoriadisV, BlackmoreS. Economics of robots and automation in field crop production. Precis Agric. 2020;21(2):278–299.
