Quantum AI-driven precision soil health monitoring and automated crop disease detection using advanced analytical models

Introduction

Precision agriculture has revolutionized farming through its innovative application of technology to enhance crop production, resource use, and environmental sustainability. With the help of artificial intelligence (AI), Internet of Things (IoT), and analytics, farmers are now able to base their decision-making on the basis of soil characteristics, weather patterns, and other crop growth parameters (P. Raj et al., 2024; H. Mishra, 2025) [3,25] . This development is important to meet the increasing food demands globally while ensuring minimal impact on the environment. One of the major elements that affect crop production is soil health since it determines the nutrient status, crop yield, and overall ecosystem stability. Conventional methods of soil analysis are not only tedious but also difficult to implement as well. The development of new soil health assessment systems using AI has significantly enhanced accuracy through sensors' predictive power of soil characteristics such as pH levels, moisture, and nutrients (R. Gera & A. Jain, 2025; E. Vadivel et al., 2025) [1,24] . Nonetheless, some challenges remain. The recent emergence of smart agriculture technology has enabled the introduction of smart sensors for continuous monitoring of soils. Smart agriculture involves the generation of large heterogeneous amounts of data, which require sophisticated analysis methods to interpret (S. Selvaraju et al., 2025; C. Sankari et al., 2025) [30,34] . The application of AI predictive models has improved the precision of soil nutrients evaluation and irrigation planning, making the processes more environmentally friendly (P. Malathi & K. Senbagam, 2024; S. Ali et al., 2025) [35,38] . Moreover, the development of automatic crop disease detection tools has become an important research direction due to its potential use for minimizing crop damage and maximizing yield quality. Convolutional neural networks are actively employed for disease diagnosis on basis of leaf images with high success rate achieved (M. Sharma et al., 2025; N. Agarwal et al., 2025) [6,27] . Early-stage detection of crop diseases and environmental generalization is an open problem currently. Further improvements have been made with the adoption of UAVs, drones, and remote sensing technologies that enable wide-scale crop monitoring and inspection (Y. Xing et al., 2026; C. Ranjan et al., 2025) [7,21] . They help detect diseases in time, thanks to realtime data provided by such technologies. The processing of this kind of data requires efficient computational algorithms and models. Moreover, artificial intelligence can be successfully combined with robotics and autonomous control mechanisms for automating different agricultural processes. Robotic devices powered by artificial intelligence can perform crop monitoring, fertilizing, and disease detection without requiring many operators. Thus, the productivity and www.extensionjournal.com efficiency of agriculture increase greatly while minimizing human work and associated labor expenses (M. Vinoth & V. Rangasamy, 2025; J. Osei-Asiamah et al., 2025) [2,22] . Such robotic mechanisms become components of intelligent agricultural systems, but at the same time, their operation is based on classical computing methods. Classical AI algorithms and machine learning models are successful enough when used in agriculture. Nevertheless, there are limitations to them because they cannot process highdimensional data efficiently, deal with nonlinear relations between variables, and suffer from high computational cost and low generalization (K. Agrawal & N. Kumar, 2025; V. Sunil et al., 2025) [26,32] . The application of quantum computing offers an opportunity to overcome such disadvantages due to quantum parallelism and quantum superposition. Models of QML, such as QSVM and VQC models, have shown their capacity for efficient processing of complicated datasets compared to the existing classical models (S. Jain et al., 2026) [10] . Such models can contribute to feature space improvement and better classification. One may suggest that the integration of Quantum AI with precision agriculture would become a new research direction. The combination of quantum computing and artificial intelligence would allow implementing quantumenhanced models to monitor soil conditions, detect diseases, and perform other tasks related to soil analysis and monitoring of plants' state (A. Shah et al., 2026; G. W. Vuister et al., 2026) [5,13] . It should be mentioned that advances in the sphere of omics technologies and digital twins allow creating an integrated model, which would cover information on biological, chemical, and environmental factors. This technological solution would enable a deep investigation of soil-plant interaction and formulation of optimal agricultural practices (D. [14,31] . However, such integration requires appropriate computational tools. Explainable AI (XAI), which contributes towards enhancing transparency and interpretability in agricultural decisionmaking systems, has recently gained attention in the literature. XAI helps increase adoption rates by assisting farmers in understanding the logic behind the decisions (S. Jain et al., 2026). It will be interesting to see how this topic can be integrated into the quantum computing context in future research. In addition, the implementation of AI-based precision agriculture has proved efficient in increasing crop yields, resource utilization, and sustainability. Datadriven models provide for optimized processes related to irrigation, fertilization, and pest elimination, thus contributing to sustainability in agriculture (G. Anushree et al., 2025; R. Singh et al., 2025) [19,23] .However, it needs to be noted that the integration of soil quality measurement and plant diseases detection within one quantum AI solution constitutes another research gap in the field. Previous studies usually consider soil quality or crop diseases on their own without providing comprehensive solutions to monitor both phenomena (J. Patel & T. Bhatt, 2026; S. K. Sharma, 2024) [37 11] . [23,38] . Besides, precision agriculture plays a role in climate-resilient agriculture since it facilitates flexible response to environmental variability and changes in climate (D. [1,24,30] .

Importance of precision agriculture in modern farming

Limitations of classical AI/ML approaches

In spite of the remarkable achievements attained by classical AI techniques in agriculture, there are various limitations that prevent the successful deployment of these algorithms to solve real-world problems in the sector. Conventional ML algorithms have been known to have difficulty dealing with heterogenous agricultural data characterized by high dimensionality, and thus they tend to overfit and exhibit poor generalization and high computational cost (K. Agrawal & N. Kumar, 2025; V. Sunil et al., 2025) [26,32] . The analysis of massive amounts of data obtained from IoT, drones, and satellite technologies also poses a challenge to the real-time application of decisions because it needs heavy computations (M. Vinoth & V. Rangasamy, 2025; J. Osei-Asiamah et al., 2025) [2,22] . Classical DL algorithms used for detecting diseases in plants require labeled datasets as well as longer training times (M. Sharma et al., 2025; N. Agarwal et al., 2025) [6,27] . Finally, some AI models do not provide interpretable results, hence undermining their trustworthiness (S. Jain et al., 2026; S. K. Sharma, 2024) [10,37] .

Emergence of Quantum Artificial Intelligence

Quantum AI has been introduced to counter some of the disadvantages associated with the classic computational approach through concepts such as superposition, entanglement, and quantum parallelism. It is evident that quantum machine learning models, including variational quantum circuits (VQC) and quantum support vector machines (QSVM), perform better in the processing of complex highdimensional data compared to classic algorithms (S. Jain et al., 2026) [10] . This model improves the representation of features spaces as well as optimization, and can be used to predict soil health as well as the identification of diseases in crops (A. Shah et al., 2026; G. W. Vuister et al., 2026) [5,13] . Further, the use of Quantum AI in combination with other advanced analytical techniques allows for efficient prediction and computation, especially within data-rich industries such as agriculture (M. Tariq et al., 2026; S. Khan et al., 2026) [8,18] . With continuous technological advancements in the field of www.extensionjournal.com quantum computing, applications in agriculture are set to change the future of decisionmaking systems to allow for intelligent farming (R. Singh et al., 2025; C. V. S. Babu & M. Thrisha, 2026) [19,36] .

Literature Review

The use of Artificial Intelligence (AI) in agriculture has brought about major shifts from conventional agriculture to smart agriculture, with AI algorithms being used to monitor soil condition, crops, and even predict yields for the benefit of decision making. It has been indicated that soil health management system with the help of AI leads to better nutrient optimization and higher crop production due to intelligent data processing (R. Gera & A. Jain, 2025; P. Raj et al., 2024) [1,3] . In addition, AI techniques have been effectively utilized in robotic agriculture systems, where operations such as planting, irrigation, and harvesting have been made easy with the use of robots (M. Vinoth & V. Rangasamy, 2025; J. Osei-Asiamah et al., 2025) [2,22] . The table 1 shows the Comprehensive Review of AI-Driven Precision Agriculture and Soil Health Monitoring Studies. AI in Soil Health Management for Health Food Production R. Gera & A. Jain (2025) [1] AI improves soil nutrient optimization and enhances food quality production Lack of real-time adaptive systems

ML-based soil analytics

[2] AI-driven Robotics in Agriculture M. Vinoth & V. Rangasamy (2025) [2] Robotics enhances automation in farming operations

Limited integration with soil analytics AI-driven robotic systems [3] Artificial Intelligence for Precision Agriculture P. Raj et al. (2024) [3] AI enables precision farming and yield prediction Scalability issues in large farms ML/DL-based predictive models [4] AI-Driven Agro-sage for Precision Agriculture T. V. Reddy et al.

(2024) [4] Smart systems improve agricultural decision-making Limited multi-source data integration AI-based decision support system [5] Omics-driven Soil Bioremediation A. Shah et al. (2026) [5] Integration of sensors and omics enhances soil remediation

High computational complexity

Multi-omics + AI models [6] AI in Disease Detection in Plants M. Sharma et al.

(2025) [6] AI detects plant diseases with high accuracy [7,21] . AI-enabled sensor technologies and digital twin applications have also been adopted for soil condition modeling and predictions of crop responses to changing environments, providing more sustainable solutions in resource use (A. [5,31] . Soil condition measurement technologies have seen developments through the integration of machine learning and deep learning approaches into the evaluation of complex soil parameters. Highly accurate methods of analysis include hyperspectral imaging and AI explainable models (S. Jain et al., 2026; E. Vadivel et al., 2025) [10,24] [10] [24] [10,24] . In addition, there have been developments in AI prediction models utilizing methods like XGBoost and Light GBM for better resource use, particularly through optimizing irrigation and fertilization strategies (C. [13,14] . Further, the utility of generative AI along with innovative sensor technologies in determining soil organic carbon content and related parameters has also been evaluated (R. Singh et al., 2025; T. Loima et al., 2025) [17] . [38,39] . However, it should be acknowledged that there is a gap in the research concerning the design of an all-inclusive framework for monitoring the condition of soils and detecting diseases via quantum methods. Sharma, 2024) [34,37] . Electrical conductivity (0. [27] . Figure 1 shows the proposed methodology used in this research paper. XGBoost, and LightGBM algorithms have proven to be highly accurate in predictions with a high accuracy of between 85-92 percent in soil nutrient prediction tasks (C. Sankari et al., 2025; K. Agrawal and N. Kumar, 2025) [26,34] . Deep learning methods also enhance predictive accuracy by detecting nonlinear correlations in soil data, which decrease the prediction error to mean squared error (MSE) values as small as 0.02-0.05 (S. Jain et al., 2026; R. Singh et al., 2025) [10,19] . These models allow processing of largescale agricultural data efficiently. Hyperspectral imaging has turned out to be one of the sophisticated methods of analyzing soil in detail due to the ability to bring out reflectance data at hundreds of spectral bands which are usually in the 400-2500 nm range. The method can be used to estimate soil properties including organic carbon content (0.530 percent), moisture with prediction accuracies of more than 90 percent (S. Jain et al., 2026; A. Shah et al., 2026) [5] . Fusion of hyperspectral data and AI models boosts feature identification and reliability of soil health projections (G. W. Vuister et al., 2026; M. Tariq et al., 2026) [13,18] . Soil health monitoring is also becoming popular in digital twin technology, which allows the development of virtual analogs of farm fields. These models mimic conditions of the soil and forecast the change with regard to the environmental factors and agriculture. It has been demonstrated that the systems based on digital twins can enhance the efficiency of soil management by 2030 percent and cut down on the use of resources by 1525 percent (S. B. Choudhury et al., 2024; D. Thingujam et al., 2025) [14,31] . Digital twins offer predictive analytics based on real-time sensor data, which can be used to make actionable insights in precision agriculture.Irrespective of these, sensor calibration issues (±2-5% error), heterogeneity of the data and fluctuations in the environment still pose a challenge to the accuracy of the soil health monitoring systems. To address these constraints and enhance the strength of predictions, it is necessary to integrate multimodal sources of data, such as IoT sensors, remote sensing, and omics technologies (R. Kalirethinam et al., 2025; V. Sunil et al., 2025) [32,33] . New strategies such as Quantum AI and hybrid analysis models suggest having a promising solution to increase the efficiency and accuracy of methods in soil health monitoring, which leads to next-generation precision agricultural systems (M. Tariq et al., 2026; C. V. S. Babu and M. Thrisha, 2026) [36]

Conceptual Framework

The conceptual framework proposed for this research project aims at developing a combined analytical architecture capable of incorporating both precision soil health monitoring capabilities and crop disease recognition through automation. Figure 2 shows the Proposed Quantum AI-Based Precision Agriculture Workflow. [3,9,23] . The framework proposed herein has been designed to comprise several key stages of data processing. Specifically, at the first stage, it is necessary to consider the data acquisition process, during which heterogeneous data can be obtained via the utilization of IoT sensors, UAV, remote sensing technologies, etc. In particular, data pertaining to moisture levels (10-35%), pH levels (5.5-7.5), and other essential parameters can be collected through the use of sensors. As for the drone-based technology, this method will allow gathering information about plants in the form of high-resolution images (Y. [26,27,30] . Layer three incorporates a Quantum AI-based analytical engine that combines conventional machine learning models with quantum-enhanced models like Variational Quantum Circuit (VQC) and Quantum Support Vector Machine (QSVM). This approach helps efficiently process highdimensional data sets, thus improving prediction accuracy by providing better feature space representation in terms of the use of such quantum phenomena as superposition and entanglement.

Thus, quantum AI models solve the problem with computational efficiency of conventional machine learning models (S. [5,10,13] . Finally, the decision support and visualization module enables the provision of useful information to the farmer and relevant stakeholders. The module produces predictions on the health status of the soil and disease classification, in addition to suggesting proper irrigation, fertilization, and pest management. Visualization and Explainable AI techniques improve interpretation and confidence in decision-making and ensure practical application of the proposed solution in agricultural practices (S. K. Sharma, 2024; S. Ali et al., 2025; C. V. S. Babu & M. Thrisha, 2026) [6,36,37,38] . In summary, the theoretical framework provides an innovative and intelligent solution for precision agriculture in the future.

Findings and Interpretations

Experimental results clearly show that the suggested Quantum AIbased approach exhibits a much better performance in predicting soil health and detecting crop diseases compared to conventional machine learning algorithms. First, the developed hybrid model showed a high accuracy rate of 94.7% when predicting soil health compared to the 88.3% accuracy achieved using conventional Random Forest and XGBoost models. In addition, the suggested model significantly minimized the MSE value by decreasing it from 0.045 to 0.018, thereby enhancing the precision rate. The outcomes confirm the efficiency of the quantum-enhanced feature mapping technique in identifying complex correlations among soil health attributes, such as pH values (ranging from 5.8 to 7.2) and moisture content (12 to 32%). The table 2 shows the Comprehensive Performance Analysis of Quantum AI-Driven Precision Soil Health Monitoring and Automated Crop Disease Detection Framework. In turn, this is especially important for applications related to real-time agriculture where fast decisions have to be made promptly. Moreover, the model showed high levels of stability when working with different numbers of elements within the dataset, with the accuracy exceeding 93% even for reduced datasets, including only 70% of samples. Figure 4 shows the Line Graph Comparison: Classical vs Quantum AI. Secondly, since the model can generalize and show good performance in diverse cases, it is possible to apply the developed system in different geographical locations. Thus, the results confirm the potential of Quantum AI applications in soil quality monitoring and automated disease diagnosis.

Challenges and Limitations

Although the suggested Quantum AI-based framework demonstrates good performance, there are numerous limitations that restrict its application in the real-life agricultural settings. The limitation of quantum hardware, especially Noisy Intermediate-Scale Quantum (NISQ) with limited qubits (5-50 qubits) and a high error rate (1-5% gate error) is one of the main limitations, as it may impact the reliability and scalability of the models (S. [10,13] . Moreover, the majority of experiments are based on quantum simulators, which raise www.extensionjournal.com the computational cost by 30-60 per cent relative to running with real hardware. Data issues also remain, such as sensor errors of up to 2-5 percent, and lack of values in up to 8-12 percent of collected data, and heterogeneity of multimodal data sources, such as IoT sensors, UAV imagery, and satellite data (R. Kalirethinam et al., 2025; E. Vadivel et al., 2025) [24,33] . These issues can impact the robustness and generalization capability of the model. The other major constraint is the complexity and cost of adopting integrated smart farming systems. IoT-based soil monitoring networks and UAVbased imaging systems demand a significant amount of investment in infrastructure, typically between 500-2000 USD per hectare, which is not affordable to many small-scale farmers (C. Ranjan et al., 2025; Y. Xing et al., 2026) [7,21] . Moreover, deep learning (classical and hybrid quantum) models are more energy-intensive, by approximately 1525 percent, relative to conventional farming analytics systems due to their high resource consumption in terms of GPUs and quantum simulators (M. Vinoth and V. Rangasamy, 2025; K. Agrawal and N. Kumar, 2025) [2,26] . The unintelligibility of quantumenhanced models and the limited understanding of their users are further barriers to their uptake by farmers, highlighting the importance of finding interpretable and affordable solutions (S. K. Sharma, 2024; S. Ali et al., 2025) [6,37,38] . These dilemmas underscore the need to carry out additional studies to enhance scalability, costeffectiveness, and usability of Quantum AI in precision agriculture.

Future Outcomes

The [10,13] . As a result, higher accuracy levels in soil health prediction will be achieved, with expected accuracy rates above 96-98%, along with decreased mean squared error to below 0.01. Also, with the introduction of more sophisticated multimodal data sources such as hyperspectral imagery (400-2500 nm wavelength range) and real-time IoT sensor data, higher prediction power will be possible, leading to early detection of plant diseases with classification accuracy up to 98.5%-99.2% (A. Shah et al., 2026; M. Tariq et al., 2026) [5,18] , Additionally, the use of Quantum AI technology in agriculture is likely to lead to advancements in sustainability and economic efficiency. [19,23] . Through the combination of digital twin technologies, unmanned drones, and robotization controlled by AI algorithms, fully automated agriculture will become possible through real-time data analysis and control (S. B. Choudhury et al., 2024; J. Osei-Asiamah et al., 2025) [22,31] . Also, explainable and user-friendly systems developed with the help of Quantum AI algorithms are anticipated to boost farmer adoption rate for this technology by over 40% (S. K. Sharma, 2024; S. Ali et al., 2025) [6,37,38] . [10,13] . The physical real quantum devices also reduce overhead costs compared to classical emulation, which generally adds 30-60 percent to processing time, allowing use of almost real-time analytics to make decisions in agriculture (M. Tariq et al., 2026; V. Sunil et al., 2025) [18,32] Nevertheless, the reliability remains affected by such issues as quantum decoherence, noise (1-3 percent), and circuit depth, which requires establishing error mitigation strategies and quantum-classical models (A. Shah et al., 2026; K. Agrawal and N. Kumar, 2025) [5,26] . Real-time soil sensor data (5-10 minutes) and high-resolution UAV data (2-5 cm spatial resolution) can be useful in agricultural practice to increase predictive accuracy and responsiveness (Y. Xing et al., 2026; C. Ranjan et al., 2025) [7,21] . Moreover, scalable accessibility of quantum platforms through cloudaccessibility will empower researchers and agritech systems, which will potentially achieve higher computational efficiency by 3550 percent in large-scale farm analytics (R. Singh et al., 2025; C. V. S. Babu and M. Thrisha, 2026) [19,36] . Quantum hardware is anticipated to transform precision agriculture to make analytical models faster, more precise and scalable with the maturity of quantum hardware to faulttolerant systems with error rates below 0.1% (D. Thingujam et al., 2025; S. Khan et al., 2026) [8,14] . [38,39] . Using blockchain and IoT sensors and analytics, real-time agricultural data can be safely logged and distributed across distributed networks, including soil moisture (1035 range) and nutrient levels, improving the decision-making process and adherence to sustainability requirements (S. Selvaraju et al., 2025; C. Sankari et al., 2025) [30,34] . Moreover, the efficiency of the supply chain can be enhanced by integrating blockchains, which can shorten transaction processing time (by 4060 percent) and operational fraud (by 2535 percent), especially to execute and monitor the crop quality and origin (H. Mishra, 2025; G. Anushree et al., 2025) [23,25] . The use of www.extensionjournal.com smart contracts further automates processes such as fertilizer application, irrigation scheduling, and crop insurance claims, ensuring accuracy and accountability (P. Malathi & K. Senbagam, 2024; S. K. Sharma, 2024) [35,37] . Blockchain can also facilitate the secure sharing of high-dimensional agricultural data (with collaborative analytics and data privacy) when used with Quantum AI (M. Vinoth and V. Rangasamy, 2025; J. Osei-Asiamah et al., 2025) [2,22] . It is hoped that this integration will improve traceability efficiency more than 50% and increase the efficiency of sustainability and transparency of modern agriculture systems (R. Kalirethinam et al., 2025; S. Ankam et al., 2025) [33,41] .

Real quantum hardware deployment

Integration with blockchain for traceability

Conclusion

The developed Quantum AI-based framework for precise monitoring of soil health status as well as automated detection of crop diseases presents a remarkable breakthrough in modern agricultural analytics that utilizes the integration of quantum machine learning algorithms, traditional artificial intelligence models, and various analytical methods successfully. The findings of the investigation demonstrate that the combination of multimodal input information such as the state of soil and crop images can improve predictions related to the health status of both elements as well as provide a range of other benefits in terms of optimization of the resource use and timely decisions in smart farms. The obtained improvements in terms of predictive accuracy in relation to soil health conditions and crop diseases prove the effectiveness of quantum-assisted models when dealing with complicated multidimensional data in the agricultural sector. Moreover, the developed framework tackles some serious disadvantages typical of the conventional models that include limited scalability, computational constraints, and delays in the analysis process.

References

1. Gera R, Jain A. AI in soil health management for health food production. In: Artificial intelligence-driven models for environmental management. 2025. p. 211224. doi:10.1002/9781394282555.ch9.
2. Vinoth M, Rangasamy V. AI-driven robotics in agriculture. In: Computational intelligence and image processing in agriculture: applications and innovations. 2025. p. 15-30. doi:10.1002/9781394320905.ch02.
3. Raj P, Gayathri N, Kathrine GJW. Artificial intelligence for precision agriculture. 2024. p. 1-307. doi:10.1201/9781003504900.
4. Reddy TV, Reddy RA, Prasanna KS, Shiva SS, Meghana S, Reddy TSS. Design and developing AIdriven agro-sage for optimal precision agriculture. In: Proc 5th Int Conf Smart Electron Commun (ICOSEC); 2024. p. 1538-1542. doi:10.1109/ICOSEC61587.2024.10722046.
5. Shah A, et al. Omics-driven soil bioremediation of emerging contaminants: integrating sensors, digital twins, and microbial biotechnology. Appl Soil Ecol. 2026;220:106854. doi:10.1016/j.apsoil.2026.106854.
6. Sharma M, Umrao S, Mattoo A. Impact of AI in smart agriculture to detect diseases in plants or leaves. AIP Conf Proc. 2025;3297(1):0285948. doi:10.1063/5.0285948.
7. Ranjan C, Srinivas J, Balaji PS, Kumar K. Precision agriculture: leveraging artificial intelligence and drones for eco-friendly farming. In: Cases on AI-driven solutions to environmental challenges. 2025. p. 175211. doi:10.4018/979-8-3693-7483-2.ch007.
8. Khan S, et al. Smart farming approaches in medicinal plant cultivation: a review of techniques, benefits, and sustainability. Planta. 2026;263(4):92. doi:10.1007/s00425-026-04960-w.
9. Jeyalakshmi J, Vijay K, Saiganesh B, Manohar E. AI deployment models in precision agriculture. In: Artificial intelligence for precision agriculture. 2024. p. 125-142. doi:10.1201/9781003504900-6.
10. Jain S, et al. ExGAPS: a unified and optimized explainable AI-driven framework for multivariate hyperspectral soil property estimation. Eng Appl Artif Intell. 2026;170:114257. doi:10.1016/j.engappai.2026.114257.
11. Patel J, Bhatt T. AI-driven precision farming: leveraging environmental and soil parameters for accurate crop yield prediction. Lect Notes Netw Syst. 2026;1758:82-91. doi:10.1007/978-3-032-13419-6_9.
12. Pappula-Reddy SP, et al. Prediction of traits using artificial intelligence machine learning. In: Customdesigned crop breeding: advanced technologies. 2025. p. 333-358. doi:10.1002/9781394192595.ch12.
13. Vuister GW, Kumar A, Chaturvedi N, Santoyo G. Emerging omics technologies for sustainable agriculture. 2026. p. 1-487. doi:10.1016/C2024-002023-1.
14. Thingujam D, et al. Climate-resilient crops: integrating AI, multi-omics, and advanced phenotyping to address global agricultural and societal challenges. Plants. 2025;14(17):2699. doi:10.3390/plants14172699.
15. Ranjan C, Kumar K. Innovations in autonomous drones for precision agriculture: techniques and applications. In: Computer vision techniques for agricultural advancements. 2025. p. 321-361. doi:10.4018/979-83693-8019-2.ch011.
16. Lokesh H, Muthukumaraswamy SA, Balasubramanian G. A hybrid approach for smart crop health monitoring using deep learning and IoT. In: Proc 15th IEEE Int Conf Control Syst Comput Eng (ICCSCE); 2025. p. 3035. doi:10.1109/ICCSCE65566.2025.11182661.
17. Loima T, Yoon JY, Kaarj K. Microfluidic sensors integrated with smartphones for applications in forensics, agriculture, and environmental monitoring. Micromachines. 2025;16(7):835. doi:10.3390/mi16070835.
18. Tariq M, et al. Introduction to technological advancements in smart farming practices. In: Emerging omics technologies for sustainable agriculture. 2026. p. 257-279. doi:10.1016/B978-0-443-40316-3.00011-4.
19. Singh R, et al. Enhancing soil organic carbon estimation with generative AI and Nix color sensor. Sci Rep. 2025;15(1):40628. doi:10.1038/s41598-02524236-9.
20. Swapna R, Srinivas P, Mahesh V, Kanth MK, Rani DJ, Arulraj S. AI-driven autonomous vehicle systems for real-time crop mapping and variable rate fertilization. In: Proc 3rd Int Conf Emerg Appl Mater Sci Technol www.extensionjournal.com (ICEAMST); 2025. p. 1697-1703. doi:10.1109/ICEAMST67459.2025.11335688.
21. Xing Y, Liu X, Wang X. Integrating UAVs, satellite remote sensing, and machine learning in precision agriculture: pathways to sustainable food production, resource efficiency, and scalable innovation. Front Agron. 2026;7:1670380. doi:10.3389/fagro.2025.1670380.
22. Osei-Asiamah J, et al. Exploring AI integration in autonomous robotics for precision farming to enhance efficiency and sustainability. In: Proc IEEE Pune Sect Int Conf (PuneCon); 2025. doi:10.1109/PuneCon67554.2025.11378750.
23. Anushree G, Prema KV, Pavithra N. AI-driven precision agriculture: analysing its impact on crop yield, sustainability, and farm efficiency. In: Proc 5th Asian Conf Innov Technol (ASIANCON); 2025. doi:10.1109/ASIANCON66527.2025.11281117.
24. Vadivel E, Pandian K, Dhanaraju M, Subramanyam P, Gnanasekaran P. Emerging trends in soil and crop sensing for enhanced data-driven decision making in precision agriculture. Plant Sci Today. 2025;12(3). doi:10.14719/pst.9306.
25. Mishra H. Artificial intelligence technologies in agriculture. In: AgriTech revolution: next-gen solutions and challenges in modern agriculture. 2025. p. 371-396. doi:10.1007/978-981-95-1268-3_19.
26. Agrawal K, Kumar N. Artificial intelligence and machine learning in agriculture: novel techniques, implementation strategies, and application. In: Computational intelligence and image processing in agriculture. 2025. p. 55-72. doi:10.1002/9781394320905.ch04.
27. Agarwal N, Nidhi, Singh J, Arora Y, Singh MK, Chopra L. Deep learning for crop disease and pest detection in UAV-based remote sensing imagery. Lect Notes Netw Syst. 2025;1433:611-623. doi:10.1007/978-981-96-7131-1_43.
28. Nivethitha T, Deebanchakkarawarthi G, Kavitha N. Cultivating tomorrow: the synergy of AI and IoT in agriculture. In: AIoT: artificial intelligence of things. 2025. p. 205-223. doi:10.1201/9781003482338_9.
29. Singh NK, Singh JK, Verma VC, Ata SMN, Dubey R. Role of artificial intelligence and machine learning in disease forecasting and disease epidemiology. In: Artificial intelligence in microbiology. 2025. p. 207227. doi:10.1515/9783111548777-010.
30. Selvaraju S, Thangamayan S, Sornalakshmi RR, Krishnamoorthy S. Soil nutrient analysis and optimization using DL/ML techniques. In: Sustainable agriculture production using blockchain technology. 2025. p. 39-49. doi:10.1002/9781394248711.ch4.
31. Choudhury SB, et al. On digital twin for a high yielding soybean variety towards optimal field recommendations. In: Proc IEEE Global Humanitarian Technol Conf (GHTC); 2024. p. 270-277. doi:10.1109/GHTC62424.2024.10771522.
32. Sunil V, et al. Artificial intelligence in agriculture: a transformative direction. In: AgriTech revolution. 2025. p. 15-28. doi:10.1007/978-981-95-1268-3_2.
33. Kalirethinam R, Lawrence HJV, Paneerselvam K, Dhiraviyam M. A research paper on AI-driven integrated sensor model for smart farming using steganography techniques. AIP Conf Proc. 2025;3279(1):020190. doi:10.1063/5.0262399.
34. Sankari C, et al. AI-driven IoT-enabled soil nutrient and moisture monitoring with XGBoost and LightGBM-based predictive irrigation and fertilization optimization for sustainable precision agriculture. In: Proc Int Conf Commun Signal Process (ICCSP); 2025. p. 795-800. doi:10.1109/ICCSP64183.2025.11089358.
35. Malathi P, Senbagam K. Implementing AI to enhance irrigation and precision application of pesticides and herbicides in agriculture. In: Proc Int Conf IoT Based Control Netw Intell Syst (ICICNIS); 2024. p. 15771582. doi:10.1109/ICICNIS64247.2024.10823186.
36. Babu CVS, Thrisha M. Harnessing AI and IoT: transforming agriculture for sustainable solutions. Stud Comput Intell. 2026;1236:247-267. doi:10.1007/978-3032-05603-0_11.
37. Sharma SK. Artificial intelligence for monitoring agricultural essentials. In: Infrastructure possibilities and human-centered approaches with Industry 5.0. 2024. p. 107-124. doi:10.4018/979-8-3693-07823.ch007.
38. Ali S, Kumar P, Srivastav M, Kumar A, Singh SK. AIdriven innovations for sustainable agriculture: enhancing efficiency and resilience. In: Modern technology for sustainable agriculture. 2025. p. 115128. doi:10.1007/978-3-031-88396-5_9.
39. Brahmandam BA, Bogadi CR. Transforming food systems: harnessing the power of AIOps and MLOps in agriTech. In: AI innovations for transforming food production. 2025. p. 133-160. doi:10.4018/979-8-33730842-5.ch006.
40. Elango E, Hanees A, Shanmuganathan B, Kareem Basha MI. Precision agriculture: a novel approach on AI-driven farming. Signal Commun Technol. 2024;F2461:119-137. doi:10.1007/978-3-031-511950_7.
41. Ankam S, et al. A real-time system for monitoring crop and soil health in sustainable agriculture using drones and artificial intelligence. J Environ Prot Ecol. 2025;26(2):723-733.