AI and Machine Learning in Precision Agriculture: The Future of Agricultural Precision Agriculture

Abstract

Agriculture is rapidly transforming with the integration of technologies such as machine learning (ML) and artificial intelligence (AI) to solve critical issues such as food security, climate change, and sustainable agriculture. Precision agriculture uses these technologies to increase yields, improve resource utilization, and reduce environmental impact. Machine learning techniques, particularly deep learning models such as convolutional neural networks (CNNs), have been successful in studying plant diseases, enabling early detection and reduction of crop losses. AI models improve decision-making by analyzing a wide range of agricultural data to predict crop yields, optimize irrigation schedules, and manage fertilization. These intelligent systems provide rapid insights, helping farmers make informed decisions and increase productivity and sustainability. While the Internet of Things enables machine learning and artificial intelligence by collecting real-time data from operations, the real breakthrough will come from machine learning algorithms that can predict outcomes, maintain standards, and work on the farm. Challenges such as high technology costs, complex data management, and implementation processes are only limited by time, but continuous advances in technology and research have the potential to transform agriculture by providing simple, effective, and practical solutions to today’s agricultural sector.

Introduction

I. INTRODUCTION

Agriculture is rapidly changing thanks to the integration of technologies such as machine learning, artificial intelligence, and the internet of things, addressing key issues such as food security, climate change, and sustainable agriculture. Precision agriculture is a modern, data-driven approach to agriculture that offers effective solutions for production and environmental impact reduction. Machine learning, especially deep learning models such as convolutional neural networks (CNNs), is widely used in plant disease research to detect pathogens, reduce crop losses, and improve agricultural sustainability. In addition, IoT-based systems combined with AI can help farmers make decisions on planting, fertilizing, and pesticide application, and provide complete farm management. Respond positively by considering soil, air, and crop health. Advances in drone control, satellite imagery, and distance measurement tools are driving advances in healthcare and care capacity. This tool provides detailed information on soil health, moisture levels, and nutrient distribution, allowing for efficient allocation of resources. However, despite its success in developing countries, the use of this technology still faces many challenges in developing countries, including financial constraints, low technology, and fragmented land. and increased support for precision agriculture decisions through the integration of IoT and machine learning. These technologies enable efficient farming, increase productivity, improve product quality, and reduce environmental damage. However, challenges such as high technology costs, complex data management, and timely completion remain and are important for future research. The role of these technologies is becoming increasingly important. The integration of these technologies will transform traditional farming practices and provide simple, effective and cost-effective solutions to farming problems.

II. LITERATURE REVIEW

This article discusses the importance of disease detection to ensure high yields in agriculture. It reviews various machine learning techniques used to identify plant diseases through image analysis. A report on the success of convolutional neural networks (CNN) in successful liver disease detection. It also explores decision trees and fuzzy Bayes classifiers as alternatives to improve detection performance. To focus on automated technology, This paper examines precision agriculture as a technology-based, sustainable approach to modern agriculture. The integration of IoT, AI, and machine learning is essential for the development of agricultural systems such as soil property prediction, yield prediction, and disease diagnosis.

This review focuses on learning models such as SVMs, random forests, and CNNs, emphasizing their applications in land and weather forecasting. The paper recommends future research on hybrid machine learning models to improve accuracy in areas such as climate change and water management [2]. It analyzes data such as PlantVillage and uses CNN-based models such as ResNet50 and MobileNetv2 to achieve accuracy in disease classification. The paper demonstrates the importance of image preprocessing and feature extraction to improve the accuracy of plant diseases, especially from CNNs. The authors suggest future research on deeper learning to improve the performance of real agriculture [14].

This paper investigates the role of precision agriculture using technologies such as GPS, GIS, and remote sensing in improving agriculture. It provides important methods for effective crop management such as decision support and site-specific management. The results showed that the use of technologies such as irrigation has a positive impact on crops such as tomatoes and peas. The paper discusses the challenges faced in implementing agricultural technology in developing countries and provides suggestions for future research on the use of these techniques in smallholder agriculture [4]. (For example, KNN, Random Forest, and Naive Bayes. The study used historical agricultural and climate data to provide accurate predictions and achieved 95% accuracy using the negative Bayes model. This paper highlights the importance of smart crop decision making for agricultural development and demonstrates the potential of web applications to support farmers under consideration [15]. This paper explores the integration of AI and IoT in precision agriculture to increase sustainability and productivity. It proposes a framework that combines IoT-based sensors with intelligent algorithms for crop health monitoring, irrigation accuracy, and soil assessment. The analysis shows that these technologies reduce resource waste and improve agricultural decision-making. Future research aims to improve the instant response capabilities of AI and IoT systems to achieve better agricultural management [6]. Excellence in precision agriculture. This study demonstrates the success of deep learning models in improving agricultural accuracy. This study suggests further research on the ecological issues of deep learning and the development of descriptive intelligence models to increase the transparency of agricultural decisions [7].

The proposed PAMICRM model provides image denoising and feature extraction techniques to improve the accuracy of irrigation scheduling. The results showed a significant improvement in the accuracy and yield of crops such as mango and rice. Future studies suggest integrating PAMICRM with IoT-based sensors to provide instantaneous notification and optimization of water activities [17]. This paper investigates the use of deep learning algorithms such as AlexNet, VGG16, and VGG19 for plant disease detection using the PlantVillage dataset.

AlexNet achieved the highest accuracy (96.63%) on the tested samples. This study demonstrates the potential of deep learning for early disease detection in plants, which is important for improving plant health and agricultural production [18]. impact. It emphasizes the use of technologies such as GPS, GIS, and artificial intelligence to improve agriculture and enhance management. This study provides insight into the current status of precision agriculture in India and suggests future research to expand the use of this technology in climate-smart agriculture [19].

Fig.1.1  Classification algorithm in Precision agriculture

III. METHODOLOGY

Plant disease diagnosis and agricultural monitoring methods have evolved, including various methods. A plant disease detection program involves several key steps, starting with image acquisition, where high-quality images of plants are captured or saved for further analysis. The next step is to create a database, a repository of information that categorizes these images into different categories. The images are then subjected to imaging techniques to develop critical features required for disease diagnosis. Feature extraction is an important step that uses various techniques to identify important features of an image and then uses machine learning (ML) such as support vector machines (SVM), random forests (RF), and convolutional neural networks (CNN) to classify the image [1]. Precision agriculture (PA) is a data-driven approach based on the deployment of IoT sensors to collect data on soil, water levels, and crop growth. This information is processed by machine learning algorithms to predict best farming practices. Functional deficiencies of IoT sensors used in agriculture have been identified to improve operations and decision-making [2].

Additionally, unmanned aerial vehicles (UAVs) integrating advanced sensors are being used for crop monitoring and pest analysis using remote sensing and geospatial imaging machines [3]. GPS, remote sensing, and geographic information systems (GIS) have played a significant role in monitoring the results in precision agriculture and in different vehicles [4]. It has a convolutional algorithm for feature extraction and all layers for classification. The model has been extensively evaluated on data containing different pest species and compared with other deep learning models in the state [5]. The integration of IoT and AI in smart permaculture (SSA) has also been explored and the central link between IoT and AI has been proposed for applications such as smart greenhouses and climate monitoring [6]. Bibliometric analysis shows that there is interest in deep learning in agriculture, identifying important issues such as increasing productivity and making sense of it from those who do [7]. A number of software methods have been included, including fuzzy logic (FL) for water scheduling, neural networks (ANN) for soil analysis, and genetic algorithms (GA) for efficient resource allocation [8]. Comparisons of IoT communication protocols such as

Wi-Fi, ZigBee, and LoRaWAN show their different performance in different agricultural environments [9]. Autonomous systems such as drones and driverless cars, driven by machine learning algorithms, are also increasingly used in agriculture for planting, harvesting, and crop monitoring purposes [10]. Long-term memory (LSTM) models have been used in crop disease research, demonstrating the role of adaptive learning and image processing in crop improvement [11]. It has revolutionized plant detection in agriculture by using texture and contour descriptors and deep learning algorithms to identify plants in RGB images. The combination of these technologies expresses the complexity of the field, where vegetation is not uniform and the environment affects the image quality. Using sensors such as humidity, temperature, and moisture sensors, these systems can monitor the field and automate irrigation systems. This multi-sensor approach enables high-precision agricultural applications by monitoring plants individually in rows, differentiating plant crops, and managing each plant type. Detailed plant libraries are created by determining the spectral, geometric, and mechanical properties of the plants, and image classification and analysis are performed using a variety of sensors, including photodiodes and CMOS cameras [12]. In the system, data from environmental sensors are sent to a cloud-based platform via LoRaWAN for storage and analysis. As discussed in [13], these systems emphasize the importance of accurate weather data and use mobile applications to interact with end users. In addition, deep learning techniques such as convolutional neural networks (CNN) have been used for plant disease detection, which include advanced techniques such as image resizing, data augmentation, and transfer learning from previous learning models such as ImageNet. This method achieves high accuracy in classifying tasks, demonstrating the potential of CNNs in agriculture [14].

Very important. Models such as K-nearest neighbor (KNN), support vector machine (SVM), and random forest have been evaluated for classification problems in precision agriculture. Random forest regression and support vector regression are used to model farming in the regression study, while statistical metrics such as Cohen's Kappa score provide insight into the performance [15]. Precision agriculture technology also includes GPS for monitoring field data, sensor technology for crop management, and value-added technology (VRT) to leverage the use of fertilizers and other inputs according to specific conditions in the field [16].

Integration of the best imaging tools with learning models such as adaptive vision and grid connectivity (GCN) further enhances the ability of agricultural classification and prediction. In [17], DeepDynaQ GraphConvolutionalNetwork (DDQGCN) is proposed for classifying tasks over time and analyzed using performance metrics such as precision, accuracy, recall, and specificity. Remote sensing and crop monitoring are used together with soil and plant sensors to provide information about the health of crops and soil to support truly high-level decision making in agriculture [18]. Diseases are recommended for harvesting and planting. Techniques such as convolutional neural networks (CNN), random forests (RF), and support vector machines (SVM) are used for tasks such as crop management, disease detection, and resource development. This method has proven to be effective in modern agriculture and ensures sustainability [19].

IV. DISCUSSION

The research review shows that there has been significant progress in agricultural technology with significant contributions from machine learning (ML) and deep learning (DL) algorithms. For example, the performance of CNN in disease detection is superior to traditional classifiers such as decision trees and negative Bayes classifiers. This feature is able to identify many crop diseases, which greatly benefits farmers [1]. This finding highlights the importance of CNN-based models in improving and developing disease diagnosis, but the focus now should be on overcoming the limitations and developing this model for general use. Learning diseases

Fig.1.2   Machine Learning for Plant Disease Detection

The success of real-time disease monitoring with UAVs and collaborative models such as climate-smart management (CSPM) continues to highlight the intersection of application technology and permaculture practices [3]. However, the scale of this technology is not without its challenges. Future research should explore how to overcome these barriers by focusing on cost reduction, user education and infrastructure to improve overall use, especially in limited areas. While successful, economic and commercial conditions continue to hinder its adoption in developing countries [4]. This highlights the need for locally tailored solutions that combine new technologies with policies that promote accessibility and efficiency. In particular, the DeepPestNet model has achieved success in classifying pests by achieving 100% accuracy on the Deng dataset and 98.92% accuracy on the Kaggle pest dataset, representing a significant advancement in pest control techniques [5]. Future efforts should focus on extending the model to different pest species and geographic regions and making it robust in different agroecosystems. Wasted resources are reduced and decisions are made better. Technologies such as drones and precision agriculture equipped with healthy crop and soil monitoring have proven to be effective, especially in applications such as smart greenhouses [6].

However, while this technology is promising, there are still issues with capacity and cost. Further research can investigate how these technologies can be used by smallholder farmers in developing regions. It has become a unique design in agriculture, especially in image-based tasks such as crop classification and pest detection. The higher accuracy of CNNs over traditional imaging techniques [7] suggests that deep learning is on the rise in agriculture. However, in-depth research is expected on how to improve these models in less controlled areas where features such as lighting, weather, etc. will be different. Regional decisions such as irrigation scheduling and crop management. The ability of fuzzy logic to deal with uncertain data has proven to be invaluable, but its applicability is still limited due to the difficulty of acquiring data over time [8]

However, while this technology is promising, there are still issues with capacity and cost. Further research can investigate how these technologies can be used by smallholder farmers in developing regions. It has become a unique design in agriculture, especially in image-based tasks such as crop classification and pest detection. The higher accuracy of CNNs over traditional imaging techniques [7] suggests that deep learning is on the rise in agriculture. However, in-depth research is expected on how to improve these models in less controlled areas where features such as lighting, weather, etc. will be different. Regional decisions such as irrigation scheduling and crop management. The ability of fuzzy logic to deal with uncertain data has proven to be invaluable, but its applicability is still limited due to the difficulty of acquiring data over time [8].  Future research can focus on developing real-time data processing methods and combining fuzzy methods with advanced machine learning models to improve decision making in the processing area.

Its scope is still limited, but it shows good performance in terms of data transfer speed and reliability. At the same time, the higher coverage and power consumption of LoRaWAN make it suitable for large-scale agriculture despite the limitations in the transfer of big data [9]. This highlights the need for hybrid communication that combines the benefits of multiple technologies to support different agricultural needs. Significant progress has been made in agriculture. While decision trees and random forests have increased the accuracy of yield estimates, CNNs and SVMs have proven particularly effective at classifying organisms based on image data [10]. As this technology matures, future research should explore how machine learning models can be integrated into autonomous vehicles such as drones and robots to perform tasks on farms with minimal human intervention.

Fig.1.3  Convolutional Neural Networks

The introduction of advanced methods such as the APDDCM-SHODL method, which combines IoT techniques with machine learning for disease diagnosis, represents a major breakthrough in precision agriculture. This model, which uses VMF technology and DenseNet-201 for feature extraction, shows great promise, although its performance in large agricultural areas needs further optimization [11]. Expanding the IoT platform to include more environmental variables such as soil moisture and nutrient levels will improve its ability to support permaculture practices. Intelligent robots: Plant detection, moisture measurement, and chemical application. Neural network algorithms play a key role in training these robots and enabling them to perform additional agricultural tasks [12]. However, for this technology to be widely used, issues related to cost, feasibility, and user acceptance need to be addressed. sexual development. Experimental analysis shows that PAMICRM consistently outperforms CROPCARE, achieving 98.91% accuracy and 99.02% accuracy on larger datasets, demonstrating its scalability and adaptability to real-time agricultural use [16].

This achievement suggests that the model has the potential for widespread use, although further research is needed to optimize it for different farms and larger datasets, which will be determined in detail. In particular, AlexNet achieved the highest score of 96.63%, improving the performance of these models in plant disease detection, demonstrating that they are better than existing methods in specialized agricultural facilities [17]. This reinforces the need for continuous innovation in deep learning to increase agricultural productivity. For example, variable fertilization technology (VRT) for nitrogen management increases productivity and reduces fertilizer use. However, the use of these technologies is hampered by issues such as illiteracy, high start-up costs, and limited technology, limiting their widespread use and good results [18]. Contribute to effective and efficient resource management. Techniques such as neural networks (ANN), support vector regression (SVR), and random forests (RF) have improved forecasting, disease detection, and crop identification, highlighting the importance of good data in these applications [19]. These advances highlight the changing role of machine learning in the development of permaculture practices and emphasize the need for continued investment in data infrastructure to support future development.

Conclusion

The combination of machine learning (ML), deep learning (DL), and the Internet of Things (IoT) with precision agriculture has transformed agriculture, leading to further improvements in crop management, disease control, quality control, and sustainable agriculture. Studies have shown that convolutional neural networks (CNN), support vector machines (SVM), and artificial neural networks (ANN) in particular have been highly successful in processes such as disease detection, yield estimation, and pest control. These technologies help farmers reduce resource wastage and increase productivity by providing them with electronic tools and quick decision-making. Sustainable Agriculture Practices (CSPM) promote sustainable agriculture. Furthermore, software technologies such as fuzzy logic and neural networks have proven useful in water planning and crop management as they can provide low-cost, cost-effective solutions to manage uncertainty, especially in agriculture. Advances in technologies such as digital transformation technologies (DRTs) and food management are beneficial in increasing crop yields and productivity, especially in crops such as tomatoes, peas, and peppers. However, despite this progress, socio-economic issues, especially in developing regions, continue to hinder the use of this technology. High start-up costs, lack of skills, and difficulty in obtaining appropriate programs are still major issues. These models, along with deep learning such as AlexNet, VGG16, and VGG19, have demonstrated important features such as adaptability and adaptability to real agricultural data, improving the performance study in deep learning models for disease diagnosis. Research should focus on improving the robustness of these models in various agricultural fields, integrating environmental and security research, and expanding IoT platforms to cover various areas of agriculture. Additionally, hybrid and cross-pollination models that combine multiple technologies can increase the accuracy and adaptability of various agricultural practices. These technologies offer a path to sustainable agricultural development by reducing environmental impacts, improving resource use, and increasing agricultural productivity to prevent climate change. Through continued research and development, precision agriculture will become a cornerstone of global food security by enabling farmers to meet their growth needs while protecting natural resources and the environment.

References

[1] U. Shruthi, V. Nagaveni and B. K. Raghavendra, \"A Review on Machine Learning Classification Techniques for Plant Disease Detection,\" 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), Coimbatore, India, 2019, pp. 281-284, doi: 10.1109/ICACCS.2019.8728415. keywords: {Diseases; Agriculture;Support vector machines;Machine learning;Feature extraction;Conferences;Pipelines;Plant disease detection;Classification;Machine Learning}, [2] A. Sharma, A. Jain, P. Gupta and V. Chowdary, \"Machine Learning Applications for Precision Agriculture: A Comprehensive Review,\" in IEEE Access, vol. 9, pp. 4843-4873, 2021, doi: 10.1109/ACCESS.2020.3048415.keywords: {Agriculture;Artificial intelligence;Internet of Things;Irrigation;Wireless sensor networks; Soil; Sensors; Agricultural engineering; machine learning;intelligent irrigation;IoT;prediction}, [3] Buja, I.; Sabella, E.; Monteduro, A.G.; Chiriacò, M.S.; De Bellis, L.; Luvisi, A.; Maruccio, G. Advances in Plant Disease Detection and Monitoring: From Traditional Assays to In-Field Diagnostics. Sensors 2021, 21, 2129. https://doi.org/10.3390/s21062129 [4] Rimpika, & ., Anushi & Manasa, S. & N., Anusha & Sharma, Sakshi & Shilpa, & Sood, Ankita. (2023). An Overview of Precision Farming. International Journal of Environment and Climate Change. 13. 441-456. 10.9734/ijecc/2023/v13i123701. [5] N. Ullah, J. A. Khan, L. A. Alharbi, A. Raza, W. Khan and I. Ahmad, \"An Efficient Approach for Crops Pests Recognition and Classification Based on Novel DeepPestNet Deep Learning Model,\" in IEEE Access, vol. 10, pp. 73019-73032, 2022, doi: 10.1109/ACCESS.2022.3189676. keywords: {Insects;Feature extraction;Crops;Support vector machines;Classification algorithms;Image recognition;Pest control;Insects pests;deep learning;transfer learning;fine-tuning;convolutional neural networks}, [6] A. A. AlZubi and K. Galyna, \"Artificial Intelligence and Internet of Things for Sustainable Farming and Smart Agriculture,\" in IEEE Access, vol. 11, pp. 78686-78692, 2023, doi: 10.1109/ACCESS.2023.3298215. keywords: {Smart agriculture;Crops;Artificial intelligence;Internet of Things; Farming; Monitoring; Soil; Internet of Things;Sustainable development;Smart agriculture;Internet of Things (IoT);artificial intelligence (AI);smart sustainable agriculture (SSA);smart farming}, [7] Coulibaly, Solemane & Kamsu-Foguem, Bernard & Kamissoko, Dantouma & Traore, Daouda. (2022). Deep learning for precision agriculture: A bibliometric analysis. Intelligent Systems with Applications. 16. 200102. 10.1016/j.iswa.2022.200102. [8] Huang, Yanbo & Lan, Yubin & Thomson, Steven & Fang, Alex & Hoffmann, Clint & Lacey, Ronald. (2010). Development of soft computing and applications in agricultural and biological engineering. Computers and Electronics in Agriculture. 71. 107-127. 10.1016/j.compag.2010.01.001. [9] A. U. H. Hashmi et al., \"Effects of IoT Communication Protocols for Precision Agriculture in Outdoor Environments,\" in IEEE Access, vol. 12, pp. 46410-46421, 2024, doi: 10.1109/ACCESS.2024.3381522. keywords: {Smart agriculture; Wireless communication; Wireless fidelity; Monitoring; Intelligent sensors; Wireless sensor networks; Farming; Protocols; Precision agriculture; Zigbee; Communication protocol; Internet of Things; LoRa; precision agriculture;smart farming; Wi-Fi;ZigBee}, [10] G. Mohyuddin, M. A. Khan, A. Haseeb, S. Mahpara, M. Waseem and A. M. Saleh, \"Evaluation of Machine Learning Approaches for Precision Farming in Smart Agriculture System: A Comprehensive Review,\" in IEEE Access, vol. 12, pp. 60155-60184, 2024, doi: 10.1109/ACCESS.2024.3390581. keywords: {Farming;Smart agriculture; Intelligent sensors;Productivity;Europe; Monitoring;Precision agriculture;Machine learning;Autonomous aerial vehicles;Artificial intelligence; Smart agriculture; precision farming; machine learning;unmanned aerial vehicles; artificial intelligence}, [11] L. Lambrinos, \"Internet of Things in Agriculture: A Decision Support System for Precision Farming,\" 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), Fukuoka, Japan, 2019, pp. 889-892, doi: 10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00163. keywords: {Handheld computers;Big Data;Internet of Things;Farming;Smart agriculture;Decision support systems; Climate change; Precision engineering; Internet of Things, agriculture, big data, decision support system, smart farming, LoRaWAN}, [12] E. A. Al-Shahari, G. Aldehim, M. Aljebreen, J. S. Alqurni, A. S. Salama and S. Abdelbagi, \"Internet of Things Assisted Plant Disease Detection and Crop Management using Deep Learning for Sustainable Agriculture,\" in IEEE Access, doi: 10.1109/ACCESS.2024.3397619. keywords: {Feature extraction;Crops;Vectors;Plant diseases;Agriculture; Internet of Things;Tuning;Detection algorithms;Hyperparameter optimization;Sustainable development;Deep learning;Plant Disease Detection; Internet of Things;hyperparameter tuning;Sustainable Agriculture;Deep Learning}, [13] A. Dahane, R. Benameur, B. Kechar and A. Benyamina, \"An IoT Based Smart Farming System Using Machine Learning,\" 2020 International Symposium on Networks, Computers and Communications (ISNCC), Montreal, QC, Canada, 2020, pp. 1-6, doi: 10.1109/ISNCC49221.2020.9297341. keywords: {Irrigation; Training; Data models; Soil moisture;Computer architecture; Atmospheric modeling; Meteorology;Smart farming;IoT;Machine learning;Sensing;Precision agriculture}, [14] V. Balafas, E. Karantoumanis, M. Louta and N. Ploskas, \"Machine Learning and Deep Learning for Plant Disease Classification and Detection,\" in IEEE Access, vol. 11, pp. 114352-114377, 2023, doi: 10.1109/ACCESS.2023.3324722. keywords: {Plant diseases;Crops;Classification algorithms;Object detection;Plants (biology);Deep learning;Neural networks;Diseases;Smart agriculture;Precision engineering;Classification;deep learning;disease detection;machine learning;object detection;precision agriculture}, [15] Pawar, Shubham & Dere, Sumit & Akangire, Ashitosh & Kamble, Harshvardhan. (2021). SMART FARMING USING MACHINE LEARNING. 8. [16] Trivedi, Ayushi & Ranade, DH & Vaani, D.K & Nandeha, Nirjharnee. (2024). Agricultural Internet of Things and Decision Support System for Precision Smart Farming. [17] R. K. Munaganuri and Y. N. Rao, \"PAMICRM: Improving Precision Agriculture Through Multimodal Image Analysis for Crop Water Requirement Estimation Using Multidomain Remote Sensing Data Samples,\" in IEEE Access, vol. 12, pp. 52815-52836, 2024, doi: 10.1109/ACCESS.2024.3386552. keywords: {Climate change;Precision agriculture;Remote sensing;Machine learning;Irrigation;Environmental monitoring;Sustainable development;Globalization;Food products;Food security;Crop yield;Soil measurements;Predictive models;Autoregressive processes;Adaptation models;Irrigation;Heuristic algorithms;Multimodal sensors;Precision agriculture;remote sensing;machine learning;irrigation optimization;environmental sustainability}, [18] Dey, Puja & Mahmud, Tanjim & Naher, Sultana & Hossain, Mohammad & Andersson, Karl. (2024). Plant Disease Detection in Precision Agriculture: Deep Learning Approaches. 661-667. 10.1109/IDCIoT59759.2024.10467525. [19] Pal, Dolgobinda & Saha, Sarathi & Banerjee, Saon. (2023). Precision Agriculture in View of Climate Change towards Long Term Sustainability. 10.2271/ed.book.2317.

Copyright

Copyright © 2025 Atharva Kalbhor, Rohit Borole, Sakshi Karekar, Nidhi Deshmukh, Aparna Lahane. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.