Agricultural Crop Recommendation System using IOT and M.L

Abstract

Agriculture has always been the backbone of many developing economies, especially in countries like India, where it provides jobs, ensures food security, and drives economic growth. As the world\'s population keeps growing, the need for sustainable farming has never been more urgent. It’s not just about producing more crops—it’s about protecting the land so future generations can continue to farm. That’s where technology comes in. Innovations like the Internet of Things (IoT) and Machine Learning (ML) are transforming agriculture, making farming smarter, more efficient, and more productive. This paper introduces a smart agricultural system that uses IoT and ML to help farmers predict how their crops will perform based on real-time weather and environmental conditions. Sensors placed throughout the fields monitor crucial factors like temperature, humidity, soil moisture, and pH levels. These sensors continuously send live updates to a central system, giving farmers accurate, up-to-date insights into their crops and the surrounding environment. Once the data is collected, Machine Learning algorithms step in to analyze it. By studying both past and present data, these algorithms can predict crop yields, detect growth trends, and assess how different environmental conditions affect plant health. With this predictive power, farmers can make well- informed decisions about watering schedules, fertilization, pest control, and more. Instead of relying on guesswork, they can use real data to improve efficiency, boost crop production, and reduce waste. The combination of IoT and ML is making precision farming a reality. This shift toward \"smart farming\" comes with many benefits—lower costs, better use of resources, and higher productivity. By embracing technology, farmers can grow more with less, ensuring a sustainable and prosperous future for agriculture.

Introduction

Farming is undergoing a major transformation through smart technologies like the Internet of Things (IoT) and Artificial Intelligence (AI), which help increase food production efficiently while conserving resources and reducing waste. With challenges like rising costs, climate change, and a growing global population, smarter farming methods are essential to meet future food demands.

The text presents a smart farming system that integrates IoT sensors and machine learning to collect real-time soil and environmental data, analyze it, and provide farmers with actionable crop recommendations. This system improves decision-making on planting, watering, and resource management, making farming more sustainable, efficient, and accessible—even for small-scale or remote farmers with limited technical skills.

Traditional farming relies on experience and manual methods, which can be unreliable and wasteful. The new technology addresses these issues by offering precise, data-driven insights, optimizing the use of water, fertilizers, and pesticides, and minimizing environmental harm.

The system uses sensors to monitor soil moisture, temperature, pH, nutrient levels, and harmful gases, sending data to a cloud platform where machine learning algorithms analyze it to recommend the best crops for the current conditions. Farmers can access recommendations via mobile apps, SMS, or voice alerts, even offline, ensuring usability in rural areas.

By improving resource management and crop yields, this technology supports food security, economic growth, and sustainable agriculture. It also aids policymakers and organizations in creating better agricultural policies and market forecasts.

The document also reviews related research highlighting the benefits and challenges of IoT and AI in farming, and details the hardware and software components of the system, including sensors, Arduino microcontroller, cloud computing, and machine learning models like Decision Trees and Random Forest.

Conclusion

Choosing the right crop is one of the most important decisions a farmer can make, as it directly impacts productivity, profitability, and resource management. Traditionally, farmers have relied on experience, advice from peers, and basic trial-and-error methods, which are often unreliable and inefficient. Without access to real-time data, many farmers struggle with soil degradation, excessive water usage, and unpredictable weather conditions, which can lead to financial losses and unstable crop yields. By integrating IoT and machine learning, this system offers a modern, data-driven approach to farming. It eliminates the need for manual calculations by automatically analyzing soil conditions, climate trends, and environmental factors to suggest the best crops for a given area. This helps farmers save time, reduce mistakes, and improve productivity, ensuring that every decision is based on scientific data rather than guesswork. With real-time monitoring and smart recommendations, farmers can optimize irrigation, nutrient management, and planting schedules, leading to higher yields and more sustainable farming practices. The Crop and Soil Health Card is another valuable feature of this system,providing farmers with detailed reports on soil quality and fertility. These insights enable farmers to adjust their farming strategies, improve soil health, and ensure long-term productivity. Additionally, these recordscan be used when applying for loans and crop insurance, helping farmers secure financial assistance more easily. By giving farmers the right tools and information, the system empowers them to make better decisions, reduce financial risk, and improve their livelihoods. Beyond helping individual farmers, this system has the potential to reshape the agricultural industry. By gathering and analyzing data from multiple regions, it can provide valuable insights for policymakers, researchers, and agricultural organizations, helping them predict food supply trends, manage resources more effectively, and design better policies. This data-driven approach can contribute to global food security, reduce agricultural waste, and promote eco-friendly farming practices. A. FutureEnhancements While this system already provides significant benefits, future improvements could make it even more powerful and accessible. One major enhancement would be integrating advanced AI models, which can analyze large-scale climate data, soil reports, and historical trends to improve crop recommendations. By learning from past patterns, the system could help farmers anticipate environmental challenges and adapt to changing conditions. Another important improvement is the use of blockchain technology to create a secure and transparent data-sharing platform. Blockchain can protect farmer data from manipulation, ensure fair pricing in supply chains, and improve trust in organic and certified farming practices. This would allow farmers, consumers, and policymakers to access verified agricultural data, strengthening transparency and accountability in the food industry. To ensure that all farmers, regardless of their background, can use the system, it should be made available in multiple languages and designed with a simple, user-friendly interface. Manyfarmers in rural areas may not have experience with digital tools, so adding voice commands, step-by-step guidance, and mobile-friendly features would make the system more accessible and practical for everyday use. Integrating dronetechnology and remote sensing could furtherenhance the system’s capabilities. Drones equipped with high-resolution cameras could monitor fields, detect early signs ofdisease, and assess crop health more effectively. This would allow farmers to take proactive measures to prevent losses, optimize fertilizer use, and improve overall productivity. Collaboration with agricultural research institutions and government agencies would also be beneficial in ensuring that the system stays up to date with the latest advancements in farming techniques. Government support in subsidizing smart farming technologies and providingtraining programs could help expand adoption, making modern agriculture accessible to small- scale and large-scale farmers alike. With continuous advancements in AI, IoT, and precision farming, the future of agriculture is smarter, moreefficient,and moreresilient. Byembracingtheseinnovations,farmers canincrease productivity, minimize risks, and contribute to a moresecureand sustainable globalfood system.

References

[1] “GlobalAgriculturetowards2050.” http://www.fao.org/fileadmin/templates/wsfs/docs/Issuespapers/HLEF2050_Global_Agriculture.pdf [2] “PrinciplesofAgronomyandAgriculturalMeteorology” http://eagri.org/eagri50/AGRO101/ [3] AModelforSmartAgricultureusingIoTJournal:XiaohuiWang,NannanLiu,\"The ApplicationofInternetofThingsinAgriculturalmeansofproductionsupplychainmanagement\" [4] “Principlesofcropprediction,DatasetforM.LModel”Dr.RaviS,KrishiVignyanaKendra,Bidar [5] Journal-“ApplicationsofMachineLearningforprediction”ML experimentationreferstotheeffortscenteredondatapreparation,algorithm selectionand modelvalidationandverification.Italsoreferstotheprocessof deployingmodelsandthe subsequentconsumptionandmonitoringofresilient, efficient andmeasurable servicesapplied to engineering problems. https://www.journals.elsevier.com/journal-ofpetroleum-science-andengineering/call-forpapers/applications-of-machine-learning-and- artificialintelligence [6] Dhabarde,S.,Bisane,S.,Gupta,A.,Pote,D.,&Yadav,A.(2022).Agriculturalcrop recommendation system using IoT and ML. Int J Adv Res SciCommun Technol. [7] Islam,MdReazul,KhondokarOliullah,MdMohsinKabir,MunzirulAlom,andM.F.Mridha. \"Machine learning enabled IoT system for soil nutrients monitoring and crop recommendation.\" Journal of Agriculture and Food Research 14 (2023): 100880. [8] Bhoi, Ashutosh, Rajendra Prasad Nayak, Sourav Kumar Bhoi, SrinivasSethi, Sanjaya Kumar Panda, KshiraSagarSahoo, and AnandNayyar. \"IoT-IIRS: Internet of Things based intelligent- irrigationrecommendationsystemusingmachinelearningapproachforefficientwaterusage.\"PeerJ Computer Science 7 (2021): e578. [9] Singh,P.,Kaur,M.andBajaj,R.,2024,August.AnIoT-EnabledCropRecommendationSystem Utilizing MQTT for Efficient Data Transmission to AI/ML Model. In 2024 7th International ConferenceonCircuitPowerandComputingTechnologies(ICCPCT)(Vol.1,pp.315320).IEEE. [10] KancharaguntaKB,AkkemY,VembadiM,GaralapatiST,HariPratapVarmaA,RuhaJessicaM. Crop Recommendation System Using Machine Learning and IoT: A Survey. InInternational ConferenceOnInnovativeComputingAndCommunication2024Feb16(pp.63-86).Singapore: Springer Nature Singapore. [11] Kiruthika,S.,&Karthika,D.(2023).IOT-BASEDprofessionalcroprecommendationsystem using a weight based long-term memory approach. Measurement: Sensors, 27, 100722. [12] Hossain, MdDelwar, MohammodAbulKashem, and ShabnomMustary. \"Iot based smart soil fertilizermonitoringand mlbasedcroprecommendationsystem.\"In2023 InternationalConference on Electrical, Computer and Communication Engineering (ECCE), pp. 1-6. IEEE, 2023. [13] Dey,Tanushree,SomnathBera,LakshmanPrasad Latua,MilanParua,AnweshaMukherjee, andDebashisDe.\"iCrop:AnIntelligentCropRecommendationSystemforAgriculture5.0.\"IEEE Transactions on AgriFood Electronics (2024). [14] Patel,DevangiHitenkumar,KamyaPremalShah,RajeshGupta,NileshKumarJadav,SudeepTanwar, BogdanConstantinNeagu, Simo Attila, Fayez Alqahtani, and AmrTolba. \"Blockchain- BasedCropRecommendationSystemforPrecisionFarminginIoTEnvironment.\"Agronomy13, no. 10 (2023): 2642. [15] Thangammal,C.B.,Nithissh,S.S.andMurugesh,K.,2024,November.SoilMonitoringand Crop Recommendation System via IoT and Machine Learning. In 2024 11th International Conference on Advances in Computing and Communications (ICACC) (pp. 1-6). IEEE. [16] MarlineJoysKumariN,ThirupathiRaoN,BhattacharyyaD.Smartirrigationandcultivation recommendation system forprecision agriculture driven by IoT. Machine Intelligence, Big Data Analytics, and IoT in Image Processing: Practical Applications. 2023 Mar 9:123-49. [17] MIMOUNE,A.,&LANTRI,F.(2024).PrecisionAgricultureUsingCropRecommendation Systems (Doctoral dissertation, ibnkhaldoun university Tiaret). [18] Sanjana,Siram,K.NithinKumar,P.Satyanarayana, KNVSureshVarma,InumulaAnitha,andV.GokulaKrishnan.\"ImplementationofOptimalCropRecommendationSystemusingMachine Learning Algorithms.\" In 2024 International Conference on Expert Clouds and Applications (ICOECA), pp. 678-683. IEEE, 2024. [19] Priyanka, S. S., Raju, M., Smitha, G., Lahari, J., Reddy, G. A., &Vinay, P. M. (2023, November). IoT Based Crop Recommendation System Using Machine Learning for Smart Agriculture.InSecondInternationalConferenceonEmergingTrendsinEngineering(ICETE2023) (pp. 893-904). Atlantis Press. [20] Latha, M. Madhavi, BhumagouniPranay, GattuRishitha, ShaikShouqib Ali, MdAmer, and RanganamainaNaresh. \"MACHINELEARNING BASED CROPRECOMMENDATION SYSTEM FOR ENHANCED YIELD PRODUCTION.\" [21] Charumathy,Jaspin,andAndreaJoeLorett.\"IoTBasedCropRecommendationSystemUsing SVM and Decision Tree Algorithm.\" International Conference on Intelligent Computing, Smart Communication and Network Technologies. Cham: Springer Nature Switzerland, 2023. [22] Muhammed, D., Ahvar, E., Ahvar, S., &Trocan, M. (2022, October). A user-friendly AIoT- basedcroprecommendationsystem(UACR):conceptandarchitecture. In202216thInternational ConferenceonSignal-ImageTechnology&Internet-BasedSystems(SITIS)(pp.569-576). IEEE. [23] Palakshappa, Anitha, SowmyaKyathanahalliNanjappa, PunithaMahadevappa, and SinchanaSinchana.\"Smartirrigationwithcroprecommendationusingmachinelearningapproach.\"Bulletin of Electrical Engineering and Informatics 13, no. 3 (2024): 1952-1960. [24] Bhatnagar, Kanika, Mamilla Jaahnavi, and BU Anu Barathi. \"Agriculture Crop Recommendation System using Machine-Learning.\" Mathematical Statistician and Engineering Applications 71, no. 3s2 (2022): 626-637. [25] Kavitha,D.,Kiranteja,P.,VenkhatShridharan,V.J.,Desigan,P.K.,&NG,R.(2024).ASmart Agricultural Assistant for Crop Recommendation using Machine Learning. Grenze International Journal of Engineering & Technology (GIJET), 10. [26] Jeyanathan, Josephine Selle, B. Veerasamy, B. Medha, G. TharunVenkataSai, R. Bharath Kumar,andVarshaSahu.\"DesignofCropRecommenderSystemusingMachineLearningandIoT.\" In 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1127- 1132. IEEE, 2023. [27] Shukla,M.K.,Sondhiya,R.R.andSingh,V.K.,2024.EvaluationofMachineLearningModels forOptimizedCropRecommendation.InMachine LearningforRealWorldApplications(pp.97- 129). Singapore: Springer Nature Singapore. [28] GulhanePG,ThakareA. CropRecommendation SystemUsingMachine Learning Algorithms. InConvergence of Deep Learning and Artificial Intelligence in Internet of Things 2022 Dec 27 (pp. 231 244). CRC Press. [29] Abhinov,Kristuboyina,KornepatiSaiSaranya,MannemMahendra,andChSureshBabu.\"Soil- Based Crop Recommendation System Using Machine Learning.\" In 2024 International Conference onAdvancesinDataEngineeringandIntelligentComputingSystems(ADICS),pp.1-6.IEEE,2024. [30] Sistla, S. S., Ketineni, K., Uppalapati, N., & Lanka, N. (2023, April). Crop Recommender FrameworkUtilizingMLApproach.In2023IEEE8thInternationalConferenceforConvergencein Technology (I2CT) (pp. 1-6). IEEE. [31] Adarsha,MonishaHM DhanushJogiK., and Dalavai SMManvithDalli.\"AWebBased Crop Recommendation System Using Various Machine Learning Algorithms.\" (2024).

Copyright

Copyright © 2025 Sameena F, Soumya Shinde, Veena Vishwakarma, Shruti H. 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.