INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 243
Comparative Analysis of AI-Driven IoT-Based Smart Agriculture
Platforms with Blockchain-Enabled Marketplaces
1
Dr. Sumathy Kingslin,
2
Ms. K. Vaishnavi
1
Associate Professor, PG Department of Computer Science, Quaid-E-Millath Government College for
Women, Chennai
2
Research Scholar, PG Department of Computer Science, Quaid-E-Millath Government College for
Women, Chennai
DOI:
https://doi.org/10.51584/IJRIAS.2025.100900021
Received: 26 August 2025; Accepted: 02 September 2025; Published: 11 October 2025
ABSTRACT
The integration of Internet of Things (IoT), Artificial Intelligence (AI), and Blockchain technology has emerged
as a transformative approach to modern agriculture. Traditional farming platforms and centralized agri-
marketplaces face challenges such as lack of transparency, high transaction costs, and limited predictive
analytics. This paper presents a comparative analysis of an AI-driven IoT-based smart agriculture platform
integrated with blockchain-enabled smart contracts against existing IoT-based and centralized agricultural
systems. The comparison is based on key performance metrics such as data security, transaction transparency,
prediction accuracy, latency, and scalability. Experimental evaluation demonstrates that the proposed system
outperforms traditional solutions by offering decentralized data management, secure peer-to-peer transactions,
and AI-powered decision support, resulting in improved efficiency and farmer profitability. The study highlights
how integrating blockchain and AI into IoT frameworks can enable sustainable, transparent, and intelligent
agricultural ecosystems.
Keywords: Smart Agriculture, IoT, Blockchain, AI-Driven Prediction, Smart Contracts, Decentralized
Marketplace, Data Security, Comparative Analysis
INTRODUCTION
Agriculture remains the backbone of many economies, yet traditional farming practices and centralized
marketplaces continue to face persistent challenges, including inefficient resource utilization, lack of
transparency, and high dependency on intermediaries. Recent advancements in digital technologies such as the
Internet of Things (IoT), Artificial Intelligence (AI), and Blockchain have opened new opportunities to address
these limitations by enabling data-driven decision-making, secure transactions, and decentralized platforms.
IoT-based smart farming systems leverage sensors to monitor environmental parameters such as soil moisture,
temperature, and humidity in real time, thereby optimizing agricultural practices. However, these solutions often
lack predictive analytics capabilities and robust data security mechanisms. Similarly, centralized agri-
marketplaces streamline produce trading but introduce trust issues, data manipulation risks, and additional costs
through intermediary involvement.
Blockchain technology, with its decentralized and immutable ledger, combined with smart contracts, offers a
secure and transparent mechanism for agricultural transactions. When integrated with AI-driven predictive
models, these systems can further enhance yield forecasting, pest detection, and resource allocation. The
convergence of these technologies promises a revolutionary shift toward sustainable and profitable farming
practices.
This paper presents a comparative analysis of an AI-driven IoT-based smart agriculture platform integrated with
blockchain-enabled smart contracts against existing IoT-based solutions and centralized agri-marketplaces. The
comparison evaluates performance across critical metrics such as data security, transaction transparency, latency,
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 244
prediction accuracy, scalability, and transaction cost. Experimental results demonstrate that the proposed
solution significantly improves trust, security, and decision-making while reducing reliance on intermediaries,
thereby fostering fair trade and empowering farmers.
RELATED WORK
Recent research in smart agriculture has primarily focused on leveraging IoT and data analytics to monitor and
manage farming operations. However, most existing solutions either lack decentralized trust mechanisms or fail
to provide predictive intelligence for decision-making.
IoT-Based Smart Farming Solutions:
Several studies have proposed IoT-enabled frameworks for precision agriculture. For example, Patil et al. (2022)
introduced an IoT-based crop monitoring system that collects environmental data using sensors and provides
insights through cloud analytics. Although effective in real-time monitoring, such systems often lack integrated
security mechanisms and predictive intelligence, making them vulnerable to cyber threats and limiting their
decision-support capabilities.
Blockchain-Integrated Agricultural Platforms:
Blockchain technology has been explored as a means to ensure transparency and traceability in agri-commerce.
Mollah et al. (2023) proposed a blockchain-based supply chain model for agricultural produce, enabling
decentralized transaction records and eliminating middlemen. While this enhances trust and accountability, the
system does not incorporate AI-driven analytics for crop yield prediction or resource optimization, reducing its
overall intelligence and adaptability.
AI-Driven Prediction in Agriculture:
AI models, particularly machine learning and deep learning algorithms, have been applied to forecast crop yield,
detect pests, and optimize irrigation. Sharma et al. (2023) developed an AI-based yield prediction model using
convolutional neural networks (CNNs) for analyzing environmental parameters. However, such systems operate
in isolation and do not integrate blockchain for secure, transparent trading, nor do they provide decentralized
data storage.
Integrated Frameworks:
A few studies have attempted to combine IoT with blockchain or AI, but rarely all three. Kumar et al. (2024)
proposed an IoT-blockchain hybrid system for secure agricultural data sharing, but it lacked AI-driven decision-
making capabilities. Similarly, Li et al. (2024) integrated AI with IoT for crop monitoring but relied on
centralized servers, exposing the system to single-point failures and trust issues.
Research Gap
From the above literature, it is evident that existing systems address specific aspects of smart agriculture—such
as IoT-based monitoring, blockchain-enabled transparency, or AI-powered prediction—but fail to offer a unified
solution. There is a clear need for an integrated platform combining IoT, AI, and blockchain to ensure real-time
monitoring, predictive analytics, decentralized trust, and secure transactions, which is the focus of this study.
PROPOSED SYSTEM
The proposed system is an AI-driven IoT-based Smart Agriculture Platform integrated with Blockchain-
enabled Smart Contracts to provide a decentralized, transparent, and intelligent ecosystem for modern farming.
The system aims to address three critical challenges:
Real-time Monitoring – IoT sensors deployed in agricultural fields collect environmental data such as soil
moisture, temperature, and humidity.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 245
Predictive Analytics – AI models (e.g., CNN/LSTM) analyze sensor data for yield prediction, irrigation
scheduling, and pest detection.
Secure & Fair Transactions – Blockchain ensures tamper-proof records and smart contracts enable direct
farmer-to-buyer transactions without intermediaries.
FIG 1 describes about the architecture as follows:
IoT Layer: Collects real-time data from sensors (soil moisture, DHT11, pH sensors).
Communication Layer: Uses MQTT/HTTP to transmit data to a Flask-based backend server.
Data Layer: Stores processed data in MongoDB for scalability and security.
Blockchain Layer: Implements Ethereum (Ganache) for decentralized transactions and smart contracts for
automating payments.
Application Layer: Web interface for farmers, buyers, and youth to monitor data, trade produce, and access AI-
driven insights.
Security Layer: Ensures authentication with JWT, data encryption with AES, and HTTPS for secure
communication.
FIG 1: PROPOSED SYSTEM ARCHITECTURE FOR AI-DRIVEN Iot-BASED SMART AGRICULTURE
PLATFORM
COMPARISON METRICS
The proposed system is compared against existing IoT-based platforms and centralized agri-marketplaces using
the following metrics:
Data Security – Level of protection against data tampering and unauthorized access.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 246
Transaction Transparency – Ability to provide immutable and verifiable transaction records.
Prediction Accuracy – Accuracy of AI-based yield and irrigation prediction.
Latency – Average response time for completing a transaction or query.
Transaction Cost – Cost per transaction considering infrastructure and middlemen.
Scalability – Ability to handle an increasing number of users and devices.
User Role Support – Types of roles supported (Farmer, Buyer, Youth, etc.).
Feature
Proposed System
IoT-Based Platform
Centralized Marketplace
Data Security
AES + Blockchain + HTTPS
HTTPS only
Low (Centralized DB)
Transparency
High (Smart Contracts)
Medium
Low
Role Support
Farmer, Buyer, Youth
Farmer Only
Farmer, Buyer
Table 1: Feature-Based Comparison Of Agricultural Platforms
Fig 1: Security Feature Score Comparison
The above table compares the key features and functional aspects of the proposed system with traditional IoT-
based platforms and centralized marketplaces.
Metric
IoT Platform
Centralized Marketplace
Prediction Accuracy (%)
80
Not Applicable
Latency (ms)
130
200
Transaction Cost (₹)
5–10
15–20
Scalability
Medium
Low
Table 2: Performance Metrics Evaluation
0 5 10 15
Data Encryption
Blockchain Support
Smart Contracts
Trust Level
Centralized Marketplace
IoT Platform
Proposed System
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 247
Fig 2: Prediction Accuracy Comparison
Fig 3: Latency Comparison
The above table presents quantitative comparison results based on experimental evaluation of latency, prediction
accuracy, and transaction cost.
Parameter
Proposed System
IoT Platform
Centralized Marketplace
Data Encryption
AES + HTTPS
HTTPS only
Basic
Blockchain Support
Yes
No
No
Smart Contracts
Yes
No
No
Trust Level
High
Medium
Low
Table 3: Security And Trust Analysis
The above table compares how each system addresses security and trust issues.
EXPERIMENTAL SETUP
To evaluate the performance of the proposed AI-driven IoT-based Smart Agriculture Platform integrated with
blockchain, an experimental setup was implemented under real-world conditions. The evaluation focused on key
metrics such as latency, prediction accuracy, transaction cost, and security features, and compared these
with IoT-based platforms and centralized agri-marketplaces.
A. Hardware Components: IoT sensors including DHT11 (temperature and humidity), soil moisture sensor,
and pH sensor were deployed and interfaced with a NodeMCU (ESP8266) microcontroller for wireless data
transmission. A regulated 5V DC power supply was used.
0
20
40
60
80
100
Prediction Accuracy (%)
Prediction Accuracy
(%)
0
100
200
300
400
500
Proposed
System
IoT-Based
Platform
Centralized
Marketplace
Latency (ms)
Latency (ms)
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 248
B. Software and Frameworks: The backend was developed using Flask (Python), while MongoDB stored
sensor data. Blockchain integration was achieved through Ethereum using Ganache for private deployment,
and smart contracts were implemented in Solidity on Remix IDE. The web interface utilized HTML, CSS, and
JavaScript. Security was ensured using JWT authentication, AES encryption, and HTTPS.
C. AI Model for Prediction: A Convolutional Neural Network (CNN) model was trained on historical soil
and environmental datasets for yield and irrigation prediction, achieving an accuracy of 94%.
D. Network Configuration: Sensor nodes transmitted data over a local Wi-Fi network to the Flask server. The
blockchain was deployed on Ganache with 10 pre-funded accounts for executing smart contracts.
E. Benchmarking for Comparison: The proposed system was compared with:
IoT-Based Platform (without blockchain and AI)
Centralized Marketplace (traditional web-based platform with centralized database and payment gateway)
F. Evaluation Parameters
Prediction Accuracy (%): Comparison with actual values
Latency (ms): Time from sensor data acquisition to UI display
Transaction Cost (₹): Average cost per transaction
Security Features: Level of encryption, authentication, and trust mechanisms
CONCLUSION
This study presented a comparative analysis of an AI-driven IoT-based Smart Agriculture Platform integrated
with blockchain technology against conventional IoT-based systems and centralized agri-marketplaces. The
experimental results demonstrated that the proposed system significantly enhances data security, transaction
transparency, and predictive intelligence, while reducing transaction costs and eliminating intermediaries. The
integration of IoT sensors for real-time data acquisition, AI models for yield and irrigation prediction, and
blockchain-based smart contracts for decentralized trade creates a robust and reliable ecosystem for modern
farming.
Compared to existing solutions, the proposed system achieved higher prediction accuracy (94%), ensured
tamper-proof transactions, and introduced peer-to-peer trust mechanisms that centralized platforms lack.
Although blockchain integration introduces slightly higher latency, the benefits of transparency, security, and
fairness outweigh this limitation.
Future work will focus on optimizing blockchain transaction efficiency, integrating edge computing for faster
data processing, and expanding AI models to include disease detection and precision resource allocation. This
research highlights the potential of combining AI, IoT, and blockchain to revolutionize agriculture and foster
sustainable, technology-driven farming practices.
REFERENCES
1. Patil, R. Kulkarni, and S. Kotecha, “IoT based smart agriculture monitoring system,” International Journal
of Innovative Research in Computer and Communication Engineering, vol. 10, no. 2, pp. 112–118, Feb.
2022.
2. M. Mollah, S. Zhao, and K. Islam, “Blockchain-based solutions for agriculture supply chain: Security,
transparency, and traceability,” IEEE Access, vol. 11, pp. 35467–35480, Apr. 2023.
3. R. Sharma, P. Singh, and A. Gupta, “AI-driven crop yield prediction using convolutional neural networks,”
Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 7891–7902, Dec. 2023.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS)
ISSN No. 2454-6194 | DOI: 10.51584/IJRIAS |Volume X Issue IX September 2025
www.rsisinternational.org
Page 249
4. V. Kumar, A. Yadav, and R. Singh, “Secure IoT-blockchain integrated architecture for smart agriculture,”
Computers and Electronics in Agriculture, vol. 210, pp. 107996, Feb. 2024.
5. X. Li, H. Wang, and J. Chen, “AI and IoT-based crop monitoring system: A case study,” IEEE Internet of
Things Journal, vol. 11, no. 3, pp. 2120–2132, Mar. 2024.
6. A. Z. Babar and O. B. Akan, “Sustainable and precision agriculture with the Internet of Everything (IoE),”
Journal of Agricultural Informatics, vol. 15, no. 2, pp. 102–115, Apr. 2024.
7. N. S. Sizan, M. A. Layek, and K. F. Hasan, “A secured triad of IoT, machine learning, and blockchain for
crop forecasting in agriculture,” International Journal of Computer Applications, vol. 182, no. 5, pp. 45–
56, May 2025.
8. M. S. M. Rafi, M. Behjati, and A. S. Rafsanjani, “Reliable and cost-efficient IoT connectivity for smart
agriculture: A comparative study of LPWAN, 5G, and hybrid models,” IEEE Internet of Things Journal,
vol. 12, no. 3, pp. 1578–1590, Mar. 2025.
9. L. Aldhaheri, A. S. Almuhammadi, and M. M. Abouelela, “LoRa communication for agriculture 4.0:
Opportunities, challenges, and future directions,” IEEE Access, vol. 12, pp. 22534–22545, Sep. 2024.
10. Md. M. Hossain, T. Jahan, and S. Rahman, “Smart-Agri: A smart agricultural management with IoT-ML-
blockchain integrated framework,” International Journal of Advanced Computer Science and Applications,
vol. 14, no. 7, pp. 235–243, Jul. 2023.
11. R. Mehra, S. Sharma, and K. Jain, “Blockchain and IoT in smart agriculture: Analysis, opportunities,
challenges and future research directions,” International Journal of Advanced Research in Computer
Science, vol. 15, no. 2, pp. 120–132, May 2025.
12. S. Mahmood, M. Zubair, and R. Khan, “Artificial intelligence-driven blockchain and Internet of Things:
Emerging applications in precision agriculture,” Environmental Engineering and Management Journal, vol.
34, no. 3, pp. 215–227, Mar. 2025.
13. P. Singh and A. Verma, “Integrated IoT, AI, and blockchain framework for sustainable growth in
aquaculture,” Computers and Electronics in Agriculture, vol. 225, pp. 107648, Feb. 2025.