Blockchain-Enabled Digital Land Registry with AI-Driven Validation for Agriculture 5.0

Abstract

Reliable land ownership records are essential for sustainable agricultural development, yet conventional land registration systems often depend on centralized databases that are susceptible to unauthorized modifications, security threats, and inefficient verification processes. To overcome these limitations, this study presents a blockchainenabled digital land registry integrated with Artificial Intelligence (AI) for Agriculture 5.0. The proposed framework employs blockchain technology to maintain transparent, decentralized, and immutable records of land transactions, while the InterPlanetary File System (IPFS) securely stores associated land documents in a distributed environment. Smart contracts automate the registration and ownership transfer process, ensuring accuracy and reducing manual intervention. To strengthen transaction validation, several machine learning models, including Logistic Regression, Random Forest, Support Vector Machine (SVM), XGBoost, and LightGBM, are evaluated for identifying fraudulent activities. Experimental analysis shows that the LightGBM model delivers the best performance with an accuracy of 99.35%, while a CNN2D-based deep learning model further improves the detection accuracy to 99.52%. A web-based application demonstrates the practical implementation of the proposed framework, enabling secure land registration, intelligent transaction validation, and efficient fraud prevention. The results indicate that the proposed approach offers a dependable and transparent solution for modern agricultural land management.