Blockchain-based Land Registration and Ownership Management System with AI-Assisted Document Verification

Abstract

Land registration in Nepal relies on a paper-intensiveprocess requiring repeated visits to government offices, withlimited transparency and a high risk of document tampering. Thispaper presents a blockchain-based land registration and ownershipmanagement ecosystem that digitizes the workflow while preservingthe legally mandated physical and biometric verification ofthe Land Revenue Office. Citizens submit applications, completeKYC, and upload documents online, while verification officersreview claims with an AI-assisted tamper-detection pipelinecombining optical character recognition (OCR) and classicalmachine learning. Only SHA-256 digests of documents andopaque property identifiers are recorded on the Ethereum Sepoliablockchain, preserving privacy, while personal data and legaldocuments remain in PostgreSQL. A state-machine workflowenforces every step before a new Lalpurja certificate is issued.On a synthetic dataset of 2,000 Lalpurja documents, the modelachieves a ROC-AUC of 0.854 and a recall of 70% at a 10%false-positive rate. Measured API latencies confirm the practicalfeasibility of the proposed approach.