Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{200157,
        author = {AISHVARYA S and GNANASEKAR V and SRISATHYA K and ACKSHARITHA C M and ARTHI C and SOWNDARIYA G and LOGESHWARI S},
        title = {Agrishield AI: Satellite-Based Crop Insurance Verification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {488-495},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200157},
        abstract = {Natural events can seriously affect farming output and create sudden financial stress for cultivators. When this happens, compensation requests are commonly submitted through crop insurance programs. In many regions, confirming whether the reported loss is genuine still depends on field visits and handwritten assessments. This procedure may become slow when many requests arrive at the same time and can also vary according to individual judgement. The present study develops Agrishield AI, a digital framework for supporting claim validation through data-driven analysis. Instead of relying only on physical inspection, the system observes farmland conditions using earth observation images captured at separate time intervals. Changes in plant growth indicators are examined to identify possible damage patterns after a reported event. Decision models then help categorize each request for acceptance, rejection, or further scrutiny. A web-based application is developed to enable seamless interaction between farmers, researchers, and insurance administrators. Farmers can submit insurance claims by providing farm details and geographic boundaries. The system then retrieves satellite data using Google Earth Engine and performs NDVI-based analysis. Machine learning models such as Logistic Regression and Random Forest are applied to classify claims into categories such as acceptance, rejection, or manual review. The proposed system improves the efficiency, accuracy, and transparency of the crop insurance process by reducing manual intervention and supporting data-driven decision-making. It also enables large-scale agricultural monitoring and helps reduce fraudulent claims, thereby benefiting both farmers and insurance providers.},
        keywords = {Crop Insurance, Satellite Imagery, NDVI, Machine Learning, Google Earth Engine, Claim Verification.},
        month = {May},
        }