AGRISURE AI : INTELLIGENT CROP DAMAGE ASSESSMENT FOR INSURANCE AUTOMATION

This paper presented. AgriSure AI: Intelligent Crop Damage Assessment for Insurance Automation, an integrated artificialintelligence- to modernize traditional agricultural insurance systems. The "AgriSure AI: Intelligent Crop Damagedrivenframeworkdesigned.                                                                                                                                                                                                                                     Assessment for Insurance Automation" Demonstrates. how AI may renovate and reshape the agricultural insurance market. The system involving the integration of the high-quality. image processing deep-learning models and automated report generation is fulfilling the primary objective which is the fast precise and automatic assessment of crop damage.The conventional method of crop assessment requires numerous. visits by agricultural officers which is time-consuming. This is therefore where AgriSure AI comes in with its transparent. and unbiased crop assessment service. The system will be capable of identifying the damaged. area as well as determining crop stress within seconds using drone Satellite and MOBILE images. Even though the system is doing outstanding work a great starting point for improvement. is as follows: Datasets real-time tracking multiple crops and connection with agricultural networks. These will make the system much better. In the end it is a great example to have AgriSure AI. Great technology that can bring a significant impact to. the agricultural and insurance. industry through the use of Artificial Intelligence. The technology holds speed accuracy transparency and scalability making a huge difference in ascertaining. fairness and timeliness regarding crop insurance to the farmer. Currently AgriSure AI has the ability to receive periodic imagery uploads via drones smartphones and satellite snapshot updates. The technology can bring. a significant impact to the agricultural industry because it managed to change the traditional crop assessment process.

[1]          I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.   [2]          T. M. Lillesand, R. W. Kiefer, and J. W. Chipman, Remote Sensing and Image Interpretation, 7th ed. Hoboken, NJ, USA: Wiley, 2015.   [3]          J. C. Russ, The Image Processing Handbook, 6th ed. Boca Raton, FL, USA: CRC Press, 2011.   [4]          A.  Kamilaris  and  F.  X.  Prenafeta-Boldú, ―Deep learning in agriculture: A survey,‖ Comput. Electron. Agric., vol. 147, pp. 70–90, Apr. 2018.   [5]          A. Singh, B. Ganapathysubramanian, A. K. Singh, and S. Sarkar, ―Machine learning for plant stress phenotyping in agriculture,‖ Trends Plant Sci., vol. 21, no. 2, pp. 110–124, Feb. 2016.   [6]          N. Kussul, M. Lavreniuk, S. Skakun, and A. Shelestov, ―Deep learning classification of land cover and crop types using remote sensing data,‖ IEEE Geosci. Remote Sens. Lett., vol. 14, no. 5, pp. 778– 782, May 2017.   [7]          S. K. Jha et al., ―Automated crop insurance assessment using remote sensing and machine learning,‖ J. Agric. Informatics, vol. 10, no. 3, pp. 45–58, 2019. [8]          M. G. Selvaraj et al., ―Convolutional neural networks for AI-powered crop disease detection,‖ Plant Methods, vol. 16, no. 1, pp. 1–14, 2020.   [9]          European Space Agency, ―Sentinel-2 user handbook,‖ ESA, Paris, France, 2015. [Online]. Available: https://sentinel.esa.int   [10]      U.S. Geological Survey, ―Landsat 8 data users handbook,‖ USGS, Reston, VA, USA, 2019. [Online]. Available: https://landsat.usgs.gov