• Venkata Sai K
• Jyothi Sravanthi P
• Vyshnavi M
• K V S S Vijay
• Vijaya Lakshmi G

Around a quarter of the crop is lost to pests and diseases every year. The biggest problem is the lack of knowledge about the condition and its treatments. In total, billions of dollars every year are being used in fungicides, out of which millions worth of wrong pesticides are incorrectly used. Early detection and diagnosis are the most significant practice for eradicating leaf diseases. For a long time, people have been working in this field, but the results were not appropriate enough. To achieve this, we discuss a solution that identifies the plant disease and provides a solution for cure using a Transfer learning-based Convolution Neural Network (CNN). EfficientNetV2B0 is the pre-trained model used in this paper. In this paper, we classify different diseases of apples, potatoes, and tomatoes. The quantity of crop loss will be reduced if leaf disease is detected early and diagnosed. Due to a lack of knowledge about fungicides, some farmers are either applying the wrong or excessive fungicides, damaging the soil and food. This will help in using a suitable solution in a suitable amount. So we can have healthy crops and reduce soil pollution.

Transfer Learning, EfficientNetV2B0.

"Leaf Fungicide Recommendation using EfficientNetV2B0", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 11, page no.d510-d517, November-2022, Available :http://www.jetir.org/papers/JETIR2211370.pdf

"Leaf Fungicide Recommendation using EfficientNetV2B0", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 11, page no. ppd510-d517, November-2022, Available at : http://www.jetir.org/papers/JETIR2211370.pdf