• Keerthana
• Dr. Sandeep Bhat

Pests play a significant impact in crop destruction. Currently, Pest infestations are causing crop production to decline, which lowers the output rate. Each year, insect infections cause up to 20–40% of crops to be lost. Conventional techniques for detecting pests are manual, labor-intensive, and more likely to make mistakes. So, Early detection can minimize crop loss, Reduced use of chemical pesticides, Ensures sustainable farming practices. CNN is used to identifying patterns, objects in images and have the Ability to process complex images and detect pests accurately. Where automated identification saves time and labor Typically, well-trained Convolutional Neural Networks (CNNs) on high-quality and diverse datasets can achieve accuracy rates exceeding 90%, with some studies reporting figures as high as 95%. For instance, a model might exhibit a training accuracy of 95%, a validation accuracy of 92%, and a test accuracy of 89%.

CNN.

"AUTOMATING EARLY PEST DETECTION FOR SUSTAINABLE AGRICULTURE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.977-981, July-2025, Available :http://www.jetir.org/papers/JETIRGX06181.pdf

"AUTOMATING EARLY PEST DETECTION FOR SUSTAINABLE AGRICULTURE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp977-981, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06181.pdf