Survey on crop pest detection using deep learning and machine learning approaches.

Area of Science:

• Agricultural Science
• Computer Science
• Data Science

Background:

• Effective pest management and control are vital for commercial food standards, as pests significantly impact crop quality and productivity.
• Traditional methods of diagnosing crop abnormalities, pests, or deficiencies by human experts are costly and time-consuming.
• Developing new tools for early pest disease diagnosis is critical to prevent major crop loss.

Purpose of the Study:

• To provide an overview of recent research in crop pest and pathogen identification using machine learning and deep learning techniques.
• To highlight modern approaches for automated monitoring of agricultural fields for pest detection.
• To define plant pest detection and categorize methods for identifying pests in crops like citrus, rice, and cotton.

Main Methods:

• Review of machine learning techniques including Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and Naive Bayes (NB).
• Exploration of deep learning methods such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Deep Convolutional Neural Network (DCNN), and Deep Belief Network (DBN).
• Analysis of strategies for automatic monitoring and identification of plant pests in various crops.

Main Results:

• Machine learning and deep learning techniques offer advanced solutions for crop pest detection.
• Automated monitoring systems reduce human error and effort in managing large agricultural areas.
• These methods enhance crop protection and improve overall crop efficiency and productivity.

Conclusions:

• Modern approaches utilizing machine learning and deep learning significantly improve crop pest detection and management.
• Automated pest identification systems are essential for increasing crop productivity and ensuring food standards.
• The reviewed techniques enable efficient monitoring, leading to better crop protection and reduced losses.