Pests pose a major danger to a variety of industries, including agriculture, public health, and ecosystems. Fast and precise pest detection, as well as the ability to predict infestations, are required for effective pest management tactics. This paper provides a comprehensive literature review on this subject to provide an overview of the state of research on pest detection and infestation prediction. The paper investigates and presents background information on the necessity of pest control as well as the difficulty in recognizing pests and forecasting. Several strategies, including approaches to data collection, modeling, and assessment of models, are reviewed in the research described. The authors examine various pest detection methods involving the utilization of convolutional neural networks and several object detection architectures categorized broadly into one‐stage and two‐stage object detection algorithms. Methods for predicting pest infestations that involve regression, classification, and time series forecasting are also thoroughly investigated. The challenges of recognizing pests and predicting infestations are underlined, as are issues with data quality, feature selection, and model interpretability. The report also indicates the limitations to pest detection and infestation prediction as well as intriguing topics for further research on the same. The findings of the literature research demonstrate how Artificial Intelligence, Computer Vision, and the Internet of Things have been applied for Pest Detection and Infestation Prediction. The research serves as a base for surveying and summarizing the approaches utilized for the task of pest detection (an object detection problem) and pest infestation prediction (a forecasting problem) and its findings and recommendations serve as a platform for future study and the development of effective pest management solutions.This article is categorized under: Application Areas > Health Care Technologies > Machine Learning Technologies > Prediction

中文翻译：

---

用于害虫检测和侵染预测的机器学习：综合综述


害虫对农业、公共卫生和生态系统等多种行业构成重大威胁。有效的害虫管理策略需要快速、精确的害虫检测以及预测侵扰的能力。本文对这一主题进行了全面的文献综述，以概述害虫检测和侵染预测的研究现状。本文调查并介绍了害虫防治的必要性以及害虫识别和预报的困难的背景信息。所描述的研究中回顾了几种策略，包括数据收集、建模和模型评估的方法。作者研究了各种害虫检测方法，涉及利用卷积神经网络和几种对象检测架构，这些架构大致分为单阶段和两阶段对象检测算法。还深入研究了涉及回归、分类和时间序列预测的害虫侵扰预测方法。强调了识别害虫和预测侵扰的挑战，以及数据质量、特征选择和模型可解释性的问题。该报告还指出了害虫检测和侵染预测的局限性，以及进一步研究的有趣主题。文献研究的结果展示了人工智能、计算机视觉和物联网如何应用于害虫检测和侵染预测。 该研究作为调查和总结用于害虫检测（目标检测问题）和害虫侵扰预测（预测问题）任务的方法的基础，其发现和建议作为未来研究和开发的平台。有效的害虫管理解决方案。本文分类为：应用领域 > 医疗保健技术 > 机器学习技术 > 预测