Artificial-intelligence and sensing techniques for the management of insect pests and diseases in cotton: a systematic literature review

Abstract

Integrated pest management (IPM) seeks to minimize the environmental impact of pesticide application, and reduce risks to human and animal health. IPM is based on two important aspects – prevention and monitoring of diseases and insect pests – which today are being assisted by sensing and artificial-intelligence (AI) techniques. In this paper, we surveyed the detection and diagnosis, with AI, of diseases and insect pests, in cotton, which have been published between 2014 and 2021. This research is a systematic literature review. The results show that AI techniques were employed – mainly – in the context of (i) classification, (ii) image segmentation and (iii) feature extraction. The most used algorithms, in classification, were support vector machines, fuzzy inference, back-propagation neural-networks and recently, convolutional neural networks; in image segmentation, k-means was the most used; and, in feature extraction, histogram of oriented gradients, partial least-square regression, discrete wavelet transform and enhanced particle-swarm optimization were equally used. The most used sensing techniques were cameras, and field sensors such as temperature and humidity sensors. The most investigated insect pest was the whitefly, and the disease was root rot. Finally, this paper presents future works related to the use of AI and sensing techniques, to manage diseases and insect pests, in cotton; for instance, implement diagnostic, predictive and prescriptive models to know when and where the diseases and insect pests will attack and make strategies to control them.

Artificial neuronal networks are revolutionizing entomological research

“…The development of such predictive models involves the integration of various data sources, including weather patterns, crop density, and the presence of other pests. The AI can analyse these factors and identify patterns that may indicate an increased risk of infestation (e.g., Toscano‐Miranda et al., 2022). The model can then predict where and when these pests are likely to appear, allowing farmers and other stakeholders to take proactive measures to prevent or mitigate their impact.…”

Rapid detection of multi‐scale cotton pests based on lightweight GBW‐YOLOv5 model

“…WIoU enhances the model's precision in locating cotton pests by balancing the learning of high and low-quality samples. The WIoU loss function is defined in Eqn (5).…”

“…3,4 This method is highly dependent on the accuracy of the extracted features and cannot be adapted to multi-scene and multi-category pest recognition tasks. 5 The primary objective of object detection using deep learning technology is the rapid and accurate identification of multiple pests. However, current detection algorithms have limitations.…”

“…Early pest recognition combined image processing algorithms with traditional machine learning techniques to extract morphological characteristics of pests using artificial design algorithms 3,4 . This method is highly dependent on the accuracy of the extracted features and cannot be adapted to multi‐scene and multi‐category pest recognition tasks 5 . The primary objective of object detection using deep learning technology is the rapid and accurate identification of multiple pests.…”

The Novel ML Approaches on Wheat Disease by CLF and FOHF of Image Equalization Techniques

“…In a number of real-world applications, the isotropic assumption is false and does not accurately reflect the probable connection between the sample's dimensional components. [13][14][15][16] As a result of the growth of artificial intelligence [14], image processing and classification research makes substantial use of deep learning techniques [15]. Dong et al [14] suggested use a convolutionl neural network with differential amplification to identify wheat diseases.…”