The paper “Artificial-intelligence and sensing techniques for the management of insect pests and diseases in cotton: a systematic literature review”, published in The Journal of Agricultural Science, has been chosen as the latest Editorial Highlight and is freely available to download for one month.

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 systematic literature review, we surveyed papers on the use of AI for detection and diagnosis of diseases and insect pests in cotton published between 2014 and 2021. The results show that AI techniques were employed – mainly – in the context of (i) image segmentation, (ii) feature extraction, and (iii) classification. Image segmentation is the process of partitioning a digital image into multiple image segments to locate objects (e.g., insect pests or diseases) and boundaries. The most commonly used algorithm, in image segmentation, was k-means. The feature extraction process takes as input the results of the image segmentation and efficiently represents the most informative parts of the image (e.g., boundary, shape, color and texture). In feature extraction, histograms of oriented gradients, partial least-square regression, discrete wavelet transformation, and enhanced particle-swarm optimization were equally used. Classification techniques process information from images or from field sensors to detect insect pests or diseases. In classification, the most commonly used algorithms were support vector machines, fuzzy inference, back-propagation neural-networks and, recently, convolutional neural networks. The 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 suggests the following future works related to the use of AI and sensing techniques for management of diseases and insect pests, in cotton: (1) Implement predictive models to understant when and where the diseases and insect pests will attack. (2) Implement prescriptive models to define how to control diseases and insect pests. (3) Predict the spread of pests with smart pheromone-traps. (4) Develop diagnostic models of diseases. (5) Make multi-detection models of diseases or pests. (6) Define a cotton-crop management-system using a cognitive-computing architecture. (7) Finally, develop smart sticky-traps for pests. Thus, the diagnostic, predictive and prescriptive models can help answer these questions, respectively: Why did it happen? What will happen? and What should we do?

The Journal of Agricultural Science Editorial Highlights are selected by the Editor-in-Chief and are freely available for one month. View the recent selections here.