Plant Disease Detection, Diagnosis, and Management: Recent Advances and Future Perspectives

A vast range of plant diseases and pests are known to affect agricultural crop and cause significant crop losses. For over many years the researchers are working on enabling a better approach for disease detection, diagnosis and control. The development of modern technology such as implementing sensors, machine learning has made it possible to identify plant pathogens quickly, precisely, and sensitively. However, the application of such advanced technologies has always been a challenge as the green house and field applications are complex and require different designDesign studies. Selection of the type of sensor to be used, the sensor platform, and other accessory techniques require great technical knowhow since all the pathosystems are unique and differ in host–pathogen–environment interactions. Therefore, large database needs to be created to enable deeper insight into these interactions. Hence, the use of a quartz crystal microbalance (QCM), surface-enhanced Raman spectroscopy (SERS), radiofrequency identification (RFID) microchips, microfluidic systems, and smartphone-based fingerprinting of leaf volatiles are some of the examples of use of sensors and other modern technologies. Wearable sensors can be used to detect and manage biotic stress. Modern machine learning techniques are created to achieve quick data analysisData analysis of such complicated datasets, which not only saves time but also permits an objective examination of the data. The potential to find likely coherent parameters during plant-pathogen-environment interactions is particularly great for deep learning systems. This aids farm management in the context of smart agriculture and assists pathologists in disease diagnosis. The powerful computers, sharp displays, and comprehensive built-in accessory sets, including high-definition cameras and smartphones are a very new way to help diagnose diseases. For the purpose of diagnosing diseases, this method makes use of image processing technology, which is typically integrated with artificial intelligence such as neural networks. So, this chapter will present the work of several researchers regarding application of sensors and other technologies in plant disease detection, diagnosis, and control.