Can AI-Based Crop Health Monitoring and Predictive Analytics Attain Sustainable Crop Production?
TL;DR
How smart sensors, satellite and aerial imaging platforms and cloud-based data infrastructures play a vital role in the development of crop health monitoring and predictive analytics is discussed, including the heterogeneity of data, false positives, and the interpretability of the AI models.
Abstract
Sustainable agriculture is critical towards providing food security in the world and at the same time dealing with environmental degradation as well as shortages of resources. The loss of soil biodiversity, an increased resistance of pests and pathogens, and general decrease in crop yield have been contributed by traditional farming methods especially excessive use of agrochemicals. The deployment of cloud computing and remote sensing through the combination of artificial intelligence (AI) has allowed the expansion and scope of smart agriculture to reach cost-effective and responsive solutions to various farming settings. Nevertheless, the existing literature does not usually consider the potential of these technologies combined and does not provide a comprehensive approach to the implementation of these technologies in the synergy of their application. This review carries out extensive discussion of AI-based sustainable crop production by combining cloud computing and remote sensors. It discusses how smart sensors, satellite and aerial imaging platforms and cloud-based data infrastructures play a vital role in the development of crop health monitoring and predictive analytics. The major issues such as the heterogeneity of data, false positives, and the interpretability of the AI models are discussed critically. The areas of future research are also proposed to aid in creating multi-modal, robust, and interpretable AI systems that can propel sustainable, intelligent, and resilient agricultural ecosystems.