A Survey of IoT and Machine Learning Based Monitoring of the Growth of Crops Using Blockchain Technology

The world is rapidly changing as a result of technological advancement. New techniques and frameworks are being created over the globe in many application fields. In recent years, there has been a lot of interest in using machine learning and Internet of Things (IoT) technologies in agricultural practices. Examining the state of research and recent developments in crop monitoring, particularly in the context of IoT and machine learning, is the goal of this review. The evaluation covers a range of topics, including the different IoT device and sensor types used, the machine learning techniques used for data analysis, and the use of blockchain technology for improved data security and traceability. This review paper investigates how IoT and machine learning can be used to track agricultural growth, with a focus on how blockchain technology can be used. The advancement in technology can reduce the burden of feeding such a huge population around the world. In this paper, monitoring using machine learning and IoT for the growth of crops using Blockchain Technology is being reviewed This review outlines the advantages and difficulties related to the IoT and machine learning-based agricultural monitoring systems through a thorough analysis of the available literature. It highlights how real-time data collecting on weather conditions, soil moisture, and other pertinent characteristics that affect crop growth is made possible by IoT devices, including sensors and actuators. Additionally, it investigates the use of machine learning algorithms for data analysis, crop growth pattern prediction, and resource allocation optimization for better agricultural practices The integration of blockchain technology is also highlighted in this assessment as a viable way to improve data security and transparency in the context of crop monitoring. It looks at the potential of blockchain to provide end-to-end traceability in the agricultural supply chain, ensure data integrity, foster stakeholder confidence, enable smart contracts for automated transactions, and more. The results of this review add to a thorough understanding of the advantages and difficulties of implementing IoT- and machine learning-based systems for crop monitoring. The knowledge acquired from this analysis will help direct future research and development projects that will use new technologies for productive and sustainable agricultural practices. The promise of combining IoT, machine learning, and blockchain technology for agricultural growth monitoring is highlighted by this review's findings. Developing agricultural practices and promoting the cause of global food security, lays the groundwork for future research and innovation in this field. After review, it is found that models previously developed need further optimization. These models can be trained faster but their evaluation speed is slow. The problem of overfitting and underfitting needs to be tackled.