DATA ENIGMA: A REVIEW OF DATA IN AGRICULTURE

As the economy grows, the people's demand for food is getting more and more. With agriculture presenting a substantial industry with a high importance, an equal increase is necessary. Facing the challenges of climate change that affects the supply chain of this industry or creating scarcity for certain resources like water are just some of the many obstacles ahead. Agriculture is a sector that does not only need traditional production practices and experiences but also requires the aid of modern science, management, and technology methods to gain a higher productivity level to meet demand in the future. Entering the 21st century, the sudden surge of data has occurred, due to the invention and creation of internet technology, cloud computing, and others that allowed data collection and storage on a massive scale. Based on this context, the term big data technology has been born. Applying big data to agriculture can achieve various things that can have a meaningful impact on human life. For instance, timely monitoring the agricultural products or increasing the output of agricultural products. The profound insight and potential improvement found in data are valuable. Many industries have benefited from its analysis, but agriculture has still faced a lot of deficits in this context. Since the 1970s, information technology has shifted agriculture from artificial towards a more intelligent and precise unit. The goal to use fewer resources consumption to gain higher agricultural harvest is the desired efficiency and effectiveness ratio targeted. However, such goals are not easily achieved as agriculture involved a wide range of connotations in all aspects of natural resources and production processes. Examples of such includes elements include breeding, planting, fertilization, pest control, and more. Today, the deployment of modern technological devices such as sensors, remote controls, and others is common. While these ideas are fundamentally providing an accumulation of agricultural data, enabling hopefully also a surge in data, developing countries or farms on a smaller scale are less able to benefit or implement such ideas. Not only that but for precision agriculture, the process of obtaining and accurately processing different types of data attributes is still a challenge. Agriculture lacks standardization, especially in terms of data management given that this is a relatively new and unexplored topic. There is still a high occurrence of inaccuracy and human error when it comes to data quality. Second, the existing agricultural information is often time-based and designed on traditional agricultural practices that don't satisfy big data requirements