Article Preview
Top1. Introduction
The United Nations estimates that it is the need to increase the food production to 50 percent by the middle of the current century (FAO, 2009). Agricultural production tripled during the last decades as the world’s population doubled (Kitzes et al., 2008). Agriculture remains essentially a primary source of food for the population and raw material for a large number of industries (da Silva et al., 2009). Population growth, climate change and bio-energy crops are worldwide trends that are increasing the importance of using science to improve agriculture (Tilman et al., 2011). With the need to produce more food using fewer inputs, agriculture is seeking new products, practices and technologies. Research activities centering on genomics, bioinformatics and computational biology of plants and animals enable the scientists and organizations to better feed the world and improve the quality of food and animal crops. Progress in agricultural growth can serve as a critical position for designing successful strategies to transform the economy and meet sustainable development (Christiaensen et al., 2010) and the investments in agricultural research play a key role to agricultural growth. Farmers will have the tools to get the most from every acre. The future of farming depends largely on adoption of cognitive solutions. While large scale research is still in progress and some applications are already available in the market, the industry is still highly underserved. When it comes to handling realistic challenges faced by farmers and using autonomous decision making and predictive solutions to solve them, farming is still at a budding stage (Jones et al., 2017). Research on new generation agricultural design models shows that the data is most important parameter for on-farm decision support, research investment and policy decision making. The agricultural industry will be transformed by data science and artificial intelligence. Collecting reliable agriculture data for farm management decision making is important scenario. The developments in the concept of smart farming make agriculture more efficient and effective with the help of high-precision algorithms (Baseca et al., 2019). The mechanism used in smart farming is machine learning (ML), the scientific field that gives machines the ability to learn without much programming. It has emerged together with big data technologies and high-performance computing to create new opportunities to ease, quantify and understand data intensive processes in agricultural operational environments. The developments indicate that agriculture can benefit from machine learning at every stage like spices management, field management, crop management and livestock management. The artificial intelligence (AI) and machine learning are used in a number of agricultural applications today include the yield prediction algorithms based on weather and historical yield data, image recognition algorithms to detect pest and diseases in plants and robotics to harvest different types of specialty crops (Tibbetts 2018). This aspect needs an adaptive method to control the data sources and decision-making systems for better production and marketing with less waste of resource. Agriculture big data is playing important role by incorporating the AI and ML. The farmers are using data to calculate harvest yields, fertilizer demands, cost savings and even to identify optimization strategies for future crops as smart machines and sensors on farms and farm data grow in quantity and scope, farming processes will become increasingly data driven and data enabled.