Agricultural Big Data is a set of technologies that allows responding to the challenges of the new data era. In conjunction with machine learning, farmers can use data to address problems such as farmers’ decision making, water management, soil management, crop management, and livestock management. Crop management includes yield prediction, disease detection, weed detection, crop quality, and species recognition. On the other hand, livestock management considers animal welfare and livestock production. The purpose of this paper is to synthesize the evidence regarding the challenges involved in implementing machine learning in agricultural Big Data. We conducted a systematic literature review applying the PRISMA protocol. This review includes 30 papers published from 2015 to 2020. We develop a framework that summarizes the main challenges encountered, machine learning techniques, and the leading technologies used. A significant challenge is the design of agricultural Big Data architectures due to the need to modify the set of technologies adapting the machine learning techniques as the volume of data increases.

The data generated in modern agricultural operations are provided by diverse elements, which allow a better understanding of the dynamic conditions of the crop, soil and climate, which indicates that these processes will be increasingly data-driven. Big Data and Machine Learning (ML) have emerged as high-performance computing technologies to create new opportunities to unravel, quantify and understand agricultural processes through data. However, there are many challenges to achieve the integration of these technologies. It implies making some adaptations to ML for using it with Big Data. These adaptations must consider the increasing volume of data, its variety and the transmission speed issues. This paper provides information on the use of Big Data and ML for agriculture, identifying challenges, adaptations and the design of architectures for these systems. We conducted a Systematic Literature Review (SLR), which allowed us to analyze 34 real cases applied in agriculture. This review may be of interest to computer or data scientists and electronic or software engineers. The results show that manipulating large volumes of data is no longer a challenge due to Cloud technologies. There are still challenges regarding (1) processing speed due to little control of the data in its different stages, raw, semi-processed and processed data (value data); (2) information visualization systems, which support technical data little understood by farmers.

No abstract

No abstract

Data warehouses (DW) must integrate information from the different areas and sources of an organization in order to extract knowledge relevant to decision-making. The DW development is not an easy task, which is why various design approaches have been put forward. These approaches can be classified in three different paradigms according to the origin of the information requirements: supply-driven, demand-driven, and hybrids of these. This article compares the methodologies for the multidimensional design of DW through a systematic mapping as research methodology. The study is presented for each paradigm, the main characteristics of the methodologies, their notations and problem areas exhibited in each one of them. The results indicate that there is no follow-up to the complete process of implementing a DW in either an academic or industrial environment; however, there is also no evidence that the attempt is made to address the design and development of a DW by applying and comparing different methodologies existing in the field.