Crop Knowledge Discovery Based on Agricultural Big Data Integration

Abstract

Nowadays, the agricultural data can be generated through various sources, such as: Internet of Thing (IoT), sensors, satellites, weather stations, robots, farm equipment, agricultural laboratories, farmers, government agencies and agribusinesses. The analysis of this big data enables farmers, companies and agronomists to extract high business and scientific knowledge, improving their operational processes and product quality. However, before analysing this data, different data sources need to be normalised, homogenised and integrated into a unified data representation. In this paper, we propose an agricultural data integration method using a constellation schema which is designed to be flexible enough to incorporate other datasets and big data models. We also apply some methods to extract knowledge with the view to improve crop yield; these include finding suitable quantities of soil properties, herbicides and insecticides for both increasing crop yield and protecting the environment.

A big data smart agricultural system: recommending optimum fertilisers for crops

“…Finally, to fix restrictions of all the above papers, a data warehouse constellation schema is used in [24,26,27] to combine diverse datasets and comply with standards of agriculture Big Data. Nevertheless, there is not much important information about farming operations in the schema of [26], e.g.…”

“…The papers [26,27] are about data warehouse design and implementation. While, in [24], the authors did not build an agricultural data warehouse. They just proposed information about insecticides, herbicides, soil properties and soil pH.…”

“…Smart farming applies statistical algorithms and data mining methods on historical data to discover new agricultural knowledge or build expert systems for improving farm productivity or being used tools for farmers [1,24]. The global agricultural analytic market will increase more than 110% from $580 million in 2018 to $1.236 million in 2023 [22].…”

Data Warehouse and Decision Support on Integrated Crop Big Data

“…Moreover, the DW concerns livestock farming. Overcoming disadvantages of the star schema, the authors of Ngo and et al (2018) and Ngo and Kechadi (2020) proposed a constellation schema for an agricultural DW architecture in order to satisfy the quality criteria. However, they did not describe how to design and implement their DW.…”

“…The precision agriculture's current mission is to use the decision-support system (DSS) based on Big Data approaches to provide precise information for more control of waste and farming efficiency, such as soil nutrient (Rogovska and et al, 2019), early warning (Rembold and et al, 2019), forecasting (Bendre and et al, 2015), irrigation systems (Huang and et al, 2013), evapotranspiration prediction (Paredes and et al, 2014), soil and herbicide, insecticide optimisation (Ngo and Kechadi, 2020), awareness (Lokers and et al, 2016), supply chain (Protopop and Shanoyan, 2016) and financial services (Ruan and et al, 2019). Normally, the DSSs implement a knowledge discovery process also called data mining process, which consists of data collection and data modelling, data warehousing, data analysis (using machine learning or statistical techniques), and knowledge deployment (Dicks and et al, 2014).…”