A proposal for a multi‐domain data fusion strategy in a climate‐smart agriculture context

Abstract

Agriculture provides food, raw materials, and employment opportunities for a significant percentage of the world's population. Climate, economic, political, social, and other conditions affect decision making in agricultural processes. In many cases, these conditions imply the loss of suitability of many areas for some traditional crops. In contrast, these areas can produce new crops by taking advantage of changing conditions. In this sense, having reliable tools and information for decision making is essential in adapting to new agricultural productivity scenarios. The above implies having sufficient and relevant data sources to reduce the uncertainty in the decision‐making processes. However, data by nature tend to be diverse in structure, storage formats, and access protocols. Data fusion tasks have been immersed in a multitude of applications and have been approached from different points of view when implementing a suitable solution. We propose a multi‐domain data fusion strategy to support data analysis tasks in agricultural contexts. We also describe all the data sources collected, which are the main input to the proposed strategy. The combined data sources were also evaluated through a preliminary exploratory analysis in a multi‐label learning approach. Finally, the data fusion strategy is explained through an example in agricultural crop production.

Agricultural Big Data Architectures in the Context of Climate Change: A Systematic Literature Review

“…On the other hand, the analysis tools that come from the Hadoop ecosystem were used in different papers. For example, Lopez et al, used HIVE, XPath, and XQuery [49]. On the other hand, Semlali et al, usde Map-Reduce with Spark and Storm [40].…”

“…For crop management, data from weather stations, agroforestry resources, sensors, remote-sensing images, GPS positioning, satellite information engines such as Google Earth, and external private/public data providers were used [47,55]. For such action, in some cases, as in Colombia, local data systems such as AVA CDKN, CVC, IDEAM, Agronet MinAgriculture, Open Data Colombia MinTIC, SAC, FAO, DANE, and DNP were used [49]. Each data source provides temperature, humidity, illumination, atmospheric pressure, soil electrical conductivity, soil and vegetation moisture content, and soil salinity [52].…”

“…The authors had to extract metadata from AquaMaps reference files, e.g., size, description, data provider, etc., and then make the metadata conform to NetCDF (Network Common Data Form) conventions. On the other hand, Lopez et al, used Hadoop tools, such as HDFS, Sqoop, Flume, and Kafka, to store and process the data in a Data Lake, which allows the storing of raw, semi-processed, and processed data in different storage areas [49]. A similar case is that of Gad et al, in which they used Hadoop technologies to process and store data from a data warehouse.…”

“…The authors used Map-Reduce to process data that are not stored in memory to be stored in Hadoop [67]. Manogaran et al [63], Lopez et al [49], and Reddy and Sureshbabu [39] also used Map-Reduce to process the data and then stored the data in Hadoop. They used Apache Hbase and Apache Hive [39,63].…”

Multi-Label Data Fusion to Support Agricultural Vulnerability Assessments

“…This study is oriented to the development of an innovative data fusion strategy using new technologies. Therefore, we managed the databases by implementing a Data Lake [52], which is described in detail in [53].…”