AgDataBox-IoT - application development for agrometeorological stations in smart

Abstract

Currently, Brazil is one of the world's largest grain producers and exporters. Agriculture has already entered its 4.0 version (2017), also known as digital agriculture, when the industry has entered the 4.0 era (2011). This new paradigm uses Internet of Things (IoT) techniques, sensors installed in the field, network of interconnected sensors in the plot, drones for crop monitoring, multispectral cameras, storage and processing of data in Cloud Computing, and Big Data techniques to process the large volumes of generated data. One of the practical options for implementing precision agriculture is the segmentation of the plot into management zones, aiming at maximizing profits according to the productive potential of each zone, being economically viable even for small producers. Considering that climate factors directly influence yield, this study describes the development of a sensor network for climate monitoring of management zones (microclimates), allowing the identification of climate factors that influence yield at each of its stages.•Application of the internet of things to assist in decision making in the agricultural production system.•AgDataBox (ADB-IoT) web platform has an Application Programming Interface (API).•An agrometeorological station capable of monitoring all meteorological parameters was developed (Kate 3.0).

Keywords: AgDataBox; AgDataBox-IoT-Meteology; Big data; Internet of things; Precision agriculture; Wireless communication networks.

Graphical abstract

Fig. 1

Development of agricultural and industrial revolutions. Source: .

Fig. 2

AgDataBox platform architecture design.

Fig. 3

Hardware and software development layer scheme.

Fig. 4

Schematic diagram of the agrometeorological station.

Fig. 5

Diagram of the electronic circuit of the agrometeorological station board.

Fig. 6

Installed network topology.

Fig. 7

Representation of fog computing. source: adapted from Stojmenovic and Wen .

Fig. 8

Flowchart of the entity-relationship database model.

Fig. 9

Location of the study area. Scenario analyses.

Fig. 10

Delimitation of management zones 1 (Z1), 2 (Z2), 3 (Z3), and 4 (Z4) in the experimental area.

Fig. 11

Architecture of agrometeorological stations in (a) 2018, (b) 2019, and (c) 2020.

Fig. 12

Illustration of stations with data collection problems: (a) wind-damaged station and (b) part of the sensors carried by the wind.

Fig. 13

Location of the ADB-IoT local server installation.

Fig. 14

Illustrative communication flowchart between stations, local server, and the server located in the PTI data center.

Fig. 15

AgDataBox-IoT user interface for viewing weather variables.

Fig. 16

ADB user Interface for filtering data by the period of interest.

Fig. 17

Statistical parameters of agrometeorological stations regarding the relative air humidity.

Fig. 18

Statistical parameters of agrometeorological stations regarding average temperature.

Fig. 19

Statistical parameters of the variable relative air humidity by management zone (MZ).

Fig. 20

Statistical parameters of the variable mean temperature by management zone (MZ).

Fig. 21

Statistical parameters of the variable mean relative humidity by management zone (MZ).