by Christian Hirsch (TU Wien)

In crop production there are still many diseases where the time of infection and outbreak in connection with the weather is still not known. Some farmers have weather stations in their fields to monitor weather conditions in order to prevent a possible spread of a disease. However, the measurements of the weather stations represent the climate within an area of several 100 m2. To overcome this problem, TU Wien and BOKU Wien are preparing an IoT infrastructure to measure micro-climate in vineyards. Many sensors are placed all over the field and the collected data will be used to create disease prediction models using machine learning algorithms.

In addition to natural disasters, crop diseases are still a major risk to crop yields in agriculture. Some diseases are already well known and studied, and there are models for these diseases that can tell a farmer the risk of its occurrence based on weather information and weather forecast. With this information the farmer is able to take steps to protect the crops right on time. However, the main causes of other diseases are still unclear, making it difficult for farmers to take steps to protect their crops. One of these diseases is the powdery mildew in vineyards.

Many fields and vineyards, used for educational and scientific purposes, are equipped with weather stations. These stations typically measure wind, precipitation, humidity, temperature and leaf wetness. The problem, however, is that the measurements of a weather station represent a whole field of several 100 m², making it impossible to detect micro-climate changes that might trigger a certain disease. To overcome this problem, TU Wien [L1] and the University of Natural Resources and Life Sciences, Vienna (BOKU Wien) [L2] will set up an Internet of Things (IoT) infrastructure consisting of small battery powered sensors [L3]. Like the weather station, the sensors will measure humidity and temperature. Additionally sensors for atmospheric pressure, soil moisture, soil temperature and CO2 equivalents will be deployed. Many sensors of the same kind will be used and placed all over the field, enabling the scientists to record climate differences within a field.

Figure 1: Simple IoT infrastructure consisting of a) the swarm (of sensors and actuators), b) the fog and c) the cloud
Figure 1: Simple IoT infrastructure consisting of a) the swarm (of sensors and actuators), b) the fog and c) the cloud.

The IoT infrastructure will consist of three basic parts: the swarm (Figure 1a), the fog (Figure 1b) and the cloud (Figure 1c). The swarm represents the set of sensors used to measure micro-climate. Typically those swarm nodes use wireless means of communication with a base station or GSM. The nodes are normally also equipped with a microprocessor powerful enough to pre-process measurements in order to reduce the amount of data that has to be transmitted. The second part of the IoT infrastructure is the fog. The fog’s main job is to communicate with the swarm and the internet, i.e., it acts as a router. The fog receives the measurements from the swarm via a wireless communication stack and transmits the data to the cloud storage. But the fog is more than just a simple router; it can also do pre-processing and simple analysis of the data before forwarding it to the cloud, known as fog- or edge computing [2]. This means that the fog can already trigger tasks, like notifications to a user, a robot or other actuators (e.g., irrigation systems) [1, 2]. Last but not least, the data from the fog will be transmitted to the cloud, which is mainly used as a database that collects all the data. In addition to acting as a simple database, the cloud also provides an interface to the data, which can, for example, visualise information for a user (user interface) and provide tools to analyse the data. Tasks done by the cloud are typically not time critical, e.g., machine-learning [1, 3].

For the specific case of analysing powdery mildew in vineyards, special swarm nodes, based on the Simblee BLE System on a Chip (SoC) have been developed. This SoC consists of an ARM-Cortex M0 processor with a BLE communication stack and an integrated antenna. This chip is used on two different swarm nodes: one that measures soil moisture, and soil temperature; the other one measures air temperature, humidity, atmospheric pressure and CO2 equivalents in the air. The fog nodes are based on the Raspberry Pi mini computer. This computer already has the ability to connect to the swarm nodes via BLE. It receives data from the swarm nodes and forwards it the cloud. The cloud is based on the open-source IoT platform Thingsboard. It already has the capability to receive data and store it in a database, and it offers a web-based user interface to present the data, as well as other interfaces to query data.

This spring, the prototypes of the swam nodes will be evaluated in the green house. Based on the results of the evaluation phase, the sensors will be upgraded in order to meet the requirements necessary for outdoor use. This includes the housings, and further deficiencies occurred during the evaluation phase. Then, the actual data recording begins and sensors are placed outdoors in the vineyards. After collecting the data from at least one season, the data analysis can start, and scientists can hunt the triggers of diseases.


[1] A. Al-Fuqaha, et al.: “Internet of things: A survey on enabling technologies, protocols, and applications,” in IEEE Communications Surveys & Tutorials, vol. 17, no. 4, pp. 2347–2376, 2015.
[2 W. Shi, et al.: “Edge computing: Vision and challenges,” IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, Oct 2016.
[3 M. Armbrust, et al.: “A view of cloud computing,” Commun. ACM, vol. 53, no. 4, pp. 50–58, Apr. 2010.

Please contact:
Christian Hirsch
TU Wien, Computer Engineering / Cyber-Physical Systems
This email address is being protected from spambots. You need JavaScript enabled to view it.

Markus Redl
BOKU Wien, Department of Crop Sciences / Divison of Plant Protection
This email address is being protected from spambots. You need JavaScript enabled to view it.

Next issue: July 2018
Special theme:
Human-Robot Interaction
Call for the next issue
Image ERCIM News 113 epub
This issue in ePub format

Get the latest issue to your desktop
RSS Feed