Precision farming – digitalisation in agriculture

Precision farming is an approach that is now over 30 years old and supports and optimizes agriculture with the help of digital technologies. Central technologies are GNSS (Global Navigation Satellite System; satellite positioning), GIS (Geographic Information Systems), data transmission technologies such as CAN (Controller Area Networks) and the use of sensor systems. Earth observation satellites are an important sensor system for agriculture. In agricultural machinery technology, GNSS is used for the automatic steering of tractors and harvesters as well as the automatic switching on and off of implements (section control) – applications that are now widely used.

Earth observation satellites provide data for agriculture, among other things, which can be used to monitor the development of crops in the field, for example. The special thing about this is that earth observation in the form of satellite images is mostly image-based and therefore captures spatial differences. The sensors (cameras) installed in the satellites have the ability to capture various frequencies of visible and non-visible light, beyond red (near-infrared). This range of light is particularly sensitive to differences in vegetation (chlorophyll content, biomass).

Site-specific land management is one of the most important sub-disciplines of precision farming: it aims to adapt the management of sub-areas of a field in terms of sowing, fertilization and plant protection. This is intended to save costs and minimize the negative effects of fertilization and crop protection on the environment (soil, water, groundwater). Satellite images provide an excellent basis for this, as they can depict/visualize the small-scale differences in crop growth.

The sensors on the satellites record the return radiation of sunlight in different wavelength ranges. The Earth’s atmosphere can cause interference in the transmission of light. With the help of appropriate correction values, some of these disturbances can be eliminated. In extreme cases, however, it can also lead to the data becoming unusable for the intended use.

In most cases, no direct conclusions about the condition of the crop can be drawn from the primary data obtained. Only by processing the data into so-called indices (NDVI, LAI, REIP…) can meaningful results be obtained. These in turn, when incorporated into a model, can provide very precise and accurate actual values and forecasts about the development status of the plants. The models are crop-specific and usually require the analysis of time series (several consecutive recordings) in order to be able to show changes over time. With the availability of artificial intelligence (AI), the development of models is increasingly better supported, as AI is able to recognize patterns in the collected data. Due to the constantly growing number of data sets and the further development of AI capabilities, it is to be expected that the models will continue to improve in quality and become more transferable to other types of fruit. Numerous new models have been developed in recent years – most of which are now based on artificial intelligence.

Comparability with analogue phenomena

Over thousands of years, agriculture has adapted to both large and small-scale climatic conditions and, above all, to soil differences. This adaptation was based on traditional knowledge and farmers’ own experience of cultivating the land, often from childhood onwards. They observed the development of different crops in different areas of agricultural land and related this to the weather. At that time, their own eyes and the sighting of clearly visible objects in the surrounding area (e.g. trees or church spires) replaced satellite navigation. They also served as sensors (plant height, number of ears of corn, discoloration of leaves, weed cover). This form of knowledge- or experience-based agriculture is no longer sufficient due to the ever-growing areas and farms and, above all, due to structural change, and is therefore in decline. The knowledge is not available for purchased or leased land. The same applies to contractors and temporary workers who carry out measures on land on behalf of farmers. Data-based or digital land management is therefore becoming increasingly important.

Social relevance

Optimizing agricultural production ensures the production of high-quality food and contributes to food security. At the same time, production costs can be reduced and negative effects on the environment minimized. Earth observation can make a significant contribution to this by revealing small-scale differences in plant growth and thus creating opportunities for adapted measures.

---