Skip main navigation

Yield Maps in Precision Farming

Learn more about how yield maps are produced.
© EIT Food

Yield maps are one of the many tools available in precision farming. Here we explore how yield data are collected and analysed in order to produce accurate, spatially explicit yield maps.

What are Yield Maps?

Yield maps are maps of fields in which the yield and its location is measured and reported. These maps are often used with cereal crops, such as wheat and barley. Crops are harvested with a combine harvester that is equipped with sensors to measure the amount/weight of grain, combined with geographic coordinates from GPS signals (geo-referencing). They enable areas of the field with higher or lower yields to be identified.

How Are They Produced?

The first step is to collect the data. A sensor installed on the combine harvester measures the amount of grain harvested at predefined time intervals (usually every 1 or 2 seconds) and/or over a predefined sampling distance. Each of these measurements are geo-referenced so they can be plotted on a map.

Automated yield measurements combined with geo-referenced spatial data to create precise yield maps. ©John Deere

Sensors may measure the yield amount in terms of the volume or mass harvested, and use a variety of technologies from weighing the grain tank to measuring the grain flow using light barriers [1]. In addition to the amount of grain harvested, the sensor also collects information on the moisture content of the harvest. As both the volume and mass of grain is affected by moisture, the moisture content needs to be taken into account in order to get accurate yield measurements [2].

Secondly, the data is cleaned. The data collected may contain errors, from sensors or due to GPS not connecting properly, so these raw data are processed to provide reliable information. This is mainly automated, but requires user input. A comparison between predicted and measured yield maps can help to identify any potential errors. Examples of incorrect data might be:

  • Yield amounts that are too high for the crop to produce.
  • Data that was recorded at points where the speed of the harvester was measured incorrectly (too high or too low). This can be checked by comparing the sample distance measurements against the ground truth speed of the harvester.
  • Yield values that are too high or too low in comparison with the average yield at data points surrounding it [3].

Finally the generalisation step reduces the level of detail, identifying the main yield trends and producing the yield maps, ready to be read and interpreted.

Example yield map of a spread of fields. Green indicates areas of higher yield, red indicates areas of lower yield. © Agricolus

This example yield map highlights areas of lower and higher yield and demonstrates the heterogeneity of individual fields – how much the yield can vary within a field. While yield maps show where these higher and lower yields are, further information (such as knowledge of the land) is needed to understand what is causing these variations [4].

You can find out more about how measurements are made for yield maps in the ‘See Also’ links at the end of this Step.

How are Yield Maps Used?

Yield maps can enable farmers to improve farming practices in a given field. They identify areas for investigation and site-specific treatment using precision farming techniques and you can then use the maps again to monitor the impact of those treatments over time [5].

Analysis of yield maps over a number of years can enable farmers to identify which areas of a field produce less in a persistent or sporadic way, allowing them to, for example, plant an alternative crop or alter a fertiliser or irrigation strategy [4]. Yield maps can also be used for yield forecasting; predicting yields in subsequent years can be used to estimate farm incomes and profits [5]. Yield maps have also been used to identify suitable locations for growing specific crops [7].

We’ll go into more detail about how yield maps are used as the basis for precision farming in the next few Steps.

© EIT Food
This article is from the free online

Innovation in Arable Farming: Technologies for Sustainable Farming Systems

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now