idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
idw - Informationsdienst
Wissenschaft
If farmers want to know how productive their harvest will be in future, it will no longer be experience alone that provides the answer - but an AI-supported technology platform. DFKI has developed a system that makes agriculture more predictable, reduces risks and optimises the use of resources. With the help of satellite data and machine learning, the platform analyses environmental influences in real time - enabling more precise decisions from sowing to harvest.
A farmer looks over his freshly tilled field. The soil has been prepared, the seed has been sown - now it's time to wait. Months pass before the harvest, during which wind, weather and other environmental influences determine success or failure. Even after many years of experience, forecasting yields is often like looking into a crystal ball. This uncertainty is not a sign of a lack of expertise, but an expression of the enormous complexity of modern agriculture.
Professor Andreas Dengel, Executive Director DFKI Kaiserslautern and Head of Research Department Smart Data & Knowledge Services: "Thanks to AI and satellite data, such uncertainties can now be significantly reduced and reliable answers to yield questions can be provided - months in advance. It doesn't make farmers' empirical knowledge superfluous, but supplements it with data-based analyses in real time. The benefits of our technology go far beyond the agricultural sector. The potential of AI in earth observation ranges from disaster prevention and forest management to urban development and infrastructure optimisation."
The European Copernicus programme with its Sentinel-2 satellites provides the basis for the yield forecast. These satellites systematically orbit the earth, creating high-resolution multispectral images of the earth's surface with a coverage of 290 kilometres. New images of each section of the earth are taken every five days.
How yield forecasting works with artificial intelligence:
This continuous stream of data is the foundation and key resource of the AI analysis. An AI model has been trained to recognise and classify the different crops and to make deductions regarding the expected yield.
To make the system - and therefore the forecast - more robust and to arm it against all eventualities, the satellite images are supplemented with topographical information, weather observations and other input data, such as historical cultivation data or digital soil models. In this way, the system can ensure that enough relevant information is available to enable a reliable forecast.
Target data collected on the ground serve as comparative values. Agricultural machinery equipped with special sensors measures the yield directly at harvest. Based on this information, the scientists can see how valid the algorithm's forecast was. The realisation after numerous test runs: The AI system achieves a high level of agreement with measured yields by utilising the satellite images and downstream data fusion.
For wheat cultivation in the USA, for example, an R² score of 0.92 is achieved. The R² value shows how closely a prediction matches the actual yield. The closer the value is to 1, the better. A value of 0.92 therefore corresponds to a congruence with the yield measured in the respective field of around 92 per cent.
Across various countries and crops, the average R² score is 0.76. However, it should be borne in mind that the congruence can only be established with the yields measured by sensors and not actual yields.
There is therefore an error tolerance not only in the system itself, but also in the comparative data used. This results in the hypothetical scenario that the algorithm is closer to the actual yield than the sensors of the agricultural machinery. AI forecasts also remain probabilistic. Factors such as extreme weather events or inaccurate sensors can influence accuracy, which is why uncertainties are modelled and taken into account.
What this technology is already doing for agriculture today
The predictability of expected yields results in direct added value for the agricultural sector. Logistics become easier to plan and the entire harvest chain becomes more efficient. In retrospect, weak points in the fields can be identified and analysed and appropriate countermeasures can be taken. Beyond the agricultural sector, the aggregated forecasts support decisions in the areas of food security, trade strategy and climate adaptation.
The modular architecture of the technology also allows it to be used beyond agriculture: from forest condition monitoring and biodiversity analyses to urban heat mapping or extreme weather forecasts. The technology platform developed at DFKI is transferable in order to visualise environmental changes and recognise trends at an early stage.
The project is a prime example of basic research with concrete application relevance. Scientists at DFKI have worked closely with companies to utilise machine learning in areas where it can offer concrete solutions to key challenges - from agriculture to climate adaptation.
Prof. Dr. Prof. h.c. Andreas Dengel
Executive Director DFKI Kaiserslautern and Head of Research Department Smart Data & Knowledge Services, DFKI
Mail: Andreas.Dengel@dfki.de
Phone: +49 631 20575 1000
https://www.dfki.de/en/web/news/harvest-forecasts-with-ki
https://www.sciencedirect.com/science/article/pii/S003442572400573X
https://nachrichten.idw-online.de/sciencevideo/234
The yield forecasts are visualised on a terrain model in the DFKI showroom.
Source: Lando Michael Lehmann
Copyright: DFKI
Illustration of a model of Multi-Modal Gated Fusion (MMGF) with four modalities used.
Copyright: ©Figure 6 from: Mena et al. (2025), Remote Sensing of Environment, 318:114547
Criteria of this press release:
Journalists
Information technology
transregional, national
Cooperation agreements, Research projects
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
