Researchers from Bayerische Landesanstalt für Landwirtschaft (LfL) and GeoPard Agriculture teamed up to look into the economics of strip-intercropping systems for sustainable farming. They shared their findings at the University of Hohenheim’s event on “Promote Biodiversity through Digital Agriculture,” focusing on eco-friendly farming practices and their financial impacts.
Their project, “Future Crop Farming,” aimed to explore new ways of farming, with a special focus on strip-intercropping. This technique involves growing different crops side by side in strips within the same field, which could reduce the need for chemicals and increase biodiversity. The researchers wanted to find ways to make farming more eco-friendly while still being profitable for farmers.
Led by Olivia Spykman and Markus Gandorfer from LfL, along with Victoria Sorokina from GeoPard, this collaboration started during the EIT Food Accelerator program. Using their knowledge in farming, digital tools, and data analysis, they set out to study the economic side of sustainable farming practices.
While addressing the reduction of synthetic inputs and the increase of biodiversity they found that the ecological potential of strip-intercropping is well-researched. However, its mechanization and labor economics, especially with autonomous equipment, require further evaluation.
They found that farmers were unsure about its practicality, especially with new technology. To address this, they talked with farmers at a strip-intercropping field lab to understand their concerns and communicate better.
Furthermore, changes to the landscape can make farmers hesitant, so providing clear information upfront is important. Therefore, digital tools, like visualizations, can facilitate communication between farmers and their communities, generating acceptance and appreciation for ecologically beneficial landscape transformations.
For example, in New Zealand, farmers used virtual reality (VR) goggles to visualize suitable areas for afforestation, aiding farm-scale planning by illustrating impacts on farm profitability, landscape aesthetics, and rural communities. Such visualizations can enhance farmers’ understanding and interest in landscape changes, though successful implementation also depends on farmers’ self-confidence.
Similarly, in this research, the cloud-based program GeoPard was used to analyze a strip intercropping production system from multiple perspectives. GeoPard’s equations were parametrized with empirical data from the Future Crop Farming project. Initial results include visualizations of herbicide and nitrogen input and yield output, with more complex calculations planned.
Furthermore, the system integrated various data sources, including:
- Yield and applied-input datasets
- Price information for crops and plant protection (provided by the user)
- Satellite imagery (Sentinel-2, Landsat, Planet)
- Topography data
- Zone maps of historical data available in GeoPard
Meanwhile, the main techniques utilized involved spatial analysis and efficient handling of spatial data using the NumPy framework. Data was sourced from .xlsx and .shp files. However, the shape file lacked specific details about individual strips, necessitating the integration of various data formats.
GeoPard facilitated organizing data spatially to link strip-specific details with their respective locations in the field. Hence, the integrated dataset, displaying the strips, formed the basis for the descriptive trial analysis in GeoPard.
Although the research didn’t examine variable-rate application of inputs, GeoPard’s high-resolution mapping (pixel size: 3×3 meters) enabled detailed visualization at the pixel level, adding complexity. This detailed mapping is valuable for future applications, like combining multiple layers or integrating more spatially variable information such as ‘yield profiles’ based on small-scale yield data collected by plot combines in the research project.
Researchers have also discovered that although GeoPard has primarily served descriptive functions, it possesses the potential for more complex visualizations. For example, incorporating sub strip-level yield data and price information could help create profit maps, showing edge effects between neighboring crop strips.
Furthermore, integrating labor economic data could reveal the impacts of reducing economies of scale to promote biodiversity. Such data can aid scenario modeling, allowing exploration of various crop rotations, strip widths, and mechanization types, focusing on field-specific outcomes to improve agricultural management and decision-making.
Hence, the setup could function as a digital twin, with real-time data transfer from field machines and sensors to GeoPard, a capability already achievable with some commercial technologies and satellite data. However, farmers’ concerns about technology compatibility emphasize the need to integrate additional data sources for broader applicability.
Precision Farming
