Diversified crop productionPhoto: ATB
Research for an environmentally controlled, diversified crop production
We develop technologies and processes for agricultural crop production. In the bioeconomy, plant biomass not only provides food and feed, but is also the basis for biobased materials and energy. With our research, we follow the concept of an environmentally controlled, highly diversified agroecological production. In doing so, we take advantage of the Digital Transformation and support the transition from precision agriculture to an "Diversity by Precision" approach.
Biodiversity loss is currently one of the most pressing problems worldwide. The mixed cultivation of different crops on the same area, i.e. the interaction of a wide variety of plants, animals and microorganisms in so-called inter- or mixed cropping systems, has many advantages, including improved resilience and higher overall yields.
The agile management of such diverse and complex production systems requires adaptation of machinery, sensors, control systems, algorithms, and especially of management strategies. The systemic approach to circular farming also requires a better understanding of the microbiome and its interactions within agricultural systems.
Our research addresses the development of smart sensors for the digital assessment of environmental conditions and plant status as well as methodological issues of intelligent image analysis. These digital methods are expected to contribute decisively to advancing sensor-based process control and automation as a prerequisite for the complex control systems of a circular bioeconomy.
A central task is the development of digital twins for knowledge-based, precise, dynamic and adaptive process control of these very complex systems.
For our research, we benefit from the ATB Fieldlab for Digital Agriculture in Marquardt with a test track for soil sensors and an installation for automated data acquisition in fruit tree cultures. In addition, research work will also be implemented in the Leibniz Innovation Farm at Groß Kreutz (currently under construction).
The research focus is on the further development of proximal soil sensor technology in order to be able to digitally record all information relevant for sustainable crop production, and on the development and application of biological sensor systems for analyzing soil health. Our objective is the sustainable use and improvement of the soil.
Our research focus is on a precise plant monitoring by using especially optical sensor systems like LIDAR or multispectral cameras - both in agriculture and in horticulture. Data from in-situ, proximity and remote sensing provide information on the status of plants as well as pathogens or pests. The aim of a precise plant monitoring is to design plant protection in an environmentally friendly way and to secure the food supply by strengthening plant health.
Digitization and robotics are to support diversity in agriculture in the long term as reliable control systems. Our research focus is on the identification and development of assistance systems as well as on automated and field robotics applications. Simulation and IoT technologies are used to develop and improve digital twins, highly automated field sensor systems, field machines and field robotics.
WetNetBB – Bewirtschaftung und Biomasseverwertung von nassen Niedermooren: Netz von Modell- und Demonstrationsvorhaben in Moorregionen Brandenburgs ▶
In Brandenburg, there are extensive lowland moor areas with a great diversity of habitats, which are, however, almost completely drained and subject to progressive degradation. There is preliminary work on rewetting in s…
DCropS4OneHealth – Diversifying cropping systems for the One Health of soils, plants and humans; BiodivGesundheit: Diversifizierung von Pflanzenbausystemen für die gemeinsame Gesundheit von Böden, Pflanzen und Menschen ▶
The diversification of crop production systems in combination with a reduction in the use of agrochemicals and an increase in landscape complexity has the potential to promote biodiversity at the field and landscape scal…
DeepFarmBots – DeepFarmBots - KI-basierte Agrarrobotik für eine effiziente und nachhaltige Landwirtschaft ▶
The network for DeepFarmBots AI-based agricultural robotics for efficient and sustainable agriculture aims to create new products, processes and services for the use of agricultural robots in different application areas …
MIKIM - DeepFarmBots – DeepFarmBots - MIKIM / KI-basierte Objekterkennung und -klassifizierung, Schutzgehäuse und landwirtschaftliche Feldversuche ▶
In the MIKIM - DeepFarmBots project, an agricultural MIMO radar system with AI-based signal processing is being developed that achieves improved angular and distance resolution and is combined with AI-based object recogn…
DaVaSus – Datenbasierte Bewertung der multifunktionalen und digitalen Transformation eines Landwirtschaftsbetriebs anhand des Beispiels von Gut & Bösel in Alt Madlitz ▶
The challenges of agriculture are manifold - in addition to the constant, intense competitive pressure, farmers are confronted with increasingly severe environmental problems as a consequence of climate change and are at…
- Tavakoli, H.; Correa Reyes, J.; Sabetizadeh, M.; Vogel, S. (2023): Predicting key soil properties from Vis-NIR spectra by applying dual-wavelength indices transformations and stacking machine learning approaches. Soil and Tillage Research. (May): p. 105684. Online: https://doi.org/10.1016/j.still.2023.105684 1.0
- Alirezazadeh, P.; Schirrmann, M.; Stolzenburg, F. (2023): Improving Deep Learning-based Plant Disease Classification with Attention Mechanism. Gesunde Pflanzen. (1): p. 49-59. Online: https://doi.org/10.1007/s10343-022-00796-y 1.0
- Salamut, C.; Kohnert, I.; Landwehr, N.; Pflanz, M.; Schirrmann, M.; Zare, M. (2023): Deep Learning Object Detection for Image Analysis of Cherry Fruit Fly (Rhagoletis cerasi L.) on Yellow Sticky Traps. Gesunde Pflanzen. (1): p. 37-48. Online: https://doi.org/10.1007/s10343-022-00794-0 1.0
- Bettoni, M.; Maerker, M.; Sacchi, R.; Bosino, A.; Conedera, M.; Simoncelli, L.; Vogel, S. (2023): What makes soil landscape robust? Landscape sensitivity towards land use changes in a Swiss southern Alpine valley. Science of the Total Environment. (2): p. 159779. Online: https://doi.org/10.1016/j.scitotenv.2022.159779 1.0
- Karimi, H.; Navid, H.; Dammer, K. (2023): A Pixel-wise Segmentation Model to Identify Bur Chervil (Anthriscus caucalis M. Bieb.) Within Images from a Cereal Cropping Field. Gesunde Pflanzen. (1): p. 25-36. Online: https://doi.org/10.1007/s10343-022-00764-6 1.0
- Antonijevic, D.; Hoffmann, M.; Prochnow, A.; Krabbe, K.; Weituschat, M.; Couwenberg, J.; Ehlert, S.; Zak, D.; Augustin, J. (2023): The unexpected long period of elevated CH4 emissions from an inundated fen meadow ended only with the occurrence of cattail (Typha latifolia). Global Change Biology. (13): p. 3678-3691. Online: https://doi.org/10.1111/gcb.16713 1.0
- Dammer, K. (2023): Arbeitstagung Sensorgestützte Erkennung von Schaderregern in Freilandkulturen am Leibniz-Institut für Agrartechnik und Bioökonomie Potsdam-Bornim (ATB), 11. und 12. Mai 2022. Gesunde Pflanzen. : p. 1-4. Online: https://doi.org/10.1007/s10343-022-00799-9 1.0
- Gautam, S.; Höhne, M.; Hansen, S.; Jenssen, R.; Kampffmeyer, M. (2023): This looks More Like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation. Pattern Recognition. (April): p. 109172. Online: https://doi.org/10.1016/j.patcog.2022.109172 1.0
- Malacrino, A.; Abdelfattah, A.; Belgacem, I.; Schena, L. (2023): Plant genotype influence the structure of cereal seed fungal microbiome. Frontiers in Microbiology. : p. 1-8. Online: https://doi.org/10.3389/fmicb.2022.1075399 1.0
- Balasundram, S.; Shamshiri, R.; Sridhara, S.; Rizan, N. (2023): The Role of Digital Agriculture in Mitigating Climate Change and Ensuring Food Security: An Overview. Sustainability. (6): p. 5325. Online: https://doi.org/10.3390/su15065325 1.0