Skip Ribbon Commands
Skip to main content
Suche
Breadcrumb Navigation

Working Groups

Hauptinhalt der Seite

​​​​​​​​​​​​​​​​​​ Pfeil links Back to the homepage of the research area

Contribution to ZALF research

Comming soon.

 

Working Groups

 

 

Dimensionality Assessment and Reduction

Image of the WG Data Dimensionality 

A key challenge of landscape research and sustainable management of landscape resources is to disentangle between various effects. E.g., the relevance of single processes in a high-dimensional setting need to be evaluated, or effects of single measures need to be differentiated from natural variability. To that end various methods of classical dimensionality assessment and reduction (e.g., Principal Component Analysis, Isometric Feature Mapping) as well as more advanced methods (e.g., Wavelet Coherence, Correlation Dimension, Sammon Mapping, Autoencoder Neural Networks, machine learning approaches) are adapted to the specific needs of landscape research and further developed. Thus the working group provides powerful diagnostic tools for the analysis of comprehensive observation data sets, for in-depth analyses of biophysical models and for efficient evaluation of monitoring programs, e.g., of environmental authorities.

Contact: Prof. Dr. Gunnar Lischeid

 

Landscape Modelling

Image of the WG Integrated Landscape Modelling

This working group develops and applies simulation models in the context of agricultural landscapes, with focus on large-area agricultural production and its feedback with the system’s water and nutrient dynamics and related human decisions. Considering mechanistic models as our core expertise, we increasingly integrate data-driven approaches as strategic enhancements of our modelling methods, also for socioeconomic processes. We use multi-sensor remote sensing data to parameterise, initialise and drive one-dimensional process-based and other types of two- to three-dimensional models across scales.

More ...

Contact: Prof. Dr. Claas Nendel

 

Ecosystem Modelling

Image of the WG Ecosystem Modelling 

TThe working group develops and applies process-based agro-ecosystem models focusing on food security, climate change, and water resources protection. Our research emphasizes understanding and simulating complex soil-crop interactions in agricultural systems, addressing both yield stagnation issues in major cereals and the dynamics of mixed cropping systems. We concentrate on reducing uncertainties in model structure and parameters while expanding the scope of represented processes. The group investigates two- and three-way interactions among environment, genotype, and management across scales, integrating experimental data, field surveys, and sensing approaches to enhance our mechanistic understanding of crop responses. This enables us to develop region-specific adaptation solutions and predictive scenarios for sustainable agricultural intensification under climate change.

More ...

Contact: Dr Ehsan Eyshi Rezaei

 

Artificial Intelligence

Image of the WG Artificial Intelligence 

The working group is committed to developing and applying cutting-edge data-driven techniques such as interpretable machine learning and deep learning for a broad range of agriculture-related problems. We are interested in exploring the potential of artificial intelligence for improving agricultural management, testing novel hypotheses that cannot be tested with conventional statistical methods, and discovering unexpected patterns from uniquely combined datasets across scales and sectors. We wish to offer AI-powered, Nature-based Solutions for global sustainability challenges.

More ...

Contact: Prof. Dr. Masahiro Ryo

 

Remote Sensing for Agriculture

Image of the WG Remote Sensing for Agriculture 

The working group is dedicated to integrating multisource Remote Sensing (RS) data to monitor cropping systems across varied scales and regions. Key efforts include developing scalable and transferable methods for assessing crop management practices, detailed phenological stages, and mapping crop types. The team also addresses drought monitoring by integrating moderate and high-resolution optical and thermal data to evaluate drought impacts and risk, as well as creating predictive models to enhance early warning systems. Additionally, the group examines the interplay between abiotic and biotic stressors, essential for understanding and managing impacts on crop productivity. A further focus is on building a cross-scale framework to develop indicators for vegetation and landscape diversity, evaluating how spatial heterogeneity affects upscaling and biodiversity assessment. The team is also committed to assessing below-ground properties, such as soil organic carbon, through the use of multispectral and hyperspectral data (proximal, UAV, satellite data).

Kontakt: Dr. Gohar Ghazaryan

 

Multi-Scale Modelling

Image of the WG Multi-Scale Modelling 

The working group focuses on cross-scale modelling of farm systems, emphasizing hybrid modelling approaches that integrate diverse model types (e.g., biophysical, hydrological, ecological, farm, market) with data-driven AI models. It develops and applies methods for combining models and data (e.g., sensors, remote sensing, and climate data). The group also integrates simulation techniques with indicator frameworks to evaluate the sustainability and resilience of cropping systems. The approaches are utilized to enhance the understanding of complex systems by examining interactions across various organizational scales, including fields, farms, landscapes, regions, and markets. They assist stakeholders, such as farmers and policymakers, in making operational, tactical, and strategic decisions, with a strong emphasis on forecasting and evaluating changes in systems influenced by factors like climate, market dynamics, and policy shifts.

Kontakt: Prof. Dr. Frank Ewert

 

Pfeil links Back to the homepage of the research area

 

​​​​
Fusszeile der Seite
Wordpress icon
Instagram icon
YouTube icon
ResearchGate icon
Mastodon icon
Bluesky icon
LinkedIn icon
© Leibniz-Zentrum für Agrarlandschaftsforschung (ZALF) e. V. Müncheberg

Funded by:

BMEL logo
MWFK logo