Monitoring of Agricultural Landscapes



Christopher Conrad





The module addresses methods on how Earth Observation and the use of geoinformation can support different fields of land and water management. Focus is set on remote sensing based concepts and methods for monitoring and supporting resource management in agricultural landscapes. Achievements and challenges are elaborated. The students will be guided to gain knowledge in selected practical examples.



Mapping the parameters

  • Mapping cropland extent, cropland use, and cropping intensity at different scales
  • Rainfed agriculture, irrigated cropland or pasture? Disentangling of complex vegetation classes
  • Quantification of cropland production, status quo and developments
  • Aproaches to mapping land abandonment
  • More crop per drop? Assessing land and water use in irrigated landscapes

Remote sensing contributions to multi-sector assessments

  • Population growth and the competition for land in rural areas
  • Understanding the role of lakes and wetlands in agricultural landscapes
  • Vulnerabillity of agricultural landscapes under changing climate conditions
  • Crop yield predictions

Practical part on cropland use intensity in irrigation systems in Central Asia.


Small classification codes in R will be written (classification and accuracy assessment).




Practical work: Mapping cropland extent, cropland vegetation phenology, and crop types at different scales (Landsat / MODIS)

  • (Segmentation)
  • Classification (random forest, knowledge-based decision trees)
  • Accuracy assessment


Seminar plus practical part.

General Course News and Updates


Our EAGLEs in 2018 visited the German Aerospace Center, namely the Earth Observation Center, close to Munich. Various topics were presented by DLR scientist and the EAGLEs hat the chance to discuss various topics in small groups with individual scientists.

read more

EAGLE Internships

On Monday, 24th of September, at 1pm the following internship reports will be presented: Bharath: "Installation and Characterization of an imaging Spectrometer for the UAV-based remote sensing" Johannes: "Crop classification based on S1/S2 in...

read more

EAGLE students coding with sweets

Today our EAGLE students applied data munging, pipes, plotting and statistics using colour distribution of sweets. They specifically used the dplyr, ggplot, kableExtra and others to compute derivatives, rearrange the data, plot it and run statistics on colour...

read more

Spatial Python block course

Last week Steven Hill and Thorsten Dahms gave a course that introduced EAGLE students to Python-based spatial data analysis. The advantages and challenges of different python libraries, data sets and methods were covered in hands-on exercises and also discussed...

read more
Share This