We use cookies on our website. Some are necessary for the operation of the website. You can also allow cookies for statistical purposes. You can adjust the data protection settings or agree to all cookies directly.
Data Protection Declaration
Imprint
Innovative remote sensing technologies are used in the project GEO FORPY to monitor the forest cover and change in cover in the Paraguayan Chaco region. These data serve as key information for policy and management design, forest monitoring and Paraguay’s scientific database enhancement. (GEO FORPY)
Project
Project code: 28I02701
Contract period: 01.05.2020
- 30.04.2022
Budget: 535,653 Euro
Purpose of research: Basic research
Keywords: knowledge transfer, networking, data management, mixed forest, monitoring, remote sensing, forest conversion, forest protection
The project will apply the latest free available earth observation time series data (e.g. satellites Sentinel 2 A&B) to enhance previous forest detection attempts conducted for the Paraguayan Chaco. The behavior of well-known classifiers such as Random Forest (RF), Artificial Neural Networks (ANN), Classification and Regression Tree (CART) will be analyze to identify which model obtains the highest level of accuracy regarding forest cover detection in the region. Additional features such as continuous spectral temporal metrics and vegetation indices would be computed and tested to analyze the level of importance of each component in the overall classification accuracy. The proposed method will generate the first 10 m resolution forest cover product for the Paraguayan Chaco. Additionally, the digital elevation model TanDEM-X DEM (12 m) will be used in the mapping methods to delineate forest structure. The sensor provides information regarding elevation differences which would be applied to derive types of forest structure, taking into consideration forest height and reflectance information. Based on the mapping algorithms developed forest and non-forest maps from the years 2015 and 2018 will be derived from Sentinel 2 imagery to study forest fragmentation levels in the Chaco region. Furthermore, Landsat imagery will be incorporated in the project to understand effects of national environmental polices over the dynamics of the forest will be assessed by deriving yearly forest cover masks from 1999 until 2018. Effectiveness of protected areas and the influence of anthropological pressure on the forest over time will be analyzed as well. Finally with a special emphasis on mapping algorithms and forest cover derivation a very detailed technical training will be conducted orientated towards project partners and environmental/research institutions in the country. The training prepared by DLR scientists will focus on the methods and products developed.
Section overview
Subjects
- Silviculture
- Forestry
