Impressions from Phenology 2015 conference

Impressions from Phenology 2015 conference

From 5 – 8 October 2015, the 3rd international conference on Phenology was held at Kusadasi/Turkey. It was jointly hosted by the Humboldt-University of Berlin and the Adnan Menderes University Aydin. 86 contributions from scientists of 23 countries were presented on the topics “Phenological observations, networks, data collection”, “Climate variablilty, change and trends”, “Phenological modelling”, and “Challenges, new approaches and progress”.
Within the session “Remote Sensing and Phenology”, Carina Kübert presented ongoing work of her PhD thesis on “Deriving phenological layers for Germany from remote sensing data: spatio-temporal analysis and validity”. One of our MSc students, Jeroen Staab, co-authered a presentation given by our former colleague Sarah Asam (now EURAC, Italy), showing first results of phenological monitoring for the entire Alps. Jeroen helped to derive phenological metrics during his internship at EURAC.

More details in the programme and abstract book (published by the German Meteorological Service (DWD)) which can be downloaded from the conference homepage

More details can also be found on twitter using the hashtags: #phenology #phenology2015

New RapidEye datasets granted from RESA platform of DLR/Black Bridge

The Department of Remote Sensing recently applied for a time series of RapidEye scenes to support a PhD thesis by Christian Bauer (Dep. of Remote Sensing, Würzburg) in the context of the project LaVaCCA. The proposal has recently been accepted, and the PhD work of Christian Bauer will be supported by a time series of RapidEye scenes acquired over two irrigated landscapes, Khorezm and Elliqkala, in Uzbekistan.

New publication on decision fusion

New publication on decision fusion

Decision_fusion_loewOur new publication in ISPRS is accepted: “Decision fusion and non-parametric classifiers for land use mapping using multi-temporal RapidEye data”.

This study addressed the classification of multi-temporal satellite data from RapidEye by considering different classifier algorithms and decision fusion. Four non-parametric classifier algorithms, decision tree (DT), random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP), were applied to map crop types in various irrigated landscapes in Central Asia. A novel decision fusion strategy to combine the outputs of the classifiers was proposed. This approach is based on randomly selecting subsets of the input data-set and aggregating the probabilistic outputs of the base classifiers with another meta-classifier. During the decision fusion, the reliability of each base classifier algorithm was considered to exclude less reliable inputs at the class-basis. The spatial and temporal transferability of the classifiers was evaluated using data sets from four different agricultural landscapes with different spatial extents and from different years. A detailed accuracy assessment showed that none of the stand-alone classifiers was the single best performing. Despite the very good performance of the base classifiers, there was still up to 50% disagreement in the maps produce by the two single best classifiers, RF and SVM. The proposed fusion strategy, however, increased overall accuracies up to 6%. In addition, it was less sensitive to reduced training set sizes and produced more realistic land use maps with less speckle. The proposed fusion approach was better transferable to data sets from other years, i.e. resulted in higher accuracies for the investigated classes. The fusion approach is computationally efficient and appears well suited for mapping diverse crop categories based on sensors with a similar high repetition rate and spatial resolution like RapidEye, for instance the upcoming Sentinel-2 mission.

 

New RapidEye datasets granted from RESA platform of DLR/Black Bridge

New RapidEye datasets granted from RESA platform of DLR/Black Bridge

The Dept. of Remote Sensing recently applied for a time series of 7 RapidEye scenes to support a PhD thesis by M.Sc Omid Karami (Sari University of Agricultural and Natural Resources Sciences, Iran). The proposal is now accepted, and th PhD work will be supported by a time series of RapidEye scenes acquired between 07.2009 and 09.2014 over a semi-Meditteranean forested site in Lorestan province in Western Iran.

The PhD thesis which will use these processed datasets is entitled  “Monitoring and modelling of Zagros forest oak decline using high resolution satellite data”, supervised and advised by Dr. Asghar Fallah (Sari University of Agricultural and Natural Resources Sciences), Dr. Shaban Shataee (University of Gorgan) and Dr. Hooman Latifi (University of Würzburg). Additional multisource datasets to be used within the work include very high resolution data from Quickbird and World View-2.

RESA already published this project in RESA project map 2015 which can be found online HERE. The project area is flagged under No. 104 (project number 168) in the map.

resa_iran

The RapidEye Science Archive (RESA) supported by DLR (BMWi) and Black Bridge AG supports scientific projects with German participation through the provision of free image data of the RapidEye satellite constellation. The projects are given the opportunity on an extensive image archive to get current and archived satellite image data to ensure optimal support for individual research projects.