New publication on decision fusion

New publication on decision fusion

August 1, 2015

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.

 

you may also like:

How does seasonal climate affect Maize cultivation in East Africa

How does seasonal climate affect Maize cultivation in East Africa

Our PhD student Adomas Liepa published new research on the impacts of seasonal differences in the local climate on maize cropping systems in East Africa. This study, conducted in collaboration with partners from the German Aerospace Center (DLR) and the International...

Five Years of Data Cube Innovations in AgriSens DEMMIN 4.0

Five Years of Data Cube Innovations in AgriSens DEMMIN 4.0

Over the past five years, we made significant advancements with our Data Cube development within the AgriSens DEMMIN 4.0 project. We enhanced the system architecture and the offerings of the Data Cube to optimize the use of remote sensing data for agricultural...

New Team Member: Sofia Haag

New Team Member: Sofia Haag

Sofia Haag joined the EORC in February 2025 as a research assistant for the EO4CAM project. After completing her Bachelor's degree in Geography at the University of Heidelberg, she pursued her Master's in Applied Physical Geography at the University of Würzburg. Sofia...

AgriSens is working towards its final symposium

AgriSens is working towards its final symposium

Results from five years of research will be presented at the final symposium of the AgriSens DEMMIN 4.0 project. Its focus is the use of digitalisation and remote sensing technologies in agricultural practice, aiming for an agriculture that is ecological, economical...

New Team Member: Daniel Gruschwitz

New Team Member: Daniel Gruschwitz

After getting in touch with Geoinformatics during his Geography studies at the Eberhard Karls University in Tübingen, Daniel embarked on the EAGLE graduate program in Würzburg. During his studies, he focused on vegetation remote sensing by completing several...