"Remote sensing images have been a significant information source for many different applications, especially for monitoring agricultural and environmental resources. Yet knowledge extraction from them is often performed by domain experts using heavily interactive computer-aided photo-interpretations due to lack of powerful automated methods. Improved spatial/spectral resolution in recent years provides details for precise monitoring, in expense of making the problem even more complicated. For monitoring agriculture in Europe, we will innovatively propose an unsupervised automated method (with limited interaction) based on advanced similarity criteria utilizing spectral/spatial characteristics and on manifold learning techniques for clustering large data sets of very-high resolution images. This will provide a fast and accurate approach for assessment of agricultural systems at the community level, which is currently done by expert image analysis. In addition, the research addressed here (novel similarity criteria harnessing different types of information and hybrid clustering), which will certainly contribute to the EU’s research excellence in remote-sensing and data mining, are expected to be advantageous for other remote-sensing applications, and also for clustering other large data sets. This will lead to interdisciplinary applications of the proposed study resulting in greater applicability beyond agricultural monitoring (which has already a broad application area encompassing whole EU, concerning about 9 million farmers and 140 million reference parcels).The CIG will integrate Dr. Taşdemir, an early career researcher with postdoctoral experience at EC Joint Research Centre (where he received the best young scientist award) and a PhD from Rice University, USA (where he received an award for contributions to graduate life), to establish his lab at Antalya International University, for research training and attracting talented individuals in the remote-sensing."