The e-ROSA project seeks to build a shared vision of a future sustainable e-infrastructure for research and education in agriculture in order to promote Open Science in this field and as such contribute to addressing related societal challenges. In order to achieve this goal, e-ROSA’s first objective is to bring together the relevant scientific communities and stakeholders and engage them in the process of coelaboration of an ambitious, practical roadmap that provides the basis for the design and implementation of such an e-infrastructure in the years to come.
This website highlights the results of a bibliometric analysis conducted at a global scale in order to identify key scientists and associated research performing organisations (e.g. public research institutes, universities, Research & Development departments of private companies) that work in the field of agricultural data sources and services. If you have any comment or feedback on the bibliometric study, please use the online form.
You can access and play with the graphs:
- Evolution of the number of publications between 2005 and 2015
- Map of most publishing countries between 2005 and 2015
- Network of country collaborations
- Network of institutional collaborations (+10 publications)
- Network of keywords relating to data - Link
Design and implementation of a knowledge-based system to improve maximum likelihood classification accuracy
Numerous classification algorithms have been developed, many of which are highly specific and only solve a reduced class of problems. Maximum likelihood classification (MLC) is the most widely used classification method. The underlying assumption in performing MLC is that the prior probability of land cover is equal. However, a priori occurrence probability has a crucial effect on classification results. The objective of this paper is to improve the accuracy of MLC using a priori information in a knowledge-based system. The mathematical formulations and the strategy are presented. Estimates of a prior probability through crop areas, crop calendar, and some a priori probability about agricultural practices have been used in augmenting the probability of pixels. An industrial agricultural field, Moghan Plain in northwestern Iran, has been selected for testing. A total of 176 ground truth points were identified and measured in the field, and 323 fields were used for accuracy evaluation. Prior probabilities were estimated based on transition matrices of five successive years. Overall classification accuracy based on conditional prior probabilities increased from 53.2% to 66.7% relative to MLC. Knowledge about harvesting time is formalized using a normalized difference vegetation index (NDVI) map from an advanced spaceborne thermal emission and reflection radiometer (ASTER) image. The overall accuracy was then increased to 72.3%. Object-based classification is used to determine the crop type of agricultural fields for which the geometry is constrained. Overall accuracy is then raised to 88.7%.
Inappropriate format for Document type, expected simple value but got array, please use list format