e-infrastructure Roadmap for Open Science in Agriculture

A bibliometric study

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:

Discover all records
Home page

Title

Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests

en
Abstract

The random forest (RF) classifier is a relatively new machine learning algorithm that can handle data sets with large numbers and types of variables. Multi-scale object-based image analysis (MOBIA) can generate dozens, and sometimes hundreds, of variables used to classify earth observation (EO) imagery. In this study, a MOBIA approach is used to classify the land cover in an area undergoing intensive agricultural development. The information derived from the elevation data and imagery from two EO satellites are classified using the RF algorithm. Using a wrapper feature selection algorithm based on the RF, a large initial data set consisting of 418 variables was reduced by similar to 60%, with relatively little loss in the overall classification accuracy. With this feature-reduced data set, the RF classifier produced a useable depiction of the land cover in the selected study area and achieved an overall classification accuracy of greater than 90%. Variable importance measures produced by the RF algorithm provided an insight into which object features were relatively more important for classifying the individual land-cover types. The MOBIA approach outlined in this study achieved the following: (i) consistently high overall classification accuracies (>85%) using the RF algorithm in all models examined, both before and after feature reduction; (ii) feature selection of a large data set with little expense to the overall classification accuracy; and (iii) increased interpretability of classification models due to the feature selection process and the use of variable importance scores generated by the RF algorithm.

en
Year
2012
en
Country
  • CA
Organization
  • Univ_Saskatchewan (CA)
  • Total_SA (CA)
  • Trent_Univ (CA)
Data keywords
  • machine learning
en
Agriculture keywords
  • agriculture
en
Data topic
  • sensors
en
SO
INTERNATIONAL JOURNAL OF REMOTE SENSING
Document type

Inappropriate format for Document type, expected simple value but got array, please use list format

Institutions 10 co-publis
  • Univ_Saskatchewan (CA)
uid:/X993PS69
Powered by Lodex 8.20.3
logo commission europeenne
e-ROSA - e-infrastructure Roadmap for Open Science in Agriculture has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 730988.
Disclaimer: The sole responsibility of the material published in this website lies with the authors. The European Union is not responsible for any use that may be made of the information contained therein.