This article describes the use of a Bayesian network (BN) for the classification of land cover from satellite imagery in northern Swaziland. The main objective of this work was to apply and evaluate the efficacy of a BN for land-cover classification using gap-filled and terrain-corrected Landsat 7 Enhanced Thematic Mapper Plus (ETM+) imagery acquired on 15 May 2007. The posterior probabilities (parameters) were estimated using the expectation-maximization (EM) and conjugate gradient descent (CGD) algorithms.
Search resultsShowing items 1 through 9 of 3.
Library ResourceJournal Articles & BooksDecember, 2011Eswatini
Library ResourceDecember, 2011Eswatini, Southern Africa, Africa
Beans are an important crop for food and income generation in Swaziland. They do very well in the higher areas of the country although can be grown in all the regions. They are also the second legume to Swazi farmers after groundnuts in importance. Different farmers grow beans for different uses such as leaves, green beans or dry beans.
Library ResourceJournal Articles & BooksDecember, 2011Switzerland, South Africa, Lesotho, China, Italy, Eswatini, Cuba, Tunisia, Argentina, Senegal, Netherlands, Europe, Asia, Africa, Northern America
The WOCAT-LADA-DESIRE mapping tool is based on the original WOCAT mapping questionnaire (WOCAT, 2007). It has been expanded to pay more attention to issues such as biological and water degradation, it also places more emphasis on direct and socio-economic causes of these phenomena, including their impacts on ecosystem services. It evaluates what type of land degradation is actually happening where and why and what is being done about it in terms of sustainable land management (SLM) in the form of a questionnaire.
Land Library Search
Through our robust search engine, you can search for any item of the over 64,800 highly curated resources in the Land Library.
If you would like to find an overview of what is possible, feel free to peruse the Search Guide.