Multi-temporal classification of land cover using Landsat7 imagery in Madiama, Mali


M. Bertelsen; C. Heatwole; K. Moore; O. Badini

Type of Document:
Conference Proceeding or Document


Not Available

Date of Publication:

Place of Publication:
Not Available


Abstract: Multi-temporal imagery from the Landsat7 satellite (ETM+) was classified using unsupervised and supervised techniques to develop a land use / land cover map of the Madiama Commune in Mali. The desired outcome of the imagery classification is to identify the basic land uses in the region, and to make inferences on overall land suitability and productivity as a resource for the commune. Since different land uses/land covers are best represented at different dates, radiometric information from different images is expected to improve classification in a difficult environment. Imagery from three dates (April 2000, August 2000, and October 2000) provide coverage of primary phenological periods in the region. Combining multiple dates improved the accuracy of the classification compared to single-date classifications. Additional field data is required to provide an adequate basis for classification and for evaluation of alternative techniques.

Additional Bibliographic Information

Heatwole, C., M. Bertelsen, K. Moore, and O. Badini. 2001. Multi-temporal classification of land cover using Landsat7 imagery in Madiama, Mali. Proc. Research Synthesis Conference, SANREM CRSP, Athens, GA. November 28-30.

Send us your questions or comments

Your Name (required)

Your Email (required)


Please enter this text: