Comparing the MLC and JavaNNS approaches in classifying multi-temporal LANDSAT satellite imagery over an ephemeral river area

This paper analyzes two pixel-based classif cation approaches to support the analysis of land cover transformations based on multitemporal LANDSAT sensor data covering a time space of about 24 years. The research activity presented in this paper was carried out using Lama San Giorgio (Bari, Italy) catchment area as a study case, being this area prone to fooding as proved by its geological and hydrological characteristics and by the signifcant number of foods occurred in the past. Land cover classes were defned in accordance with on the CNmethod with the aim of characterizing land use based on attitude to generate runoff. Two different classifers, i.e. Maximum Likelihood Classifer (MLC) and Java Neural Network Simulator (JavaNNS) models, were compared. The Artif cial Neural Networks (ANN) approach was found to be the most reliable and effcient when lacking ground reference data and a priori knowledge on input data distribution.