Vegetation is profoundly impacted by anthropogenic activities, particularly trampling. The ultimate effect of trampling is a reduction in amount of vegetation, often resulting in complete loss of vegetation cover. Satellite remote sensed data for land cover, landuse and its changes is a key to many diverse applications. Methods for monitoring vegetation change range from intensive field sampling with plot inventories to extensive analysis of remotely sensed data which has proven to be more cost effective for large regions, small site assessment and analysis. Remotely sensed change detection based on artificial neural networks presents a new technique using training algorithm. The trained neural network detected changes on a pixel-by-pixel basis in real time applications. The trained four-layered neural network (for example, decreased, some decrease, some increase and increased) provided complete categorical information about the nature of changes and detected complete land cover change “from-to” information, which is desirable in most change detection applications. This paper presents an application of the use of Landsat ETM+ images and MODIS EVI/NDVI time-series vegetation phenology algorithms of Faisalabad and Multan districts for evaluation of soil productivity and comparison of temporal change detection. The proposed method is successfully applied to actual multi-temporal and multi-spectral images.
Key words: Algorithm, change detection, enhanced vegetation index (EVI), Landsat, normalized difference vegetation index (NDVI), phenology, remote sensing.
Copyright © 2021 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0