Understanding the spatial distribution of vegetation species is essential to gain knowledge on the recovery process of an ecosystem. Few studies have used deep learning and machine learning models for image processing focusing on forest/crop classification. This study, therefore, makes use of a multi-layer perceptron (MLP) deep neural network to discriminate grass species in a mountainous region using Sentinel-2 images. Vegetation indices, Sentinel-1 and ASTER DEM were combined with Sentinel-2 images to improve classification accuracy. Stratified K-fold was used to ensure balanced training and test data. The results, when compared with other commonly used machine learning models, outperformed them all. It produced a better discriminate of the grass species when ASTER DEM was combined with Sentinel-2 images, with overall F1 score of 92%. The results of the species discrimination show a general increase in increaser II species such as Eragrostis curvula and a decrease in decreaser species like Phragmites australis.

Wildfires are one of the major threats to the biodiversity of protected and mountainous landscapes. The severity of these fires is an important factor that influence vegetation recovery. Several remote sensing techniques has been used in previous studies to assess fire severity, but the Normalized Burn Ratio (NBR) has become the standard SI approach to assess burn severity. The Normalized Burn Ratio (NBR) demarcates burnt and unburned pixels in the pre-/post-fire season and, then creates an index of the severity of a burn using multi-spectral sensors, which establishes an ideal tool for fire severity assessment. In this study, the fire severity level is computed using the NBR Index from LANDSAT image. The images of pre-and postfire are used to evaluate the severity level, which is defined as a difference in NBR Index of pre- and post-fire. Results shows that in year 2000, 30704.22 ha of area burned with low to high severity, 31352.13 ha in year 2005,4697 ha in year 2013 and 30009.33 ha in 2017. A hundred field plots and fire records were used to validate the fire severity map for 2013 and 2017 with an accuracy of 74% which supports the use of NBR for assessing fire severity.