Climatic, topographic, and geological diversity, together with frequent disturbance and recovery cycles, produce highly complex spatial patterns of trees, shrubs, dwarf-shrubs and bare ground patches. Assessment of spatial and temporal variations of these life-forms patterns under climate change is of high ecological priority. This study is one of the very few attempts to classify 3 density levels for the main three Mediterranean life-forms’ patterns. The development of an extensive database of orthophoto images representing the different pattern categories was instrumental for training and testing pre-trained and newly-trained DL models utilizing DenseNet architecture. Both models demonstrated the advantages of using Deep Learning approaches over existing spectral and spatial (pattern or texture) algorithmic methods in differentiation of 9 life-forms’ spatial mixtures categories.
1. Mr. Matan Cohen
Deep Learning Strategies for Mapping Complex Vegetation Patterns (CVP) in Mediterranean Environments undergoing Climate Change
Bar-Ilan University, Israel