Review of CNN-Based Vegetation Mapping in Suburban Areas Using Satellite Imagery

The detection and analysis of plant species across spatial and temporal scales is essential in multiple fields, including agriculture, conservation, and forest management. In suburban landscapes, where natural and developed environments intersect, satellite-based observation has become a vital tool for uncovering vegetation dynamics over time and space. The growing availability of data from satellites has heightened the need for efficient and precise methods to assess and monitor vegetation, particularly in suburban regions. In recent decades, deep learning has proven capable of automatically identifying relevant features from data in an end-to-end process. Recent studies have shown that Convolutional Neural Networks (CNNs) are highly effective in capturing spatial patterns, making them well-suited for extracting diverse vegetation characteristics from satellite imagery, especially in complex suburban environments. This review highlights the key concepts of CNNs and their growing role in vegetation mapping, focusing on recent advances in data sources, sensor types, and network architectures. CNNs offer adaptable tools for vegetation analysis in suburban areas, with growing visualization methods improving both interpretation and insight. Though still emerging, they are transforming vegetation monitoring.

کلیدواژه ها:

Convolutional Neural Networks (CNN) ، Deep Learning ، Suburban Areas ، Plants ، Vegetation ، Satellite Images