What is it about?
In this paper, we present a deep learning (DL) approach from artificial intellingence for mapping poplar plantations using Sentinel-2 time series. A reference dataset of poplar plantations was available for a large study area of more than 46,000 km2 in Northern Italy and served as training and testing data. Two classification methods were compared: (1) a fully connected neural network (also called multilayer perceptron), and (2) a traditional logistic regression.
Featured Image
Why is it important?
Poplars are one of the most widespread fast-growing tree species used for forest plantations. Owing to their distinct features (fast growth and short rotation) and the dependency on the timber price market, poplar plantations are characterized by large inter-annual fluctuations in their extent and distribution. Therefore, monitoring poplar plantations requires a frequent update of information – not feasible by National Forest Inventories due to their periodicity – achievable by remote sensing systems applications. In particular, the new Sentinel-2 mission, with a revisiting period of 5 days, represents a potentially efficient tool for meeting this need.
Perspectives
Forest tree monitoring and assessment are rapidly evolving as new information needs arise and new techniques and tools become available. Among these, the most widely applied and promising approaches today are ensemble methods and DL. The major contribution of this study is the set-up of an efficient automatic approach to map forest tree plantations on farm land using S2 multitemporal imagery. The procedure here developed and tested provide automatically good results and can be applied to different reference datasets.
Piermaria Corona
CREA Research Centre for Forestry and Wood
Read the Original
This page is a summary of: A deep learning approach for automatic mapping of poplar plantations using Sentinel-2 imagery, GIScience & Remote Sensing, October 2021, Taylor & Francis,
DOI: 10.1080/15481603.2021.1988427.
You can read the full text:
Contributors
The following have contributed to this page
