Alvar: Ailanthus altissima visual aid for reconnaissance

Alvar is a Google Earth Engine cloud application for early reconnaissance of Ailanthus altissima.

Alvar is based on Copernicus Sentinel-2 optical imagery at 10m ground pixel resolution.

The service rationale is that each plant species shows peculiar signals in the optical range and, possibly, time-series signatures. Hence, recognising the invasive alien species A. altissima is in principle feasible, given a characteristic optical spatiotemporal signature. However, even if we can have physiological clues, we do not know such a signature.

Alvar supports the search and reconnaissance of A. altissima optical signature exploiting the cloud computing capability of fast time series search of the images and the vegetation-related associated optical indices, without the need for local data download.

Alvar exploits the machine learning algorithms exposed by the Google Earth Engine APIs and trains them by

means of a user-provided training/control set of empirical observations.

The user interface is GUI-based and the intervention on the code consists only in importing the appropriate

training set and tuning the area of interest bounding box accordingly.

Date ( Publication): 2025-11-21

Status: Completed

Creator

National Research Council (CNR), Research Institute on Terrestrial Ecosystems (IRET) - Marco Ciolfi

Version: v.1.0

Keywords: e-Service

Keywords: invasive alien species

Keywords: identification

Keywords: Sentinel-2

Keywords: cloud computing

Keywords: environmental monitoring

Keywords: habitat mapping

Keywords: remote sensing

Access constraints: License

Use limitation: GNU GPL-3.0

Other constraints: Users must be logged as Google developers in order to use the application.

OnLine resource: Alvar service (
URL
)

OnLine resource: DOI (
DOI
)

Operation name: Aalto: Sample training set for Ailanthus altissima visual aid reconnaissance

Web site: https://data.lifewatchitaly.eu/handle/123456789/326276

Description: The Aalto shapefile consists in a set of training and control points to train different classification algorithms provided by Google Engine. The Alvar and Aalto pair is meant to be a minumim working example for training and classifications. Users can operate with their own datasets, following the simple class and type structure of the Aalto file.

Function: The Alvar script produces a map of potential sites infested by the invasive species Ailanthus altissima. This result is computed based on a traning set (Aalto shapefile) containing information about infested / not-infested areas (sampling sites) and a similar control set to assess the accuracy of the classification.