Mapping real-time forest disturbances is a key challenge to combat global deforestation, and to monitoring forest disturbances at sub-annual scales. For this purpose, the new Planetscope nano-satellite constellation is a game changer, with a revisit time of 1 day and a pixel size of 3-m.
In the new paper publish in the European Journal of Remote Sensing, we present a near-real time forest disturbances alert system “the Thresholding Rewards and Penances algorithm (TRP)” that produces a new forest change map as soon as a new PlanetScope image is acquired.
We tested the new “TRP” algorithm in Tuscany to detect forest disturbances between 1 May 2018 and 5 July 2019. We processed 572 PlanetScope images and we found that TRP was able to construct forest change maps during the study period for which the final user’s accuracy was 86% and the final producer’s accuracy was 92%.
The full paper is available open-access at this link https://doi.org/10.1080/22797254.2020.1806734
We would like to congratulate with Saverio Francini for his first paper as first author!
To cite the article: Saverio Francini, Ronald E. McRoberts, Francesca Giannetti, Marco Mencucci, Marco Marchetti, Giuseppe Scarascia Mugnozza & Gherardo Chirici (2020) Near-real time forest change detection using PlanetScope imagery, European Journal of Remote Sensing, 53:1, 233-244, DOI: 10.1080/22797254.2020.1806734