@Article{DalagnolWGBOSBPSFSA:2023:MaTrFo,
author = "Dalagnol, Ricardo and Wagner, Fabien Hubert and Galv{\~a}o,
L{\^e}nio Soares and Braga, Daniel and Osborn, Fiona and Sagang,
Le Bienfaiteur and Bispo, Polyanna da Concei{\c{c}}{\~a}o and
Payne, Matthew and Silva Junior, Celso and Favrichon, Samuel and
Silgueiro, Vinicius and Anderson, Liana O.",
affiliation = "{University of California} and {University of California} and
{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and CTrees and {University
of California} and {University of Manchester} and {University of
Manchester} and {University of California} and {NASA-Jet
Propulsion Laboratory} and {Instituto Centro de Vida (ICV)} and
{Centro Nacional de Monitoramento e Alertas de Desastres Naturais
(CEMADEN)}",
title = "Mapping tropical forest degradation with deep learning and Planet
NICFI data",
journal = "Remote Sensing of Environment",
year = "2023",
volume = "298",
pages = "e113798",
month = "Dec.",
keywords = "Amazon, Fire, Forest degradation, Logging, U-net.",
abstract = "Tropical rainforests from the Brazilian Amazon are frequently
degraded by logging, fire, edge effects and minor unpaved roads.
However, mapping the extent of degradation remains challenging
because of the lack of frequent high-spatial resolution satellite
observations, occlusion of understory disturbances, quick recovery
of leafy vegetation, and limitations of conventional
reflectance-based remote sensing techniques. Here, we introduce a
new approach to map forest degradation caused by logging, fire,
and road construction based on deep learning (DL), henceforth
called DL-DEGRAD, using very high spatial (4.77 m) and bi-annual
to monthly temporal resolution of the Planet NICFI imagery. We
applied DL-DEGRAD model over forests of the state of Mato Grosso
in Brazil to map forest degradation with attributions from 2016 to
2021 at six-month intervals. A total of 73,744 images (256 × 256
pixels in size) were visually interpreted and manually labeled
with three semantic classes (logging, fire, and roads) to
train/validate a U-Net model. We predicted the three classes over
the study area for all dates, producing accumulated degradation
maps biannually. Estimates of accuracy and areas of degradation
were performed using a probability design-based stratified random
sampling approach (n = 2678 samples) and compared it with existing
operational data products at the state level. DL-DEGRAD performed
significantly better than all other data products in mapping
logging activities (F1-score = 68.9) and forest fire (F1-score =
75.6) when compared with the Brazil's national maps (SIMEX, DETER,
MapBiomas Fire) and global products (UMD-GFC, TMF, FireCCI,
FireGFL, GABAM, MCD64). Pixel-based spatial comparison of
degradation areas showed the highest agreement with DETER and
SIMEX as Brazil official data products derived from visual
interpretation of Landsat imagery. The U-Net model applied to
NICFI data performed as closely to a trained human delineation of
logged and burned forests, suggesting the methodology can readily
scale up the mapping and monitoring of degraded forests at
national to regional scales. Over the state of Mato Grosso, the
combined effects of logging and fire are degrading the remaining
intact forests at an average rate of 8443 km2 year\−1 from
2017 to 2021. In 2020, a record degradation area of 13,294 km2 was
estimated from DL-DEGRAD, which was two times the areas of
deforestation.",
doi = "10.1016/j.rse.2023.113798",
url = "http://dx.doi.org/10.1016/j.rse.2023.113798",
issn = "0034-4257",
language = "en",
targetfile = "1-s2.0-S0034425723003498-main.pdf",
urlaccessdate = "12 maio 2024"
}