Mapping Atlantic rainforest degradation and regeneration history with indicator species using convolutional network

Author(s)

Wagner, Fabien H. ^{[1, 2]} ; Sanchez, Alber ^[1] ; Aidar, Marcos P. M. ^[3] ; Rochelle, Andre L. C. ^[4] ; Tarabalka, Yuliya ^{[5, 6]} ; Fonseca, Marisa G. ^[1] ; Phillips, Oliver L. ^[7] ; Gloor, Emanuel ^[7] ; Aragao, Luiz E. O. C. ^{[8, 1]}

Affiliation

^[1] Natl Inst Space Res INPE, Remote Sensing Div, Sao Jose Dos Campos, SP - Brazil

^[2] Fdn Sci Technol & Space Applicat FUNCATE, Geoproc Div, Sao Jose Dos Campos, SP - Brazil

^[3] Inst Bot, Dept Plant Physiol & Biochem, Sao Paulo - Brazil

^[4] Natl Inst Space Res INPE, Ctr Earth Syst Sci, Sao Jose Dos Campos, SP - Brazil

^[5] Inria Sophia Antipolis, Sophia Antipolis - France

^[6] Luxcarta Technol, Parc Activite Argile, Mouans Sartoux - France

^[7] Univ Leeds, Sch Geog, Ecol & Global Change, Leeds, W Yorkshire - England

^[8] Univ Exeter, Coll Life & Environm Sci, Exeter, Devon - England

• Document type: Journal article
• Source: PLoS One; v. 15, n. 2 FEB 28 2020.
• Web of Science Citations: 0

Abstract

The Atlantic rainforest of Brazil is one of the global terrestrial hotspots of biodiversity. Despite having undergone large scale deforestation, forest cover has shown signs of increases in the last decades. Here, to understand the degradation and regeneration history of Atlantic rainforest remnants near Sao Paulo, we combine a unique dataset of very high resolution images from Worldview-2 and Worldview-3 (0.5 and 0.3m spatial resolution, respectively), georeferenced aerial photographs from 1962 and use a deep learning method called U-net to map (i) the forest cover and changes and (ii) two pioneer tree species, Cecropia hololeuca and Tibouchina pulchra. For Tibouchina pulchra, all the individuals were mapped in February, when the trees undergo mass-flowering with purple and pink blossoms. Additionally, elevation data at 30m spatial resolution from NASA Shuttle Radar Topography Mission (SRTM) and annual mean climate variables (Terraclimate datasets at similar to 4km of spatial resolution) were used to analyse the forest and species distributions. We found that natural forests are currently more frequently found on south-facing slopes, likely because of geomorphology and past land use, and that Tibouchina is restricted to the wetter part of the region (southern part), which annually receives at least 1600 mm of precipitation. Tibouchina pulchra was found to clearly indicate forest regeneration as almost all individuals were found within or adjacent to forests regrown after 1962. By contrast, Cecropia hololeuca was found to indicate older disturbed forests, with all individuals almost exclusively found in forest fragments already present in 1962. At the regional scale, using the dominance maps of both species, we show that at least 4.3% of the current region's natural forests have regrown after 1962 (Tibouchina dominated, similar to 4757 ha) and that similar to 9% of the old natural forests have experienced significant disturbance (Cecropia dominated). (AU)

• FAPESP's process: 12/51872-5 - ECOFOR: Biodiversity and ecosystem functioning in degraded and recovering Amazonian and Atlantic Forests
• Grantee: Carlos Alfredo Joly
• Support Opportunities: BIOTA-FAPESP Program - Thematic Grants
• FAPESP's process: 16/17652-9 - Functional diversity of intact and regenerating Amazon, Atlantic Forest and Cerrado systems using hyperspectral imagery
• Grantee: Fabien Hubert Wagner
• Support Opportunities: Scholarships in Brazil - Young Researchers
• FAPESP's process: 15/50484-0 - Functional diversity of intact and regenerating Amazon, Atlantic Forest, and Cerrado systems using hyperspectral imagery
• Grantee: Fabien Hubert Wagner
• Support Opportunities: Research Grants - Young Investigators Grants
• FAPESP's process: 16/03397-7 - Tools for satellite images management in array databases
• Grantee: Alber Hamersson Sánchez Ipia
• Support Opportunities: Scholarships in Brazil - Technical Training Program - Technical Training
• FAPESP's process: 13/50533-5 - Understanding the response of photosynthetic metabolism in tropical forests to seasonal climate variations
• Grantee: Luiz Eduardo Oliveira e Cruz de Aragão
• Support Opportunities: Regular Research Grants