Academia.edu no longer supports Internet Explorer.
To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to upgrade your browser.
2022
Trees sustain livelihoods and mitigate climate change but a predominance of trees outside forests and limited resources make it difficult for many tropical countries to conduct automated nation-wide inventories. Here, we propose an approach to map the carbon stock of each individual overstory tree at the national scale of Rwanda using aerial imagery from 2008 and deep learning. We show that 72% of the mapped trees are located in farmlands and savannas and 17% in plantations, accounting for 48.6% of the national aboveground carbon stocks. Natural forests cover 11% of the total tree count and 51.4% of the national carbon stocks, with an overall carbon stock uncertainty of 16.9%. The mapping of all trees allows partitioning to any landscapes classification and is urgently needed for effective planning and monitoring of restoration activities as well as for optimization of carbon sequestration, biodiversity and economic benefits of trees.
Trees sustain livelihoods and mitigate climate change, but a predominance of trees outside forests and limited resources make it difficult for many developing countries to conduct frequent nation-wide inventories. Here, we propose a rapid and accurate approach to map the carbon stock of each individual tree and shrub at the national scale of Rwanda using aerial imagery and deep learning. We show that 72% of the mapped trees are located in farmlands and savannas, and 15% in plantations. These non-forest trees account for 41% of the national carbon stocks. Natural forests cover 5% of the country and 11% of the total tree count, but comprise 59% of the national carbon stocks. The mapping of all trees facilitates any landscape stratification and is urgently needed for effective planning and monitoring of landscape restoration activities as well as for optimization of carbon sequestration, biodiversity and economic benefits of trees.
While closed canopy forests have been an important focal point for land cover change monitoring and climate change mitigation, less consideration has been given to methods for large scale measurements of trees outside of forests. Trees outside of forests are an important but often overlooked natural resource throughout sub-Saharan Africa, providing benefits for livelihoods as well as climate change mitigation and adaptation. In this study, the development of an individual tree cover map using very high-resolution remote sensing and a comparison with a new automated machine learning mapping product revealed an important contribution of trees outside of forests to landscape tree cover and carbon stocks in a region where trees outside of forests are important components of livelihood systems. Here, we test and demonstrate the use of allometric scaling from remote sensing crown area to provide estimates of landscape-scale carbon stocks. Prominent biomass and carbon maps from global-scal...
The consistent monitoring of trees both inside and outside of forests is key to mitigating climate change. Current monitoring systems either ignore trees outside forests or are too expensive to be applied consistently across countries on a repeated basis. Here we make use of the PlanetScope nanosatellite constellation, which delivers global very high-resolution daily imagery, to map both forest and non-forest tree cover for continental Africa using images from a single year. Our prototype map of 2019 demonstrates that a precise assessment of all tree-based systems is possible at continental scale, and reveals that 29% of tree cover is found outside areas previously classified as tree cover, such as in croplands and grassland. Such accurate mapping of tree cover at metric resolution down to the level of individual trees and consistent among countries has the potential to redefine land use impacts, move beyond the need for forest definitions, build the basis for natural climate soluti...
International Journal of Applied Earth Observation and Geoinformation
Forest mapping and monitoring in Africa using Sentinel-2 data and deep learning2022 •
We propose and investigate a method for creating large scale forest height maps at 10 m resolution from Sentinel- 2 data using deep neural networks. In addition, we demonstrate how clear-cutting events can be detected in a time series of the resulting forest height maps. The network architecture is a convolutional neural network based on the U-Net architecture. The 13 Sentinel-2 spectral bands are resampled to 10 m spatial resolution and input to the U-Net, which outputs a map with per-pixel forest height estimates. The network is trained with ground truth data acquired from airborne lidar scanning surveys from three different geographical regions. They cover different types of forests: lowland tropical rainforest in the Democratic Republic of Congo, Miombo woodlands (dry forest) in Liwale, Tanzania, and submontane tropical rainforest in Amani, Tanzania. We demonstrate that the trained network generalizes to new geographical regions within the African continent with a mean average error of 4.6 m. This is on-par with a previously published method’s ability to generalize to new geographical regions within the same country. Clear-cutting events are detected using a t-test. The null-hypothesis of the t-test is that the forest height has not changed after any given point in time in the forest height time-series.
2021 •
Documenting the impacts of climate change and human activities on tropical rainforests is imperative for protecting tropical biodiversity and for better implementation of REDD+ and UN Sustainable Development Goals. Recent advances in very high-resolution satellite sensor systems (i.e., WorldView-3), computing power, and machine learning (ML) have provided improved mapping of fine-scale changes in the tropics. However, approaches so far focused on feature extraction or the extensive tuning of ML parameters, hindering the potential of ML in forest conservation mapping by not using textural information, which is found to be powerful for many applications. Additionally, the contribution of shortwave infrared (SWIR) bands in forest cover mapping is unknown. The objectives were to develop end-to-end mapping of the tropical forest using fully convolution neural networks (FCNNs) with WorldView-3 (WV-3) imagery and to evaluate human impact on the environment using the Betampona Nature Reserv...
Nature Communications
More than one quarter of Africa’s tree cover is found outside areas previously classified as forestThe consistent monitoring of trees both inside and outside of forests is key to sustainable land management. Current monitoring systems either ignore trees outside forests or are too expensive to be applied consistently across countries on a repeated basis. Here we use the PlanetScope nanosatellite constellation, which delivers global very high-resolution daily imagery, to map both forest and non-forest tree cover for continental Africa using images from a single year. Our prototype map of 2019 (RMSE = 9.57%, bias = −6.9%). demonstrates that a precise assessment of all tree-based ecosystems is possible at continental scale, and reveals that 29% of tree cover is found outside areas previously classified as tree cover in state-of-the-art maps, such as in croplands and grassland. Such accurate mapping of tree cover down to the level of individual trees and consistent among countries has the potential to redefine land use impacts in non-forest landscapes, move beyond the need for forest...
2014 •
2020 •
Accurate tree cover mapping is of paramount importance in many fields, from biodiversity conservation to carbon stock estimation, ecohydrology, erosion control, or Earth system modelling. Despite this importance, there is still uncertainty about global forest cover, particularly in drylands. Recently, the Food and Agriculture Organization of the United Nations (FAO) conducted a costly global assessment of dryland forest cover through the visual interpretation of orthoimages using the Collect Earth software, involving hundreds of operators from around the world. Our study proposes a new automatic method for estimating tree cover using artificial intelligence and free orthoimages. Our results show that our tree cover classification model, based on convolutional neural networks (CNN), is 23% more accurate than the manual visual interpretation used by FAO, reaching up to 79% overall accuracy. The smallest differences between the two methods occurred in the driest regions, but disagreeme...
2008 •
The Government of Rwanda aims at making forestry one pillar of the economic development. In this regard, the vision 2020, which contains major targets that have been set by the government to be achieved by year 2020, fixed 30% as the target to be attained in terms of national forest cover. There is need therefore to monitor constantly reforestation achievements in order to make sure that vision 2020 targets are met. This paper reports on a forest mapping assignment carried out to update the forest cover map of Rwanda including all forested areas of at least 0.25 hausing largely high resolution aerial photographs taken during 2008 aerial survey mission by Swedesurvey. Several hints of visual image interpretation for forest classification were used in order to ease the extraction of forest polygons. After ground truthing (fieldwork confirmation of different forest cover classes) throughout the country, five forest classes in natural forests and thirteen classes in forest plantations w...
Côte d’Ivoire and Ghana, the world’s largest producers of cocoa, account for two thirds of the global cocoa production. In both countries, cocoa is the primary perennial crop, providing income to almost two million farmers. Yet precise maps of the area planted with cocoa are missing, hindering accurate quantification of expansion in protected areas, production and yields and limiting information available for improved sustainability governance. Here we combine cocoa plantation data with publicly available satellite imagery in a deep learning framework and create high-resolution maps of cocoa plantations for both countries, validated in situ. Our results suggest that cocoa cultivation is an underlying driver of over 37% of forest loss in protected areas in Côte d’Ivoire and over 13% in Ghana, and that official reports substantially underestimate the planted area (up to 40% in Ghana). These maps serve as a crucial building block to advance our understanding of conservation and economi...
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.
Computational Vision and Bio-Inspired Computing
Using Deep Learning on Satellite Images to Identify Deforestation/Afforestation2020 •
scientific data
Global forest management data for 2015 at a 100m resolution2022 •
2011 •
Scientific reports
Spatial Distribution of Carbon Stored in Forests of the Democratic Republic of Congo2017 •
Ecological Applications
Assessing aboveground tropical forest biomass using Google Earth canopy images2012 •
arXiv (Cornell University)
High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach2022 •
2020 •
2021 Second International Conference on Intelligent Data Science Technologies and Applications (IDSTA)
Estimating Deforestation using Machine Learning Algorithms2021 •
Environmental monitoring and assessment
Mapping tropical deforestation in Central Africa2005 •
2013 •