Mapping tree species proportions from satellite imagery using spectral–spatial deep learning

Bolyn, Corentin; Lejeune, Philippe; Michez, Adrien; Latte, Nicolas

doi:10.1016/j.rse.2022.113205

Cited by 39 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While more and more NFIs provide data with fine-scale spatial resolution (e.g. 10 – 14 ), most countries deliver area-level statistics at national or subnational scale. Consequently, at the European level, NFI data refer to different periods, biomass pools, and spatial scales that hamper their comparability and integration 9 , 15 .…”

Section: Background and Summarymentioning

confidence: 99%

Harmonised statistics and maps of forest biomass and increment in Europe

Avitabile,

Pilli,

Migliavacca

et al. 2024

Sci Data

Self Cite

View full text Add to dashboard Cite

Forest biomass is an essential resource in relation to the green transition and its assessment is key for the sustainable management of forest resources. Here, we present a forest biomass dataset for Europe based on the best available inventory and satellite data, with a higher level of harmonisation and spatial resolution than other existing data. This database provides statistics and maps of the forest area, biomass stock and their share available for wood supply in the year 2020, and statistics on gross and net volume increment in 2010–2020, for 38 European countries. The statistics of most countries are available at a sub-national scale and are derived from National Forest Inventory data, harmonised using common reference definitions and estimation methodology, and updated to a common year using a modelling approach. For those counties without harmonised statistics, data were derived from the State of Europe’s Forest 2020 Report at the national scale. The maps are coherent with the statistics and depict the spatial distribution of the forest variables at 100 m resolution.

show abstract

Section: Background and Summarymentioning

confidence: 99%

Harmonised statistics and maps of forest biomass and increment in Europe

Avitabile,

Pilli,

Migliavacca

et al. 2024

Sci Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…The rst prerequisite to assess spruce dieback was to map the species distribution at a ne scale. For the south of Belgium (Wallonia), we used reliable composition maps from Bolyn et al, (2022), in order to restrict our analysis to Norway spruce stands. These composition maps consist in presence probabilities for eight major species, from which we discriminated Norway spruce stands by selecting areas with equals or greater than 80% of probability of presence.…”

Section: Focus On Spruce Standsmentioning

confidence: 99%

Spatial and remote sensing monitoring shows the end of the bark beetle outbreak on Belgian and north-eastern France Norway spruce (Picea abies) stands

Arthur,

Jonathan,

Juliette

et al. 2024

Environ Monit Assess

View full text Add to dashboard Cite

In 2022, Europe emerged from eight of the hottest years on record, leading to signi cant spruce mortality across Europe. The particularly dry weather conditions of 2018 triggered an outbreak of bark beetles (Ips typographus), causing the loss of thousands of hectares of Norway spruce stands, including in Wallonia and North-eastern France.A methodology for detecting the health status of spruce was developed based on dense time series of satellite imagery (Sentinel-2). The time series of satellite images allowed the modelling of the spectral response of healthy spruce forests over the seasons: a decrease in photosynthetic activity of the forest canopy causes deviations from this normal seasonal vegetation index trajectory. These anomalies are caused by a bark beetle attack and are detected automatically. The method leads in the production of annual spruce health map of Wallonia and Grand-Est.The resulting map are used to assess the damage caused by bark beetle and to study the relation between the dieback and environmental conditions.Lasted six years (2017-2022), bark beetle has destroyed 12.2% (23,674 ha) of the spruce area in Wallonia and Grand-Est of France. This study area is composed of three bioclimatic areas: Plains, Ardennes and Vosges, which have not been equally affected by bark beetle attacks. The plains were the most affected, with 50% of spruce forests destroyed, followed by the Ardennes, which lost 11.3% of its spruce stands. The Vosges was the least affected bioclimatic area, with 5.6% of spruce stands lost.

show abstract

“…In tree detection processes, especially when hyperspectral images are used, the training data is inserted into the training piecemeal, not in bulk, in order to train the weights of the architecture. The Unet++ model aims to reduce overfitting and strengthen model generalization by making weight adjustments (Bolyn et al, 2022).…”

Section: Deep Learningmentioning

confidence: 99%

“…With hyperspectral and multispectral images, individual tree identifications can be made as well as stand-based species mapping (Ferreira et al, 2020;Grabska et al, 2020). With the without restraint development of technology, the increase in artificial intelligence applications has also contributed to remotely sensed images (Bolyn et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Exploiting hyperspectral and multispectral images in the detection of tree species: A review

Yel

Görmüş

2023

Front. Remote Sens.

View full text Add to dashboard Cite

Classification of tree species provides important data in forest monitoring, sustainable forest management and planning. The recent developments in Multi Spectral (MS) and Hyper Spectral (HS) Imaging sensors in remote sensing have made the detection of tree species easier and accurate. With this systematic review study, it is aimed to understand the contribution of using the Multi Spectral and Hyper Spectral Imaging data in the detection of tree species while highlighting recent advances in the field and emphasizing important directions together with new possibilities for future inquiries. In this review, researchers and decision makers will be informed in two different subjects: First one is about the processing steps of exploiting Multi Spectral and HS images and the second one is about determining the advantages of exploiting Multi Spectral and Hyper Spectral images in the application area of detecting tree species. In this way exploiting satellite data will be facilitated. This will also provide an economical gain for using commercial Multi Spectral and Hyper Spectral Imaging data. Moreover, it should be also kept in mind that, as the number of spectral tags that will be obtained from each tree type are different, both the processing method and the classification method will change accordingly. This review, studies were grouped according to the data exploited (only Hyper Spectral images, only Multi Spectral images and their combinations), type of tree monitored and the processing method used. Then, the contribution of the image data used in the study was evaluated according to the accuracy of classification, the suitable type of tree and the classification method.

show abstract

Mapping tree species proportions from satellite imagery using spectral–spatial deep learning

Cited by 39 publications

References 32 publications

Harmonised statistics and maps of forest biomass and increment in Europe

Harmonised statistics and maps of forest biomass and increment in Europe

Spatial and remote sensing monitoring shows the end of the bark beetle outbreak on Belgian and north-eastern France Norway spruce (Picea abies) stands

Exploiting hyperspectral and multispectral images in the detection of tree species: A review

Contact Info

Product

Resources

About