Les peupleraies : Quels enjeux pour l’avenir de la populiculture française ?

Paillassa, Eric

doi:10.4267/2042/56060

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the increased demand for poplar wood, planted areas continue to decrease [2]. Indeed, for the past 20 years, the poplar sector has undergone several economic, social and environmental upheavals and have consequently had an impact on the planting rate [3]. This deficit of several years has led the sector to an unavoidable wood shortage, which is expected to reach at least 500,000 m 3 /year in 2025, according to the CNP.…”

Section: Introductionmentioning

confidence: 99%

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

Hamrouni

Paillassa

Chéret

et al. 2021

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

show abstract

Section: Introductionmentioning

confidence: 99%

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2

Hamrouni

Paillassa

Chéret

et al. 2021

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Average annual poplar harvesting reached 2.4 million m 3 ( [FCBA] Forêt Cellulose Bois-construction Ameublement 2013). According to Paillassa (2014), plywood and veneer still account for the largest share of poplar products with 59.9% of total production ( [FAO] Food and Agriculture Organization 2011). Plywood industry is the main target for poplar growers (Ball et al 2005).…”

Section: Introductionmentioning

confidence: 99%

“…In France, this industry was leaning on few poplar cultivars, but because of recent shifts in resistance to rust disease and changing industrial demands, new selected poplar cultivars were introduced (Paillassa 2014). However, the evaluation of the wood quality of these new cultivars has not been sufficiently taken into account.…”

Section: Introductionmentioning

confidence: 99%

Some properties of plywood produced from 10 cultivars of poplar

Haouzali

Marchal

Bléron

et al. 2020

International Wood Products Journal

View full text Add to dashboard Cite

The aim of this paper is to study the possible influence of poplar cultivar and soil on the mechanical properties of plywood produced from 10 cultivars having grown in different soils. For each cultivar, two trees were harvested per station; crosscut into bolts then peeled 1.4 mm thick for one tree and 3 mm thick for the other one: in total, 80 trees were sampled. The veneers were used to make 160 boards using 2 adhesives: polyvinyl acetate (PVAc) and melamine-urea-formaldehyde (MUF). These boards were then cut into standardized samples for non-destructive and destructive mechanical tests. The properties of plywood were characterized by measuring their density, modulus of elasticity and modulus of rupture. The results showed that poplar plywood properties could be influenced by adhesive and veneer thickness. The cultivar and soil effects were never relevant. A tight correlation was found between destructive and non-destructive modulus of elasticity tests.

show abstract