M. Alonzo, H. Andersen, D. Morton, and B. Cook, Quantifying Boreal Forest Structure 475 and Composition Using UAV Structure from Motion, vol.9, 2018.

S. Arlot and A. Celisse, A survey of cross-validation procedures for model selection, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00407906

. Statist and . Surv, , vol.4, pp.40-79

G. P. Asner, M. Keller, R. Pereira, and J. C. Zweede, Remote sensing of selective 480 logging in Amazonia: Assessing limitations based on detailed field observations, p.481, 2002.

E. Landsat, Remote Sensing of Environment, vol.80, pp.483-496

G. P. Asner, D. E. Knapp, A. Balaji, and G. Páez-acosta, Automated mapping of tropical 483 deforestation and forest degradation: CLASlite, Journal of Applied Remote Sensing, vol.484, issue.3, pp.33543-033543, 2009.

G. P. Asner, J. Mascaro, H. C. Muller-landau, G. Vieilledent, R. Vaudry et al., , p.486

J. S. Hall and M. Van-breugel, A universal airborne LiDAR approach for tropical 487 forest carbon mapping, Oecologia, vol.168, pp.1147-1160, 2012.

A. Baccini, W. Walker, L. Carvalho, M. Farina, D. Sulla-menashe et al., 490 Tropical forests are a net carbon source based on aboveground measurements of 491 gain and loss, Science, vol.358, pp.230-234, 2017.

N. Barbier and P. Couteron, Attenuating the bidirectional texture variation of satellite 493 images of tropical forest canopies, Remote Sensing of Environment, vol.171, pp.245-260, 2015.

N. Barbier, P. Couteron, C. Proisy, Y. Malhi, and J. Gastellu-etchegorry, The 496 variation of apparent crown size and canopy heterogeneity across lowland 497 Amazonian forests: Amazon forest canopy properties, Global Ecology and 498 Biogeography, vol.19, pp.72-84, 2010.

J. Barlow, G. D. Lennox, J. Ferreira, E. Berenguer, A. C. Lees et al., , p.500

S. F. Ferraz, B. De, J. Louzada, V. H. Oliveira, L. Parry et al., Ribeiro de Castro Solar, p.502

R. C. De, O. Souza, C. M. Moura, N. G. Nunes, S. S. Siqueira et al., , p.503

J. M. Silveira, F. Z. Vaz-de-mello, R. C. Veiga, A. Venturieri, and T. A. Gardner, , p.504, 2016.

, Anthropogenic disturbance in tropical forests can double biodiversity loss from 505 deforestation, Nature, vol.535, pp.144-147

J. Bastin, N. Barbier, P. Couteron, B. Adams, A. Shapiro et al., Aboveground biomass mapping of African forest mosaics using canopy texture 508 analysis: toward a regional approach, Ecological applications, vol.507, 1984.

E. Berenguer, J. Ferreira, T. A. Gardner, L. E. Aragão, P. B. De-camargo et al., , p.510

M. Durigan, R. C. Oliveira, I. C. Vieira, and J. Barlow, A large-scale field 511 assessment of carbon stocks in human-modified tropical forests, Global Change 512 Biology, vol.20, pp.3713-3726, 2014.

E. Berenguer, Y. Malhi, P. Brando, A. Cardoso, N. Cordeiro et al., , p.514

L. C. Rossi, Tree growth and stem carbon accumulation in human-modified 515 Amazonian forests following drought and fire 8, 2018.

C. Bourgoin, L. Blanc, J. Bailly, G. Cornu, E. Berenguer et al., , p.517

F. Laurent, A. F. Hasan, P. Sist, and V. Gond, The Potential of Multisource 518 Remote Sensing for Mapping the Biomass of a Degraded Amazonian Forest 21, 2018.

L. Breiman, Random forests, Machine learning, vol.45, pp.5-32, 2001.

G. Briant, V. Gond, and S. G. Laurance, Habitat fragmentation and the desiccation of 521 forest canopies: A case study from eastern Amazonia, Biological Conservation, vol.143, pp.2763-2769, 2010.

E. Broadbent, G. Asner, M. Keller, D. Knapp, P. Oliveira et al., Forest 524 fragmentation and edge effects from deforestation and selective logging in the 525 Brazilian Amazon, Biological Conservation, vol.141, pp.1745-1757, 2008.

,

E. L. Bullock, C. E. Woodcock, and P. Olofsson, Monitoring tropical forest degradation 528 using spectral unmixing and Landsat time series analysis. Remote Sensing of 529 Environment, 2018.

R. L. Chazdon, P. H. Brancalion, L. Laestadius, A. Bennett-curry, and K. Buckingham, , p.531

C. Kumar, J. Moll-rocek, I. C. Vieira, and S. J. Wilson, When is a forest a 532 forest? Forest concepts and definitions in the era of forest and landscape restoration, 2016.

, Ambio, vol.45, pp.538-550

C. Chung, C. Wang, H. Hsieh, and C. Huang, Comparison of forest canopy 535 height profiles in a mountainous region of Taiwan derived from airborne lidar and 536 unmanned aerial vehicle imagery, GIScience & Remote Sensing, vol.56, pp.1289-1304, 2019.

,

P. Couteron, Quantifying change in patterned semi-arid vegetation by Fourier 539 analysis of digitized aerial photographs, International Journal of Remote Sensing, vol.23, pp.3407-3425, 2002.

P. Couteron, R. Pelissier, E. A. Nicolini, and D. Paget, Predicting tropical forest stand 542 structure parameters from Fourier transform of very high-resolution remotely sensed 543 canopy images, Journal of applied ecology, vol.42, pp.1121-1128, 2005.

P. Couteron, R. Pelissier, E. A. Nicolini, and D. Paget, Predicting tropical forest stand 545 structure parameters from Fourier transform of very high-resolution remotely sensed 546 canopy images: Predicting tropical forest stand structure, Journal of Applied Ecology, vol.547, pp.1121-1128, 2005.

J. Dandois, M. Olano, and E. Ellis, Optimal Altitude, Overlap, and Weather Conditions for 549 Computer Vision UAV Estimates of Forest Structure, Remote Sensing, vol.7, p.13895, 2015.

B. Devries, M. Decuyper, J. Verbesselt, A. Zeileis, M. Herold et al., Tracking 552 disturbance-regrowth dynamics in tropical forests using structural change detection 553 and Landsat time series, Remote Sensing of Environment, vol.169, pp.320-334, 2015.

,

F. K. Dwomoh, M. C. Wimberly, M. A. Cochrane, and I. Numata, Forest degradation 556 promotes fire during drought in moist tropical forests of Ghana. Forest Ecology and 557 Management, vol.440, pp.158-168, 2019.

G. W. Frazer, M. A. Wulder, and K. O. Niemann, Simulation and quantification of the fine-559 scale spatial pattern and heterogeneity of forest canopy structure: A lacunarity-based 560 method designed for analysis of continuous canopy heights. Forest Ecology and 561 Management, vol.214, pp.65-90, 2005.

S. Frolking, M. W. Palace, D. B. Clark, J. Q. Chambers, H. H. Shugart et al., 563 Forest disturbance and recovery: A general review in the context of spaceborne 564 remote sensing of impacts on aboveground biomass and canopy structure, Journal, p.565, 2009.

, Geophysical Research, vol.114

B. Gao, NDWI-A normalized difference water index for remote sensing of vegetation 567 liquid water from space, Remote Sensing of Environment, vol.58, pp.257-266, 1996.

, , pp.67-70

J. Ghazoul and R. Chazdon, Degradation and Recovery in Changing Forest 570 Landscapes: A Multiscale Conceptual Framework, Annual Review of Environment 571 and Resources, vol.42, pp.161-188, 2017.

S. Goetz, M. Hansen, R. A. Houghton, W. Walker, N. T. Laporte et al., 573 Measurement and Monitoring for REDD+: The Needs, Current Technological 574 Capabilities, and Future Potential, SSRN Electronic Journal, vol.575, 2014.

J. E. Goldstein, The Afterlives of Degraded Tropical Forests: New Value for 577 Conservation and Development, Environment and Society: Advances in Research, vol.5, pp.124-140, 2014.

O. C. Hamsici and A. M. Martinez, Bayes Optimality in Linear Discriminant Analysis. IEEE 580 Transactions on Pattern Analysis and Machine Intelligence, vol.30, pp.647-657, 2008.

,

A. F. Hasan, F. Laurent, F. Messner, C. Bourgoin, and L. Blanc, Cumulative 583 disturbances to assess forest degradation using spectral unmixing in the north-584 eastern Amazon. Appl Veg Sci avsc, 2019.

M. Herold, R. M. Román-cuesta, D. Mollicone, Y. Hirata, P. Van-laake et al., , p.586

C. Souza, M. Skutsch, V. Avitabile, and K. Macdicken, Options for monitoring 587 and estimating historical carbon emissions from forest degradation in the context of 588 REDD+. Carbon balance and management 6, p.13, 2011.

M. Hirschmugl, H. Gallaun, M. Dees, P. Datta, J. Deutscher et al., Methods for mapping forest disturbance and degradation from optical earth 591 observation data: A review, Current Forestry Reports, vol.3, pp.32-45, 2017.

F. Husson, J. Josse, and J. Pages, Principal component methods -hierarchical 593 clustering -partitional clustering: why would we need to choose for visualizing data, vol.594, p.17, 2010.

D. J. Ketchen and C. L. Shook, The Application Of Cluster Analysis In Strategic 596 Management Research: An Analysis And Critique, Strategic Management Journal, vol.597, pp.441-458, 1996.

L. P. Koh and S. A. Wich, Dawn of Drone Ecology: Low-Cost Autonomous Aerial Vehicles 600 for Conservation, Tropical Conservation Science, vol.5, pp.121-132, 2012.

,

R. Kohavi, A Study of Cross-Validation and Bootstrap for Accuracy Estimation and 603 Model Selection 7, 1995.

M. Kuhn and K. Johnson, Applied predictive modeling, 2013.

F. Laurent, D. Arvor, M. Daugeard, R. Osis, I. Tritsch et al., Le tournant 607 environnemental en Amazonie : ampleur et limites du découplage entre production et 608 déforestation, 2017.

S. Lê, J. Josse, and F. Husson, FactoMineR : An R Package for Multivariate Analysis, 610 Journal of Statistical Software, vol.25, 2008.

S. L. Lewis, D. P. Edwards, and D. Galbraith, Increasing human dominance of tropical 612 forests, Science, vol.349, pp.827-832, 2015.

A. Liaw and M. Wiener, Classification and regression by randomForest, vol.2, pp.18-614, 2002.

M. Longo, M. Keller, M. N. Dos-santos, V. Leitold, E. R. Pinagé et al., , p.616

E. M. Nogueira, M. Batistella, and D. C. Morton, Aboveground biomass variability 617 across intact and degraded forests in the Brazilian Amazon: AMAZON INTACT AND 618 DEGRADED FOREST BIOMASS, Global Biogeochemical Cycles, vol.30, pp.1639-1660, 2016.

Y. Malhi, T. A. Gardner, G. R. Goldsmith, M. R. Silman, and P. Zelazowski, Tropical 621 Forests in the Anthropocene, Annual Review of Environment and Resources, vol.39, pp.125-159, 2014.

Y. Malhi and R. M. Román-cuesta, Analysis of lacunarity and scales of spatial 624 homogeneity in IKONOS images of Amazonian tropical forest canopies, vol.112, pp.2074-2087, 2008.

L. Mazzei, P. Sist, A. Ruschel, F. E. Putz, P. Marco et al., , 2010.

, Above-ground biomass dynamics after reduced-impact logging in the Eastern 628 Amazon, Forest Ecology and Management, vol.259, pp.367-373

,

A. Mercier, J. Betbeder, F. Rumiano, V. Gond, L. Blanc et al., , p.631

R. Poccard-chapuis, J. Baudry, and L. Hubert-moy, Evaluation of Sentinel-1 and 632 2 Time Series for Land Cover Classification of Forest-Agriculture Mosaics in 633 Temperate and Tropical Landscapes 20, 2019.

V. Meyer, S. Saatchi, D. B. Clark, M. Keller, G. Vincent et al., Canopy area of large trees 636 explains aboveground biomass variations across neotropical forest landscapes, 2018.

, Biogeosciences, vol.15, pp.3377-3390

A. L. Mitchell, A. Rosenqvist, and B. Mora, Current remote sensing approaches to 639 monitoring forest degradation in support of countries measurement, reporting and 640 verification (MRV) systems for REDD+. Carbon Balance and Management 12, vol.641, 2017.

D. C. Morton, Y. Le-page, R. Defries, G. J. Collatz, and G. C. Hurtt, Understorey fire 643 frequency and the fate of burned forests in southern Amazonia, Philosophical 644 Transactions of the Royal Society B: Biological Sciences, vol.368, 2013.

D. Panagiotidis, A. Abdollahnejad, P. Surový, and V. Chiteculo, Determining tree height 647 and crown diameter from high-resolution UAV imagery, International Journal of 648 Remote Sensing, vol.38, pp.2392-2410, 2017.

P. Ploton, N. Barbier, P. Couteron, C. M. Antin, N. Ayyappan et al., , p.650

N. Barathan, J. Bastin, G. Chuyong, G. Dauby, and V. Droissart, , p.651

J. Etchegorry, N. G. Kamdem, D. Kenfack, M. Libalah, G. Mofack et al., , p.652

S. Pargal, P. Petronelli, C. Proisy, M. Réjou-méchain, B. Sonké et al., , p.653

D. Thomas, P. Verley, D. Zebaze-dongmo, U. Berger, and R. Pélissier, Toward 654 a general tropical forest biomass prediction model from very high resolution optical 655 satellite images, Remote Sensing of Environment, vol.200, pp.140-153, 2017.

,

P. Ploton, R. Pélissier, C. Proisy, T. Flavenot, N. Barbier et al., , p.658, 2012.

, Assessing aboveground tropical forest biomass using Google Earth canopy images, Ecological Applications, vol.659, pp.993-1003

P. Potapov, M. C. Hansen, L. Laestadius, S. Turubanova, A. Yaroshenko et al., , p.661

W. Smith, I. Zhuravleva, A. Komarova, and S. Minnemeyer, The last 662 frontiers of wilderness: Tracking loss of intact forest landscapes from, Science Advances, vol.3, issue.663, 2000.

F. E. Putz and K. H. Redford, The Importance of Defining 'Forest': Tropical Forest 665 Degradation, Deforestation, Long-term Phase Shifts, and Further Transitions: 666 Importance of Defining 'Forest, Biotropica, vol.42, pp.10-20, 2010.

D. I. Rappaport, D. C. Morton, M. Longo, M. Keller, R. Dubayah et al., Quantifying long-term changes in carbon stocks and forest structure from 670 Amazon forest degradation, Environmental Research Letters, vol.669, 2018.

C. Silva, A. Hudak, L. Vierling, C. Klauberg, M. Garcia et al., , p.673

S. Saatchi, Impacts of Airborne Lidar Pulse Density on Estimating Biomass 674 Stocks and Changes in a Selectively Logged Tropical Forest. Remote Sensing 9, vol.675, p.1068, 2017.

S. S. Silva, . Da, P. M. Fearnside, P. M. Graça, A. De et al., Dynamics of forest fires in the southwestern Amazon. Forest Ecology and 678 Management, vol.677, pp.312-322, 2018.

C. Silva-junior, L. Aragão, M. Fonseca, C. Almeida, L. Vedovato et al., , p.680, 2018.

, Deforestation-Induced Fragmentation Increases Forest Fire Occurrence in Central 681 Brazilian Amazonia, vol.9, p.305

M. Singh, Y. Malhi, and S. Bhagwat, Biomass estimation of mixed forest landscape using 683 a Fourier transform texture-based approach on very-high-resolution optical satellite 684 imagery, International Journal of Remote Sensing, vol.35, pp.3331-3349, 2014.

,

J. Souza, C. Siqueira, J. Sales, M. Fonseca, A. Ribeiro et al., , p.687

C. Barber, D. Roberts, and J. Barlow, Ten-Year Landsat Classification of 688 Deforestation and Forest Degradation in the Brazilian Amazon, Remote Sensing, vol.5, pp.5493-5513, 2013.

I. Thompson, B. Mackey, S. Mcnulty, and A. Mosseler, Forest resilience, biodiversity, and climate change: a 692 synthesis of the biodiversity, resilience, stabiblity relationship in forest ecosystems, 2009.

I. Tritsch, P. Sist, I. Narvaes, L. Mazzei, L. Blanc et al., Multiple Patterns of Forest Disturbance and Logging Shape Forest 695 Landscapes in Paragominas, Brazil. Forests, vol.694, 2016.

W. N. Venables and B. D. Ripley, Modern Applied Statistics with S 504, 2002.

M. J. Westoby, J. Brasington, N. F. Glasser, M. J. Hambrey, and J. M. Reynolds, Structure-from-Motion' photogrammetry: A low-cost, effective tool for geoscience 699 applications, Geomorphology, vol.698, pp.300-314, 2012.

,

J. Zhang, J. Hu, J. Lian, Z. Fan, X. Ouyang et al., Seeing the forest from drones: 702 Testing the potential of lightweight drones as a tool for long-term forest monitoring, 2016.

, Biological Conservation, vol.198, p.705