Stacked Sparse Autoencoder Modeling Using the Synergy of Airborne LiDAR and Satellite Optical and SAR Data to Map Forest Above-Ground Biomass

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Volumn 10, Issue 12, 2017, Pages 5569-5582

  Shao, Zhenfeng ^a   Zhang, Linjing ^a   Wang, Lei ^a  

^a WUHAN UNIVERSITY   (China)

Author keywords

Biomass; deep learning (DL); Landsat 8; light detection and ranging (LiDAR); Sentinel 1A; stacked sparse autoencoder network (SSAE)

Indexed keywords

BACKPROPAGATION; BIOMASS; CARBON; DATA INTEGRATION; DECISION TREES; DEEP LEARNING; FORECASTING; FORESTRY; IMAGING TECHNIQUES; LEARNING SYSTEMS; MAPPING; MEAN SQUARE ERROR; NEAREST NEIGHBOR SEARCH; NEURAL NETWORKS; OPTICAL IMAGE STORAGE; RADAR IMAGING; REMOTE SENSING; SATELLITES; SPACE-BASED RADAR; SYNTHETIC APERTURE RADAR; TRACKING RADAR;

AUTO ENCODERS; BIOMEDICAL OPTICAL IMAGING; LANDSAT; LIGHT DETECTION AND RANGING; OPTICAL IMAGING; OPTICAL SATURATION; SENTINEL-1;

OPTICAL RADAR;

ABOVEGROUND BIOMASS; FOREST INVENTORY; LIDAR; MACHINE LEARNING; MAPPING; MODELING; SATELLITE IMAGERY; SENTINEL; SYNTHETIC APERTURE RADAR;

EID: 85030755958     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2017.2748341     Document Type: Article

References (72)

1. R. A. Houghton, F. Hall, and S. J. Goetz, "Importance of biomass in the global carbon cycle, " J. Geophys. Res. Biogeosci., vol. 114, pp. 558-558, 2009.
2. O. W. Tsui, N. C. Coops, M. A. Wulder, and P. L. Marshall, "Integrating airborne LiDARand space-borne radar via multivariate Kriging to estimate above-ground biomass, " Remote Sens. Environ., vol. 139, pp. 340-352, 2013.
3. L. Korhonen, J. Heiskanen, and I. Korpela, "Modelling Lidar-derived boreal forest canopy cover with SPOT 4 HRVIR data, " Int. J. Remote Sens., vol. 34, pp. 8172-8181, 2013.
4. T. J. Hawbaker, N. S. Keuler, A. A. Lesak, G. Terje, C. Kirk, and V. C. Radeloff, "Improved estimates of forest vegetation structure and biomass with a LiDAR-optimized sampling design, " J. Geophys. Res. Atmos., vol. 114, pp. 363-369, 2009.
5. H. S. J. Zald et al., "Influence of Lidar, Landsat imagery, disturbance history, plot location accuracy, and plot size on accuracy of imputation maps of forest composition and structure, " Remote Sens. Environ., vol. 143, pp. 26-38, 2014.
6. M. J. Falkowski, A. T. Hudak, N. L. Crookston, P. E. Gessler, E. H. Uebler, and A. M. S. Smith, "Landscape-scale parameterization of a tree-level forest growthmodel: a k-nearest neighbor imputation approach incorporating LiDAR data, " Can. J. Forest Res., vol. 40, pp. 184-199, 2010.
7. A. T. Hudak, N. L. Crookston, J. S. Evans, D. E. Hall, and M. J. Falkowski, "Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDARdata, " Remote Sens. Environ., vol. 112, pp. 2232-2245, 2008.
8. L. Korhonen, I. Korpela, J. Heiskanen, and M. Maltamo, "Airborne discrete-return LIDAR data in the estimation of vertical canopy cover, angular canopy closure and leaf area index, " Remote Sens. Environ., vol. 115, pp. 1065-1080, 2011.
9. D. Gatziolis, "Comparison of LiDAR-and photointerpretation-based estimates of canopy cover, " U. S. Forest Service, Washington, DC, USA, 2012.
10. X. Tian et al., "Estimation of forest above-ground biomass using multiparameter remote sensing data over a cold and arid area, " Int. J. Appl. Earth Obs. Geoinf., vol. 14, pp. 160-168, 2012.
11. D. Stojanova, P. Panov, V. Gjorgjioski, A. Kobler, and S. D?zeroski, "Estimating vegetation height and canopy cover from remotely sensed data with machine learning, " Ecolgical Informat., vol. 5, pp. 256-266, 2010.
12. W. Li et al., "Geostatistical modeling using LiDAR-derived prior knowledge with SPOT-6 data to estimate temperate forest canopy cover and above-ground biomass via stratified random sampling, " Int. J. Appl. Earth Obs. Geoinf., vol. 41, pp. 88-98, 2015.
13. H. S. J. Zald et al., "Integrating Landsat pixel composites and change metrics with Lidar plots to predictively map forest structure and aboveground biomass in Saskatchewan, Canada, " Remote Sens. Environ., vol. 176, pp. 188-201, 2016.
14. O. S. Ahmed, S. E. Franklin, M. A. Wulder, and J. C. White, "Characterizing stand-level forest canopy cover and height using Landsat time series, samples of airborne LiDAR, and the random forest algorithm, " ISPRS J. Photogramm. Remote Sens., vol. 101, pp. 89-101, 2015.
15. S. Labrecque, R. A. Fournier, J. E. Luther, and D. Piercey, "A comparison of four methods to map biomass from Landsat-TM and inventory data in western Newfoundland, " Forest Ecology Manage., vol. 226, pp. 129-144, 2006.
16. L. I. Duncanson, K. O. Niemann, and M. A. Wulder, "Integration of GLAS and Landsat TM data for aboveground biomass estimation, " Can. J. Remote Sens., vol. 36, pp. 129-141, 2010.
17. Z. Shao and L. Zhang, "Estimating forest aboveground biomass by combining optical and SAR data: A case study in Genhe, Inner Mongolia, China, " Sensors, vol. 16, 2016, Art. no. 834.
18. S. Gao, Z. Niu, N. Huang, and X. Hou, "Estimating the Leaf Area Index, height and biomass of maize using HJ-1 and RADARSAT-2, " Int. J. Appl. Earth Obs. Geoinf., vol. 24, pp. 1-8, 2013.
19. Y. Inoue et al., "Season-long daily measurements of multifrequency (Ka, Ku, X, C, and L) and full-polarization backscatter signatures over paddy rice field and their relationship with biological variables, " Remote Sens. Environ., vol. 81, pp. 194-204, 2002.
20. E. T. A. Mitchard et al., "Measuring biomass changes due to woody encroachment and deforestation/degradation in a forest-Savanna boundary region of central Africa using multi-temporal L-band radar backscatter, " Remote Sens. Environ., vol. 115, pp. 2861-2873, 2011.
21. J. M. B. Carreiras, M. J. Vasconcelos, and R. M. Lucas, "Understanding the relationship between aboveground biomass and ALOS PALSAR data in the forests of Guinea-Bissau (West Africa), " Remote Sens. Environ., vol. 121, pp. 426-442, 2012.
22. T. R. K. Chand and K. V. S. Badarinath, "Analysis of ENVISAT ASAR data for forest parameter retrieval and forest type classification-A case study over deciduous forests of central India, " Int. J. Remote Sens., vol. 28, pp. 4985-4999, 2007.
23. M. Cougo et al., "Radarsat-2 backscattering for the modeling of biophysical parameters of regenerating mangrove forests, " Remote Sens., vol. 7, pp. 17097-17112, 2015.
24. Q. He et al., "Forest stand biomass estimation using ALOS PALSAR data based on LiDAR-derived prior knowledge in the Qilian Mountain, Western China, " Int. J. Remote Sens., vol. 33, pp. 710-729, 2012.
25. T. Hame, Y. Rauste, O. Antropov, and H. A. Ahola, "Improved mapping of tropical forests with optical and SAR imagery, Part II: Above ground biomass estimation, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 6, no. 1, pp. 92-101, Feb. 2013.
26. S. Attarchi and R. Gloaguen, "Improving the estimation of above ground biomass using dual polarimetric PALSAR and ETM+ data in the Hyrcanian mountain forest (Iran), " Remote Sens., vol. 6, pp. 3693-3715, 2014.
27. M. A. Wulder and D. Seemann, "Forest inventory height update through the integration of Lidar data with segmented Landsat imagery, " Can. J. Remote Sens., vol. 29, pp. 536-543, 2014.
28. T. Hilker, M. A. Wulder, and N. C. Coops, "Update of forest inventory data with Lidar and high spatial resolution satellite imagery, " Can. J. Remote Sens., vol. 34, pp. 5-12, 2008.
29. G. Chen and G. J. Hay, "A support vector regression approach to estimate forest biophysical parameters at the object level using airborne Lidar transects and Quickbird data, " Photogramm. Eng. Remote Sens., vol. 77, pp. 733-741, 2011.
30. X. Tian et al., "Estimating Montane forest above-ground biomass in the upper reaches of the Heihe River Basin using Landsat-TM data, " Int. J. Remote Sens., vol. 35, pp. 7339-7362, 2014.
31. F. E. Fassnacht et al., "Importance of sample size, data type and prediction method for remote sensing-based estimations of aboveground forest biomass, " Remote Sens. Environ., vol. 154, pp. 102-114, 2014.
32. B. Chen et al., "Spatio-temporal prediction of leaf area index of rubber plantation using HJ-1A/1B CCD images and recurrent neural network, " ISPRS J. Photogramm. Remote Sens., vol. 102, pp. 148-160, 2015.
33. H. Latifi and B. Koch, "Evaluation of most similar neighbour and random forest methods for imputing forest inventory variables using data from target and auxiliary stands, " Int. J. Remote Sens., vol. 33, pp. 6668-6694, 2012.
34. J. Verrelst et al., "Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and-3, " Remote Sens. Environ., vol. 118, pp. 127-139, 2012.
35. D. Tuia, J. Verrelst, L. Alonso, and F. Perez-Cruz, "Multioutput support vector regression for remote sensing biophysical parameter estimation, " IEEE Geosci. Remote Sens. Lett., vol. 8, no. 4, pp. 804-808, Jul. 2011.
36. S. S. Panda, D. P. Ames, and S. Panigrahi, "Application of vegetation indices for agricultural crop yield prediction using neural network techniques, " Remote Sens., vol. 2, pp. 673-696, 2010.
37. K. T. Chang, L. S. Liang, F. G. Yiu, and R. Y. Wang, "Estimation of carbon sequestration by using vegetation indices, " in Proc. Geosci. Remote Sens. Symp., 2012, pp. 6376-6379.
38. H. Latifi, A. Nothdurft, and B. Koch, "Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: application ofmultiple optical/LiDAR-derived predictors, " Forestry, vol. 83, pp. 395-407, 2010.
39. Y. Yu, J. Li, H. Guan, and C. Wang, "Automated detection of threedimensional cars in mobile laser scanning point clouds using DBMHough-forests, " IEEE Trans. Geosci. Remote Sens., vol. 57, no. 7, pp. 4130-4142, Jul. 2016.
40. Y. Chen, Z. Lin, X. Zhao, G. Wang, and Y. Gu, "Deep learning-based classification of hyperspectral data, " IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 7, no. 6, pp. 2094-2107, Jun. 2014.
41. L. Zhang, Z. Shi, and J. Wu, "A hierarchical oil tank detector with deep surrounding features for high-resolution optical satellite imagery, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 8, no. 10, pp. 4895-4909, Oct. 2015.
42. H. Liang and Q. Li, "Hyperspectral imagery classification using sparse representations of convolutional neural network features, " Remote Sens., vol. 8, 2016, Art. no. 99.
43. Y. Yu, J. Li, H. Guan, F. Jia, and C. Wang, "Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 8, no. 2, pp. 709-726, Feb. 2015.
44. L. Zhang, W. Ma, and D. Zhang, "Stacked sparse autoencoder in PolSAR Data classification using local spatial information, " IEEE Geosci. Remote Sens. Lett., vol. 13, no. 9, pp. 1359-1363, Sep. 2016.
45. K. K. Singh, G. Chen, J. B. Mccarter, and R. K. Meentemeyer, "Effects of LiDAR point density and landscape context on estimates of urban forest biomass, " ISPRS J. Photogramm. Remote Sens., vol. 101, pp. 310-322, 2015.
46. C. Godwin, G. Chen, and K. K. Singh, "The impact of urban residential development patterns on forest carbon density: An integration of Li-DAR, aerial photography and field mensuration, " Landscape Urban Plan., vol. 136, pp. 97-109, 2015.
47. J. Fang, G. Liu, and S. Xu, "Biomass and net production of forest vegetation in China, " Acta Ecologica Sinica, vol. 16, pp. 497-508, 1996.
48. J. Hyyppa et al., "Advances in forest inventory using airborne laser scanning, " Remote Sens., vol. 4, pp. 1190-1207, 2012.
49. M. A. Wulder et al., "Lidar sampling for large-area forest characterization: A review, " Remote Sens. Environ., vol. 121, pp. 196-209, 2012.
50. D. Lu, "The potential and challenge of remote sensing-based biomass estimation, " Int. J. Remote Sens., vol. 27, pp. 1297-1328, 2006.
51. C. J. Gleason and J. H. Im, "A review of remote sensing of forest biomass and biofuel: Options for small-area applications, " Geosci. Remote Sens., vol. 48, pp. 141-170, 2011.
52. T. Dube, O. Mutanga, T. Dube, and O. Mutanga, "Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa, " ISPRS J. Photogramm. Remote Sens., vol. 101, pp. 36-46, 2015.
53. T. Dube andO. Mutanga, "Investigating the robustness of the newLandsat-8 operational land imager derived texture metrics in estimating plantation forest aboveground biomass in resource constrained areas, " ISPRS J. Photogramm. Remote Sens., vol. 108, pp. 12-32, 2015.
54. H. El-Askary, S. H. A. El-Mawla, J. Li, M. M. El-Hattab, and M. El-Raey, "Change detection of coral reef habitat using Landsat-5 TM, Landsat 7 ETM+ and Landsat 8 OLI data in the Red Sea (Hurghada, Egypt), " Int. J. Remote Sens., vol. 35, pp. 2327-2346, 2014.
55. N. Pahlevan and J. R. Schott, "Leveraging EO-1 to evaluate capability of new generation of Landsat sensors for coastal/inland water studies, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 6, no. 2, pp. 360-374, Apr. 2013.
56. G. Chirici, R. E. Mcroberts, L. Fattorini, M. Mura, and M. Marchetti, "Comparing echo-based and canopy height model-based metrics for enhancing estimation of forest aboveground biomass in a model-assisted framework, " Remote Sens. Environ., vol. 174, pp. 1-9, 2016.
57. S. P. Healey, Z. Yang, W. B. Cohen, and D. J. Pierce, "Application of two regression-based methods to estimate the effects of partial harvest on forest structure using Landsat data, " Remote Sens. Environ., vol. 101, pp. 115-126, 2006.
58. W. B. Cohen, T. A. Spies, R. J. Alig, D. R. Oetter, T. K. Maiersperger, and M. Fiorella, "Characterizing 23 Years (1972-95) of stand replacement disturbance inwesternOregon forestswith Landsat imagery, " Ecosystems, vol. 5, pp. 122-137, 2002.
59. M. A. Wulder, J. C. White, B. Bentz, M. F. Alvarez, and N. C. Coops, "Estimating the probability of mountain pine beetle red-attack damage, " Remote Sens. Environ., vol. 101, pp. 150-166, 2006.
60. K. Kelsey and J. Neff, "Estimates of aboveground biomass from texture analysis of Landsat imagery, " Remote Sens., vol. 6, pp. 6407-6422, 2014.
61. Y. Su et al., "Spatial distribution of forest aboveground biomass in China: Estimation through combination of spaceborne Lidar, optical imagery, and forest inventory data, " Remote Sens. Environ., vol. 173, pp. 187-199, 2016.
62. M. Li, J. Im, L. J. Quackenbush, and T. Liu, "Forest biomass and carbon stock quantification using airborne LiDAR data: A case study over Huntington wildlife forest in the Adirondack park, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 7, no. 7, pp. 3143-3156, Jul. 2014.
63. A. T. Hudak, M. A. Lefsky, W. B. Cohen, and M. Berterretche, "Integration of Lidar and Landsat ETM+ data for estimating and mapping forest canopy height, " Remote Sens. Environ., vol. 82, pp. 397-416, 2002.
64. C. R. Team, "Team RDC. R: A language and environment for statistical computing. R Foundation for statistical computing: Vienna, Austria, " Computing, vol. 1, pp. 12-21, 2013.
65. O. Bousquet, U. V. Luxburg, and G. Rätsch, "Advanced Lectures on Machine Learning (Lecture Notes in Computer Science), vol. 3176. New York, NY, USA: Springer, 2004.
66. T. Kattenborn, J. Maack, F. Faßnacht, F. Enßle, J. Ermert, and B. Koch, "Mapping forest biomass from space-Fusion of hyperspectral EO1-hyperion data and Tandem-X and WorldView-2 canopy height models, " Int. J. Appl. Earth Obs. Geoinf., vol. 35, pp. 359-367, 2015.
67. L. Breiman, "Random forests, " Mach. Learn., vol. 45, pp. 5-32, 2001.
68. P. Krahwinkler and J. Rossman, "Using decision tree based multiclass support vector machines for forest mapping, " in Proc. IEEE Int. Geosci. Remote Sens. Symp., Vancouver, Canada, 2011, pp. 949-952.
69. S. Deng, M. Katoh, Q. Guan, N. Yin, and M. Li, "Estimating forest aboveground biomass by combining ALOS PALSAR and WorldView-2 data: A case study at Purple Mountain National Park, Nanjing, China, " Remote Sens., vol. 6, pp. 7878-7910, 2014.
70. T. M. Basuki, A. Skidmore, Y. Hussin, and I. Van Duren, "Estimating tropical forest biomass more accurately by integrating ALOS PALSAR and Landsat-7 ETM+ data, " Int. J. Remote Sens., vol. 34, pp. 4871-4888, 2013.
71. K. K. Singh, G. Chen, J. B. Vogler, and R. K. Meentemeyer, "When big data are too much: Effects of LiDAR Returns and point density on estimation of forest biomass, " IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens., vol. 9, no. 7, pp. 3210-3218, Jul. 2016.
72. E. Næsset, "Predicting forest stand characteristics with airborne scanning laser using a practical two-stage procedure and field data, " Remote Sens. Environ., vol. 80, pp. 88-99, 2002.