Restricted accessResearch articleFirst published online 2017-6
Optimizing spaceborne LiDAR and very high resolution optical sensor parameters for biomass estimation at ICESat/GLAS footprint level using regression algorithms
Forests sequester large quantity of carbon in their woody biomass and hence accurate estimation of forest biomass is extremely crucial. The present study aims at combining information from spaceborne LiDAR (ICESat/GLAS) and high resolution optical data to estimate forest biomass. Estimation of aboveground biomass (AGB) at ICESat/GLAS footprint level was done by integrating data from multiple sensors using two regression algorithms, viz. random forest (RF) and support vector machine (SVM). The study used forest height and canopy return ratio (rCanopy) for determination of effective size of ICESat/GLAS footprints for field data collection. The forest height was predicted with root mean square error (RMSE) of 1.35 m. The study showed that six most important parameters derived from LiDAR, and passive optical data were able to explain 78.7% (adjusted) variation in the observed AGB with an RMSE of 13.9 Mg ha–1. It was also observed that 15 most important parameters were able to explain 83% (adjusted) variation in the observed AGB. It was found that SVM regression algorithm explained 88.7% of variation in AGB with an RMSE of 13.6 Mg ha–1 on the combined datasets while RF regression algorithm explained 83.5% of variation in AGB with an RMSE of 20.57 Mg ha–1. The study demonstrated that RF regression algorithm performs equally well on datasets irrespective of the correlation of underlying variables with the predicted variable whereas SVM regression was found to perform well on those datasets which had a subset of underlying variables that are correlated with the predicted variable. The study highlighted that sensor integration approach is more accurate than single sensor approach in predicting the AGB.
AbdalatiWZwallyHJBindschadlerR. (2010) The ICESat-2 laser altimetry mission. Proceedings of the IEEE98(5): 735–751.
2.
AbshireJBSunXLRirisH. (2005) Geoscience Laser Altimeter System (GLAS) on the ICESat mission: on-orbit measurement performance. Geophysical Research Letters32: L21S02.
3.
AikenLSWestSGPittsSC (2003) Multiple linear regression. Handbook of Psychology19: 481–507.
4.
Anonymous (2010) Working Plan of Kalsi Soil Conservation Forest Division, Kalsi Shiwalik Circle (2009–10 to 2018–19). Dehradun: Government of Uttarakhand.
5.
ArmstonJDisneyMLewisP. (2013) Direct retrieval of canopy gap probability using airborne waveform LiDAR. Remote Sensing of Environment134: 24–38.
6.
ArunKLangmeadCJ (2006) Structure based chemical shift prediction using Random Forest non-linear regression. ABPC: 317–326.
7.
BacciniAGSJGoetzSJWalkerWS. (2012) Estimated carbon dioxide emissions from tropical deforestation improved by carbon-density maps. Nature Climate Change2(3): 182–185.
8.
BreimanL (2001) Random forests. Machine Learning45(1): 5–32.
9.
CeamanosXWaskeBBenediktssonJA. (2010) A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data. International Journal of Image and Data Fusion1(4): 293–307.
10.
ChampionHGSethSK (1968) A Revised Survey of the Forest Types of India. New Delhi: Manager of Publications, Government of India.
11.
ChenXDisneyMLewisP. (2014) Sensitivity of direct canopy gap fraction retrieval from airborne waveform LiDAR to topography and survey characteristics. Remote Sensing of Environment143: 15–25.
12.
DobsonMCUlabyFTLeToanT. (1992) Dependence of radar backscatter on coniferous forest biomass. IEEE Transactions on Geoscience and Remote Sensing30(2): 412–415.
13.
DubayahRGoetzSJBlairJB. (2014) The global ecosystem dynamics investigation. AGU Fall Meeting Abstracts1: 7.
14.
DuongHV (2010) Processing and Application of ICESat Large Footprint Full Waveform Laser Range Data. PhD Thesis, Technische Universiteit Delft, the Netherlands.
15.
EckertS (2012) Improved forest biomass and carbon estimations using texture measures from WorldView-2 satellite data. Remote Sensing4(4): 810–829.
16.
FatoyinboTESimardM (2013) Height and biomass of mangroves in Africa from ICESat/GLAS and SRTM. International Journal of Remote Sensing34(2): 668–681.
17.
FRI (2002) Indian Woods: Their Identification, Properties and Uses. Vols I–VI. Rev ed. Dehradun, India: Forest Research Institute, Indian Council of Forestry Research and Education, Ministry of Environment and Forests, Government of India.
18.
FSI (1996) Volume Equations for Forests of India, Nepal and Bhutan. Dehradun, India: Forest Survey of India, Ministry of Environment and Forests, Government of India.
19.
GhoshSNandySPatraS. (2016) Land cover classification using ICESat/GLAS Full waveform data. Journal of the Indian Society of Remote Sensing. Epub ahead of print 20 June 2016. DOI: 10.1007/s12524-016-0602-5.
20.
GibbsHKBrownSNilesJO. (2007) Monitoring and estimating tropical forest carbon stocks: making REDD a reality. Environmental Research Letters2(4): 045023.
21.
GleasonCJImJ (2012) Forest biomass estimation from airborne LiDAR data using machine learning approaches. Remote Sensing of Environment125: 80–91.
22.
GoetzSJDubayahRO (2011) Advances in remote sensing technology and implications for measuring and monitoring forest carbon stocks and change. Carbon Management2(3): 231–244.
23.
GoetzSJBacciniALaporteNT. (2009) Mapping and monitoring carbon stocks with satellite observations: a comparison of methods. Carbon Balance and Management4(1): 2.
24.
GuoZChiHSunG. (2010) Estimating forest aboveground biomass using HJ-1 Satellite CCD and ICESat GLAS waveform data. Science China Earth Sciences53(1): 16–25.
25.
HallFGBergenKBlairJB. (2011) Characterizing 3D vegetation structure from space: mission requirements. Remote Sensing of Environment115(11): 2753–2775.
26.
HancockS.LewisPFosterM. (2012) Measuring forests with dual wavelength LiDAR: a simulation study over topography. Agricultural and Forest Meteorology161: 123–133.
27.
HardingDJCarabajalCC (2005) ICESat waveform measurements of within-footprint topographic relief and vegetation vertical structure. Geophysical Research Letters32: L21S10.
28.
HaripriyaGS (2000) Estimates of biomass in Indian forests. Biomass and Bioenergy19: 245–258.
29.
HayashiMSaigusaNOgumaH. (2013) Forest canopy height estimation using ICESat/GLAS data and error factor analysis in Hokkaido, Japan. ISPRS Journal of Photogrammetry and Remote Sensing81: 12–18.
30.
HayashiMSaigusaNYamagataY. (2015) Regional forest biomass estimation using ICESat/GLAS spaceborne LiDAR over Borneo. Carbon Management6(1–2): 19–33.
31.
HeyojooBPNandyS (2014) Estimation of above-ground phytomass and carbon in tree resources outside the forest (TROF): a geo-spatial approach. Banko Janakari24(1): 34–40.
32.
HoughtonRA (2007) Balancing the global carbon budget. Annual Review of Earth and Planetary Sciences35: 313–347.
33.
HoughtonRAHallFGoetzSJ (2009) Importance of biomass in the global carbon cycle. Journal of Geophysical Research114: G00E03.
34.
HueteADidanKMiuraT. (2002) Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment83(1–2): 195–213.
35.
HydePDubayahRWalkerW. (2006) Mapping forest structure for wildlife habitat analysis using multi-sensor (LiDAR, SAR/InSAR, ETM+, Quickbird) synergy. Remote Sensing of Environment102(1–2): 63–73.
36.
IqbalIADashJUllahS. (2013) A novel approach to estimate canopy height using ICESat/GLAS data: a case study in the New Forest National Park, UK. International Journal of Applied Earth Observation and Geoinformation23: 109–118.
37.
JordanCF (1969) Derivation of leaf area index from quality of light on the floor. Ecology50: 663–666.
38.
KellndorferJMWalkerWSLaPointE. (2010) Statistical fusion of LiDAR, InSAR and optical remote sensing data for forest stand height characterization: a regional-scale method based on LVIS, SRTM, Landsat ETM+ and ancillary data sets. Journal of Geophysical Research: Biogeosciences115(G2).
39.
KochB (2010) Status and future of laser scanning, synthetic aperture radar and hyperspectral remote sensing for forest biomass assessment. ISPRS Journal of Photogrammetry and Remote Sensing65: 581–590.
40.
KushwahaSPSNandySGuptaM (2014) Growing stock and woody biomass assessment in Asola-Bhatti Wildlife Sanctuary, Delhi, India. Environmental Monitoring and Assessment186(9): 5911–5920.
41.
LealRRButlerPLaneP. (1997) Data fusion and artificial neural networks for biomass estimation. IEE Proceedings-Science, Measurement and Technology144(2): 69–72.
42.
LefskyMA (2010) A global forest canopy height map from the Moderate Resolution Imaging Spectroradiometer and the Geoscience Laser Altimeter System. Geophysical Research Letters37(15): L15401.
43.
LefskyMACohenWBAckerSA. (1999) LiDAR remote sensing of the canopy structure and biophysical properties of Douglas-fir western hemlock forests. Remote sensing of environment70(3): 339–361.
44.
LefskyMACohenWBHardingDJ. (2002) Lidar remote sensing of above-ground biomass in three biomes. Global Ecology and Biogeography11: 393–399.
45.
LefskyMAHardingDJKellerM. (2005) Estimates of forest canopy height and aboveground biomass using ICESat. Geophysical Research Letters32: L22S02.
46.
LefskyMAKellerMPangY. (2007) Revised method for forest canopy height estimation from Geoscience Laser Altimeter System waveforms. Journal of Applied Remote Sensing1(1): 013537.
47.
Le ToanTQueganSDavidsonMWJ. (2011) The BIOMASS mission: mapping global forest biomass to better understand the terrestrial carbon cycle. Remote Sensing of Environment115(11): 2850–2860.
48.
LosSORosetteJABKljunN. (2012) Vegetation height and cover fraction between 60°S and 60°N from ICESat GLAS data. Geoscientific Model Development5(2): 413–432.
49.
LuoSWangCLiG. (2013) Retrieving leaf area index using ICESat/GLAS full-waveform data. Remote Sensing Letters4(8): 745–753.
50.
MahoneyCKljunNLosSO. (2014) Slope estimation from ICESat/GLAS. Remote Sensing6(10): 10051–10069.
51.
Main-KnornMCohenWBKennedyRE. (2013) Monitoring coniferous forest biomass change using a Landsat trajectory-based approach. Remote Sensing of Environment139: 277–290.
52.
MannaSNandySChandaA. (2014) Estimating aboveground biomass in Avicennia marina plantation in Indian Sundarbans using high-resolution satellite data. Journal of Applied Remote Sensing8(1): 083638.
53.
MeansJEAckerSAHardingDJ. (1999) Use of large-footprint scanning airborne LiDAR to estimate forest stand characteristics in the western cascades of Oregon. Remote Sensing of Environment67(3): 298–308.
54.
MitchardETASaatchiSSWhiteLJT. (2012) Mapping tropical forest biomass with radar and spaceborne LiDAR in Lopé National Park, Gabon: overcoming problems of high biomass and persistent cloud. Biogeosciences9: 179–191.
55.
MontesanoPMCookBDSunG. (2013) Achieving accuracy requirements for forest biomass mapping: a spaceborne data fusion method for estimating forest biomass and LiDAR sampling error. Remote Sensing of Environment130: 153–170.
56.
MuukkonenPHeiskanenJ (2007) Biomass estimation over a large area based on standwise forest inventory data and ASTER and MODIS satellite data: a possibility to verify carbon inventories. Remote Sensing of Environment107(4): 617–624.
57.
PeregonAYamagataY (2013) The use of ALOS/PALSAR backscatter to estimate above-ground forest biomass: a case study in Western Siberia. Remote Sensing of Environment137: 139–146
58.
PopescuSC (2007) Estimating biomass of individual pine trees using airborne LiDAR. Biomass and Bioenergy31(9): 646–655.
59.
PopescuSCZhaoKNeuenschwanderA. (2011) Satellite LiDAR vs small footprint airborne LiDAR: comparing the accuracy of aboveground biomass estimates and forest structure metrics at footprint level. Remote Sensing of Environment115(11): 2786–2797.
60.
RondeauxGStevenMBaretF (1996) Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment55(2): 95–107.
61.
RosetteJABNorthPRJSuarezJC (2008) Vegetation height estimates for a mixed temperate forest using satellite laser altimetry. International Journal of Remote Sensing29(5): 1475–1493.
62.
RosetteJABNorthPRJSuarezJC. (2010) Uncertainty within satellite LiDAR estimations of vegetation and topography. International Journal of Remote Sensing31(5): 1325–1342.
63.
RouseJWHaasRHDeeringDW. (1974) Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. NASA/GSFC Type III, Final Report. Greenbelt, MD: NASA.
64.
SaatchiSSNancyLHSandraB. (2011) Benchmark map of forest carbon stocks in tropical regions across three continents. Proceedings of the National Academy of Sciences108(24): 9899–9904.
65.
SchutzBEZwallyHJShumanCA. (2005) Overview of the ICESat mission. Geophysical Research Letters32: L21S01.
66.
SelkowitzDJGreenGPetersonB. (2012) A multi-sensor LiDAR, multi-spectral and multi-angular approach for mapping canopy height in boreal forest regions. Remote Sensing of Environment121: 458–471.
67.
ShugartHHSaatchiSHallFG (2010) Importance of structure and its measurement in quantifying function of forest ecosystems. Journal of Geophysical Research115 (G2): G00E13.
68.
SimardMPintoNFisherJB. (2011) Mapping forest canopy height globally with spaceborne LiDAR. Journal of Geophysical Research116 (G4): G04021.
69.
SolbergSAstrupRBreidenbachJ. (2013) Monitoring spruce volume and biomass with InSAR data from TanDEM-X. Remote Sensing of Environment139: 60–67.
70.
SunGRansonKMasekJ. (2007) Predicting tree height and biomass from GLAS data. In: 10th international symposium on physical measurements and signatures in remote sensing, Davos, Switzerland, 12–14 March 2007.
71.
SwatantranADubayahRRobertsD. (2011) Mapping biomass and stress in the Sierra Nevada using LiDAR and hyperspectral data fusion. Remote Sensing of Environment115(11): 2917–2930.
72.
VapnikV (1979) Estimation of Dependences Based on Empirical Data. Moscow: Nauka (in Russian) (English translation: New York: Springer Verlag, 1982).
73.
WangXChengXGongP. (2011) Earth science applications of ICESat/GLAS: a review. International Journal of Remote Sensing32(23): 8837–8864.
74.
WaringRHWayJHuntERJ. (1995) Imaging radar for ecosystem studies. BioScience45: 715–723.
75.
WaskeBvan der LindenSBenediktssonJA. (2010) Sensitivity of support vector machines to random feature selection in classification of hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing48(7): 2880–2889.
76.
XingYGierADZhangJ. (2010) An improved method for estimating forest canopy height using ICESat-GLAS full waveform data over sloping terrain: a case study in Changbai mountains, China. International Journal of Applied Earth Observation and Geoinformation12: 385–392.
77.
YadavBKVNandyS (2015) Mapping aboveground woody biomass using forest inventory, remote sensing and geostatistical techniques. Environmental Monitoring and Assessment187(5): 1–12.
78.
YangWNi-MeisterWLeeS (2011) Assessment of the impacts of surface topography, off-nadir pointing and vegetation structure on vegetation LiDAR waveforms using an extended geometric optical and radiative transfer model. Remote Sensing of Environment115(11): 2810–2822.
79.
YuYSaatchiSHeathLS. (2010) Regional distribution of forest height and biomass from multi-sensor data fusion. Journal of Geophysical Research: Biogeosciences115(G2).
80.
ZolkosSGGoetzSJDubayahR (2013) A meta-analysis of terrestrial above ground biomass estimation using LiDAR remote sensing. Remote Sensing of Environment128: 289–298.
81.
ZwallyHJSchutzBAbdalatiW. (2002) ICESat’s laser measurements of polar ice, atmosphere, ocean, and land. Journal of Geodynamics34(3–4): 405–445.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
