Estimating Above-Ground Biomass in Sub-Tropical Buffer Zone Community Forests, Nepal, Using Sentinel 2 Data

Accurate assessment of above-ground biomass (AGB) is important for the sustainable management of forests, especially buffer zone (areas within the protected area, where restrictions are placed upon resource use and special measure are undertaken to intensify the conservation value of protected area) areas with a high dependence on forest products. This study presents a new AGB estimation method and demonstrates the potential of medium-resolution Sentinel-2 Multi-Spectral Instrument (MSI) data application as an alternative to hyperspectral data in inaccessible regions. Sentinel-2 performance was evaluated for a buffer zone community forest in Parsa National Park, Nepal, using field-based AGB as a dependent variable, as well as spectral band values and spectral-derived vegetation indices as independent variables in the Random Forest (RF) algorithm. The 10-fold cross-validation was used to evaluate model effectiveness. The effect of the input variable number on AGB prediction was also investigated. The model using all extracted spectral information plus all derived spectral vegetation indices provided better AGB estimates (R2 = 0.81 and RMSE = 25.57 t ha−1). Incorporating the optimal subset of key variables did not improve model variance but reduced the error slightly. This result is explained by the technically-advanced nature of Sentinel-2, which includes fine spatial resolution (10, 20 m) and strategically-positioned bands (red-edge), conducted in flat topography with an advanced machine learning algorithm. However, assessing its transferability to other forest types with varying altitude would enable future performance and interpretability assessments of Sentinel-2.

[1]  M. Steininger Satellite estimation of tropical secondary forest above-ground biomass: Data from Brazil and Bolivia , 2000 .

[2]  Robert C. Glen,et al.  Random Forest Models To Predict Aqueous Solubility , 2007, J. Chem. Inf. Model..

[3]  Eero Muinonen,et al.  Utilizing a Multi-Source Forest Inventory Technique, MODIS Data and Landsat TM Images in the Production of Forest Cover and Volume Maps for the Terai Physiographic Zone in Nepal , 2012, Remote. Sens..

[4]  A. Huete A soil-adjusted vegetation index (SAVI) , 1988 .

[5]  N. H. Brogea,et al.  Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density , 2022 .

[6]  Achim Zeileis,et al.  Conditional variable importance for random forests , 2008, BMC Bioinformatics.

[7]  Shou-Tsung Wu,et al.  Leaf chlorophyll content and surface spectral reflectance of tree species along a terrain gradient in Taiwan ’ s Kenting National , 2007 .

[8]  Ke Wang,et al.  Landsat Imagery-Based Above Ground Biomass Estimation and Change Investigation Related to Human Activities , 2016 .

[9]  A. Gitelson,et al.  Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation , 1994 .

[10]  P. Chavez An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data , 1988 .

[11]  G. Foody,et al.  Predictive relations of tropical forest biomass from Landsat TM data and their transferability between regions , 2003 .

[12]  M. Hill Vegetation index suites as indicators of vegetation state in grassland and savanna: An analysis with simulated SENTINEL 2 data for a North American transect , 2013 .

[13]  O. Mutanga,et al.  Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review , 2010, Wetlands Ecology and Management.

[14]  Heather Reese,et al.  Mapping Tree Canopy Cover and Aboveground Biomass in Sudano-Sahelian Woodlands Using Landsat 8 and Random Forest , 2015, Remote. Sens..

[15]  Tawanda W. Gara,et al.  Estimating wood volume from canopy area in deciduous woodlands of Zimbabwe , 2014 .

[16]  Timo Tokola,et al.  Effect of field plot location on estimating tropical forest above-ground biomass in Nepal using airborne laser scanning data , 2014 .

[17]  Jan G. P. W. Clevers,et al.  Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3 , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  C. Tucker Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[20]  P. Cunningham,et al.  Solutions to Instability Problems with Sequential Wrapper-based Approaches to Feature Selection , 2002 .

[21]  O. Mutanga,et al.  Examining the strength of the newly-launched Sentinel 2 MSI sensor in detecting and discriminating subtle differences between C3 and C4 grass species , 2017 .

[22]  Jindi Wang,et al.  Comparison and Evaluation of Three Methods for Estimating Forest above Ground Biomass Using TM and GLAS Data , 2017, Remote. Sens..

[23]  R. Hall,et al.  Modeling forest stand structure attributes using Landsat ETM+ data: Application to mapping of aboveground biomass and stand volume , 2006 .

[24]  Onisimo Mutanga,et al.  High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[25]  M. Govender,et al.  A review of hyperspectral remote sensing and its application in vegetation and water resource studies , 2009 .

[26]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[27]  R. Houghton,et al.  Characterizing 3D vegetation structure from space: Mission requirements , 2011 .

[28]  Azuraliza Abu Bakar,et al.  A review of feature selection techniques in sentiment analysis , 2019, Intell. Data Anal..

[29]  W. Cohen,et al.  An evaluation of alternate remote sensing products for forest inventory, monitoring, and mapping of Douglas-fir forests in western Oregon , 2001 .

[30]  Jason H. Moore,et al.  Feature Selection using a Random Forests Classifier for the Integrated Analysis of Multiple Data Types , 2006, 2006 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology.

[31]  Heather McNairn,et al.  International Journal of Applied Earth Observation and Geoinformation , 2014 .

[32]  J. Chambers,et al.  Tree allometry and improved estimation of carbon stocks and balance in tropical forests , 2005, Oecologia.

[33]  Janne Heiskanen,et al.  Estimating biomass for boreal forests using ASTER satellite data combined with standwise forest inventory data , 2005 .

[34]  Gerald Forkuor,et al.  Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2’s red-edge bands to land-use and land-cover mapping in Burkina Faso , 2018 .

[35]  Moses Azong Cho,et al.  Toward structural assessment of semi-arid African savannahs and woodlands: The potential of multitemporal polarimetric RADARSAT-2 fine beam images , 2013 .

[36]  Honggang Bu,et al.  Active-Optical Sensors Using Red NDVI Compared to Red Edge NDVI for Prediction of Corn Grain Yield in North Dakota, U.S.A. , 2015, Sensors.

[37]  David G. Rossiter,et al.  The Precision of C Stock Estimation in the Ludhikola Watershed Using Model-Based and Design-Based Approaches , 2013, Natural Resources Research.

[38]  C. Gomez,et al.  Joint use of Sentinel-1 and Sentinel-2 for land cover classification : a machine learning approach , 2017 .

[39]  A. Gitelson,et al.  Non‐destructive optical detection of pigment changes during leaf senescence and fruit ripening , 1999 .

[40]  S. Baral,et al.  MAPPING CARBON STOCK USING HIGH RESOLUTION SATELLITE IMAGES IN SUB- TROPICAL FOREST OF NEPAL , 2011 .

[41]  Olga Sykioti,et al.  Monitoring canopy biophysical and biochemical parameters in ecosystem scale using satellite hyperspectral imagery: An application on a Phlomis fruticosa Mediterranean ecosystem using multiangular CHRIS/PROBA observations , 2010 .

[42]  Martial Bernoux,et al.  Estimating tree biomass of sub-Saharan African forests: a review of available allometric equations. , 2011 .

[43]  Gary R. Watmough,et al.  Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation , 2013 .

[44]  T. Treue,et al.  Beyond buffer zone protection: a comparative study of park and buffer zone products' importance to villagers living inside Royal Chitwan National Park and to villagers living in its buffer zone. , 2006, Journal of environmental management.

[45]  Kenneth B. Pierce,et al.  Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: A comparison of empirical modeling approaches , 2010 .

[46]  G. Kaplan,et al.  MAPPING AND MONITORING WETLANDS USING SENTINEL-2 SATELLITE IMAGERY , 2017 .

[47]  C. Jordan Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[48]  Andrew K. Skidmore,et al.  Potential of Sentinel-2 spectral configuration to assess rangeland quality , 2015 .

[49]  Akin Ozçift,et al.  Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. , 2011, Computers in biology and medicine.

[50]  Josef Aschbacher,et al.  The European Earth monitoring (GMES) programme: Status and perspectives , 2012 .

[51]  R. Valentini,et al.  Discrimination of tropical forest types, dominant species, and mapping of functional guilds by hyperspectral and simulated multispectral Sentinel-2 data , 2016 .

[52]  Xu Aigong,et al.  Integration of WorldView-2 and airborne LiDAR data for tree species level carbon stock mapping in Kayar Khola watershed, Nepal , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[53]  S. Ustin,et al.  A Comparison of Spatial and Spectral Image Resolution for Mapping Invasive Plants in Coastal California , 2007, Environmental management.

[54]  P. Groves,et al.  Methodology For Hyperspectral Band Selection , 2004 .

[55]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[56]  A. Skidmore,et al.  Narrow band vegetation indices overcome the saturation problem in biomass estimation , 2004 .

[57]  Anthony M. Filippi,et al.  stimation of floodplain aboveground biomass using multispectral emote sensing and nonparametric modeling , 2014 .

[58]  R. Valentini,et al.  Above ground biomass estimation in an African tropical forest with lidar and hyperspectral data , 2014 .

[59]  O. Mutanga,et al.  Examining the potential of Sentinel-2 MSI spectral resolution in quantifying above ground biomass across different fertilizer treatments , 2015 .

[60]  Joanne C. White,et al.  Optical remotely sensed time series data for land cover classification: A review , 2016 .

[61]  Jin Chen,et al.  Estimating aboveground biomass of grassland having a high canopy cover: an exploratory analysis of in situ hyperspectral data , 2009 .

[62]  S. Ustin Remote sensing for natural resource management and environmental monitoring , 2004 .

[63]  D. Lu Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon , 2005 .

[64]  Jon Atli Benediktsson,et al.  Recent Advances in Techniques for Hyperspectral Image Processing , 2009 .

[65]  O. Mutanga,et al.  Estimating standing biomass in papyrus (Cyperus papyrus L.) swamp: exploratory of in situ hyperspectral indices and random forest regression , 2014 .

[66]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[67]  D. Lu The potential and challenge of remote sensing‐based biomass estimation , 2006 .

[68]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[69]  Ranga B. Myneni,et al.  Remote sensing estimates of boreal and temperate forest woody biomass: carbon pools, sources, and sinks , 2003 .

[70]  O. Mutanga,et al.  Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa , 2015 .

[71]  Chengquan Huang,et al.  Quantifying Live Aboveground Biomass and Forest Disturbance of Mountainous Natural and Plantation Forests in Northern Guangdong, China, Based on Multi-Temporal Landsat, PALSAR and Field Plot Data , 2016, Remote. Sens..

[72]  Sandra A. Brown,et al.  Monitoring and estimating tropical forest carbon stocks: making REDD a reality , 2007 .

[73]  P. Curran Imaging spectrometry for ecological applications , 2001 .

[74]  N. Broge,et al.  Deriving green crop area index and canopy chlorophyll density of winter wheat from spectral reflectance data , 2002 .

[75]  M. Hardisky The Influence of Soil Salinity, Growth Form, and Leaf Moisture on-the Spectral Radiance of Spartina alterniflora Canopies , 2008 .