Modeling wetland aboveground biomass in the Poyang Lake National Nature Reserve using machine learning algorithms and Landsat-8 imagery

Abstract. Quantitative estimation of wetland aboveground biomass (AGB) is an essential aspect in evaluating the health and conservation of this valuable ecosystem. We combine AGB field measurements and remote sensing data to establish a suitable model for estimating wetland AGB in the Poyang Lake National Nature Reserve (PLNNR), which is included in the Ramsar Convention’s List of Wetlands of International Importance. All field sampling points cover four dominant vegetation communities (Carex cinerascen, Phalaris arundinacea, Artemisia selengensis, and Miscanthus sacchariflorus) in the PLNNR. Wetland AGB is retrieved from the Landsat-8 OLI image. To improve the accuracy of wetland AGB estimation, we compare the performances of three machine learning algorithms, namely, random forest (RF), back-propagation neural network (BPNN), and support vector regression (SVR), with linear regression (LR) in estimating the AGB in the PLNNR. Results are as follows: (1) the RF model with a root-mean-square error of 0.25  kg m  −  2 performs better than BPNN (0.29  kg m  −  2), SVR (0.27  kg m  −  2), and LR (0.31  kg m  −  2) in our testing dataset, and AGB density in the PLNNR is between 0 and 1.973  kg m  −  2. (2) The four most important features for AGB modeling are near-infrared, short-wave infrared 1 band, enhanced vegetation index, and red band. Our study presents an effective and operational RF model that estimates wetland AGB from Landsat data, providing a scientific basis for floodplain wetland carbon accounting and possible future studies, such as the linkage between wetland AGB and the great water level fluctuations.

[1]  W. Verhoef,et al.  PROSPECT+SAIL models: A review of use for vegetation characterization , 2009 .

[2]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[3]  V. K. Dadhwal,et al.  Neural network-based modelling for forest biomass assessment , 2017 .

[4]  Jianhua Gong,et al.  Urban Flood Mapping Based on Unmanned Aerial Vehicle Remote Sensing and Random Forest Classifier—A Case of Yuyao, China , 2015 .

[5]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

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

[7]  Jingjuan Liao,et al.  Estimation of wetland vegetation biomass in the Poyang Lake area using Landsat TM and Envisat ASAR data , 2010, International Symposium on Digital Earth.

[8]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[9]  Johannes R. Sveinsson,et al.  Random Forest classification of multisource remote sensing and geographic data , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[10]  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 .

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

[12]  Dieu Tien Bui,et al.  Biomass estimation of Sonneratia caseolaris (l.) Engler at a coastal area of Hai Phong city (Vietnam) using ALOS-2 PALSAR imagery and GIS-based multi-layer perceptron neural networks , 2017 .

[13]  C. Proisy,et al.  Predicting and mapping mangrove biomass from canopy grain analysis using Fourier-based textural ordination of IKONOS images , 2007 .

[14]  Biswajeet Pradhan,et al.  Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree , 2016, Landslides.

[15]  Weijun Zhang,et al.  Biomass concentration prediction via an input-weighed model based on artificial neural network and peer-learning cuckoo search , 2017 .

[16]  Dirk Pflugmacher,et al.  Monitoring coniferous forest biomass change using a Landsat trajectory-based approach , 2013 .

[17]  H. Xie,et al.  Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region , 2018 .

[18]  B. Parresol.  Assessing tree and stand biomass: a review with examples and critical comparisons , 1999 .

[19]  R. M. Hoffer,et al.  Biomass estimation on grazed and ungrazed rangelands using spectral indices , 1998 .

[20]  Xiaolin Zhu,et al.  Improving forest aboveground biomass estimation using seasonal Landsat NDVI time-series , 2015 .

[21]  Onisimo Mutanga,et al.  Estimation of high density wetland biomass: combining regression model with vegetation index developed from Worldview-2 imagery , 2012, Remote Sensing.

[22]  Giles M. Foody,et al.  Mapping the biomass of Bornean tropical rain forest from remotely sensed data , 2001 .

[23]  Patrick Hostert,et al.  Evaluating the Remote Sensing and Inventory-Based Estimation of Biomass in the Western Carpathians , 2011, Remote. Sens..

[24]  A. Baccini,et al.  Capabilities and limitations of Landsat and land cover data for aboveground woody biomass estimation of Uganda , 2012 .

[25]  A. R. Harrison,et al.  The NDVI and spectral decomposition for semi-arid vegetation abundance estimation , 1998 .

[26]  Rongrong Wan,et al.  Non-stationary water-level fluctuation in China’s Poyang Lake and its interactions with Yangtze River , 2015, Journal of Geographical Sciences.

[27]  M Buscema,et al.  Back propagation neural networks. , 1998, Substance use & misuse.

[28]  J. Ragle,et al.  IUCN Red List of Threatened Species , 2010 .

[29]  J. R. Jensen,et al.  The measurement of mangrove characteristics in southwest Florida using spot multispectral data , 1991 .

[30]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[31]  Emanuele Santi,et al.  Neural network adaptive algorithm applied to high resolution C-band SAR images for soil moisture retrieval in bare and vegetated areas , 2010, Remote Sensing.

[32]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

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

[34]  Haydee Karszenbaum,et al.  Assessing multi-temporal Landsat 7 ETM+ images for estimating above-ground biomass in subtropical dry forests of Argentina , 2010 .

[35]  Jan de Leeuw,et al.  Will the Three Gorges Dam affect the underwater light climate of Vallisneria spiralis L. and food habitat of Siberian crane in Poyang Lake? , 2008, Hydrobiologia.

[36]  Ming-Hsi Hsu,et al.  Predicting typhoon-induced storm surge tide with a two-dimensional hydrodynamic model and artificial neural network model , 2012 .

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

[38]  R. Kauth,et al.  The tasselled cap - A graphic description of the spectral-temporal development of agricultural crops as seen by Landsat , 1976 .

[39]  Li Ren,et al.  An Estimation of Wetland Vegetation Biomass in the Poyang Lake Using Landsat ETM Data , 2001 .

[40]  D. Hutchinson.  USGS science for a changing world , 2006 .

[41]  Jinfei Wang,et al.  Estimating leaf area index of a degraded mangrove forest using high spatial resolution satellite data , 2004 .

[42]  Kevin B. Smith,et al.  Effects of seasonal hydrologic patterns in south Florida wetlands on radar backscatter measured from ERS-2 SAR imagery , 2003 .

[43]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[44]  Randolph H. Wynne,et al.  Estimating forest biomass using small footprint LiDAR data: An individual tree-based approach that incorporates training data , 2005 .

[45]  李延风 Li Yanfeng,et al.  Remote sensing estimation of the aboveground biomass of reed wetland in the Western Songnen Plain, China, based on MODIS data , 2016 .

[46]  Dong Lei,et al.  Neural Network-based Biomass Estimation in the Poyang Lake Wetland Using Envisat ASAR Data , 2010 .

[47]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[48]  Paola Zuccolotto,et al.  Variable Selection Using Random Forests , 2006 .

[49]  T. C. Whitmore,et al.  International Union for Conservation of Nature and Natural Resources , 1970, Nature.

[50]  W. Cohen,et al.  Lidar remote sensing of above‐ground biomass in three biomes , 2002 .

[51]  G. Foody,et al.  Estimating tropical forest biomass with a combination of SAR image texture and Landsat TM data: An assessment of predictions between regions , 2012 .

[52]  P. Thenkabail,et al.  Hyperspectral Vegetation Indices and Their Relationships with Agricultural Crop Characteristics , 2000 .

[53]  Kacilda Naomi Kuki,et al.  High-performance prediction of macauba fruit biomass for agricultural and industrial purposes using Artificial Neural Networks , 2017 .

[54]  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.

[55]  Qing Ye,et al.  Analysis of the correlations between environmental factors and rare cranes in the Poyang Lake region of China , 2017 .

[56]  M. Simard,et al.  A remote sensing-based model of tidal marsh aboveground carbon stocks for the conterminous United States , 2018 .

[57]  Daniel A. Friess,et al.  Mangrove biomass estimation in Southwest Thailand using machine learning , 2013 .

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

[59]  Hui Qing Liu,et al.  A feedback based modification of the NDVI to minimize canopy background and atmospheric noise , 1995, IEEE Transactions on Geoscience and Remote Sensing.

[60]  Jennifer L. Dungan,et al.  Seasonal LAI in slash pine estimated with landsat TM , 1992 .

[61]  Xiaolong Wang,et al.  Responses of wetland vegetation in Poyang Lake, China to water-level fluctuations , 2016, Hydrobiologia.

[62]  D. Basak,et al.  Support Vector Regression , 2008 .

[63]  K. Liu,et al.  Regression and analytical models for estimating mangrove wetland biomass in South China using Radarsat images , 2007 .

[64]  I. Burke,et al.  Estimating stand structure using discrete-return lidar: an example from low density, fire prone ponderosa pine forests , 2005 .

[65]  Roland R. Draxler,et al.  Root mean square error (RMSE) or mean absolute error (MAE) , 2014 .

[66]  Richard A. Fournier,et al.  Mapping aboveground tree biomass at the stand level from inventory information: test cases in Newfoundland and Quebec , 2003 .

[67]  B. He,et al.  Estimation above-ground biomass of wetland bulrush in Qaidam Basin, China, combining regression model with vegetation index , 2011, 2011 19th International Conference on Geoinformatics.

[68]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[69]  Xu Zhang,et al.  Optimal Support Vector Machines for forest above-ground biomass estimation from multisource remote sensing data , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

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