Improving the accuracy of forest aboveground biomass using Landsat 8 OLI images by quantile regression neural network for Pinus densata forests in southwestern China

It is a challenge to reduce the uncertainties of the underestimation and overestimation of forest aboveground biomass (AGB) which is common in optical remote sensing imagery. In this study, four models, namely, the linear stepwise regression (LSR), artificial neural network (ANN), quantile regression (QR), and quantile regression neural network (QRNN) were used to estimate Pinus densata forest AGB data by collecting 146 sample plots combined with Landsat 8-Operational Land Imager (OLI) images in Shangri-La City, Yunnan Province, southwestern China. The results showed that compared with the LSR, the R2 and mean square error (RMSE) of the ANN, QR, and QRNN had improved significantly. In particular, the QRNN was able to significantly improve the situation of overestimation and underestimation when we estimated forest biomass, which had the highest R2 (0.971) and lowest RMSE (9.791 Mg/ha) for the whole biomass segment. Meanwhile, through model validation, we found that the QRNN had the highest R2 (0.761) and lowest RMSE (6.486 Mg/ha) on the biomass segment of <40 Mg/ha. Furthermore, it had the highest R2 (0.904) and lowest RMSE (9.059 Mg/ha) on the biomass segment of >160 Mg/ha, which offered great potential for improving the estimation accuracy of the Pinus densata forest AGB. In conclusion, the QRNN, combining the advantages of QR and ANN, provides great potential for reducing the precision influence caused by the overestimation and underestimation in forest AGB estimation using optical remote sensing data.

[1]  Joanne C. White,et al.  Fifty years of Landsat science and impacts , 2022, Remote Sensing of Environment.

[2]  S. Tshering,et al.  Terrestrial Biomass and Carbon Stock in Broad-leaved Forests of Punakha District, Western Bhutan , 2022, Nature Environment and Pollution Technology.

[3]  S. Tuominen,et al.  Comparison of neural networks and k-nearest neighbors methods in forest stand variable estimation using airborne laser data , 2022, ISPRS Open Journal of Photogrammetry and Remote Sensing.

[4]  R. Hall,et al.  Improved k-NN Mapping of Forest Attributes in Northern Canada Using Spaceborne L-Band SAR, Multispectral and LiDAR Data , 2022, Remote. Sens..

[5]  C. Woodcock,et al.  Mapping Forest Aboveground Biomass Using Multisource Remotely Sensed Data , 2022, Remote. Sens..

[6]  Zhao-ming Zhang,et al.  Vegetation Monitoring of Protected Areas in Rugged Mountains Using an Improved Shadow-Eliminated Vegetation Index (SEVI) , 2022, Remote. Sens..

[7]  K. Philippopoulos,et al.  Solar Cycle Signal in Climate and Artificial Neural Networks Forecasting , 2022, Remote. Sens..

[8]  Ding Wang,et al.  Artificial Neural Network-Based Ionospheric Delay Correction Method for Satellite-Based Augmentation Systems , 2022, Remote. Sens..

[9]  A. Mansourian,et al.  A GIS-Based Landslide Susceptibility Mapping and Variable Importance Analysis Using Artificial Intelligent Training-Based Methods , 2022, Remote. Sens..

[10]  Xiaoli Zhang,et al.  Above-Ground Biomass Estimation of Plantation with Complex Forest Stand Structure Using Multiple Features from Airborne Laser Scanning Point Cloud Data , 2021, Forests.

[11]  Yueming Hu,et al.  Estimation of forest aboveground biomass by using mixed-effects model , 2021 .

[12]  Biswajeet Pradhan,et al.  Earthquake Vulnerability Assessment for Urban Areas Using an ANN and Hybrid SWOT-QSPM Model , 2021, Remote. Sens..

[13]  Yonggen Zhang,et al.  Modelling Aboveground Biomass Carbon Stock of the Bohai Rim Coastal Wetlands by Integrating Remote Sensing, Terrain, and Climate Data , 2021, Remote. Sens..

[14]  Mohammed M. Alquraish,et al.  Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models , 2021, Remote. Sens..

[15]  Mingguo Ma,et al.  Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques , 2021, Remote. Sens..

[16]  A. Sousa,et al.  Estimating tree aboveground biomass using multispectral satellite-based data in Mediterranean agroforestry system using random forest algorithm , 2021, Remote Sensing Applications: Society and Environment.

[17]  Guoqing Zhou,et al.  Aboveground mangrove biomass estimation in Beibu Gulf using machine learning and UAV remote sensing , 2021 .

[18]  Qian Ai,et al.  A Parallel Electrical Optimized Load Forecasting Method Based on Quasi-Recurrent Neural Network , 2021 .

[19]  Lei Zhao,et al.  Forest Aboveground Biomass Estimation Using Multi-Features Extracted by Fitting Vertical Backscattered Power Profile of Tomographic SAR , 2021, Remote. Sens..

[20]  Surya Kant,et al.  Fusion of Spectral and Structural Information from Aerial Images for Improved Biomass Estimation , 2020, Remote. Sens..

[21]  Yuzhen Zhang,et al.  Fusion of Multiple Gridded Biomass Datasets for Generating a Global Forest Aboveground Biomass Map , 2020, Remote. Sens..

[22]  Lukas W. Lehnert,et al.  Land Cover Classification using Google Earth Engine and Random Forest Classifier - The Role of Image Composition , 2020, Remote. Sens..

[23]  Adrian Constantinescu,et al.  Synergy of High-Resolution Radar and Optical Images Satellite for Identification and Mapping of Wetland Macrophytes on the Danube Delta , 2020, Remote. Sens..

[24]  Huarong Jia,et al.  Improving Co-Registration for Sentinel-1 SAR and Sentinel-2 Optical Images , 2020, Remote. Sens..

[25]  Pierre Couteron,et al.  Airborne Lidar Sampling Pivotal for Accurate Regional AGB Predictions from Multispectral Images in Forest-Savanna Landscapes , 2020, Remote. Sens..

[26]  Zhongyi Zhu,et al.  Weighted quantile regression in varying-coefficient model with longitudinal data , 2020, Comput. Stat. Data Anal..

[27]  Hui Xu,et al.  Improving Forest Aboveground Biomass Estimation of Pinus densata Forest in Yunnan of Southwest China by Spatial Regression using Landsat 8 Images , 2019, Remote. Sens..

[28]  Lênio Soares Galvão,et al.  Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms , 2019, Remote Sensing of Environment.

[29]  Honglin He,et al.  Estimating grassland aboveground biomass on the Tibetan Plateau using a random forest algorithm , 2019, Ecological Indicators.

[30]  Naomi S. Altman,et al.  Quantile regression , 2019, Nature Methods.

[31]  Chao Li,et al.  Improving Aboveground Biomass Estimation of Pinus densata Forests in Yunnan Using Landsat 8 Imagery by Incorporating Age Dummy Variable and Method Comparison , 2019, Remote. Sens..

[32]  Caixia Liu,et al.  Integration of multi-resource remotely sensed data and allometric models for forest aboveground biomass estimation in China , 2019, Remote Sensing of Environment.

[33]  Mingyang Li,et al.  Improving Forest Aboveground Biomass (AGB) Estimation by Incorporating Crown Density and Using Landsat 8 OLI Images of a Subtropical Forest in Western Hunan in Central China , 2019, Forests.

[34]  Furno Marilena,et al.  Quantile Regression , 2018, Wiley Series in Probability and Statistics.

[35]  C. Jiang,et al.  Conditional density forecast of China’s energy demand via QRNN model , 2018 .

[36]  Guangxing Wang,et al.  Estimating aboveground biomass of Pinus densata-dominated forests using Landsat time series and permanent sample plot data , 2018, Journal of Forestry Research.

[37]  Suhartono,et al.  Hybrid Quantile Regression Neural Network Model for Forecasting Currency Inflow and Outflow in Indonesia , 2018, Journal of Physics: Conference Series.

[38]  Haiyan Li,et al.  Probability density forecasting of wind power using quantile regression neural network and kernel density estimation , 2018 .

[39]  Andreas Fries,et al.  Estimation of Above Ground Biomass in a Tropical Mountain Forest in Southern Ecuador Using Airborne LiDAR Data , 2018, Remote. Sens..

[40]  Leiguang Wang,et al.  ESTIMATION OF FOREST BIOMASS BASED ON MULITI-SOURCE REMOTE SENSING DATA SET – A CASE STUDY OF SHANGRI-LA COUNTY , 2018 .

[41]  Lijuan Liu,et al.  Comparative Analysis of Modeling Algorithms for Forest Aboveground Biomass Estimation in a Subtropical Region , 2018, Remote. Sens..

[42]  Jean‐François Bastin,et al.  Toward a general tropical forest biomass prediction model from very high resolution optical satellite images , 2017 .

[43]  Hua Sun,et al.  Mapping Forest Ecosystem Biomass Density for Xiangjiang River Basin by Combining Plot and Remote Sensing Data and Comparing Spatial Extrapolation Methods , 2017, Remote. Sens..

[44]  Guangxing Wang,et al.  Examining Spectral Reflectance Saturation in Landsat Imagery and Corresponding Solutions to Improve Forest Aboveground Biomass Estimation , 2016, Remote. Sens..

[45]  Ramón A. Díaz-Varela,et al.  Evaluation of Radiometric and Atmospheric Correction Algorithms for Aboveground Forest Biomass Estimation Using Landsat 5 TM Data , 2016, Remote. Sens..

[46]  Jason S. Sibold,et al.  Spatial and temporal trends of drought effects in a heterogeneous semi-arid forest ecosystem. , 2016 .

[47]  T. Hilker,et al.  Comparison of uncertainty in per unit area estimates of aboveground biomass for two selected model sets , 2015 .

[48]  C. Woodcock,et al.  Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images , 2015 .

[49]  Thuy Le Toan,et al.  Relating P-Band Synthetic Aperture Radar Tomography to Tropical Forest Biomass , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[50]  W. Verhoef,et al.  Hyperspectral analysis of mangrove foliar chemistry using PLSR and support vector regression , 2013 .

[51]  David Saah,et al.  Aboveground Forest Biomass Estimation with Landsat and LiDAR Data and Uncertainty Analysis of the Estimates , 2012 .

[52]  Cao Chunxiang,et al.  Topographic correction-based retrieval of leaf area index in mountain areas , 2012 .

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

[54]  John F. Weishampel,et al.  Portable and Airborne Small Footprint LiDAR: Forest Canopy Structure Estimation of Fire Managed Plots , 2011, Remote. Sens..

[55]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[56]  Luca Oneto,et al.  Advances in artificial neural networks, machine learning and computational intelligence , 2011, Neurocomputing.

[57]  Matthias Peichl,et al.  Allometry and partitioning of above- and belowground tree biomass in an age-sequence of white pine forests , 2007 .

[58]  W. Ju,et al.  Combining remote sensing imagery and forest age inventory for biomass mapping. , 2007, Journal of environmental management.

[59]  Bette A. Loiselle,et al.  Predicting species distributions from herbarium collections: does climate bias in collection sampling influence model outcomes? , 2007 .

[60]  P. Friederichs,et al.  Statistical Downscaling of Extreme Precipitation Events Using Censored Quantile Regression , 2007 .

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

[62]  Michael A. Lefsky,et al.  Combining lidar estimates of aboveground biomass and Landsat estimates of stand age for spatially extensive validation of modeled forest productivity , 2005 .

[63]  L. Zhang,et al.  Local Modeling of Tree Growth by Geographically Weighted Regression , 2004 .

[64]  B. Cade,et al.  A gentle introduction to quantile regression for ecologists , 2003 .

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

[66]  C. Justice,et al.  Atmospheric correction of MODIS data in the visible to middle infrared: first results , 2002 .

[67]  J. Cihlar,et al.  An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images , 2002 .

[68]  James W. Taylor.  A Quantile Regression Neural Network Approach to Estimating the Conditional Density of Multiperiod Returns , 2000 .

[69]  Francis Juanes,et al.  INFERRING ECOLOGICAL RELATIONSHIPS FROM THE EDGES OF SCATTER DIAGRAMS: COMPARISON OF REGRESSION TECHNIQUES , 1998 .

[70]  Cheng Wang,et al.  Forest emissions reduction assessment using airborne LiDAR for biomass estimation , 2022, Resources, Conservation and Recycling.

[71]  P. Chauhan,et al.  Above-ground biomass estimation of Indian tropical forests using X band Pol-InSAR and Random Forest , 2021 .

[72]  Feng Ling,et al.  Mapping water bodies under cloud cover using remotely sensed optical images and a spatiotemporal dependence model , 2021, Int. J. Appl. Earth Obs. Geoinformation.

[73]  Xu Qi-f.  Financial risk measure of VaR based on quantile regression neural network , 2014 .

[74]  Julien Leider.  A Quantile Regression Study of Climate Change in Chicago, 1960-2010 , 2012 .

[75]  Luo Youqing,et al.  Application of stepwise regression model in predicting the movement of Artemisia ordosica boring insects. , 2009 .

[76]  R. Koenker,et al.  Regression Quantiles , 2007 .