Prediction of Urban Forest Aboveground Carbon Using Machine Learning Based on Landsat 8 and Sentinel-2: A Case Study of Shanghai, China

The aboveground carbon storage (AGC) of urban forests is an important indicator reflecting the ecological function of urban forests. It is essential to monitor the AGC of urban forests and analyze their spatiotemporal distributions. Remote sensing is a technical tool that can be leveraged to accurately monitor forest AGC, whereas machine learning is an important algorithm for the accurate prediction of AGC. Therefore, in this study, single Landsat 8 (L) remote sensing data, single Sentinel-2 (S) remote sensing data, and combined Landsat 8 and Sentinel-2 (L + S) data are used as data sources. Four machine learning methods, support vector regression (SVR), random forest (RF), XGBoost (extreme gradient boosting), and CatBoost (categorical boosting), are used to predict forest AGC based on two phases of forest sample plots in Shanghai. We chose the optimal model to predict the AGC and simulate the spatiotemporal distribution. The study shows that both machine learning models based on separate Landsat 8 OLI and Sentinel-2 satellite remote sensing data can accurately predict the AGC and spatiotemporal distribution of the Shanghai urban forest. Nevertheless, the accuracy of the combined data (L + S) and CatBoost-integrated AGC models is higher than the others, with fitting and validation accuracy R2 values of 0.99 and 0.70, respectively. The RMSE was also smaller at 0.67 and 6.29 Mg/ha, respectively. The uncertainty of the AGC spatial distribution in the Shanghai urban forest derived from the CatBoost model prediction from the 2016–2019 data was small and consistent with the actual situation. Furthermore, the statistics showed that the AGC of the Shanghai forest increased from 24.90 Mg/ha in 2016 to 25.61 Mg/ha in 2019.

• Publication year

  2023

• Venue

  Remote Sensing

• Publication date

  2023-01-03

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.3390/rs15010284
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A linear approach for wheat yield prediction by using different spectral vegetation indices

  2022cited by this paper
• A Fuzzy Multi-Criteria Decision-Making approach for the assessment of forest health applying Hyper Spectral Imagery: A case study from Ramsar forest, North of Iran.

  2022cited by this paper
• Modeling carbon storage in urban vegetation: Progress, challenges, and opportunities

  2022cited by this paper
• Space-Time Sea Surface pCO2 Estimation in the North Atlantic Based on CatBoost

  2021cited by this paper
• Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches

  2021cited by this paper
• Patterns and driving factors of biomass carbon and soil organic carbon stock in the Indian Himalayan region.

  2021cited by this paper
• Multiscale leaf area index assimilation for Moso bamboo forest based on Sentinel-2 and MODIS data

  2021cited by this paper
• Classification comparison of Landsat-8 and Sentinel-2 data in Google Earth Engine, study case of the city of Kabul

  2021cited by this paper
• Investigation of the Performance of Different Wavelet-Based Fusions of SAR and Optical Images Using Sentinel-1 and Sentinel-2 Datasets

  2021cited by this paper
• Remote Sensing Estimation of Bamboo Forest Aboveground Biomass Based on Geographically Weighted Regression

  2021cited by this paper
• Very High Resolution Remote Sensing Imagery Classification Using a Fusion of Random Forest and Deep Learning Technique—Subtropical Area for Example

  2020cited by this paper
• Towards national-scale characterization of grassland use intensity from integrated Sentinel-2 and Landsat time series

  2020cited by this paper
• Spatiotemporal Evolution of Urban Expansion Using Landsat Time Series Data and Assessment of Its Influences on Forests

  2020cited by this paper
• North West

  2020cited by this paper
• An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

  2020cited by this paper
• Evaluation of Sentinel-2 vegetation indices for prediction of LAI, fAPAR and fCover of winter wheat in Bulgaria

  2020cited by this paper
• Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

  2020cited by this paper
• Mapping aboveground biomass and carbon in Shanghai's urban forest using Landsat ETM+ and inventory data

  2020cited by this paper
• Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

  2020cited by this paper
• OBJECT BASED BURNED AREA MAPPING WITH RANDOM FOREST ALGORITHM

  2019cited by this paper
• Importance of structural and spectral parameters in modelling the aboveground carbon stock of urban vegetation

  2019cited by this paper
• Forest aboveground biomass estimation using machine learning regression algorithm in Yok Don National Park, Vietnam

  2019cited by this paper
• Estimating Forest Aboveground Carbon Storage in Hang-Jia-Hu Using Landsat TM/OLI Data and Random Forest Model

  2019cited by this paper
• Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

  2019cited by this paper
• Retrieval of Evapotranspiration from Sentinel-2: Comparison of Vegetation Indices, Semi-Empirical Models and SNAP Biophysical Processor Approach

  2019cited by this paper
• Using negative soil adjustment factor in soil-adjusted vegetation index (SAVI) for aboveground living biomass estimation in arid grasslands.

  2018cited by this paper
• [Difference analysis in estimating biomass conversion and expansion factors of masson pine in Fujian Province, China based on national forest inventory data: A comparison of three decision tree models of ensemble learning.]

  2018cited by this paper
• Lower Noise Annoyance Associated with GIS-Derived Greenspace: Pathways through Perceived Greenspace and Residential Noise

  2018cited by this paper
• Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression

  2018cited by this paper
• Estimating bamboo forest aboveground biomass using EnKF-assimilated MODIS LAI spatiotemporal data and machine learning algorithms

  2018cited by this paper
• Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery

  2018cited by this paper
• Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran)

  2018cited by this paper
• The quantitative estimation of forest carbon storage and its response to land use change in Fuzhou, China

  2016cited by this paper
• Study on Remote Sensing Image Geometric Correction Model

  2015cited by this paper
• Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa

  2015cited by this paper
• Improving forest aboveground biomass estimation using seasonal Landsat NDVI time-series

  2015cited by this paper
• Forest Biomass Mapping of Northeastern China Using GLAS and MODIS Data

  2014cited by this paper
• Landsat-8: Science and Product Vision for Terrestrial Global Change Research

  2014cited by this paper
• Satellite-based carbon stock estimation for bamboo forest with a non-linear partial least square regression technique

  2012cited by this paper
• Benchmark map of forest carbon stocks in tropical regions across three continents

  2011cited by this paper
• Application of a Random Forest algorithm to predict spatial distribution of the potential yield of Ruditapes philippinarum in the Venice lagoon, Italy

  2011cited by this paper
• Boruta – A System for Feature Selection

  2010cited by this paper
• Feature Selection with the Boruta Package

  2010cited by this paper
• Uncertainty assessment of soil water content spatial patterns using geostatistical simulations: An empirical comparison of a simulation accounting for single attribute and a simulation accounting for secondary information

  2007cited by this paper
• A comparison of four methods to map biomass from Landsat-TM and inventory data in western Newfoundland

  2006cited by this paper
• Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon

  2005cited by this paper
• Vegetation Index and Its Advances

  2003cited by this paper
• Strategy for direct and indirect methods for correcting the aerosol effect on remote sensing: From AVHRR to EOS-MODIS

  1996cited by this paper

• Research on the influencing factors and prediction model of carbon storage of urban forest in Harbin, China

  2026cites this paper
• Contributions of Multiple UAV Features to Cotton SPAD Estimation from the Perspective of Explainable Machine Learning

  2026cites this paper
• Remote sensing-based analysis of land use/land cover dynamics and blue carbon assessment in Mahakam River Delta, Indonesia

  2026cites this paper
• Operationalizing urban greenery for carbon mitigation futures: From potential to practice

  2026cites this paper
• Estimation of Anthocyanins in Apple Leaves Based on Ground Hyperspectral Imaging and Machine Learning Models

  2025cites this paper
• Spatially continuous estimation of urban forest aboveground biomass with UAV-LiDAR and multispectral scanning: An allometric model of forest structural diversity

  2025cites this paper
• Time-series forest age estimation in Xinjiang based on forest disturbance and recovery detection

  2025cites this paper
• Assessing the impact of land use and cover change on above-ground carbon storage in subtropical forests: a case study of Zhejiang Province, China

  2025influential citation
• Land Use and Land Cover Change and Its Impact on Carbon Stock in the Yellow River Delta Wetland Ecosystem of China

  2025cites this paper
• Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR

  2025cites this paper
• Estimation of forest aboveground carbon storage based on GEDI and GF-6 in Jiyuan City, China

  2025cites this paper
• Remote sensing of urban tree carbon stocks: A methodological review

  2025cites this paper
• Estimating Forest Carbon Stock Using Enhanced ResNet and Sentinel-2 Imagery

  2025cites this paper
• Modeling Urban-Vegetation Aboveground Carbon by Integrating Spectral–Textural Features with Tree Height and Canopy Cover Ratio Using Machine Learning

  2025cites this paper
• Estimating coastal mangrove aboveground biomass of Zhejiang province based on sentinel-2 images and multiple machine learning algorithms

  2025cites this paper
• An improved YOLOv7 network achieved precise mapping of Moso bamboo stem density by UAV combined with Sentinel-2 images

  2025cites this paper
• Improving Forest Above-Ground Biomass Estimation Using UAV LiDAR and RGB with Machine Learning Algorithm

  2025cites this paper
• Estimation of Above-Ground Carbon Storage in Urban Green Space Trees Incorporating Crown Volume Structural Parameters

  2025cites this paper
• Performance Of Random Forest and Cart Algorithms In Land-Use and Land-Cover Classification on Cotijuba Island (Pa) From 1989 To 2023

  2025cites this paper
• Landsat-based spatiotemporal estimation of subtropical forest aboveground carbon storage using machine learning algorithms with hyperparameter tuning

  2024cites this paper
• Optimization of SVR and CatBoost models using metaheuristic algorithms to assess landslide susceptibility

  2024cites this paper
• Monitoring and Assessment of Carbon stock through Geospatial Technique in Sathyamangalam Forest, Erode district, Tamilnadu

  2024cites this paper
• A Spatial Downscaling Framework for SMAP Soil Moisture Based on Stacking Strategy

  2024cites this paper
• UAV-LiDAR Integration with Sentinel-2 Enhances Precision in AGB Estimation for Bamboo Forests

  2024cites this paper
• Estimation aboveground biomass in subtropical bamboo forests based on an interpretable machine learning framework

  2024cites this paper
• Assessing above-ground biomass in reforested urban landscapes using machine learning and remotely sensed data

  2024cites this paper
• Coupling the PROSAIL Model and Machine Learning Approach for Canopy Parameter Estimation of Moso Bamboo Forests from UAV Hyperspectral Data

  2024cites this paper
• Forest age estimation using UAV-LiDAR and Sentinel-2 data with machine learning algorithms- a case study of Masson pine (Pinus massoniana)

  2024cites this paper
• Evaluating Machine Learning Approaches for Aboveground Biomass Prediction in Fragmented High-Elevated Forests Using Multi-Sensor Satellite Data

  2024cites this paper
• Improving forest age prediction performance using ensemble learning algorithms base on satellite remote sensing data

  2024cites this paper
• Multi-scale geographically weighted regression estimation of carbon storage on coniferous forests considering residual distribution using remote sensing data

  2024cites this paper
• Urban Forest Above-Ground Biomass Estimation Based on UAV 3D Real Scene

  2023cites this paper
• An Algorithm of Forest Age Estimation Based on the Forest Disturbance and Recovery Detection

  2023cites this paper
• The Development of an Experimental Framework to Explore the Generative Design Preference of a Machine Learning-Assisted Residential Site Plan Layout

  2023cites this paper
• Assessment of Forest Ecological Function Levels Based on Multi-Source Data and Machine Learning

  2023cites this paper
• Study on the Regeneration Probability of Understory Coniferous Saplings in the Liangshui Nature Reserve Based on Four Modeling Techniques

  2023cites this paper