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

Li, Huimian; Zhang, Guilian; Zhong, Qicheng; Xing, Luqi; Du, Huaqiang

doi:10.3390/rs15010284

Cited by 13 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding is consistent with the results obtained by Ou et al, who used Landsat 8 and a spatial regression model for predicting AGB [38]. For AGC estimation methods, there are also nonparametric and machine-learning models, which are higher than GWR in terms of fitting accuracy [30,83]. Li et al employed Sentinel-2 and used four machine learning methods to estimate forest AGC in Shanghai.…”

Section: Uncertainty Analysis Of Agc Estimationsupporting

confidence: 85%

Estimation of Above-Ground Carbon Storage and Light Saturation Value in Northeastern China’s Natural Forests Using Different Spatial Regression Models

Wu,

Sun,

Jia

et al. 2023

Forests

View full text Add to dashboard Cite

In recent years, accurate estimation and spatial mapping of above-ground carbon (AGC) storage in forests have been crucial for formulating carbon trading policies and promoting sustainable development strategies. Forest structure complexities mean that during their growth, trees may be affected by the surrounding environment, giving rise to spatial autocorrelation and heterogeneity in nearby forest segments. When estimating forest AGC through remote sensing, data saturation can arise in dense forest stands, adding to the uncertainties in AGC estimation. Our study used field-measured stand factors data from 138 forest fire risk plots located in Fenglin County in the Northeastern region, set within a series of temperate forest environments in 2021 and Sentinel-2 remote sensing image data with a spatial resolution of 10 m. Using ordinary least squares (OLS) as a baseline, we constructed and compared it against four spatial regression models, spatial lag model (SLM), spatial error model (SEM), spatial Durbin model (SDM), and geographically weighted regression (GWR), to better understand forest AGC spatial distribution. The results of local spatial analysis reveal significant spatial effects among plot data. The GWR model outperformed others with an R2 value of 0.695 and the lowest rRMSE at 0.273, considering spatial heterogeneity and extending the threshold range for AGC estimation. To address the challenge of light saturation during AGC estimation, we deployed traditional linear functions, the generalized additive model (GAM), and the quantile generalized additive model (QGAM). AGC light saturation values derived from QGAM most accurately reflect the actual conditions, with the forests in Fenglin County exhibiting a light saturation range of 108.832 to 129.894 Mg/ha. The GWR effectively alleviated the impact of data saturation, thereby reducing the uncertainty of AGC spatial distribution in Fenglin County. Overall, accurate predictions of large-scale forest carbon storage provide valuable guidance for forest management, forest conservation, and the promotion of sustainable development strategies.

show abstract

Section: Uncertainty Analysis Of Agc Estimationsupporting

confidence: 85%

Estimation of Above-Ground Carbon Storage and Light Saturation Value in Northeastern China’s Natural Forests Using Different Spatial Regression Models

Wu,

Sun,

Jia

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

“…By comparing and analyzing the three MBF canopy parameter estimation methods for the PROSAIL_MLRA model, PROSAIL_XGBR outperformed PRO-SAIL_ETR, which, in turn, was superior to PROSAIL_MLPR (Table 4). The tree-based integration algorithms (e.g., ETR, XGBR) performed better than the MLPR in terms of performance [68,69]. The better performance of tree-based integration algorithms stemmed from their flexibility and strength in handling all data types.…”

Section: Mixed Inversion Modeling Of Canopy Parametersmentioning

confidence: 99%

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

Zhou,

Li,

Chen

et al. 2024

Forests

Self Cite

View full text Add to dashboard Cite

Parameters such as the leaf area index (LAI), canopy chlorophyll content (CCH), and canopy carotenoid content (CCA) are important indicators for evaluating the ecological functions of forests. Currently, rapidly developing unmanned aerial vehicles (UAV) equipped with hyperspectral technology provide advanced technical means for the real-time dynamic acquisition of regional vegetation canopy parameters. In this study, a hyperspectral sensor mounted on a UAV was used to acquire the data in the study area, and the canopy parameter estimation model of moso bamboo forests (MBF) was developed by combining the PROSAIL radiative transfer model and the machine learning regression algorithm (MLRA), inverted the canopy parameters such as LAI, CCH, and CCA. The method first utilized the extended Fourier amplitude sensitivity test (EFAST) method to optimize the global sensitivity analysis and parameters of the PROSAIL model, and the successive projections algorithm (SPA) was used to screen the characteristic wavebands for the inversion of MBF canopy parameter inversion. Then, the optimized PROSAIL model was used to construct the ‘LAI-CCH-CCA-canopy reflectance’ simulation dataset for the MBF; multilayer perceptron regressor (MLPR), extra tree regressor (ETR), and extreme gradient boosting regressor (XGBR) employed used to construct PROSAIL_MLPR, PROSAIL_ETR, and PROSAIL_XGBR, respectively, as the three hybrid models. Finally, the best hybrid model was selected and used to invert the spatial distribution of the MBF canopy parameters. The following results were obtained: Waveband sensitivity analysis reveals 400–490 and 710–1000 nm as critical for LAI, 540–650 nm for chlorophyll, and 490–540 nm for carotenoids. SPA narrows down the feature bands to 43 for LAI, 19 for CCH, and 9 for CCA. The three constructed hybrid models were able to achieve high-precision inversion of the three parameters of the MBF, the model fitting accuracy of PROSAIL_MLRA reached more than 95%, with lower RMSE values, and the PROSAIL_XGBR model yielded the best fitting results. Our study provides a novel method for the inversion of forest canopy parameters based on UAV hyperspectral data.

show abstract

“…The superiority of XGBoost and LightGBM in SM downscaling has been confirmed [14,21]. CatBoost is widely used in various ML tasks due to its advantages in dealing with categorical features and regression issues [22,23]. But its applications in SM downscaling are relatively limited, and it is necessary to evaluate its applicability.…”

Section: Introductionmentioning

confidence: 96%

A Spatial Downscaling Framework for SMAP Soil Moisture Based on Stacking Strategy

Xu,

Su,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Soil moisture (SM) data can provide guidance for decision-makers in fields such as drought monitoring and irrigation management. Soil Moisture Active Passive (SMAP) satellite offers sufficient spatial resolution for global-scale applications, but its utility is limited in regional areas due to its lower spatial resolution. To address this issue, this study proposed a downscaling framework based on the Stacking strategy. The framework integrated extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost) to generate 1 km resolution SM data using 15 high-resolution factors derived from multi-source datasets. In particular, to test the influence of terrain partitioning on downscaling results, Anhui Province, which has diverse terrain features, was selected as the study area. The results indicated that the performance of the three base models varied, and the developed Stacking strategy maximized the potential of each model with encouraging downscaling results. Specifically, we found that: (1) The Stacking model achieved the highest accuracy in all regions, and the performance order of the base models was: XGBoost > CatBoost > LightGBM. (2) Compared with the measured SM at 87 sites, the downscaled SM outperformed other 1 km SM products as well as the downscaled SM without partitioning, with an average ubRMSE of 0.040 m3/m3. (3) The downscaled SM responded positively to rainfall events and mitigated the systematic bias of SMAP. It also preserved the spatial trend of the original SMAP, with higher levels in the humid region and relatively lower levels in the semi-humid region. Overall, this study provided a new strategy for soil moisture downscaling and revealed some interesting findings related to the effectiveness of the Stacking model and the impact of terrain partitioning on downscaling accuracy.

show abstract

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

Cited by 13 publications

References 47 publications

Estimation of Above-Ground Carbon Storage and Light Saturation Value in Northeastern China’s Natural Forests Using Different Spatial Regression Models

Estimation of Above-Ground Carbon Storage and Light Saturation Value in Northeastern China’s Natural Forests Using Different Spatial Regression Models

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

A Spatial Downscaling Framework for SMAP Soil Moisture Based on Stacking Strategy

Contact Info

Product

Resources

About