Regional Scale Inversion of Chlorophyll Content of Dendrocalamus giganteus by Multi-Source Remote Sensing

Forests, Journal Year: 2024, Volume and Issue: 15(7), P. 1211 - 1211

Published: July 12, 2024

The spectrophotometer method is costly, time-consuming, laborious, and destructive to the plant. Samples will be lost during transportation process, can only obtain sample point data. This poses a challenge estimation of chlorophyll content at regional level. In this study, in order improve accuracy, new collaborative inversion using Landsat 8 Global Ecosystem Dynamics Investigation (GEDI) proposed. Specifically, data set combined with preprocessed two remote-sensing (RS) factors construct three regression models support vector machine (SVM), BP neural network (BP) random forest (RF), better model selected for inversion. addition, ordinary Kriging (OK) used interpolate GEDI attribute into surface modeling. results showed following: (1) single plant was y = 0.1373x1.7654. (2) optimal semi-variance function pai, pgap_theta pgap_theta_a3 are exponential models. (3) top correlations between RS were B2_3_SM, B2_3_HO, B2_5_EN pgap_theta, pgap_theta_a3. (4) combination imagery resulted highest modeling RF had best performance, R2, RMSE P values 0.94, 0.18 g/m2 83.32%, respectively. study shows that it reliable use images retrieve Dendrocalamus giganteus (D. giganteus), revealing potential multi-source ecological parameters.

Language: Английский

---

Research on Estimation Model of Carbon Stock Based on Airborne LiDAR and Feature Screening

Sustainability, Journal Year: 2024, Volume and Issue: 16(10), P. 4133 - 4133

Published: May 15, 2024

The rapid and accurate estimation of forest carbon stock is important for analyzing the cycle. In order to obtain efficiently, this paper utilizes airborne LiDAR data research applicability different feature screening methods in combination with machine learning model. First, Spearman’s Correlation Coefficient (SCC) Extreme Gradient Boosting tree (XGBoost) were used screen out variables that extracted via Airborne a higher correlation stock. Then, Bagging, K-nearest neighbor (KNN), Random Forest (RF) construct results show height statistical variable more strongly correlated stocks than density are. RF suitable construction model compared instance-based KNN algorithm. Furthermore, XGBoost algorithm performs best, an R2 0.85 MSE 10.74 on training set 0.53 21.81 testing set. This study demonstrates effectiveness construction. has wider screening.

Language: Английский

---

Quantifying forest stocking changes in Sundarbans mangrove using remote sensing data

Science of Remote Sensing, Journal Year: 2024, Volume and Issue: unknown, P. 100181 - 100181

Published: Dec. 1, 2024

Language: Английский

---

Forest aboveground biomass estimation based on spaceborne LiDAR combining machine learning model and geostatistical method

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Dec. 11, 2024

Estimation of forest biomass at regional scale based on GEDI spaceborne LiDAR data is great significance for quality assessment and carbon cycle. To solve the problem discontinuous footprints, this study mapped different echo indexes in footprints to surface by inverse distance weighted interpolation method, verified influence number results. Random algorithm was chosen estimate spruce-fir combined with parameters provided 138 sample plots Shangri-La. The results show that: (1) By extracting numbers visualize it, revealed that a higher correlates denser distribution more pronounced stripe phenomenon. (2) prediction accuracy improves as decreases. group highest R 2 , lowest RMSE MAE footprint extracted every 100 shots, 10 shots had worst effect. (3) inverted random ranged from 51.33 t/hm 179.83 an average 101.98 . total value 3035.29 × 4 This shows will have certain impact mapping information presents methodological reference selecting appropriate derive various vertical structure ecosystems.

Language: Английский

---

Co-Kriging-Guided Interpolation for Mapping Forest Aboveground Biomass by Integrating Global Ecosystem Dynamics Investigation and Sentinel-2 Data

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(16), P. 2913 - 2913

Published: Aug. 9, 2024

Mapping wall-to-wall forest aboveground biomass (AGB) at large scales is critical for understanding global climate change and the carbon cycle. In previous studies, a regression-based method was commonly used to map spatially continuous distribution of AGB with aid optical images, which may suffer from saturation effect. The Global Ecosystem Dynamics Investigation (GEDI) can collect vertical structure information high precision on scale. this study, we proposed collaborative kriging (co-kriging) interpolation-based mapping by integrating GEDI Sentinel-2 data. First, fusing spectral features images GEDI, optimal estimation model footprint-level determined comparing different machine-learning algorithms. Second, predicted as main variable, rh95 B12 covariates, build co-kriging guided interpolation model. Finally, employed AGB. results showed following: (1) For AGB, CatBoost achieved highest accuracy data (R2 = 0.87, RMSE 49.56 Mg/ha, rRMSE 27.06%). (2) based exhibited relatively mitigated effect in areas higher 0.69, 81.56 40.98%, bias −3.236 Mg/ha). result demonstrates that combined multi-source be promising solution monitoring

Language: Английский

---

Cross-modal fusion approach with Multispectral, LiDAR, and SAR data for Forest Canopy Height Mapping in Mountainous Region

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: unknown, P. 103819 - 103819

Published: Nov. 1, 2024

Language: Английский

---

Understory Terrain Estimation by Synergizing Ice, Cloud, and Land Elevation Satellite-2 and Multi-Source Remote Sensing Data

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(24), P. 4770 - 4770

Published: Dec. 21, 2024

Forest ecosystems are incredibly valuable, and understory terrain is crucial for estimating various forest structure parameters. As the demand monitoring increases, quickly accurately understanding spatial distribution patterns of has become a new challenge. This study used ICESat-2 data as reference validation basis, integrating multi-source remote sensing (including Landsat 8, ICESat-2, SRTM) applying machine learning methods to estimate sub-canopy topography area. The results from random model show significant improvement in accuracy compared traditional SRTM products, with an R2 0.99, ME 0.22 m, RMSE 3.59 STD m. In addition, we assessed estimates different landforms, canopy heights, cover types, coverage. demonstrate that estimation minimally impacted by ground elevation, type, coverage, indicating good stability. approach holds promise at regional global scales, providing support protecting ecosystems.

Language: Английский

---