Evaluating site-specific and generic spatial models of aboveground forest biomass based on landsat Time-Series and LiDAR strip samples in the Eastern USA

Keyphrases

• LiDAR 100%
• Spatial Modeling 100%
• Eastern USA 100%
• Site-specific Model 100%
• Biomass-based 100%
• Forest Aboveground Biomass 100%
• Landsat Time Series 100%
• Generic Model 50%
• Minnesota 33%
• New Jersey 33%
• South Carolina 33%
• Pennsylvania 33%
• Multiple Linear Regression 33%
• Adjusted R2 33%
• Maine 33%
• New South 33%
• Statistical Model 16%
• Monitoring Program 16%
• Prediction Accuracy 16%
• Modeling Framework 16%
• Landsat 16%
• Machine Learning Approach 16%
• National Forest Inventory 16%
• Field Sampling 16%
• Ordinary Least Squares 16%
• Model Fitting 16%
• Random Forest 16%
• Polynomial Model 16%
• Remote Sensing Data 16%
• Statistical Equivalence 16%
• Pixel Level 16%
• Proportions of Variance 16%
• DATAPLOT 16%
• Random Forest Machine Learning 16%
• Image Time Series 16%
• Fit Statistics 16%
• Forest Inventory Plots 16%
• Predicted Data 16%
• Inventory Position 16%
• Spatial Predictors 16%
• Generic Reference 16%
• Biomass Assessment 16%
• Sampling Measurement 16%
• National Forest Inventory Data 16%
• Large-area Estimation 16%
• National Forest Monitoring 16%

Earth and Planetary Sciences

• United States of America 100%
• Landsat 100%
• Time Series 100%
• Optical Radar 100%
• Forest Inventory 75%
• Minnesota 50%
• Pennsylvania 50%
• South Carolina 50%
• New Jersey 50%
• Maine 50%
• Machine Learning 25%
• Statistical Model 25%

Agricultural and Biological Sciences

• National Forests 100%
• Forest Inventory 100%
• Landsat 100%
• Jersey 66%
• Statistical Model 33%
• Learning System 33%
• Machine Learning 33%
• Least Squares Method 33%