Utility of hyperspectral compared to multispectral remote sensing data in estimating forest biomass and structure variables in Finnish boreal forest

Keyphrases

• Forest Biomass 100%
• Hyperspectral 100%
• Boreal Forest 100%
• Structure Variable 100%
• Multispectral Remote Sensing Data 100%
• Forest Structure 100%
• Stand Level 75%
• Tree Species 50%
• Leaf Area Index 50%
• Forest Variables 50%
• Remote Sensing Data 50%
• Basal Area 50%
• Mean Height 50%
• Additional Value 50%
• Stem Biomass 50%
• Plot Level 50%
• Regression Algorithm 50%
• Finland 25%
• Specific Information 25%
• Carbon Sink 25%
• Tree Leaves 25%
• In Situ Measurements 25%
• Estimation Accuracy 25%
• Management Practices 25%
• Forestry 25%
• Forest Resources 25%
• Forest Industry 25%
• High Spectral Resolution 25%
• Carbon-carbon 25%
• Remote Sensing Application 25%
• Biomass Carbon 25%
• Kernel Regression 25%
• Variables of Interest 25%
• Satellite Mission 25%
• Gaussian Process 25%
• Carbon Pools 25%
• Land Surface 25%
• Natural Resource Management 25%
• Sentinel-2 25%
• Forest Variable Estimation 25%
• Species-area Relationship 25%
• Machine Learning Regression Algorithms 25%
• Least Squares Support Vector Regression (LSSVR) 25%
• Optical Remote Sensing Technique 25%
• Kernel-based Machine Learning 25%
• Hyperspectral Remote Sensing Data 25%
• Hyperspectral Satellite 25%
• Holdout 25%
• Structure Estimation 25%
• Variable Estimation 25%
• Relative Root Mean Square Error (RRMSE) 25%
• Up-To-date Information 25%
• Basal Stem 25%

INIS

• comparative evaluations 100%
• data 100%
• biomass 100%
• forests 100%
• remote sensing 100%
• utilities 100%
• levels 36%
• algorithms 27%
• resolution 27%
• values 18%
• information 18%
• height 18%
• kernels 18%
• forestry 18%
• tools 9%
• finland 9%
• resources 9%
• applications 9%
• carbon 9%
• pools 9%
• industry 9%
• machine learning 9%
• errors 9%
• satellites 9%
• validation 9%
• accuracy 9%
• surface area 9%
• carbon sinks 9%
• roots 9%
• datasets 9%
• resource management 9%
• vectors 9%
• gaussian processes 9%

Earth and Planetary Sciences

• Boreal Forest 100%
• Remote Sensing 100%
• Leaf Area 40%
• Basal Area 40%
• Surface Area 20%
• Forest Resource 20%
• Spectral Resolution 20%
• Remote Sensing Application 20%
• Root-Mean-Square Error 20%
• Machine Learning 20%
• In Situ Measurement 20%
• Satellite Mission 20%
• Optical Remote Sensing 20%
• Land Surface 20%
• Natural Resource Management 20%
• Finland 20%
• Sentinel-2 20%
• Support Vector Machine 20%