Ensemble Machine Learning Approach Improves Predicted Spatial Variation of Surface Soil Organic Carbon Stocks in Data-Limited Northern Circumpolar Region

Computer Science

• Machine Learning Approach 100%
• Spatial Variation 100%
• Prediction Accuracy 80%
• Random Decision Forest 40%
• Gradient Boosting 40%
• Support Vector Machine 40%
• Ensemble Median 40%
• Spatial Prediction 40%
• Machine Learning Technique 20%
• Multiple Machine 20%
• Prediction Technique 20%
• Single Prediction 20%
• Spatial Autocorrelation 20%
• Validation Dataset 20%
• Spatial Detail 20%
• Spatial Resolution 20%
• Computational Resource 20%
• Hybrid Approach 20%
• Relative Importance 20%
• Prediction Error 20%

Earth and Planetary Sciences

• Spatial Variation 100%
• Machine Learning 100%
• Soil Organic Carbon 100%
• Environmental Factor 50%
• Soil Property 50%
• Kriging 50%
• Support Vector Machine 33%
• Spatial Resolution 16%
• Autocorrelation 16%
• Soil Profile 16%
• Land Cover 16%
• Geology 16%
• Soils 16%
• Regional Geography 16%
• Bedrock 16%

Mathematics

• Validation Dataset 20%
• Mathematical Complexity 20%