Uncertainty Quantification of Soil Organic Carbon Estimation from Remote Sensing Data with Conformal Prediction

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 3; p. 438
• Main Authors: Kakhani, Nafiseh, Alamdar, Setareh, Kebonye, Ndiye Michael, Amani, Meisam, Scholten, Thomas
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2024
• Subjects: Accuracy; Algorithms; Carbon; Carbon content; conformal prediction; data collection; digital soil mapping; ecosystems; Emissions; Estimation; Europe; Greenhouse gases; Machine learning; Methods; Model accuracy; model uncertainty; Monte Carlo simulation; Neural networks; Nutrient cycles; Organic carbon; Organic soils; prediction; Predictions; Remote sensing; Sensors; soil organic carbon; soil quality; Soil sciences; Soils; Statistical analysis; Uncertainty; uncertainty quantification; Vegetation; Germany; Europe
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16030438

Soil organic carbon (SOC) contents and stocks provide valuable insights into soil health, nutrient cycling, greenhouse gas emissions, and overall ecosystem productivity. Given this, remote sensing data coupled with advanced machine learning (ML) techniques have eased SOC level estimation while revealing its patterns across different ecosystems. However, despite these advances, the intricacies of training reliable and yet certain SOC models for specific end-users remain a great challenge. To address this, we need robust SOC uncertainty quantification techniques. Here, we introduce a methodology that leverages conformal prediction to address the uncertainty in estimating SOC contents while using remote sensing data. Conformal prediction generates statistically reliable uncertainty intervals for predictions made by ML models. Our analysis, performed on the LUCAS dataset in Europe and incorporating a suite of relevant environmental covariates, underscores the efficacy of integrating conformal prediction with another ML model, specifically random forest. In addition, we conducted a comparative assessment of our results against prevalent uncertainty quantification methods for SOC prediction, employing different evaluation metrics to assess both model uncertainty and accuracy. Our methodology showcases the utility of the generated prediction sets as informative indicators of uncertainty. These sets accurately identify samples that pose prediction challenges, providing valuable insights for end-users seeking reliable predictions in the complexities of SOC estimation.