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

被引:1
|
作者
Kakhani, Nafiseh [1 ,2 ]
Alamdar, Setareh [3 ]
Kebonye, Ndiye Michael [1 ,4 ]
Amani, Meisam [5 ]
Scholten, Thomas [1 ,2 ,4 ]
机构
[1] Univ Tubingen, Dept Geosci Soil Sci & Geomorphol, D-72070 Tubingen, Germany
[2] Univ Tubingen, CRC RessourceCultures 1070, D-72070 Tubingen, Germany
[3] Univ Guelph, Sch Environm Sci, 50 Stone Rd East, Guelph, ON N1G 2W1, Canada
[4] Univ Tubingen, DFG Cluster Excellence Machine Learning, D-72070 Tubingen, Germany
[5] WSP Environm & Infrastructure Canada Ltd, Ottawa, ON K2E 7L5, Canada
关键词
uncertainty quantification; conformal prediction; soil organic carbon; digital soil mapping; remote sensing; CLIMATE; FOREST; MAP;
D O I
10.3390/rs16030438
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
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.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Remote Sensing Techniques for Soil Organic Carbon Estimation: A Review
    Angelopoulou, Theodora
    Tziolas, Nikolaos
    Balafoutis, Athanasios
    Zalidis, George
    Bochtis, Dionysis
    [J]. REMOTE SENSING, 2019, 11 (06)
  • [2] Prediction of soil organic carbon by hyperspectral remote sensing imagery
    Lu, Peng
    Niu, Zheng
    Li, Linghao
    [J]. 2012 THIRD GLOBAL CONGRESS ON INTELLIGENT SYSTEMS (GCIS 2012), 2012, : 291 - 293
  • [3] Soil organic carbon estimation using remote sensing data-driven machine learning
    Chen, Qi
    Wang, Yiting
    Zhu, Xicun
    [J]. PEERJ, 2024, 12
  • [4] Prediction of soil moisture from remote sensing data
    Taktikou, Eftychia
    Bourazanis, George
    Papaioannou, Georgia
    Kerkides, Petros
    [J]. INTERNATIONAL CONFERENCE ON EFFICIENT & SUSTAINABLE WATER SYSTEMS MANAGEMENT TOWARD WORTH LIVING DEVELOPMENT (2ND EWAS 2016), 2016, 162 : 309 - 316
  • [5] Estimation of soil organic carbon in agricultural fields: A remote sensing approach
    Madugundu, R.
    Al-Gaadi, K. A.
    Tola, E.
    Edrris, M.
    Edrees, H.
    Alameen, A.
    Fulleros, R. B.
    [J]. JOURNAL OF ENVIRONMENTAL BIOLOGY, 2022, 43 (01): : 73 - 84
  • [6] Uncertainty quantification for direction-of-arrival estimation with conformal prediction
    Khurjekar, Ishan D.
    Gerstoft, Peter
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2023, 154 (02): : 979 - 990
  • [7] Mapping and prediction of soil organic carbon by an advanced geostatistical technique using remote sensing and terrain data
    Mallik, Santanu
    Bhowmik, Tridip
    Mishra, Umesh
    Paul, Niladri
    [J]. GEOCARTO INTERNATIONAL, 2022, 37 (08) : 2198 - 2214
  • [8] Proxies for soil organic carbon derived from remote sensing
    Rasel, S. M. M.
    Groen, T. A.
    Hussin, Y. A.
    Diti, I. J.
    [J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2017, 59 : 157 - 166
  • [9] Open Remote Sensing Data in Digital Soil Organic Carbon Mapping: A Review
    Radocaj, Dorijan
    Gasparovic, Mateo
    Jurisic, Mladen
    [J]. AGRICULTURE-BASEL, 2024, 14 (07):
  • [10] Soil Organic Carbon Mapping Using Multispectral Remote Sensing Data: Prediction Ability of Data with Different Spatial and Spectral Resolutions
    Zizala, Daniel
    Minarik, Robert
    Zadorova, Tereza
    [J]. REMOTE SENSING, 2019, 11 (24)