Transferability of Covariates to Predict Soil Organic Carbon in Cropland Soils

被引:19
作者
Broeg, Tom [1 ,2 ]
Blaschek, Michael [3 ]
Seitz, Steffen [2 ]
Taghizadeh-Mehrjardi, Ruhollah [2 ,4 ]
Zepp, Simone [5 ]
Scholten, Thomas [2 ,4 ,6 ]
机构
[1] Thunen Inst Farm Econ, Bundesallee 63, D-38116 Braunschweig, Germany
[2] Univ Tubingen, Dept Geosci Soil Sci & Geomorphol, D-72070 Tubingen, Germany
[3] State Author Geol Resources & Min, Albertstr 5, D-79104 Freiburg, Germany
[4] Univ Tubingen, CRC 1070 Ressource Culture, D-72070 Tubingen, Germany
[5] German Aerosp Ctr DLR, German Remote Sensing Data Ctr DFD, Muenchener Str 20, D-82234 Wessling, Germany
[6] Univ Tubingen, DFG Cluster Excellence Machine Learning, D-72070 Tubingen, Germany
关键词
machine learning; digital soil mapping; soil organic carbon; model transfer; extrapolation; soil reflectance composite; legacy soil maps; Baden-Wurttemberg; Bavaria; SPATIAL PREDICTION; EXTRAPOLATION; GERMANY;
D O I
10.3390/rs15040876
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Precise knowledge about the soil organic carbon (SOC) content in cropland soils is one requirement to design and execute effective climate and food policies. In digital soil mapping (DSM), machine learning algorithms are used to predict soil properties from covariates derived from traditional soil mapping, digital elevation models, land use, and Earth observation (EO). However, such DSM models are trained for a specific dataset and region and have so far only allowed limited general statements to be made that would enable the models to be transferred to different regions. In this study, we test the transferability of SOC models for cropland soils using five different covariate groups: multispectral soil reflectance composites (satellite), soil legacy data (soil), digital elevation model derivatives (terrain), climate parameters (climate), and combined models (combined). The transferability was analyzed using data from two federal states in southern Germany: Bavaria and Baden-Wuerttemberg. First, baseline models were trained for each state with combined models performing best in both cases (R-2 = 0.68/0.48). Next, the models were transferred and tested with soil samples from the other state whose data were not used during model calibration. Only satellite and combined models were transferable, but accuracy declined in both cases. In the final step, models were trained with samples from both states (mixed-data models) and applied to each state separately. This process significantly improved the accuracies of satellite, terrain, and combined models, while it showed no effect on climate models and decreased the models based on soil covariates. The experiment underlines the importance of EO for the transfer and extrapolation of DSM models.
引用
收藏
页数:25
相关论文
共 77 条
[21]   Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran [J].
Emadi, Mostafa ;
Taghizadeh-Mehrjardi, Ruhollah ;
Cherati, Ali ;
Danesh, Majid ;
Mosavi, Amir ;
Scholten, Thomas .
REMOTE SENSING, 2020, 12 (14)
[22]  
EORC J., 2021, ALOS World, V1, P1
[23]   Spatiotemporal Assessment of Soil Organic Carbon Change Using Machine-Learning in Arid Regions [J].
Fathizad, Hassan ;
Taghizadeh-Mehrjardi, Ruhollah ;
Ardakani, Mohammad Ali Hakimzadeh ;
Zeraatpisheh, Mojtaba ;
Heung, Brandon ;
Scholten, Thomas .
AGRONOMY-BASEL, 2022, 12 (03)
[24]   Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: A case study in Iran [J].
Fathololoumi, Solmaz ;
Vaezi, Ali Reza ;
Alavipanah, Seyed Kazem ;
Ghorbani, Ardavan ;
Saurette, Daniel ;
Biswas, Asim .
SCIENCE OF THE TOTAL ENVIRONMENT, 2020, 721
[25]  
Fryda Tomas, 2024, CRAN
[26]  
GDAL/OGR, 2022, CONTR GDAL OGR GEOSP
[27]   Emerging technologies for in situ measurement of soil carbon [J].
Gehl, Ronald J. ;
Rice, Charles W. .
CLIMATIC CHANGE, 2007, 80 (1-2) :43-54
[28]   Soil organic carbon estimation using VNIR-SWIR spectroscopy: The effect of multiple sensors and scanning conditions [J].
Gholizadeh, Asa ;
Neumann, Carsten ;
Chabrillat, Sabine ;
van Wesemael, Bas ;
Castaldi, Fabio ;
Boruvka, Lubos ;
Sanderman, Jonathan ;
Klement, Ales ;
Hohmann, Christian .
SOIL & TILLAGE RESEARCH, 2021, 211
[29]  
Guanter L., 2016, EnMAP Science Plan, DOI [10.2312/enmap.2016.006, DOI 10.2312/ENMAP.2016.006]
[30]   Mapping soil organic carbon stock by hyperspectral and time-series multispectral remote sensing images in low-relief agricultural areas [J].
Guo, Long ;
Sun, Xiaoru ;
Fu, Peng ;
Shi, Tiezhu ;
Dang, Lina ;
Chen, Yiyun ;
Linderman, M. ;
Zhang, Ganlin ;
Zhang, Yu ;
Jiang, Qinghu ;
Zhang, Haitao ;
Zeng, Chen .
GEODERMA, 2021, 398