3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning
Abstract Soil organic C (SOC) and soil moisture (SM) affect the agricultural productivity of soils. For sustainable food production, knowledge of the horizontal as well as vertical variability of SOC and SM at field scale is crucial. Machine learning models using depth‐related data from multiple ele...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Vadose Zone Journal |
| Online Access: | https://doi.org/10.1002/vzj2.20062 |
| _version_ | 1831678387701153792 |
|---|---|
| author | Tobias Rentschler Ulrike Werban Mario Ahner Thorsten Behrens Philipp Gries Thomas Scholten Sandra Teuber Karsten Schmidt |
| author_facet | Tobias Rentschler Ulrike Werban Mario Ahner Thorsten Behrens Philipp Gries Thomas Scholten Sandra Teuber Karsten Schmidt |
| author_sort | Tobias Rentschler |
| collection | DOAJ |
| description | Abstract Soil organic C (SOC) and soil moisture (SM) affect the agricultural productivity of soils. For sustainable food production, knowledge of the horizontal as well as vertical variability of SOC and SM at field scale is crucial. Machine learning models using depth‐related data from multiple electromagnetic induction (EMI) sensors and a gamma‐ray spectrometer can provide insights into this variability of SOC and SM. In this work, we applied weighted conditioned Latin hypercube sampling to calculate 25 representative soil profile locations based on geophysical measurements on the surveyed agricultural field, for sampling and modeling. Ten additional random profiles were used for independent model validation. Soil samples were taken from four equal depth increments of 15 cm each. These were used to approximate polynomial and exponential functions to reproduce the vertical trends of SOC and SM as soil depth functions. We modeled the function coefficients of the soil depth functions spatially with Cubist and random forests with the geophysical measurements as environmental covariates. The spatial prediction of the depth functions provides three‐dimensional (3D) maps of the field scale. The main findings are (a) the 3D models of SOC and SM had low errors; (b) the polynomial function provided better results than the exponential function, as the vertical trends of SOC and SM did not decrease uniformly; and (c) the spatial prediction of SOC and SM with Cubist provided slightly lower error than with random forests. Hence, we recommend modeling the second‐degree polynomial with Cubist for 3D prediction of SOC and SM at field scale. |
| first_indexed | 2024-12-20T04:58:49Z |
| format | Article |
| id | doaj.art-1710d72746c6419f89d9a855386e3545 |
| institution | Directory Open Access Journal |
| issn | 1539-1663 |
| language | English |
| last_indexed | 2024-12-20T04:58:49Z |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Vadose Zone Journal |
| spelling | doaj.art-1710d72746c6419f89d9a855386e35452022-12-21T19:52:37ZengWileyVadose Zone Journal1539-16632020-01-01191n/an/a10.1002/vzj2.200623D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learningTobias Rentschler0Ulrike Werban1Mario Ahner2Thorsten Behrens3Philipp Gries4Thomas Scholten5Sandra Teuber6Karsten Schmidt7Dep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Monitoring and Exploration Technologies Helmholtz Centre for Environmental Research–UFZ Permoserstr. 15 Leipzig 04318 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyDep. of Geosciences Chair of Soil Science and Geomorphology Univ. of Tübingen Rümelinstr. 19‐23 Tübingen 72070 GermanyAbstract Soil organic C (SOC) and soil moisture (SM) affect the agricultural productivity of soils. For sustainable food production, knowledge of the horizontal as well as vertical variability of SOC and SM at field scale is crucial. Machine learning models using depth‐related data from multiple electromagnetic induction (EMI) sensors and a gamma‐ray spectrometer can provide insights into this variability of SOC and SM. In this work, we applied weighted conditioned Latin hypercube sampling to calculate 25 representative soil profile locations based on geophysical measurements on the surveyed agricultural field, for sampling and modeling. Ten additional random profiles were used for independent model validation. Soil samples were taken from four equal depth increments of 15 cm each. These were used to approximate polynomial and exponential functions to reproduce the vertical trends of SOC and SM as soil depth functions. We modeled the function coefficients of the soil depth functions spatially with Cubist and random forests with the geophysical measurements as environmental covariates. The spatial prediction of the depth functions provides three‐dimensional (3D) maps of the field scale. The main findings are (a) the 3D models of SOC and SM had low errors; (b) the polynomial function provided better results than the exponential function, as the vertical trends of SOC and SM did not decrease uniformly; and (c) the spatial prediction of SOC and SM with Cubist provided slightly lower error than with random forests. Hence, we recommend modeling the second‐degree polynomial with Cubist for 3D prediction of SOC and SM at field scale.https://doi.org/10.1002/vzj2.20062 |
| spellingShingle | Tobias Rentschler Ulrike Werban Mario Ahner Thorsten Behrens Philipp Gries Thomas Scholten Sandra Teuber Karsten Schmidt 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning Vadose Zone Journal |
| title | 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| title_full | 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| title_fullStr | 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| title_full_unstemmed | 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| title_short | 3D mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| title_sort | 3d mapping of soil organic carbon content and soil moisture with multiple geophysical sensors and machine learning |
| url | https://doi.org/10.1002/vzj2.20062 |
| work_keys_str_mv | AT tobiasrentschler 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT ulrikewerban 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT marioahner 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT thorstenbehrens 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT philippgries 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT thomasscholten 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT sandrateuber 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning AT karstenschmidt 3dmappingofsoilorganiccarboncontentandsoilmoisturewithmultiplegeophysicalsensorsandmachinelearning |