|
Project properties |
|
| Title | National Scale Predictions of Soil Organic Matter: Mechanistic vs. Machine Learning Models |
| Group | Soil Geography and Landscape |
| Project type | thesis |
| Credits | 36 |
| Supervisor(s) | Anatol Helfenstein (SGL), Titia Mulder (SGL), Chantal Hendriks (WEnR) |
| Examiner(s) | Gerard Heuvelink |
| Contact info | anatol.helfenstein@wur.nl |
| Begin date | 2022/01/01 |
| End date | |
| Description | Soil Organic Matter (SOM) plays an important role in climate change mitigation and contributes to soil fertility by enhancing the availability of plant nutrients, improving moisture retention, stabilizing soil structure and increasing permeability among other factors. Therefore, national-scale predictions of SOM are essential for land users and policy makers. However, the chosen modelling approach may yield in substantially different estimations of SOM. To test this hypothesis and explore the advantages and disadvantages of different approaches, this research aims to compare the performance of two established approaches currently used in the Netherlands: a statistical and machine learning model (BIS-4D {https://www.wur.nl/en/project/Developing-a-high-resolution-4-dimensional-soil-modelling-and-mapping-platform-for-the-Netherlands-BIS-4D.htm}) with a mechanistic model (MITERRA-NL, which is derived from MITERRA-Europe {https://doi.org/10.2134/jeq2008.0108}). |
| Used skills | R scripting, (open source) GIS |
| Requirements | Basic knowledge of R scripting and GIS |