Articles | Volume 17, issue 15
https://doi.org/10.5194/gmd-17-5897-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-5897-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Methods for assessment of models
| 
07 Aug 2024
Methods for assessment of models |
| 07 Aug 2024
| 07 Aug 2024
kNNDM CV: k-fold nearest-neighbour distance matching cross-validation for map accuracy estimation
Jan Linnenbrink
CORRESPONDING AUTHOR
Institute of Landscape Ecology, University of Münster, Münster, Germany
Carles Milà
Barcelona Institute for Global Health (ISGlobal), Barcelona, Spain
Universitat Pompeu Fabra (UPF), Barcelona, Spain
Marvin Ludwig
Institute of Landscape Ecology, University of Münster, Münster, Germany
Hanna Meyer
Institute of Landscape Ecology, University of Münster, Münster, Germany
Viewed
Total article views: 2,355 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 05 Jul 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,817 | 463 | 75 | 2,355 | 85 | 101 |
- HTML: 1,817
- PDF: 463
- XML: 75
- Total: 2,355
- BibTeX: 85
- EndNote: 101
Total article views: 995 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Aug 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 802 | 164 | 29 | 995 | 39 | 65 |
- HTML: 802
- PDF: 164
- XML: 29
- Total: 995
- BibTeX: 39
- EndNote: 65
Total article views: 1,360 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 05 Jul 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,015 | 299 | 46 | 1,360 | 46 | 36 |
- HTML: 1,015
- PDF: 299
- XML: 46
- Total: 1,360
- BibTeX: 46
- EndNote: 36
Viewed (geographical distribution)
Total article views: 2,355 (including HTML, PDF, and XML)
Thereof 2,353 with geography defined
and 2 with unknown origin.
Total article views: 995 (including HTML, PDF, and XML)
Thereof 995 with geography defined
and 0 with unknown origin.
Total article views: 1,360 (including HTML, PDF, and XML)
Thereof 1,358 with geography defined
and 2 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
17 citations as recorded by crossref.
- Global hotspots of mycorrhizal fungal richness are poorly protected M. Van Nuland et al. 10.1038/s41586-025-09277-4
- Spatio-temporal mapping reveals changes in soil organic carbon stocks across the contiguous United States since 1955 C. Yang et al. 10.1038/s43247-025-02605-6
- Hawai‘i's pelagic longline fishery demonstrates the need to consider multispecies impacts in bluewater time-area closures J. Van Wert et al. 10.1093/icesjms/fsaf111
- An interpretable spatially weighted machine learning approach for revealing spatial nonstationarity impacts of the built environment on air pollution S. Wang et al. 10.1016/j.buildenv.2025.113150
- CycloneWind: A Dynamics-Constrained Deep Learning Model for Tropical Cyclone Wind Field Downscaling Using Satellite Observations Y. Hu et al. 10.3390/rs17183134
- On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction Y. Wang et al. 10.1080/15481603.2025.2460513
- Mapping desert shrub aboveground biomass in the Junggar Basin, Xinjiang, China using quantile regression forest (QRF) X. Yang 10.7717/peerj.19099
- Predicting historical oxygen deficiency areas in the western Baltic Sea: A multi-model approach S. Piehl et al. 10.1016/j.marpolbul.2025.118464
- Interpretable machine learning for academic performance prediction: A SHAP-based analysis of key influencing factors Y. Guan et al. 10.1080/14703297.2025.2532050
- Shapley values reveal geomorphic controls on exposed bedrock-gravel differentiation X. Zhang et al. 10.1016/j.geoderma.2025.117525
- Moving Beyond Temperature Metrics in Coral Bleaching Prediction Using Interpretable Machine Learning M. Cheung et al. 10.1111/geb.70105
- kNNDM CV: k-fold nearest-neighbour distance matching cross-validation for map accuracy estimation J. Linnenbrink et al. 10.5194/gmd-17-5897-2024
- Soil carbon in the world’s tidal marshes T. Maxwell et al. 10.1038/s41467-024-54572-9
- Random forests with spatial proxies for environmental modelling: opportunities and pitfalls C. Milà et al. 10.5194/gmd-17-6007-2024
- High-resolution canopy fuel maps based on GEDI: a foundation for wildfire modeling in Germany J. Heisig et al. 10.1088/2752-664X/adaaf9
- Adopting yield-improving practices to meet maize demand in Sub-Saharan Africa without cropland expansion F. Aramburu-Merlos et al. 10.1038/s41467-024-48859-0
- A review of regularised estimation methods and cross-validation in spatiotemporal statistics P. Otto et al. 10.1214/24-SS150
11 citations as recorded by crossref.
- Global hotspots of mycorrhizal fungal richness are poorly protected M. Van Nuland et al. 10.1038/s41586-025-09277-4
- Spatio-temporal mapping reveals changes in soil organic carbon stocks across the contiguous United States since 1955 C. Yang et al. 10.1038/s43247-025-02605-6
- Hawai‘i's pelagic longline fishery demonstrates the need to consider multispecies impacts in bluewater time-area closures J. Van Wert et al. 10.1093/icesjms/fsaf111
- An interpretable spatially weighted machine learning approach for revealing spatial nonstationarity impacts of the built environment on air pollution S. Wang et al. 10.1016/j.buildenv.2025.113150
- CycloneWind: A Dynamics-Constrained Deep Learning Model for Tropical Cyclone Wind Field Downscaling Using Satellite Observations Y. Hu et al. 10.3390/rs17183134
- On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction Y. Wang et al. 10.1080/15481603.2025.2460513
- Mapping desert shrub aboveground biomass in the Junggar Basin, Xinjiang, China using quantile regression forest (QRF) X. Yang 10.7717/peerj.19099
- Predicting historical oxygen deficiency areas in the western Baltic Sea: A multi-model approach S. Piehl et al. 10.1016/j.marpolbul.2025.118464
- Interpretable machine learning for academic performance prediction: A SHAP-based analysis of key influencing factors Y. Guan et al. 10.1080/14703297.2025.2532050
- Shapley values reveal geomorphic controls on exposed bedrock-gravel differentiation X. Zhang et al. 10.1016/j.geoderma.2025.117525
- Moving Beyond Temperature Metrics in Coral Bleaching Prediction Using Interpretable Machine Learning M. Cheung et al. 10.1111/geb.70105
6 citations as recorded by crossref.
- kNNDM CV: k-fold nearest-neighbour distance matching cross-validation for map accuracy estimation J. Linnenbrink et al. 10.5194/gmd-17-5897-2024
- Soil carbon in the world’s tidal marshes T. Maxwell et al. 10.1038/s41467-024-54572-9
- Random forests with spatial proxies for environmental modelling: opportunities and pitfalls C. Milà et al. 10.5194/gmd-17-6007-2024
- High-resolution canopy fuel maps based on GEDI: a foundation for wildfire modeling in Germany J. Heisig et al. 10.1088/2752-664X/adaaf9
- Adopting yield-improving practices to meet maize demand in Sub-Saharan Africa without cropland expansion F. Aramburu-Merlos et al. 10.1038/s41467-024-48859-0
- A review of regularised estimation methods and cross-validation in spatiotemporal statistics P. Otto et al. 10.1214/24-SS150
Latest update: 08 Oct 2025
Short summary
Estimation of map accuracy based on cross-validation (CV) in spatial modelling is pervasive but controversial. Here, we build upon our previous work and propose a novel, prediction-oriented k-fold CV strategy for map accuracy estimation in which the distribution of geographical distances between prediction and training points is taken into account when constructing the CV folds. Our method produces more reliable estimates than other CV methods and can be used for large datasets.
Estimation of map accuracy based on cross-validation (CV) in spatial modelling is pervasive but...
