Investigating Moran’s I Properties for Spatial Machine Learning: A Preliminary Analysis
Jakub Nowosad
Institute of Landscape Ecology, University of Münster, Heisenbergstraße 2, Münster, 48149, Germany
Institute of Geoecology and Geoinformation, Adam Mickiewicz University, B. Krygowskiego 10, Poznań, 61-680, Poland
Hanna Meyer
Institute of Landscape Ecology, University of Münster, Heisenbergstraße 2, Münster, 48149, Germany
Related authors
Jakub Nowosad
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4-W12-2024, 127–133, https://doi.org/10.5194/isprs-archives-XLVIII-4-W12-2024-127-2024, https://doi.org/10.5194/isprs-archives-XLVIII-4-W12-2024-127-2024, 2024
J. Nowosad, T. F. Stepinski, and M. Iwicki
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4-W1-2022, 337–344, https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-337-2022, https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-337-2022, 2022
Fabian Lukas Schumacher, Christian Knoth, Marvin Ludwig, and Hanna Meyer
EGUsphere, https://doi.org/10.5194/egusphere-2024-2730, https://doi.org/10.5194/egusphere-2024-2730, 2024
Short summary
Short summary
Machine learning is increasingly used in environmental sciences for spatial predictions, but its effectiveness is challenged when models are applied beyond the areas they were trained on. We propose a Local Training Data Point Density (LPD) approach that considers how well a model's environment is represented by training data. This method provides a valuable tool for evaluating model applicability and uncertainties, crucial for broader scientific and practical applications.
Carles Milà, Marvin Ludwig, Edzer Pebesma, Cathryn Tonne, and Hanna Meyer
Geosci. Model Dev., 17, 6007–6033, https://doi.org/10.5194/gmd-17-6007-2024, https://doi.org/10.5194/gmd-17-6007-2024, 2024
Short summary
Short summary
Spatial proxies, such as coordinates and distances, are often used as predictors in random forest models for predictive mapping. In a simulation and two case studies, we investigated the conditions under which their use is appropriate. We found that spatial proxies are not always beneficial and should not be used as a default approach without careful consideration. We also provide insights into the reasons behind their suitability, how to detect them, and potential alternatives.
Jan Linnenbrink, Carles Milà, Marvin Ludwig, and Hanna Meyer
Geosci. Model Dev., 17, 5897–5912, https://doi.org/10.5194/gmd-17-5897-2024, https://doi.org/10.5194/gmd-17-5897-2024, 2024
Short summary
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.
Jakub Nowosad
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4-W12-2024, 127–133, https://doi.org/10.5194/isprs-archives-XLVIII-4-W12-2024-127-2024, https://doi.org/10.5194/isprs-archives-XLVIII-4-W12-2024-127-2024, 2024
J. Nowosad, T. F. Stepinski, and M. Iwicki
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-4-W1-2022, 337–344, https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-337-2022, https://doi.org/10.5194/isprs-archives-XLVIII-4-W1-2022-337-2022, 2022
M. Ludwig, J. Bahlmann, E. Pebesma, and H. Meyer
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 135–141, https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-135-2022, https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-135-2022, 2022
Hanna Meyer, Marwan Katurji, Florian Detsch, Fraser Morgan, Thomas Nauss, Pierre Roudier, and Peyman Zawar-Reza
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2019-215, https://doi.org/10.5194/essd-2019-215, 2019
Preprint withdrawn
Short summary
Short summary
Air temperature is an important baseline parameter for terrestrial Antarctica in the context of patterns and processes in climatology, hydrology or ecology. In this paper, we present AntAir, a new dataset of gridded air temperatures in 1 km spatial and daily temporal resolution that is available since 2003. AntAir was created by modelling daily air temperature from MODIS satellite-based land surface temperature using machine learning algorithms and measurements from 70 weather stations.
Hanna Meyer, Johannes Drönner, and Thomas Nauss
Atmos. Meas. Tech., 10, 2009–2019, https://doi.org/10.5194/amt-10-2009-2017, https://doi.org/10.5194/amt-10-2009-2017, 2017
Short summary
Short summary
A spatially explicit mapping of rainfall is required for southern Africa but obtaining accurate estimates is still a challenging task. We estimated hourly rainfall based on optical satellite data and neural networks. The results indicated that the majority of rainfall events could be captured by the model, but with a clear tendency to overestimate rainfall. Despite being a comparably simple approach, the presented rainfall retrieval could outperform a complex global rainfall product.