Spatial Prediction Framework: From Point Measurements to Grid-Scale Estimates using Machine Learning models

Talk
In session Artificial Intelligence/ Machine Learning methods in Earth System Sciences , Sept. 3, 2025, 13:30 – 15:15
Exact timing: 14:30 – 14:45
Room info: Lecture Hall

Braack, Malte¹ , Parameswaran, N. K.² , Wallmann, K.²

We present a comprehensive machine learning framework for predicting spatially distributed geographical data from point measurements. The framework takes as input a set of geographical features at a specified grid resolution (e.g., 5 arc-minute scale) and corresponding point measurements with their spatial coordinates and target values. The framework trains and evaluates multiple machine learning models, including both tree-based methods (Random Forest, XGBoost, CatBoost) and deep learning architectures (feed forward neural networks, TabPFN[1]), to identify the optimal predictive model for the given dataset.
The framework incorporates hyperparameter search(depth and width) for deep learning models and systematic parameter search for tree-based models (e.g., number of estimators). This ensures robust model selection and performance optimization across different geographical contexts and data characteristics. The framework outputs the best-performing model along with comprehensive performance metrics and uncertainty estimates.
As a non-trivial application, we demonstrate the framework's effectiveness in predicting total organic carbon (TOC) concentrations[2] and sedimentation rates in the ocean. This involves integrating features from both the sea surface and seafloor, encompassing a diverse array of oceanographic, geological, geographic, biological, and biogeochemical parameters. The framework successfully identifies the most suitable model architecture and hyperparameters for this complex spatial prediction task, providing both high accuracy and reliable uncertainty quantification.

References

[1] Hollmann, N., Müller, S., Purucker, L. et al. Accurate predictions on small data with a tabular foundation model. Nature 637 , 319–326 (2025). https://doi.org/10.1038/s41586-024-08328-6

[2] Parameswaran, N., Gonzalez, E., Burwicz-Galerne, E., Braack, M., & Wallmann, K. (2025). NN-TOC v1: global prediction of total organic carbon in marine sediments using deep neural networks. Geoscientific Model Development, 18(9), 2521–2544.