Data-Centric Machine Learning for Earth Observation: Necessary and Sufficient Features
Preprint
Abstract
The availability of temporal geospatial data in multiple modalities has been extensively leveraged to enhance the performance of machine learning models. While efforts on the design of adequate model architectures are approaching a level of saturation, focusing on a data-centric perspective can complement these efforts to achieve further enhancements in data usage efficiency and model generalization capacities. This work contributes to this direction. We leverage model explanation methods to identify the features crucial for the model to reach optimal performance and the smallest set of features sufficient to achieve this performance. We evaluate our approach on three temporal multimodal geospatial datasets and compare multiple model explanation techniques. Our results reveal that some datasets can reach their optimal accuracy with less than 20% of the temporal instances, while in other datasets, the time series of a single band from a single modality is sufficient.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Common Practices and Taxonomy in Deep Multiview Fusion for Remote Sensing ApplicationsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIACM Computing Surveys, 2023
- Marine big data-driven ensemble learning for estimating global phytoplankton group composition over two decades (1997–2020)Remote Sensing of Environment, 2023
- Pixel-based yield mapping and prediction from Sentinel-2 using spectral indices and neural networksField Crops Research, 2023
- Gene Selection for Cancer Classification using Support Vector MachinesMachine Learning, 2002
- Regression Shrinkage and Selection Via the LassoJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996