Challenges in data-driven geospatial modeling for environmental research and practice.
Where this comes from
- Record sourced from PubMed, PMID 39702456.
- Also identified by DOI 10.1038/s41467-024-55240-8 and PMC identifier 11659326.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Machine learning-based geospatial applications offer unique opportunities for environmental monitoring due to domains and scales adaptability and computational efficiency. However, the specificity of environmental data introduces biases in straightforward implementations. We identify a streamlined pipeline to enhance model accuracy, addressing issues like imbalanced data, spatial autocorrelation, prediction errors, and the nuances of model generalization and uncertainty estimation. We examine tools and techniques for overcoming these obstacles and provide insights into future geospatial AI developments. A big picture of the field is completed from advances in data processing in general, including the demands of industry-related solutions relevant to outcomes of applied sciences.