Potential of Domain Adaptation in Machine Learning in Ecology and Hydrology to Improve Model Extrapolability

arXiv:2403.11331v1 Announce Type: cross
Abstract: Due to the heterogeneity of the global distribution of ecological and hydrological ground-truth observations, machine learning models can have limited adaptability when applied to unknown locations, which is referred to as weak extrapolability. Domain adaptation techniques have been widely used in machine learning domains such as image classification, which can improve the model generalization ability by adjusting the difference or inconsistency of the domain distribution between the training and test sets. However, this approach has …

abstract adaptability arxiv cs.lg distribution domain domain adaptation ecology global ground-truth hydrology locations machine machine learning machine learning models physics.data-an physics.geo-ph truth type