Evolution-based Feature Selection for Predicting Dissolved Oxygen Concentrations in Lakes
This work addresses the need for precise feature selection in environmental monitoring for lake ecosystems, representing an incremental advancement in evolutionary algorithms for domain-specific applications.
The paper tackles the problem of predicting dissolved oxygen concentrations in lakes by developing the Multi-population Cognitive Evolutionary Search (MCES) algorithm for feature interaction selection, resulting in accurate predictions with few labels and revealing phenological patterns across diverse lake types.
Accurate prediction of dissolved oxygen (DO) concentrations in lakes requires a comprehensive study of phenological patterns across ecosystems, highlighting the need for precise selection of interactions amongst external factors and internal physical-chemical-biological variables. This paper presents the Multi-population Cognitive Evolutionary Search (MCES), a novel evolutionary algorithm for complex feature interaction selection problems. MCES allows models within every population to evolve adaptively, selecting relevant feature interactions for different lake types and tasks. Evaluated on diverse lakes in the Midwestern USA, MCES not only consistently produces accurate predictions with few observed labels but also, through gene maps of models, reveals sophisticated phenological patterns of different lake types, embodying the innovative concept of "AI from nature, for nature".