Evolutionary Architecture Search for Chlorophyll-$a$ Prediction in Lakes using Sentinel-2

Özetle: Small tabular datasets with expert-designed spectral features are the norm in operational Earth observation, and the networks applied to them are typically hand-designed.

Özet

Small tabular datasets with expert-designed spectral features are the norm in operational Earth observation, and the networks applied to them are typically hand-designed. We revisit one such published model — a Sentinel-2 algal bloom classifier — and ask what architecture search adds, holding the task, the features and the lake-level train/test split of the original study fixed. Searching an extended multilayer-perceptron space with regularized evolution, and selecting on inner-cross-validation AUC only, we find networks that improve held-out AUC from 0.790 to 0.820 and accuracy from 0.733 to 0.748 while using 409 trainable parameters, 26 times fewer than the strongest hand-designed reference. The search converges on a consistent recipe — a single narrow layer, RMS normalisation, $tanh$ activation, step-decayed RMSprop and weight averaging — that a practitioner would be unlikely to reach by default. At 1.6,kB the resulting model is small enough to serve as an onboard screening trigger, which is the setting that motivates the work. Code: https://github.com/VU-AIML/automl4eo-bloom-nas.

Orijinal Özet (İngilizce)

Small tabular datasets with expert-designed spectral features are the norm in operational Earth observation, and the networks applied to them are typically hand-designed. We revisit one such published model — a Sentinel-2 algal bloom classifier — and ask what architecture search adds, holding the task, the features and the lake-level train/test split of the original study fixed. Searching an extended multilayer-perceptron space with regularized evolution, and selecting on inner-cross-validation AUC only, we find networks that improve held-out AUC from 0.790 to 0.820 and accuracy from 0.733 to 0.748 while using 409 trainable parameters, 26 times fewer than the strongest hand-designed reference. The search converges on a consistent recipe — a single narrow layer, RMS normalisation, $tanh$ activation, step-decayed RMSprop and weight averaging — that a practitioner would be unlikely to reach by default. At 1.6,kB the resulting model is small enough to serve as an onboard screening trigger, which is the setting that motivates the work. Code: https://github.com/VU-AIML/automl4eo-bloom-nas.

Kaynak: arXiv:2610.10496 · PDF