arXiv：cs.LG· Kursat Komurcu, Linas Petkevicius·· 4 小时前AI 评分32
用进化架构搜索改进 Sentinel-2 湖泊叶绿素-a 预测
Evolutionary Architecture Search for Chlorophyll-$a$ Prediction in Lakes using Sentinel-2
AI 导读
研究以已发表的 Sentinel-2 藻华分类器为基准，在任务、特征和湖泊级训练/测试划分不变的前提下，用正则化进化搜索扩展的多层感知机空间，仅按内层交叉验证 AUC 选型。
正文
Abstract: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: this https URL.
| Comments: | Accepted at AutoML4EO 2026 (non-archival AutoML conference workshop). 4 pages + references. this https URL |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.10496 [cs.NE] |
| (or arXiv:2610.10496v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10496 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Linas Petkevičius [view email]
[v1]
Wed, 7 Oct 2026 17:47:17 UTC (12 KB)
来源：arXiv：cs.LG · arxiv.org