论文提出可嵌入 Transformer 的能量平衡防霜冻预报模块 PET-E
A plug-in energy-balance freezing module for transformer frost nowcasting without leaf-sensor inputs
搞农业气象或时序预测的可以看看这篇。它把物理公式直接塞进 Transformer 结构里做霜冻预警,不用叶片传感器也能跑,CSI 0.516 比 LightGBM 的 0.478 强。物理嵌入模型结构这个思路对做可解释预测的人有参考价值。
一篇 arXiv 论文提出 PET-E 模块,把叶片能量平衡物理直接嵌入 Transformer 结构,用于无叶片传感器输入的霜冻预报。机制上,模块用能量平衡温度参考加可学习残差预测叶片温度,再通过一个乘性门控施加随温度变化的概率上限,并数学证明了条件单调性与警报边界。
实验覆盖韩国 19 个站、五个霜冻季、12 个小时级预报时效。在 2025-2026 留出季且无叶片传感器输入的条件下,PET-E 的 lead-mean CSI 达 0.516,超过固定配置的 LightGBM 的 0.478,且 12 个时效全部显著提升;相比未修改的骨干,观测叶片温度不低于 2°C 时的误报比例从 0.087 降到 0.051。
在留出季与 2024-2025 回溯评估中,该模块在 time-token transformer 和 iTransformer 两种骨干上都降低了 Brier 分数与暖表面误报率。在无静态和叶片传感器输入的留出站上,两个配备模块的骨干在全部 12 个时效超过 LightGBM(CSI 分别为 0.468 和 0.467,对 0.437)。论文还区分了把温度信息放在输出通路与注意力机制中的不同收益。
A plug-in energy-balance freezing module for transformer frost nowcasting without leaf-sensor inputs
Frost protection requires local warnings where leaf-sensor inputs are unavailable. In the frost literature we surveyed, physics entered machine-learning models through inputs, numerical-model coupling, or losses, rather than model structure. We develop a transformer-compatible module that embeds leaf energy-balance physics in freezing-probability forecasts: an energy-balance temperature reference and a learned residual predict leaf temperature, which drives a multiplicative gate imposing a temperature-dependent probability cap. We mathematically prove conditional monotonicity and an alarm boundary, and test whether placing the same information in the output pathway or in attention yields different benefits. We evaluated 12 hourly leads at 19 Korean stations over five frost seasons, with and without leaf-sensor inputs. In the 2025-2026 hold-out season without these inputs, our time-token transformer (PET-E) achieved a lead-mean critical success index (CSI) of 0.516 versus 0.478 for fixed-configuration, joint-lead LightGBM, with significant gains at all 12 leads, and the fraction of alarms at observed leaf temperatures of at least 2 degrees C fell from 0.087 to 0.051 relative to the unmodified backbone. Across the hold-out and a retrospective 2024-2025 evaluation, the module reduced Brier scores and warm-surface alarm fractions in both the time-token transformer and iTransformer, with no significant CSI decrease at any lead. At held-out stations without static or leaf-sensor inputs, both module-equipped backbones exceeded LightGBM at all 12 leads (CSI 0.468 and 0.467 versus 0.437). In the time-token backbone, the temperature pathway reduced this alarm fraction in all four settings, whereas the attention prior increased CSI in three. These findings link an explicit temperature-dependent probability cap to improved forecasts and distinguish output-side from attention-based embedding.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include PET-E, iTransformer, LightGBM, time series forecasting.
Source attribution: curated from arXiv cs.LG (@Juyeon Kim, Chaeyeon Yi, Yun Am Seo).