用时间扭曲迁移学习，让10小时燃料湿度模型预测其他类型燃料湿度。
Transfer Learning for Dead Fuel Moisture Prediction Using Time-Warping Recurrent Neural Networks
- 通过时间扭曲调整LSTM模型的动态变化节奏，实现跨燃料类别的迁移。
- 在俄克拉荷马州实地数据上验证，对1小时、100小时和1000小时燃料均有效。
- 适合气象与火灾预警研究者，尤其关注少样本燃料类型的建模需求。
本文提出一种时间扭曲迁移学习方法，利用带有长短期记忆（LSTM）层的循环神经网络（RNN），通过时序重标定其学习到的动力学特性，实现不同燃料湿度类别间的任务迁移。燃料湿度含量（FMC）按特征滞留时间划分为理想化类别：10小时燃料有大量实时观测数据来自气象站传感器，而其他类别在时空上数据稀疏。本研究采用迁移学习，将预训练于10小时燃料湿度的RNN用于预测1小时、100小时及1000小时燃料的湿度。方法在俄克拉荷马州一项标志性野外研究数据上进行了验证，该数据曾用于校准最先进的Nelson燃料湿度模型。
原文摘要 · Abstract (English)
This paper proposes a time-warping transfer learning method, a technique for temporally rescaling the learned dynamics of a recurrent neural network (RNN) with a Long Short-Term Memory (LSTM) layer to enable task transfer across fuel moisture classes. Fuel moisture content (FMC) is divided into idealized classes based on characteristic lag time. Large quantities of real-time data are available for 10h fuels from sensors on weather stations, but observations of other fuel classes are sparse in space and time. We use transfer learning to adapt an RNN pretrained on 10h FMC to predict FMC for 1h, 100h, and 1000h fuels. We validate this method using data from a landmark field study conducted in Oklahoma that was used to calibrate the state-of-the-art Nelson fuel moisture model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。