Advancing provenance assignment using machine learning and time series analysis of chemical chronologies in archival tissues

Accurately assigning the provenance of organisms is critical for understanding ecological connectivity and guiding effective conservation and management. Natural chemical chronologies stored in metabolically inert, incrementally growing tissues (e.g., otoliths) provide a powerful tool for this purpose. However, traditional approaches face biological challenges (e.g., dispersal, maternal effects), collapse chronological data into summary metrics, and rely on subjective interpretation—limiting their accuracy and scalability. We present a novel, flexible framework that integrates machine learning, time-series analysis, and ensemble modeling to improve provenance assignment from archival tissue chemistry. Using otolith 87Sr/86Sr profiles from 17 natal sources of California Central Valley Chinook salmon (Oncorhynchus tshawytscha), we moved beyond conventional summary-based methods by developing fully automated time-series feature extraction, explicit time-series classification (includin..., , # Advancing provenance assignment using machine learning and time series analysis of chemical chronologies in archival tissues

Dataset DOI: [10.5061/dryad.3bk3j9kz3](10.5061/dryad.3bk3j9kz3)

## Description of the data and file structure

This README was generated on 2025-10-27 by K Arai.

**Author (Name, Institution, Email):**
K. Arai, University of California Davis, [[e-mail]](mailto:[e-mail])

This README is in reference to the data sets and R codes (.Rmd) needed to recreate the figures and analyses in the manuscript *“Advancing Provenance Assignment using Machine Learning and Time Series Analysis of Chemical Chronologies in Archival Tissues”*, submitted by K Arai.

There are four major analyses within the manuscript. The first script `01_cross_validation_2025-10-27.Rmd` compares the performance of different assignment models through cross-validation. The second script `02_unknown_juvenile_assignment_2025-10-27.Rmd` assigns natal origin to real-world, wild unknow...,

准确确定生物的生源归属，对于理解生态连通性与指导高效保护管理工作至关重要。储存在代谢惰性、渐进生长组织（例如耳石（otoliths））中的天然化学年代序列，为此提供了强有力的研究工具。然而，传统方法面临诸多生物学挑战（例如扩散效应、母体效应），会将年代学数据简化为汇总统计量，且依赖主观解读——这极大限制了其准确性与可扩展性。我们提出了一种新颖且灵活的分析框架，整合机器学习、时间序列分析与集成建模，以优化基于存档组织化学的生源溯源任务。本研究使用来自加利福尼亚中央谷奇努克鲑鱼（*Oncorhynchus tshawytscha*）17个出生地种群的耳石87Sr/86Sr剖面数据，摒弃了传统的基于汇总统计的分析方法，开发了全自动的时间序列特征提取方案与显式时间序列分类方法（包括……，# 推进基于存档组织化学年代序列的机器学习与时间序列分析以优化生源溯源）。

数据集DOI: [10.5061/dryad.3bk3j9kz3](10.5061/dryad.3bk3j9kz3)

## 数据与文件结构说明
本README文档于2025年10月27日由K Arai生成。
**作者（姓名、机构、邮箱）：**
K. Arai，加利福尼亚大学戴维斯分校，[[e-mail]](mailto:[e-mail])
本说明文档对应复现论文《推进基于存档组织化学年代序列的机器学习与时间序列分析以优化生源溯源（Advancing Provenance Assignment using Machine Learning and Time Series Analysis of Chemical Chronologies in Archival Tissues）》（由K Arai提交）所需的数据集与R代码（.Rmd格式文件）。
该论文包含四项核心分析内容。首个脚本`01_cross_validation_2025-10-27.Rmd`通过交叉验证对比不同溯源模型的性能表现。第二个脚本`02_unknown_juvenile_assignment_2025-10-27.Rmd`用于对野生未知幼体进行出生地归属分类（原文截断）……