arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.03480stat.APcs.LG
收藏

用于物种分布建模中空间-时间模型无偏交叉验证的基础

Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling

Skolkovo Institute of Science and Technology(斯克洛夫诺科学与技术研究所)

Diana Koldasbayeva, Alexey Zaytsev

AI总结:

本文提出基于空间自相关阻塞和外部时间验证的稳健SDM工作流程,以提高物种分布模型在空间和时间转移中的可靠性。

摘要:

评估物种分布模型(SDMs)在现实部署场景中的预测性能需要仔细处理数据中的空间和时间依赖性。交叉验证(CV)是模型评估的标准方法,但其设计强烈影响性能估计的有效性。当SDMs用于空间或时间转移时,随机CV可能导致由于邻近观测之间的空间自相关(SAC)而产生过于乐观的结果。我们对四个机器学习算法(GBM、XGBoost、LightGBM、随机森林)在两个真实世界的存在-缺失数据集上进行基准测试,一个温带植物和一个洄游鱼类,使用多种CV设计:随机、空间、时空、环境和前瞻性验证。评估两种训练数据使用策略(LAST FOLD和RETRAIN),并在每种CV方案中进行超参数调优。使用AUC、MAE和相关性指标在独立的非时间测试集上评估模型性能。随机CV在AUC上高估最多0.16,并产生比空间阻塞替代方案高80%的MAE值。在经验SAC范围内阻塞显著减少了这种偏差。训练策略影响评估结果:LAST FOLD在强SAC下产生更小的验证-测试差异,而RETRAIN在SAC较弱时实现更高的测试AUC。提升的集成模型在空间结构化的CV设计下始终表现最佳。我们推荐基于SAC意识阻塞、阻塞超参数调优和外部时间验证的稳健SDM工作流程,以在空间和时间转移下提高可靠性。

英文摘要:

Evaluating the predictive performance of species distribution models (SDMs) under realistic deployment scenarios requires careful handling of spatial and temporal dependencies in the data. Cross-validation (CV) is the standard approach for model evaluation, but its design strongly influences the validity of performance estimates. When SDMs are intended for spatial or temporal transfer, random CV can lead to overoptimistic results due to spatial autocorrelation (SAC) among neighboring observations. We benchmark four machine learning algorithms (GBM, XGBoost, LightGBM, Random Forest) on two real-world presence-absence datasets, a temperate plant and an anadromous fish, using multiple CV designs: random, spatial, spatio-temporal, environmental, and forward-chaining. Two training data usage strategies (LAST FOLD and RETRAIN) are evaluated, with hyperparameter tuning performed within each CV scheme. Model performance is assessed on independent out-of-time test sets using AUC, MAE, and correlation metrics. Random CV overestimates AUC by up to 0.16 and produces MAE values up to 80 percent higher than spatially blocked alternatives. Blocking at the empirical SAC range substantially reduces this bias. Training strategy affects evaluation outcomes: LAST FOLD yields smaller validation-test discrepancies under strong SAC, while RETRAIN achieves higher test AUC when SAC is weaker. Boosted ensemble models consistently perform best under spatially structured CV designs. We recommend a robust SDM workflow based on SAC-aware blocking, blocked hyperparameter tuning, and external temporal validation to improve reliability under spatial and temporal shifts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑