STELLAR: 面向长尾物种分布建模的时空环境学习与潜在对齐精炼
STELLAR: Spatio-Temporal Environmental Learning with Latent Alignment and Refinement for Long-Tailed Species Distribution Modeling
AI总结:
提出STELLAR框架,通过图-时间编码器、上下文锚定潜在对齐和不平衡感知解码模块,联合优化动态栖息地上下文和群落结构,有效解决物种分布建模中的时空耦合与长尾不平衡问题。
摘要:
联合物种分布建模(JSDM)是生物多样性监测和保护规划的关键工具。然而,准确的JSDM面临两个耦合挑战:环境驱动因素和物种分布本质上是时空的,而物种共现模式表现出复杂的非线性群落结构以及由稀有物种导致的严重长尾不平衡。现有方法通常孤立地处理这些因素,从静态协变量中学习或忽略动态群落结构的历史轨迹。为克服这些限制,我们提出STELLAR(时空环境学习与潜在对齐精炼),一种新颖的框架,学习一个共享潜在空间,其中动态栖息地上下文和群落结构被联合优化。我们的方法整合了三个互补组件:(1)图-时间编码器,采用图注意力和循环单元来聚合空间邻域效应并捕捉环境上下文和群落结构的共同演化历史动态;(2)上下文锚定潜在对齐机制,利用标签激活的混合先验和监督对比学习结构化潜在空间,基于共享环境偏好主动聚类物种;(3)不平衡感知解耦解码模块,利用非对称损失聚焦于困难稀有物种样本的学习,防止长尾中的模式崩溃。在领域专家精心整理的大规模eBird数据集上的实验表明,我们的框架显著优于最先进的基线,特别是在预测稀有物种和揭示可解释的物种相互作用方面。
英文摘要:
Joint Species Distribution Modeling (JSDM) is a key enabler for biodiversity monitoring and conservation planning. However, accurate JSDM faces two coupled challenges: environmental drivers and species distributions are inherently spatio-temporal, while species co-occurrence patterns exhibit complex non-linear community structure and severe long-tail imbalance driven by rare species. Existing approaches often address these factors in isolation, learning from static covariates or neglecting the historical trajectories of dynamic community structure. To overcome these limitations, we propose STELLAR (Spatio-Temporal Environmental Learning with Latent Alignment and Refinement), a novel framework that learns a shared latent space where dynamic habitat context and community structure are optimized jointly. Our approach integrates three complementary components: (1) a Graph-Temporal Encoder that employs graph attention and recurrent units to aggregate spatial neighborhood effects and capture the co-evolving historical dynamics of environmental context and community structure; (2) a Context-Anchored Latent Alignment mechanism that structures the latent space using a label-activated mixture prior and supervised contrastive learning, actively clustering species based on shared environmental preferences; and (3) an Imbalance-Aware Decoupled Decoding module that utilizes Asymmetric Loss to focus learning on hard, rare species samples, preventing mode collapse in the long tail. Experiments on the large-scale eBird dataset, curated with domain experts, demonstrate that our framework significantly outperforms state-of-the-art baselines, particularly in predicting rare species and revealing interpretable species interactions.
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。