发表机构
Huron High School; University of Florida; Industrial and Systems Engineering; Forest, Fisheries, and Geomatics Sciences（休伦高中; 佛罗里达大学; 工业与系统工程系; 森林、渔业与地理信息科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对天坑预测中负样本缺失和多模态数据整合难题，提出多模态Cox比例风险生存分析模型，将未报告位置视为右删失，通过模态编码器与跨模态融合生成时间感知的易发性地图，并在佛罗里达案例中验证其有效性。
AI 中文摘要
天坑是喀斯特地貌中一种广泛分布的地质灾害。在佛罗里达州，可溶性碳酸盐岩基岩、浅层地下水和强降雨共同作用，使得地面沉降既普遍又具有空间异质性。预测天坑发生的地点和时间存在两个难点。首先，没有报告天坑的位置不能直接标记或采样为真正的负样本位置。其次，控制天坑风险的潜在因素跨越了异质的数据模态，因此需要在统一的建模框架内进行仔细整合。我们通过提出的模型解决了这两个问题，该模型是一个用于天坑易发性的多模态Cox比例风险框架。我们的贡献有三方面。首先，我们将比例风险公式扩展到异质多模态输入，通过模态特定的编码器和跨模态融合层实现。其次，我们将未报告的位置视为右删失而非负样本，避免了硬负样本标记，并从预测的生存函数中产生连续的、时间感知的易发性。第三，一项全州范围的佛罗里达案例研究，采用空间分块验证和消融研究，量化了多模态整合的益处。佛罗里达案例研究表明，所提出的方法能有效对天坑风险进行排序，并生成一幅捕捉天坑发生空间变化的全州易发性地图。
英文摘要
Sinkholes are a widespread geohazard in karst terrain. In Florida, soluble carbonate bedrock, shallow groundwater, and intense rainfall combine to make subsidence both common and spatially heterogeneous. Predicting where and when sinkholes will occur is difficult for two reasons. First, locations without reported sinkholes cannot be directly labeled or sampled as true negative locations. Second, the potential factors governing sinkhole risk span heterogeneous data modalities and therefore require careful integration within a unified modeling framework. We address both problems with our proposed model, a multimodal Cox proportional hazards framework for sinkhole susceptibility. Our contributions are threefold. First, we extend the proportional-hazards formulation to heterogeneous multimodal input through modality-specific encoders and a cross-modal fusion layer. Second, we treat unreported locations as right-censored rather than negative, avoiding hard-negative labeling and yielding continuous, time-aware susceptibility from the predicted survival function. Third, a statewide Florida case study with spatially blocked validation and ablation studies quantifies the benefit of multimodal integration. A Florida case study demonstrates that the proposed method effectively ranks sinkhole risk and produces a statewide susceptibility map that captures spatial variations in sinkhole occurrence.
