The mountain pine beetle (MPB) is among the most destructive eruptive forest pests in North America. A recent increase in the frequency and severity of outbreaks, combined with an eastward range expansion towards untouched boreal pine forests, has spurred a great interest by government, industry and academia into the population ecology of this tree-killing bark beetle. Modern approaches to studying the spread of the MPB often involve the analysis of large-scale, high-resolution datasets on landscape-level damage to pine forests. This creates a need for new modelling tools to handle the unique challenges associated with large sample sizes and spatial effects. In two companion papers (Koch et al. in Environ Ecol Stat. https://doi.org/10.1007/s10651-020-00456-2, 2020a; J R Soc Interface 17(170):20200434, 2020b), we explain how the computational challenges of dispersal and spatial autocorrelation can be addressed using separable kernels. In this paper, we use these ideas to capture nonstationary patterns in the dispersal flights of MPB. This facilitates a landscape-level inference of subtle properties of MPB attack behaviour based on aerial surveys of killed pine. Using this model, we estimate the size of the cryptic endemic MPB population, which formerly has been measurable only by means of costly and time-intensive ground surveys.

山松甲虫 (MPB) 是北美最具破坏性的爆发性森林害虫之一。最近爆​​发的频率和严重程度的增加，加上向东向未受破坏的北方松林扩展，激发了政府、工业和学术界对这种杀死树木的树皮甲虫种群生态的极大兴趣。研究 MPB 传播的现代方法通常涉及对松林景观级破坏的大规模高分辨率数据集的分析。这就需要新的建模工具来应对与大样本量和空间效应相关的独特挑战。在两篇配套论文中（Koch et al. in Environ Ecol Stat. https://doi.org/10.1007/s10651-020-00456-2, 2020a; JR Soc Interface 17(170):20200434, 2020b），我们解释了如何使用可分离内核来解决分散和空间自相关的计算挑战。在本文中，我们使用这些想法来捕捉 MPB 扩散飞行中的非平稳模式。这有助于基于对死亡松树的航空调查对 MPB 攻击行为的微妙属性进行景观级推断。使用这个模型，我们估计了神秘的地方性 MPB 种群的大小，以前只能通过昂贵且耗时的地面调查来测量。