Shared landscapes in which humans and wildlife coexist, are increasingly recognized as integral to conservation. Fine‐scale data on the distribution and density of threatened wildlife are therefore critical to promote long‐term coexistence. Yet, the spatial complexity of habitat, anthropic threats and animal behaviour in shared landscapes challenges conventional survey techniques. For social wildlife in particular, the size of sub‐groups or clusters is likely to both vary in space and influence detectability, biasing density estimation and spatial prediction. Using the R package ‘inlabru', we develop a full‐likelihood joint log‐Gaussian Cox process to simultaneously perform spatial distance sampling and model a spatially varying cluster size distribution, which we condition upon detection probability to mitigate cluster‐size detection bias. We accommodate spatial dependencies by incorporating a non‐stationary Gaussian Markov random field, enabling the explicit inclusion of geographical barriers to wildlife dispersal. We demonstrate this model using 136 georeferenced detections of Campbell's monkey Cercopithecus campbelli clusters, collected with 398.56 km of line transects across a shared agroforest landscape mosaic (1067 km2) in Guinea‐Bissau. We assess a suite of anthropogenic and environmental spatial covariates, finding that normalized difference vegetation index (NDVI) and proximity to mangroves are both powerful spatial predictors of density. We captured strong spatial variation in cluster size, likely driven by fission–fusion in response to the complex distribution of resources and risk in the landscape. If left unaccounted for under existing approaches, such variation may bias density surface estimation. We estimate a population of 10 301 (95% CI [7606–14 104]) individuals and produce a fine‐scale predictive density map, revealing the importance of mangrove‐habitat interfaces for the conservation of this heavily hunted primate. This work demonstrates a powerful, widely applicable approach for monitoring socially flexible wildlife and informing evidence‐based conservation in complex, heterogeneous landscapes moving forward.

中文翻译：

---

在异质景观中持续存在大量猎杀的灵长类动物的集群大小和密度的联合空间建模


人类和野生动物共存的共享景观越来越被认为是保护不可或缺的一部分。因此，关于受威胁野生动物分布和密度的精细数据对于促进长期共存至关重要。然而，栖息地的空间复杂性、人类威胁和共享景观中的动物行为对传统的调查技术提出了挑战。特别是对于社会性野生动物，子群或群的大小可能在空间上有所不同，并影响可探测性，使密度估计和空间预测产生偏差。使用 R 包 'inlabru'，我们开发了一个全似然联合对数高斯 Cox 过程，以同时执行空间距离采样并模拟空间变化的集群大小分布，我们根据检测概率对其进行条件调节，以减轻集群大小的检测偏差。我们通过合并非平稳高斯马尔可夫随机场来适应空间依赖关系，从而能够明确包含野生动物扩散的地理障碍。我们使用 136 个坎贝尔猴 Cercopithecus campbelli 集群的地理参考检测来演示这个模型，这些检测是在几内亚比绍共享的农林景观马赛克 （1067 km2） 上收集的 398.56 公里的线样带收集的。我们评估了一组人为和环境空间协变量，发现归一化差异植被指数 （NDVI） 和与红树林的接近程度都是密度的强大空间预测因子。我们捕捉到了星团大小的强烈空间变化，这可能是由裂变-聚变驱动的，以应对景观中资源和风险的复杂分布。如果在现有方法下不考虑，这种变化可能会使密度表面估计产生偏差。 我们估计了 10 301 （95% CI [7606–14 104]） 个体的种群，并制作了一张精细的预测密度图，揭示了红树林-栖息地界面对保护这种被大量猎杀的灵长类动物的重要性。这项工作展示了一种强大、广泛适用的方法，用于监测社会灵活的野生动物，并为未来复杂、异质景观中的循证保护提供信息。