Tropical moist forests are not the homogeneous green carpet often illustrated in maps or considered by global models. They harbour a complex mixture of forest types organized at different spatial scales that can now be more accurately mapped thanks to remote sensing products and artificial intelligence. In this study, we built a large‐scale vegetation map of the North of Congo and assessed the environmental drivers of the main forest types, their forest structure, their floristic and functional compositions and their faunistic composition. To build the map, we used Sentinel‐2 satellite images and recent deep learning architectures. We tested the effect of topographically determined water availability on vegetation type distribution by linking the map with a water drainage depth proxy (HAND, height above the nearest drainage index). We also described vegetation type structure and composition (floristic, functional and associated fauna) by linking the map with data from large inventories and derived from satellite images. We found that water drainage depth is a major driver of forest type distribution and that the different forest types are characterized by different structure, composition and functions, bringing new insights about their origins and successional dynamics. We discuss not only the crucial role of soil–water depth, but also the importance of consistently reproducing such maps through time to develop an accurate monitoring of tropical forest types and functions, and we provide insights on peculiar forest types (Marantaceae forests and monodominant Gilbertiodendron forests) on which future studies should focus more. Under the current context of global change, expected to trigger major forest structural and compositional changes in the tropics, an appropriate monitoring strategy of the spatio‐temporal dynamics of forest types and their associated floristic and faunistic composition would considerably help anticipate detrimental shifts.

中文翻译：

---

结合卫星和实地数据揭示了刚果的森林类型结构、功能和组成


热带潮湿的森林并不是地图中经常显示的或全球模型考虑的同质绿地毯。它们隐藏着以不同空间尺度组织的复杂森林类型混合物，由于遥感产品和人工智能，现在可以更准确地绘制这些森林类型的地图。在这项研究中，我们构建了刚果北部的大比例植被图，并评估了主要森林类型的环境驱动因素、森林结构、植物区系和功能组成以及动物群落组成。为了构建地图，我们使用了 Sentinel-2 卫星图像和最新的深度学习架构。我们通过将地图与排水深度代理（HAND，高于最邻近排水指数的高度）链接，测试了地形确定的可用水量对植被类型分布的影响。我们还通过将地图与来自大型清单和卫星图像的数据联系起来，描述了植被类型的结构和组成（植物区系、功能和相关动物群）。研究发现，排水深度是森林类型分布的主要驱动因素，不同的森林类型具有不同的结构、组成和功能，为它们的起源和演替动态带来了新的见解。我们不仅讨论了土壤-水深的关键作用，还讨论了随着时间的推移持续复制此类地图以准确监测热带森林类型和功能的重要性，并提供了对特殊森林类型（Marantaceae 森林和单一优势的 Gilbertiodendron 森林）的见解，未来的研究应该更多地关注这些类型。 在当前全球变化的背景下，预计将引发热带地区重大的森林结构和成分变化，对森林类型的时空动态及其相关的植物区系组成的适当监测策略将大大有助于预测有害的变化。