Probabilistic Mapping and Spatial Pattern Analysis of Grazing Lawns in Southern African Savannahs Using WorldView-3 Imagery and Machine Learning Techniques

Savannah grazing lawns are a key food resource for large herbivores such as blue wildebeest (Connochaetes taurinus), hippopotamus (Hippopotamus amphibius) and white rhino (Ceratotherium simum), and impact herbivore densities, movement and recruitment rates. They also exert a strong influence on fire behaviour including frequency, intensity and spread. Thus, variation in grazing lawn cover can have a profound impact on broader savannah ecosystem dynamics. However, knowledge of their present cover and distribution is limited. Importantly, we lack a robust, broad-scale approach for detecting and monitoring grazing lawns, which is critical to enhancing understanding of the ecology of these vital grassland systems. We selected two sites in the Lower Sabie and Satara regions of Kruger National Park, South Africa with mesic and semiarid conditions, respectively. Using spectral and texture features derived from WorldView-3 imagery, we (i) parameterised and assessed the quality of Random Forest (RF), Support Vector Machines (SVM), Classification and Regression Trees (CART) and Multilayer Perceptron (MLP) models for general discrimination of plant functional types (PFTs) within a sub-area of the Lower Sabie landscape, and (ii) compared model performance for probabilistic mapping of grazing lawns in the broader Lower Sabie and Satara landscapes. Further, we used spatial metrics to analyse spatial patterns in grazing lawn distribution in both landscapes along a gradient of distance from waterbodies. All machine learning models achieved high F-scores (F1) and overall accuracy (OA) scores in general savannah PFTs classification, with RF (F1 = 95.73 ± 0.004%, OA = 94.16 ± 0.004%), SVM (F1 = 95.64 ± 0.002%, OA = 94.02 ± 0.002% ) and MLP (F1 = 95.71 ± 0.003%, OA = 94.27 ± 0.003% ) forming a cluster of the better performing models and marginally outperforming CART (F1 = 92.74 ± 0.006%, OA = 90.93 ± 0.003%). Grazing lawn detection accuracy followed a similar trend within the Lower Sabie landscape, with RF, SVM, MLP and CART achieving F-scores of 0.89, 0.93, 0.94 and 0.81, respectively. Transferring models to the Satara landscape however resulted in relatively lower but high grazing lawn detection accuracies across models (RF = 0.87, SVM = 0.88, MLP = 0.85 and CART = 0.75). Results from spatial pattern analysis revealed a relatively higher proportion of grazing lawn cover under semiarid savannah conditions (Satara) compared to the mesic savannah landscape (Lower Sabie). Additionally, the results show strong negative correlation between grazing lawn spatial structure (fractional cover, patch size and connectivity) and distance from waterbodies, with larger and contiguous grazing lawn patches occurring in close proximity to waterbodies in both landscapes. The proposed machine learning approach provides a novel and robust workflow for accurate and consistent landscape-scale monitoring of grazing lawns, while our findings and research outputs provide timely information critical for understanding habitat heterogeneity in southern African savannahs.

稀树草原放牧草地（Savannah grazing lawns）是蓝牛羚（Connochaetes taurinus）、河马（Hippopotamus amphibius）和白犀牛（Ceratotherium simum）等大型植食动物的关键食物资源，会影响植食动物的种群密度、移动模式与种群补充率。同时，它们对火行为包括发生频率、强度与蔓延范围均具有显著影响。因此，放牧草地覆盖度的变化会对更广尺度的稀树草原生态系统动态产生深远影响。然而，当前学界对其现存覆盖范围与分布的认知仍较为有限。尤为关键的是，我们尚缺乏一套可靠的大范围检测与监测放牧草地的方法，而这对于深化理解这类至关重要的草原生态系统的生态学特征而言至关重要。我们在南非克鲁格国家公园的下萨比（Lower Sabie）与萨塔拉（Satara）区域分别选取了两个样地，二者分别处于湿润（mesic）与半干旱（semiarid）生境条件下。基于WorldView-3卫星影像提取的光谱与纹理特征，我们（i）针对下萨比区域子样地内的植物功能型（plant functional types, PFTs）开展通用识别，对随机森林（Random Forest, RF）、支持向量机（Support Vector Machines, SVM）、分类与回归树（Classification and Regression Trees, CART）以及多层感知器（Multilayer Perceptron, MLP）模型进行参数化并评估其分类质量；（ii）针对更大范围的下萨比与萨塔拉景观，对比各模型在放牧草地概率制图任务中的表现。此外，我们借助空间度量指标，分析了两个景观中放牧草地分布的空间格局，并探讨了其与距水体距离梯度的相关性。所有机器学习模型在通用稀树草原植物功能型分类任务中均取得了较高的F1值（F-score, F1）与总体精度（overall accuracy, OA），其中随机森林（F1=95.73±0.004%，OA=94.16±0.004%）、支持向量机（F1=95.64±0.002%，OA=94.02±0.002%）与多层感知器（F1=95.71±0.003%，OA=94.27±0.003%）构成了表现最优的模型集群，其性能小幅优于分类与回归树（F1=92.74±0.006%，OA=90.93±0.003%）。在下萨比景观中，放牧草地检测精度也呈现出类似趋势：随机森林、支持向量机、多层感知器与分类与回归树的F值分别为0.89、0.93、0.94与0.81。但将模型迁移至萨塔拉景观时，各模型的放牧草地检测精度虽仍处于较高水平，却相对有所降低：随机森林为0.87、支持向量机为0.88、多层感知器为0.85，分类与回归树为0.75。空间格局分析结果显示，半干旱生境的萨塔拉景观中，放牧草地覆盖占比相对高于湿润生境的下萨比景观。此外，研究结果表明放牧草地的空间结构（覆盖占比、斑块面积与连通性）与距水体距离呈显著负相关，两个景观中更大且连片的放牧草地斑块均分布在靠近水体的区域。本研究提出的机器学习方法为精准且稳定的景观尺度放牧草地监测提供了一套新颖且可靠的工作流程，而我们的研究发现与产出成果也为理解南部非洲稀树草原的生境异质性提供了亟需的关键信息。