The spatial distribution of soil coarse fragments (CF) is important for a variety of agricultural and environmental applications because it directly impacts soil processes including hydrology and nutrient cycling. However, there is often insufficient measured data to reliably model and map CF using a digital soil mapping approach. By targeting CF layer occurrence rather than CF as a continuous soil property, we increased the number of data sites available for spatial modelling which improved predicted patterns. We define CF layers as hard CF and segregations size > 2 mm, > 20% by volume, and > 10 cm thick, the definition of a ferric diagnostic horizon in the Australian Soil Classification system. Highly variable legacy data yielded nearly 40,000 georeferenced sites over the 1 M square kilometre study area. The binary classification models evaluated were random forest using regression trees (probability machines) and classification trees, with and without class balancing. The best performing models were regression forests, followed by classification using the threshold that maximised the Kappa coefficient. Prediction accuracy was determined by validating with a subset of legacy data randomly selected on an unaligned grid and withheld from model training; validation was performed on all modelling methods, plus other available CF digital soil maps. Incorporating low quality legacy observations improved CF predictions significantly. The final maps depict CF layer presence or absence in four depth slices (0–5, 5–15, 15–30, and 30–80 cm) and anywhere within the top 80 cm, for both CF of any composition and specifically for ironstone gravel (sesquioxide nodules). These new maps have high predictive power: ironstone gravel layers had AUC ranging from 0.86 to 0.89, Kappa between 0.48 and 0.52, and overall accuracy from 0.82 to 0.92; for CF layers of mixed composition AUC ranged from 0.79 to 0.84, with Kappa 0.43 to 0.46, and overall accuracy from 0.74 to 0.88. The maps are plausible representations of local variation in soil properties across the landscape. They reflect the expert knowledge encoded in conventional soil maps, and are more locally credible than other available modelled CF maps. Modelling CF as layers rather than continuous properties led to high accuracy spatial representation of simple but still useful soil features for our study area. These soil feature maps complement the quantitative soil property surfaces common to digital soil mapping studies that are frequently constrained by data availability.

土壤粗碎片 (CF) 的空间分布对于各种农业和环境应用很重要，因为它直接影响土壤过程，包括水文和养分循环。然而，通常没有足够的测量数据来使用数字土壤绘图方法对 CF 进行可靠的建模和映射。通过将 CF 层发生而不是 CF 作为连续的土壤属性，我们增加了可用于空间建模的数据站点数量，从而改进了预测模式。我们将 CF 层定义为硬 CF 和偏析尺寸 > 2 毫米、> 20% 体积和 > 10 厘米厚，这是澳大利亚土壤分类系统中铁诊断层的定义。高度可变的遗留数据在 100 万平方公里的研究区域内产生了近 40,000 个地理参考站点。评估的二元分类模型是使用回归树（概率机）和分类树的随机森林，有和没有类平衡。表现最好的模型是回归森林，其次是使用最大化 Kappa 系数的阈值进行分类。通过在未对齐的网格上随机选择并从模型训练中保留的遗留数据子集进行验证来确定预测准确性；对所有建模方法以及其他可用的 CF 数字土壤图进行了验证。结合低质量的传统观测显着改善了 CF 预测。最终的地图描绘了四个深度切片（0-5、5-15、15-30 和 30-80 厘米）以及顶部 80 厘米内任何地方的 CF 层存在与否，适用于任何成分的 CF，尤其适用于铁石砾石（倍半氧化物结核）。这些新地图具有很高的预测能力：铁石砾石层的 AUC 在 0.86 到 0.89 之间，Kappa 在 0.48 到 0.52 之间，整体精度从 0.82 到 0.92；对于混合成分的 CF 层，AUC 范围为 0.79 至 0.84，Kappa 为 0.43 至 0.46，总体准确度为 0.74 至 0.88。这些地图是整个景观土壤特性局部变化的合理表示。它们反映了在传统土壤图中编码的专家知识，并且比其他可用的建模 CF 地图更具有局部可信度。将 CF 建模为层而不是连续属性，可以为我们的研究区域提供简单但仍然有用的土壤特征的高精度空间表示。