Soil nitrogen isotope composition (δ¹⁵N) is an essential tool for investigating ecosystem nitrogen balances, plant–microbe interactions, ecological niches, animal migration, food origins, and forensics. The advancement of these applications is limited by a lack of robust geospatial models that are capable of capturing variation in soil δ¹⁵N (i.e., isotopic landscapes or isoscapes). Due to the complexity of the nitrogen cycle and general scarcity of isotopic information, previous approaches have reconstructed regional to global soil δ¹⁵N patterns via highly uncertain linear regression models. Here, we develop a new machine learning approach to ascertain a finer‐scale understanding of geographic differences in soil δ¹⁵N, using the South American continent as a test case. We use a robust training set spanning 278 geographic locations across the continent, spanning all major biomes. We tested three different machine learning methods: cubist, random forest (RF), and stochastic gradient boosting (GBM). 10‐fold cross‐validation revealed that the RF method outperformed both the cubist and GBM approaches. Variable importance analysis of the RF framework pointed to biome type as the most crucial auxiliary variable, followed by soil organic carbon content, in determining the model performance. We thereby created a biogeographic boundary map, which predicted an expected multiscale spatial pattern of soil δ¹⁵N with a high degree of confidence, performing substantially better than all previous approaches for the continent of South America. Therefore, the RF machine learning framework showed to be a great opportunity to explore a broad array of ecological, biogeochemical, and forensic issues through the lens of soil δ¹⁵N.

中文翻译：

---

重建土壤δ15N的大陆尺度变化：南美的机器学习方法

土壤氮同位素组合物（δ ¹⁵ N）是用于研究的生态系统平衡的氮，植物微生物相互作用，生态小环境，动物迁移，食物来源，和法医的必要工具。这些应用程序的进步是由缺乏稳健的地理空间模型，能够捕获在土壤δ变化的限制¹⁵ N（即同位素风景或isoscapes）。由于氮循环和同位素信息普遍匮乏的复杂性，以前的方法有δ重建区域到全球土壤^15种通过高度不确定的线性回归模型N种模式。在这里，我们开发了一个新的机器学习方法，以确定在土壤δ地理差异更精细尺度的理解¹⁵N，以南美大陆为例。我们使用了强大的培训集，涵盖了整个非洲大陆278个地理位置，涵盖了所有主要生物群落。我们测试了三种不同的机器学习方法：立体主义者，随机森林（RF）和随机梯度提升（GBM）。10倍的交叉验证表明，RF方法优于立体派和GBM方法。RF框架的变量重要性分析指出，在确定模型性能时，生物群落类型是最关键的辅助变量，其次是土壤有机碳含量。我们由此创建的生物地理边界地图，其预测的土壤δ的预期的多尺度空间图案¹⁵N具有高度的信心，其性能比南美大陆以前的所有方法都要好得多。因此，RF机器学习框架显示是通过土壤的镜头δ探索生态，生物地球化学和法医问题浩如烟海一个很好的机会，¹⁵ N.