Soil fungi play important roles in the functioning of ecosystems, but they are challenging to measure. Using a continental-scale dataset, we developed and evaluated a new method to estimate the relative abundance of the dominant phyla and diversity of fungi in Australian soil. The method relies on the development of spectrotransfer functions with state-of-the-art machine learning and uses publicly available data on soil and environmental proxies for edaphic, climatic, biotic and topographic factors, and visible–near infrared (vis–NIR) wavelengths, to estimate the relative abundances of Ascomycota, Basidiomycota, Glomeromycota, Mortierellomycota and Mucoromycota and community diversity measured with the abundance-based coverage estimator (ACE) index. The algorithms tested were partial least squares regression (PLSR), random forest (RF), Cubist, support vector machines (SVM), Gaussian process regression (GPR), extreme gradient boosting (XGBoost) and one-dimensional convolutional neural networks (1D-CNNs). The spectrotransfer functions were validated with a 10-fold cross-validation (n=577). The 1D-CNNs outperformed the other algorithms and could explain between 45 % and 73 % of fungal relative abundance and diversity. The models were interpretable, and showed that soil nutrients, pH, bulk density, ecosystem water balance (a proxy for aridity) and net primary productivity were important predictors, as were specific vis–NIR wavelengths that correspond to organic functional groups, iron oxide and clay minerals. Estimates of the relative abundance for Mortierellomycota and Mucoromycota produced R²≥0.60, while estimates of the abundance of the Ascomycota and Basidiomycota produced R² values of 0.5 and 0.58 respectively. The spectrotransfer functions for the Glomeromycota and diversity were the poorest with R² values of 0.48 and 0.45 respectively. There is no doubt that the method provides estimates that are less accurate than more direct measurements with conventional molecular approaches. However, once the spectrotransfer functions are developed, they can be used with very little cost, and could serve to supplement the more expensive and laborious molecular approaches for a better understanding of soil fungal abundance and diversity under different agronomic and ecological settings.

中文翻译：

---

利用深度学习光谱传递函数在宏观生态尺度上估计土壤真菌丰度和多样性

土壤真菌在生态系统的功能中发挥着重要作用，但它们的测量具有挑战性。使用大陆规模的数据集，我们开发并评估了一种新方法来估计澳大利亚土壤中优势门的相对丰度和真菌多样性。该方法依赖于使用最先进的机器学习开发光谱传递函数，并使用土壤和环境代理的公开数据，用于土壤、气候、生物和地形因素，以及可见-近红外 (vis-NIR) 波长，估计子囊菌门、担子菌门、球囊菌门、被孢霉门和毛霉菌门的相对丰度以及用基于丰度的覆盖率估计 (ACE) 指数测量的群落多样性。测试的算法是偏最小二乘回归 (PLSR)、随机森林 (RF)、Cubist、支持向量机 (SVM)、高斯过程回归 (GPR)、极端梯度提升 (XGBoost) 和一维卷积神经网络 (1D-CNN)。光谱传递函数通过 10 倍交叉验证（n = 577 )。1D-CNN 的性能优于其他算法，可以解释 45% 到 73% 的真菌相对丰度和多样性。这些模型是可解释的，并表明土壤养分、pH、容重、生态系统水平衡（干旱的代表）和净初级生产力是重要的预测因子，与有机官能团、氧化铁和粘土矿物。估计被孢霉门和毛霉菌门的相对丰度产生R ² ≥0.60，而估计子囊菌门和担子菌门的丰度产生R ²值分别为 0.5 和 0.58。Glomeromycota 和多样性的光谱传递函数最差，R ²值分别为 0.48 和 0.45。毫无疑问，该方法提供的估计不如使用传统分子方法的更直接测量准确。然而，一旦开发了光谱传递函数，它们就可以以非常低的成本使用，并且可以作为更昂贵和费力的分子方法的补充，以便更好地了解不同农艺和生态环境下的土壤真菌丰度和多样性。