当前位置: X-MOL 学术Soil › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Estimating soil fungal abundance and diversity at a macroecological scale with deep learning spectrotransfer functions
Soil ( IF 5.8 ) Pub Date : 2021-09-13 , DOI: 10.5194/soil-2021-79
Yuanyuan Yang , Zefang Shen , Andrew Bisset , Raphael A. Viscarra Rossel

Abstract. 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 spectro-transfer functions with state-of-the-art machine learning and using 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 the Ascomycota, Basidiomycota, Glomeromycota, Mortierellomycota and Mucoromycota and community diversity measured with the abundance-based coverage estimator (ACE) index. The machine learning algorithms tested were partial least squares regression (PLSR), random forest (RF), Cubist, support vector machines (SVM), Gaussian process regression (GPR), XG-boost (XGB) and one-dimensional convolutional neural networks (1D-CNNs). The spectro-transfer 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, an 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 spectro-transfer 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 spectro-transfer 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:

使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

摘要。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。使用大陆尺度数据集,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。该方法依赖于利用最先进的机器学习开发光谱传递函数,并使用土壤、气候、生物和地形因素以及可见光-近红外(可见光)的公开可用数据。 NIR) 波长,以估计子囊菌门、担子菌门、球囊菌门、被孢霉门和毛霉菌门的相对丰度以及使用基于丰度的覆盖率估计器 (ACE) 指数测量的群落多样性。测试的机器学习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)、XG-boost (XGB) 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) 进行验证。1D-CNN 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 值、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、氧化铁相对应的特定 vis-NIR 波长也是如此和粘土矿物。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R XG-boost (XGB) 和一维卷积神经网络 (1D-CNNs)。光谱传递函数通过 10 倍交叉验证 (n = 577) 进行验证。1D-CNN 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 值、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、氧化铁相对应的特定可见近红外波长也是如此和粘土矿物。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R XG-boost (XGB) 和一维卷积神经网络 (1D-CNNs)。光谱传递函数通过 10 倍交叉验证 (n = 577) 进行验证。1D-CNN 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 值、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、氧化铁相对应的特定 vis-NIR 波长也是如此和粘土矿物。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R 1D-CNN 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 值、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、氧化铁相对应的特定 vis-NIR 波长也是如此和粘土矿物。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R 1D-CNN 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 值、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、氧化铁相对应的特定 vis-NIR 波长也是如此和粘土矿物。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R 与有机官能团、氧化铁和粘土矿物相对应的特定可见光-近红外波长也是如此。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R 与有机官能团、氧化铁和粘土矿物相对应的特定可见光-近红外波长也是如此。Mortierellomycota 和 Mucoromycota 的相对丰度估计值产生 R2 ≥ 0.60,而子囊菌门和担子菌门的丰度估计值分别为 0.5 和 0.58 的R 2值。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更直接的测量准确。然而,一旦光谱传递函数被开发出来,它们就可以以很少的成本使用,并且可以用来补充更昂贵和费力的分子方法,以更好地了解不同农艺和生态环境下土壤真菌的丰度和多样性。
更新日期:2021-09-13
down
wechat
bug