We compared Support Vector Machine (SVM) and Random Forest (RF) machine learning approaches with the widely used Jarvis-type phenomenological model for predicting stomatal conductance (g_s) in wheat (Triticum aestivum L.) using historical measurements collected in the Australian Grains Free-Air CO₂ Enrichment (AGFACE) facility. The machine learning-based methods produced greater accuracy than the Jarvis-type model in predicting g_s from leaf age, atmospheric [CO₂], photosynthetically active radiation, vapour pressure deficit, temperature, time of day, and soil water availability (i.e. phenological and environmental variables determining g_s). The R² was 0.76 for the Jarvis-type but 0.92 for SVM and 0.97 for RF machine learning-based models, with a calculated RMSE of 0.292 mol m⁻² s⁻¹ in the Jarvis-type compared to 0.129 mol m⁻² s⁻¹ in SVM and 0.081 mol m⁻² s⁻¹ in RF. The machine learning models, however, needed large datasets for training to achieve statistical significance, and do not offer the same opportunity to provide physiological insights through a statistically testable hypothesis. These results show that using the machine-learning based methods can achieve high prediction accuracy of g_s that is especially important when incorporated into larger models, but their ability to extrapolate beyond observed data ranges will need to be assessed before they could be considered in place of the physical model.

我们将支持向量机（SVM）和随机森林（RF）机器学习方法与广泛使用的Jarvis型现象学模型进行了比较，该模型使用澳大利亚谷物中收集的历史数据来预测小麦（Triticum aestivum L.）的气孔导度（g _s）。自由空气中的CO ₂浓缩（AGFACE）设施。基于机器学习的方法在根据叶龄，大气[CO ₂ ]，光合有效辐射，蒸气压赤字，温度，一天中的时间和土壤水分利用率（即物候性）预测g _s方面，比Jarvis型模型具有更高的准确性。和环境变量决定g _s）。对于Jarvis型，R ²为0.76，对于基于SVM的模型，R ²为0.92，对于基于RF机器学习的模型，R ²为0.97，在Jarvis型中，RSE的计算得出的RMSE为0.292 mol m ^-2 s ^-1，相比之下，为0.129 mol m ^-2 s ^-1在SVM和0.081摩尔米^-2小号^-1在RF。然而，机器学习模型需要大量的数据集进行训练以达到统计学上的意义，并且无法通过可统计检验的假设提供相同的机会来提供生理学见识。这些结果表明，使用基于机器学习的方法可以实现较高的g _s预测精度 当将其合并到较大的模型中时，这一点尤其重要，但是在考虑将其推断为物理模型之前，需要评估其推断数据范围之外的能力。