We consider energy-dispersive X-ray Fluorescence (EDXRF) applications where the fundamental parameters method is impractical such as when instrument parameters are unavailable. For example, on a mining shovel or conveyor belt, rocks are constantly moving (leading to varying angles of incidence and distances) and there may be other factors not accounted for (like dust). Neural networks do not require instrument and fundamental parameters but training neural networks requires XRF spectra labelled with elemental composition, which is often limited because of its expense. We develop a neural network model that learns from limited labelled data and learns to invert a forward model. The forward model uses transition energies and probabilities of all elements and parameterized distributions to approximate other fundamental and instrument parameters. We evaluate the model and baseline models on a rock dataset from a lithium mineral exploration project and identify which elements are appropriate for this method. This model demonstrates the potential to calibrate a neural network in a noisy environment where labelled data is limited.

翻译：我们认为,在基本参数方法不切实际的情况下,例如没有仪器参数时,基本参数方法(EDXRF)的应用是不切实际的。例如,在采矿铲子或传送带上,岩石在不断移动(导致发生和距离的不同角度),而且可能还有其他因素(如尘埃)没有被计算在内。神经网络不需要仪器和基本参数,但培训神经网络需要带有元素构成的XRF光谱,这种光谱往往因其成本而受到限制。我们开发了一个神经网络模型,从有限的标签数据中学习,并学会反向前方模型。远方模型利用所有元素的过渡能量和概率以及参数分布为其他基本参数和仪器参数的近似值。我们评估了来自一个矿物勘探项目的岩石数据集的模型和基线模型,并确定了哪些要素适合这种方法。这一模型展示了在标签数据有限的噪音环境中校准一个神经网络的潜力。