In climate science, we often want to compare across different datasets. Difficulties can arise in doing this due to inevitable mismatches that arise between observational and reanalysis data, or even between different reanalyses. This misalignment can raise problems for any work that seeks to make inferences about one dataset from another. We considered tropical cyclone location as an example task with one dataset providing atmospheric conditions (ERA5) and another providing storm tracks (IBTrACS). We found that while the examples often aligned well, there were a considerable proportion (around 25%) which were not well aligned. We trained a neural network to map from the wind field to the storm location; in this setting misalignment in the datasets appears as "label noise" (i.e. the labelled storm location does not correspond to the underlying wind field). We found that this neural network trained only on the often noisy labels from IBTrACS had a denoising effect, and performed better than the IBTrACS labels themselves, as measured by human preferences. Remarkably, this even held true for training points, on which we might have expected the network to overfit to the IBTrACS predictions.

翻译：在气候科学中，我们经常需要比较不同的数据集。由于观测数据与再分析数据之间，甚至不同再分析数据之间不可避免地存在不匹配，这种比较可能面临困难。这种数据错位会对任何试图从一个数据集推断另一个数据集信息的工作造成问题。我们以热带气旋定位为例，其中一个数据集提供大气条件（ERA5），另一个提供风暴轨迹（IBTrACS）。研究发现，虽然多数样本能较好匹配，但仍有相当比例（约25%）存在明显错位。我们训练了一个神经网络，用于从风场映射到风暴位置；在此背景下，数据集间的错位表现为“标签噪声”（即标注的风暴位置与底层风场不对应）。研究发现，仅使用IBTrACS中常含噪声的标签进行训练的神经网络具有去噪效果，且根据人工偏好评估，其表现优于IBTrACS原始标签。值得注意的是，即使在训练数据点上——我们原本预期网络会对IBTrACS预测产生过拟合——这一结论仍然成立。