Data Science advances in sports commonly involve "big data", i.e., large sport-related data sets. However, such big data sets are not always available, necessitating specialized models that apply to relatively few observations. One important area of sport-science research that features small data sets is the study of energy recovery from exercise. In this area, models are typically fitted to data collected from exhaustive exercise test protocols, which athletes can perform only a few times. Recent findings highlight that established recovery models like W' balance (W'bal) models are too simple to adequately fit observed trends in the data. Therefore, we investigated a hydraulic model that requires the same few data points as W'bal models to be applied, but promises to predict recovery dynamics more accurately. To compare the hydraulic model to established W'bal models, we retrospectively applied them to a compilation of data from published studies. In total, one hydraulic model and three W'bal models were compared on data extracted from five studies. The hydraulic model outperformed established W'bal models on all defined metrics, even those that penalize models featuring higher numbers of parameters. These results incentivize further investigation of the hydraulic model as a new alternative to established performance models of energy recovery.

中文翻译：

---

一种液压模型优于工作平衡模型，用于预测间歇性运动的恢复动力学

体育数据科学的进步通常涉及“大数据”，即与体育相关的大型数据集。然而，这样的大数据集并不总是可用的，因此需要适用于相对较少的观察的专门模型。以小数据集为特征的运动科学研究的一个重要领域是研究运动中的能量恢复。在这个领域，模型通常适用于从详尽的运动测试协议中收集的数据，运动员只能执行几次。最近的研究结果强调，像 W' balance (W'bal) 模型这样的已建立的恢复模型过于简单，无法充分拟合观察到的数据趋势。因此，我们研究了一种水力模型，该模型需要与 W'bal 模型相同的少量数据点才能应用，但有望更准确地预测恢复动态。为了将水力模型与已建立的 W'bal 模型进行比较，我们回顾性地将它们应用于已发表研究的数据汇编。总的来说，一个水力模型和三个 W'bal 模型对从五项研究中提取的数据进行了比较。水力模型在所有定义的指标上都优于既定的 W'bal 模型，即使是那些惩罚具有更多参数的模型的模型。这些结果激励对水力模型的进一步研究，作为已建立的能量回收性能模型的新替代方案。bal 模型在所有定义的指标上，即使是那些惩罚具有更多参数的模型的模型。这些结果激励对水力模型的进一步研究，作为已建立的能量回收性能模型的新替代方案。bal 模型在所有定义的指标上，即使是那些惩罚具有更多参数的模型的模型。这些结果激励对水力模型的进一步研究，作为已建立的能量回收性能模型的新替代方案。