Abstract While sugarcane growth models could assist farmers in harvesting fields as close as possible to peak maturity, few of them are available to the industry. Even in those that are available, either there is room for improvement in sugar content estimation, or they were not properly assessed as to how they would perform given weather variability. In this work, we show that when developed with a dataset comprised of typical weather patterns, the outputs of empirical models that have been recently developed are qualitatively analogous to those of a process-based model and have smaller errors. However, when the training data is not representative, the same doesn’t happen and they are not consistent with known responses from sugarcane and with the output of mechanistic models. We used data from three years of harvests of a sugarcane mill to develop and evaluate the performance of machine learning models, as well as to evaluate an empirical model recently developed and DSSAT/Canegro. All models’ performances were evaluated in each of the three years separately, as well as through sensitivity analysis, to observe the effects of unknown weather in the estimates obtained by the model. This evaluation suggests that while machine learning techniques applied to industry data may be a promising tool for decision-makers, by themselves they are not capable of capturing all the effects that influence sucrose accumulation in sugarcane stalks.

中文翻译：

---

用于估计甘蔗中糖含量的模型有多好？

摘要 虽然甘蔗生长模型可以帮助农民在尽可能接近成熟高峰时收割田地，但很少有可供该行业使用的模型。即使在那些可用的情况下，糖含量估计也有改进的余地，或者没有正确评估它们在给定天气变化的情况下的表现。在这项工作中，我们表明，当使用由典型天气模式组成的数据集开发时，最近开发的经验模型的输出定性地类似于基于过程的模型的输出，并且误差较小。但是，当训练数据不具有代表性时，就不会发生同样的情况，并且它们与甘蔗的已知响应和机械模型的输出不一致。我们使用甘蔗厂三年收成的数据来开发和评估机器学习模型的性能，以及评估最近开发的经验模型和 DSSAT/Canegro。所有模型的性能在三年中的每一年都分别进行了评估，并通过敏感性分析来观察未知天气对模型估计的影响。该评估表明，虽然应用于行业数据的机器学习技术可能是决策者的一个有前途的工具，但它们本身并不能捕捉影响甘蔗茎中蔗糖积累的所有影响。所有模型的性能在三年中的每一年都分别进行了评估，并通过敏感性分析来观察未知天气对模型估计的影响。该评估表明，虽然应用于行业数据的机器学习技术可能是决策者的一个有前途的工具，但它们本身并不能捕捉影响甘蔗茎中蔗糖积累的所有影响。所有模型的性能在三年中的每一年都分别进行了评估，并通过敏感性分析来观察未知天气对模型估计的影响。该评估表明，虽然应用于行业数据的机器学习技术可能是决策者的一个有前途的工具，但它们本身并不能捕捉影响甘蔗茎中蔗糖积累的所有影响。