Abstract Random Forest (RF) is a machine learning technique that has been proved to be highly accurate in several agricultural applications. However, to yield prediction, how much this technique may be improved with the adoption of a ranking-based strategy is still an unknown issue. Here we propose a ranking-based approach to potentialize the RF method for maize yield prediction. This approach is based on the correlation parameter of individual vegetation indices (VIs). The VIs were individually ranked based on a merit metric that measures the improvement on the Pearson’s correlation coefficient by using RF against a baseline method. As a result, only the most relevant VIs were considered as input features to the RF model. We used 33 VIs extracted from multispectral UAV-based (unmanned aerial vehicle) imagery. The multispectral data were generated with two different sensors: Sequoia and MicaSense; during the 2017/2018 and 2018/2019 crop seasons, respectively. Amongst all the evaluated indices, NDVI, NDRE, and GNDVI were the top three in the ranking-based analysis, and their combination with RF increased the maize yield prediction. Our approach also outperformed other known machine learning methods, like support vector machine and artificial neural network. Additive regression, using the RF as the base weak learner, provided a higher accuracy with a correlation coefficient and MAE (Mean Absolute Error) of 0.78 and 853.11 kg ha−1, respectively. We conclude that the ranking-based strategy of VIs is appropriate to predict maize yield using machine learning methods and data derived from multispectral images. We demonstrated that our approach reduces the number of VIs needed to determine a high accuracy and relative low MAE, and the approach may contribute to decision-making actions, resulting in accurate management of maize fields.

中文翻译：

---

基于无人机的植被光谱指数预测玉米产量的随机森林排序方法

摘要 随机森林 (RF) 是一种机器学习技术，已被证明在多种农业应用中高度准确。然而，为了产生预测，通过采用基于排名的策略可以改进多少这种技术仍然是一个未知的问题。在这里，我们提出了一种基于排名的方法来潜在化用于玉米产量预测的 RF 方法。该方法基于单个植被指数 (VI) 的相关参数。这些 VI 是根据评价指标单独排名的，该指标通过使用 RF 与基线方法来衡量 Pearson 相关系数的改进。因此，只有最相关的 VI 被视为 RF 模型的输入特征。我们使用了从基于多光谱 UAV（无人机）图像中提取的 33 个 VI。多光谱数据由两个不同的传感器生成：Sequoia 和 MicaSense；分别在 2017/2018 和 2018/2019 作物季节期间。在所有评估指标中，NDVI、NDRE和GNDVI在基于排名的分析中位居前三，它们与RF的结合增加了玉米产量预测。我们的方法也优于其他已知的机器学习方法，如支持向量机和人工神经网络。使用 RF 作为基础弱学习器的加法回归提供了更高的准确度，相关系数和 MAE（平均绝对误差）分别为 0.78 和 853.11 kg ha-1。我们得出的结论是，基于排序的 VI 策略适用于使用机器学习方法和多光谱图像数据来预测玉米产量。