Abstract Accurate estimation of biomass and Leaf Area Index (LAI) requires appropriate models and predictor variables. These biophysical parameters are indicative of crop productivity, and thus, are of interest in applications such as crop yield forecasting and precision farming. This study evaluated the potential of leveraging vegetation indices derived from multi-temporal RapidEye data using a machine learning approach to estimate crop biomass and LAI. Both near-infrared and red-edge based indices were considered in this study. In-situ measurements of these two parameters for three main cash crops, including canola, corn, and soybeans, were collected during a field campaign and used for model calibration and validation. Crops models were developed using the artificial neural network (ANN) and support vectors regression (SVR). Results showed that, for each crop, the SVR modeled LAI and biomass more accurately than ANN. For biomass, the SVR’s Root Mean Square Errors (RMSEs) were reported as 25.22 g/m2 for canola, 88.13 g/m2 for corn, 5.91 g/m2 for soybean, and 56.14 g/m2 for all crops pooled. Similarly, for the LAI, SVR provided the best model with RMSE = 0.59 m2/m2 for canola, RMSE = 0.27 m2/m2 for corn, RMSE = 0.21 m2/m2 for soybean, and RMSE = 0.51 m2/m2 for all crops together.

中文翻译：

---

使用机器学习方法从多时相和多光谱图像估计作物生物量和叶面积指数

摘要 生物量和叶面积指数 (LAI) 的准确估计需要适当的模型和预测变量。这些生物物理参数是作物生产力的指标，因此在作物产量预测和精准农业等应用中很受关注。本研究使用机器学习方法评估利用源自多时态 RapidEye 数据的植被指数来估计作物生物量和 LAI 的潜力。本研究同时考虑了基于近红外和红边的指数。在田间活动期间收集了三种主要经济作物（包括油菜籽、玉米和大豆）的这两个参数的原位测量值，并将其用于模型校准和验证。作物模型是使用人工神经网络 (ANN) 和支持向量回归 (SVR) 开发的。结果表明，对于每种作物，SVR 对 LAI 和生物量的建模比 ANN 更准确。对于生物量，SVR 的均方根误差 (RMSE) 报告为油菜籽为 25.22 g/m2，玉米为 88.13 g/m2，大豆为 5.91 g/m2，所有汇总作物为 56.14 g/m2。同样，对于 LAI，SVR 提供了最佳模型，油菜籽的 RMSE = 0.59 m2/m2，玉米的 RMSE = 0.27 m2/m2，大豆的 RMSE = 0.21 m2/m2，所有作物的 RMSE = 0.51 m2/m2 .