Grasslands are crucial ecosystems that support and provide a diverse number of ecosystem services. Sown biodiverse pastures rich in legumes (SBP) were developed with the main goal of increasing grassland production while minimizing fertilizers inputs. In this paper, the main properties of SBP in Portugal were estimated using remote sensing and machine learning in six different farms and two production years (spring 2018 and 2019). Four pasture characteristics were considered: aboveground standing biomass, fraction of legumes, plant nitrogen (N) content and plant phosphorus (P) content. Remote sensing data were obtained from Sentinel-2. The spectral bands combined with 5 vegetation indices and 9 covariates were used. Multiple linear regression, LASSO, Ridge, random forests, XGBoost and LightGBM regression models were used. Two cross-validation approaches were used: (1) a random approach with random selection of the folds (RN-CV), and (2) a structured approach where each fold is a unique combination of farm and year, which is subsequently used to assess the performance of the model obtained with the 8 other folds (LLYO-CV). Results showed that the random forest method had the best estimation accuracy for all pasture characteristics. Regarding cross-validation approaches, the algorithms with RN-CV have higher estimation accuracy for all pasture characteristics (on average about 10% lower RMSE and an R² 85% higher), as compared to the algorithms with LLYO-CV. However, LLYO-CV should avoid overfitting and improve generalization of the models because in each fold the model is tested in a farm and year that was not used for training. The RMSE for all variables were significantly low, especially in RN-CV. Plant P is the variable where the choice of CV approach has the least influence (RMSE of test set with RN-CV: 0.71 g P kg^− 1; LLYO-CV: 0.72 g P kg^− 1). Standing biomass is the variable with the highest difference between CV approaches (RN-CV: 722 kg ha^− 1; LLYO-CV: 825 kg ha^− 1). The RMSE, of legumes and plant N were moderately affected by the CV approach (legume RN-CV: 0.11; LLYO-CV: 0.12 – plant N RN-CV: 3.96 g N kg^− 1; LLYO-CV: 3.99 g N kg^− 1). The algorithms developed here were applied for entire parcels in the two farms with the most different climate conditions as demonstration of their potential future use for precision farming.

草原是支持和提供多种生态系统服务的重要生态系统。种植富含豆科植物 (SBP) 的播种生物多样性牧场的主要目标是增加草地产量，同时尽量减少化肥投入。在本文中，葡萄牙 SBP 的主要特性使用遥感和机器学习在六个不同的农场和两个生产年份（2018 年春季和 2019 年）进行了估计。考虑了四个牧场特征：地上站立生物量、豆科植物分数、植物氮 (N) 含量和植物磷 (P) 含量。遥感数据来自 Sentinel-2。使用了结合 5 个植被指数和 9 个协变量的光谱带。使用了多元线性回归、LASSO、Ridge、随机森林、XGBoost 和 LightGBM 回归模型。使用了两种交叉验证方法：(1) 随机选择褶皱 (RN-CV) 的随机方法，以及 (2) 结构化方法，其中每个褶皱都是农场和年份的独特组合，随后用于评估使用 8 个其他折叠 (LLYO-CV) 获得的模型的性能。结果表明，随机森林法对所有牧场特征的估计精度最好。关于交叉验证方法，使用 RN-CV 的算法对所有牧场特征具有更高的估计精度（平均降低 10% 左右的 RMSE 和 R 随后用于评估使用其他 8 个折叠 (LLYO-CV) 获得的模型的性能。结果表明，随机森林法对所有牧场特征的估计精度最好。关于交叉验证方法，使用 RN-CV 的算法对所有牧场特征具有更高的估计精度（平均降低 10% 左右的 RMSE 和 R 随后用于评估使用其他 8 个折叠 (LLYO-CV) 获得的模型的性能。结果表明，随机森林法对所有牧场特征的估计精度最好。关于交叉验证方法，使用 RN-CV 的算法对所有牧场特征具有更高的估计精度（平均降低 10% 左右的 RMSE 和 R² 85% 以上），与 LLYO-CV 的算法相比。但是，LLYO-CV 应该避免过度拟合并提高模型的泛化能力，因为在每个折叠中，模型都在未用于训练的农场和年份进行测试。所有变量的 RMSE 都非常低，尤其是在 RN-CV 中。Plant P 是 CV 方法的选择影响最小的变量（使用 RN-CV 的测试集的 RMSE：0.71 g P kg ^{- 1}；LLYO-CV：0.72 g P kg ^{- 1}）。常设生物量是 CV 方法之间差异最大的变量（RN-CV：722 kg ha ^-1；LLYO-CV：825 kg ha ^-1）。豆科植物和植物 N 的 RMSE 受到 CV 方法的中度影响（豆科植物 RN-CV：0.11；LLYO-CV：0.12 – 植物 N RN-CV：3.96 g N kg^{- 1} ; LLYO-CV：3.99 g N kg ^{- 1} )。这里开发的算法被应用于气候条件最不同的两个农场的整个地块，以证明它们未来在精准农业中的潜在用途。