Grasslands in Portugal are key managed ecosystems, supporting and providing a diverse number of ecosystem services. Here, we developed a procedure for rapid estimation of soil organic carbon (SOC) in soil samples of sown biodiverse permanent pastures rich in legumes (SBP) in Portugal. We combined laboratory NIR spectral data analysis with artificial neural networks (ANN) to estimate the SOC content of SBP soil samples. To train and test the ANN, we used more than 340 soil samples collected in the 0–20 cm topsoil layer from three farms in 2018 and 2019 and two other farms in 2019 only. The number of bands of the spectra (800–2778 nm) was reduced using two different approaches: (a) aggregation to Sentinel-2 (S2) bands using the average reflectance within each bandwidths; and (b) principal component analysis (PCA). For the S2 approach, we considered the six S2 bands that overlap with the spectral range of the instrument used. For the PCA approach, we considered the five first principal components. Additional covariates were used for prediction, including weather and terrain attributes, e.g. accumulated precipitation, average temperature, elevation, and slope. To test for transferability of the models to different farms, we used an eight-fold leave-one-out cross-validation approach to calculate estimation errors. Each fold is a unique combination of farm and year and is used to assess the model's performance calibrated from the seven other folds. The ANN was able to estimate both low and high SOC contents without systematic errors and with similar estimation errors for both full and reduced spectral data approaches. The average root mean squared error (RMSE) for the S2 approach was 1.95 g kg⁻¹ (0.45 – 2.33 g kg⁻¹ depending on the hold-out fold) and for the PCA approach was 1.81 g kg⁻¹ (0.74 – 2.42 g kg⁻¹) (compared to the average SOC content of 12 g kg⁻¹). These RMSE values were similar to the RMSE obtained using the full spectra, suggesting that the original spectral resolution could be reduced without losing information. These results suggest the potential for using remotely sensed data to estimate the variation of SOC content for SBP. They are a first step towards developing algorithms that can alleviate the cost and time of soil sampling and chemical SOC laboratory analysis through indirect estimation.

葡萄牙的草原是关键的管理生态系统，支持和提供多种生态系统服务。在这里，我们开发了一种快速估算葡萄牙富含豆类 (SBP) 的具有生物多样性的永久性牧场土壤样本中土壤有机碳 (SOC) 的程序。我们将实验室 NIR 光谱数据分析与人工神经网络 (ANN) 相结合来估计 SBP 土壤样品的 SOC 含量。为了训练和测试 ANN，我们使用了 2018 年和 2019 年从三个农场以及 2019 年仅从其他两个农场收集的 0-20 厘米表土层中收集的 340 多个土壤样本。使用两种不同的方法减少光谱 (800–2778 nm) 的波段数：(a) 使用每个带宽内的平均反射率聚合到 Sentinel-2 (S2) 波段；(b) 主成分分析 (PCA)。对于 S2 方法，我们考虑了与所用仪器的光谱范围重叠的六个 S2 波段。对于 PCA 方法，我们考虑了五个第一主成分。其他协变量用于预测，包括天气和地形属性，例如累积降水、平均温度、海拔和坡度。为了测试模型对不同农场的可转移性，我们使用了八折留一法交叉验证方法来计算估计误差。每个折叠都是农场和年份的独特组合，用于评估从其他七个折叠校准的模型性能。ANN 能够在没有系统误差的情况下估计低和高 SOC 含量，并且对于全光谱数据方法和简化光谱数据方法具有类似的估计误差。^-1（0.45 – 2.33 g kg ^-1取决于保留倍数）和 PCA 方法为 1.81 g kg ^-1（0.74 – 2.42 g kg ^-1）（与 12 g kg ^-的平均 SOC 含量相比）¹）。这些 RMSE 值与使用全光谱获得的 RMSE 相似，表明可以在不丢失信息的情况下降低原始光谱分辨率。这些结果表明使用遥感数据来估计 SBP SOC 含量变化的潜力。它们是开发算法的第一步，该算法可以通过间接估计减少土壤采样和化学 SOC 实验室分析的成本和时间。