Previous studies for retrieving soil moisture content (SMC) from visible and near-infrared hyperspectral data over vegetation-covered surfaces using spectral unmixing, non-negative matrix factorization, and albedo/vegetation coverage in trapezoid spaces have required mass spectral preprocessing and offered only limited improvements in prediction accuracy. Recently, deep learning has triggered some improvements in soil properties prediction from hyperspectral data because of its automatic feature extraction and high accuracy. In this study, hyperspectral data in a simulation experiment with different vegetation coverages, SMCs, and soil types were acquired. Deep learning models, one-dimensional convolutional neural network (1D-CNN), and long short-term memory network (LSTM) are proposed to predict SMC. The results showed that two deep learning models achieved excellent predictions (residual prediction deviation [RPD] > 2.5) using the unpreprocessed mixed spectra and partial least squares regression (PLSR) had a good prediction (RPD = 1.88). The 1D-CNN (R²_p = .91) and LSTM (R²_p = .90) significantly outperformed PLSR (R²_p = .72), which demonstrated that deep learning could improve SMC prediction over partially vegetation-covered surfaces. However, when only using bare soil spectra, the prediction accuracy was commensurate, whether through the 1D-CNN, LSTM, or PLSR models; additionally, 1D-CNN and LSTM had better performance on all mixed spectra than bare soil spectra. These results indicated that deep learning had no advantage on smaller datasets. We also found that SMC prediction with deep learning was affected by vegetation coverage and soil type but was still very good. The 1D-CNN and LSTM are effective models for predicting SMC with large hyperspectral datasets acquired from complex soil surface conditions.

中文翻译：

---

利用深度学习从高光谱数据预测部分植被覆盖表面的土壤水分含量

以前使用光谱解混、非负矩阵分解和梯形空间中的反照率/植被覆盖率从植被覆盖表面的可见光和近红外高光谱数据中检索土壤水分含量 (SMC) 的研究需要质谱预处理，并且仅提供有限的预测精度的提高。最近，由于其自​​动特征提取和高精度，深度学习在从高光谱数据中预测土壤特性方面取得了一些进步。在本研究中，获得了具有不同植被覆盖度、SMC 和土壤类型的模拟实验中的高光谱数据。提出了深度学习模型、一维卷积神经网络 (1D-CNN) 和长短期记忆网络 (LSTM) 来预测 SMC。结果表明，两个深度学习模型使用未预处理的混合谱实现了出色的预测（残差预测偏差 [RPD] > 2.5），偏最小二乘回归（PLSR）具有良好的预测（RPD = 1.88）。1D-CNN (R ² _p  = .91) 和 LSTM ( R ² _p  = .90) 显着优于 PLSR ( R ² _p = .72)，这表明深度学习可以改善部分植被覆盖表面的 SMC 预测。然而，当仅使用裸土光谱时，无论是通过 1D-CNN、LSTM 还是 PLSR 模型，预测精度都是相称的；此外，1D-CNN 和 LSTM 在所有混合光谱上都比裸土光谱具有更好的性能。这些结果表明深度学习在较小的数据集上没有优势。我们还发现深度学习的 SMC 预测受植被覆盖度和土壤类型的影响，但仍然非常好。1D-CNN 和 LSTM 是使用从复杂土壤表面条件获得的大型高光谱数据集预测 SMC 的有效模型。