The technology for estimating soil properties using visible and near-infrared spectroscopy has been maturing, with corresponding advances and breakthroughs in deep learning models. In this study, based on the large soil spectral library LUCAS, we explore the potential of encoder-decoder structures to improve convolutional neural network regression predictions. By introducing an encoder-decoder structure into the feature channels of a six-layer CNN model (TRNN model), we significantly enhanced the performance of shallow CNN models and successfully carried out regression predictions for seven soil properties. We employed IntegratedGradients, DeepLift, GradientShap, and DeepLiftShap methods to interpret the output of the TRNN model. Our TRNN model, built on raw spectra, demonstrated high accuracy in predicting multiple soil properties, outperforming residual architectures, LSTMs, various CNN architectures, and other traditional machine learning methods proposed in previous studies. We also investigated the impact of multi-task output structures (TRNN 1-M and TRNN M−M) and single-task output structures (TRNN 1-1) on model performance. For the TRNN model with an encoder-decoder structure, multi-task output structures resulted in a reduction in performance. The TRNN showed outstanding results in regression analysis of the seven soil properties selected in this study (cation exchange capacity, organic carbon content, calcium carbonate content, pH, clay content, silt content, and sand content), with R2 values exceeding 0.93 for all seven properties. Different soil characteristics correspond to different wavelengths, with multiple characteristic peaks commonly observed. This research convincingly demonstrates the enormous potential of combining large model architectures with traditional deep learning approaches for predicting soil properties, which could significantly advance precision agriculture.

中文翻译：

---

使用编码器-解码器结构推进土壤特性预测，将传统深度学习方法集成到 Vis-NIR 光谱中


使用可见光和近红外光谱估计土壤特性的技术已经成熟，深度学习模型也取得了相应的进展和突破。在这项研究中，基于大型土壤光谱库 LUCAS，我们探索了编码器-解码器结构在改进卷积神经网络回归预测方面的潜力。通过在六层 CNN 模型 （TRNN 模型） 的特征通道中引入编码器-解码器结构，我们显著提高了浅层 CNN 模型的性能，并成功对 7 种土壤特性进行了回归预测。我们采用了 IntegratedGradients、DeepLift、GradientShap 和 DeepLiftShap 方法来解释 TRNN 模型的输出。我们的 TRNN 模型建立在原始光谱之上，在预测多种土壤特性方面表现出很高的准确性，优于残差结构、LSTM、各种 CNN 架构和以前研究中提出的其他传统机器学习方法。我们还研究了多任务输出结构（TRNN 1-M 和 TRNN M-M）和单任务输出结构（TRNN 1-1）对模型性能的影响。对于具有编码器-解码器结构的 TRNN 模型，多任务输出结构导致性能下降。TRNN 在本研究选择的 7 种土壤特性（阳离子交换能力、有机碳含量、碳酸钙含量、pH 值、粘土含量、淤泥含量和沙子含量）的回归分析中显示出出色的结果，所有 7 种特性的 R2 值都超过 0.93。不同的土壤特征对应于不同的波长，通常观察到多个特征峰。 这项研究令人信服地证明了将大型模型架构与传统深度学习方法相结合来预测土壤特性的巨大潜力，这可能会显着推动精准农业。