Visible and near-infrared (Vis–NIR) spectroscopy enables the rapid prediction of soil properties but faces three limitations with conventional machine learning: information loss and overfitting from high-dimensional spectral features; inadequate modeling of nonlinear soil–spectra relationships; and failure to integrate multi-scale spatial features. To address these challenges, we propose ReSE-AP Net, a multi-scale attention residual network with spatial pyramid pooling. Built on convolutional residual blocks, the model incorporates a squeeze-and-excitation channel attention mechanism to recalibrate feature weights and an atrous spatial pyramid pooling (ASPP) module to extract multi-resolution spectral features. This architecture synergistically represents weak absorption peaks (400–1000 nm) and broad spectral bands (1000–2500 nm), overcoming single-scale modeling limitations. Validation on the LUCAS2009 dataset demonstrated that ReSE-AP Net outperformed conventional machine learning by improving the R² by 2.8–36.5% and reducing the RMSE by 14.2–69.2%. Compared with existing deep learning methods, it increased the R² by 0.4–25.5% for clay, silt, sand, organic carbon, calcium carbonate, and phosphorus predictions, and decreased the RMSE by 0.7–39.0%. Our contributions include statistical analysis of LUCAS2009 spectra, identification of conventional method limitations, development of the ReSE-AP Net model, ablation studies, and comprehensive comparisons with alternative approaches.

Rapid and accurate acquisition of soil composition information is essential for efficient land resource management and precision forestry. This study proposes a convolutional neural network (CNN) model to predict soil available potassium content using hyperspectral data. The goal is to establish a low‐cost, low‐risk, and environmentally friendly method for soil nutrient estimation. The main contributions of this work are as follows: (1) Three CNN models with different network structures and loss functions are developed and compared in terms of predictive performance. (2) A principal component regression (PCR) model is constructed as a baseline for comparison, highlighting the improvements achieved by deep learning methods. (3) To enhance the generalization ability of the CNN, a regularization term based on the L2 norm of the difference between adjacent weights is added to the mean square error loss function. This promotes smoother transitions between neighboring spectral bands and maintains spectral continuity. Experimental results on Eucalyptus plantation soil from the Huangmian Forest Farm show that the enhanced CNN model significantly outperforms the PCR model, achieving a root mean square error (RMSE) that meets practical application requirements. This research demonstrates the potential of CNN‐based approaches for rapid, accurate, and cost‐effective prediction of soil nutrient content. Moreover, the model’s performance was found to be competitive when compared with literature‐reported approaches, highlighting the robustness of the proposed method.

Accurate assessment of forest soil nitrogen from hyperspectral spectra is critical for precision fertilization, yet conventional preprocessing and baseline CNNs constrain predictive accuracy. We introduce streamlined spectral preprocessing and an optimized CNN–LSTM framework and evaluate it on Guangxi forest soils against competitive models using standard validation metrics. Results: The proposed approach outperformed comparative models (CNN, LSTM, and BiLSTM), achieving a validation set R² of 0.889 and RMSE of 16.5722, representing improvements of 6.79–10.37% in R² and 18.60–24.44% in RMSE over baseline methods. The method delivers accurate, scalable nitrogen estimation from spectra, supporting timely fertilization decisions and sustainable soil management.