Soil nutrients are essential factors that reflect farmland quality. Nitrogen, phosphorus, and potassium are essential elements for plants, while silicon is considered a “quasi-essential” element. This study investigated the spatial distribution of plant nutrients in soil in a hilly region of the Pearl River Delta in China. A total of 201 soil samples were collected from farmland topsoil (0–20 cm) for the analysis of total nitrogen (TN), available phosphorus (AP), available potassium (AK), and available silicon (ASi). The coefficients of variation ranged from 47.88% to 76.91%. The NSRs of TN, AP, AK, and ASi were 0.15, 0. 07, 0.12, and 0.13, respectively. The NSRs varied from 0.02 to 0.20. All variables exhibited weak spatial dependence (R2 < 0.5), except for TN (R2 = 0.701). After comparing the prediction accuracy of the different methods, we used the inverse distance weighting method to analyze the spatial distribution of plant nutrients in soil. The uniform spatial distribution of AK, TN overall showed a trend of increasing from northeast to southwest, and the overall spatial distribution of AP and ASi showed that the northeast was higher than the southwest. This study provides support for the delimitation of basic farmland protection areas, the formulation of land use spatial planning, and the formulation of accurate farmland protection policies.

Soil fertility affects crop yield and quality. A quick, accurate evaluation of soil fertility is crucial for agricultural production. Few satellite image-based evaluation studies have quantified soil fertility during the crop growth period. Therefore, this study proposes a new approach to the quantitative evaluation of soil fertility. Firstly, the optimal crop spectral variables were selected using the integration of an extreme gradient boosting (XGBoost) algorithm with variance inflation factor (VIF). Then, based on the optimal crop spectral variables where the red-edge indices were introduced for the first time, the estimation models were developed using the backpropagation neural network (BPNN) algorithm to assess soil fertility. The model was finally adopted to map the soil fertility using Sentinel-2 imagery. This study was performed in the Conghua District of Guangzhou, Guangdong Province, China. The results of our research are as follows: (1) five crop spectral variables (inverted red-edge chlorophyll index (IRECI), chlorophyll vegetation index (CVI), normalized green-red difference index (NGRDI), red-edge position (REP), and triangular greenness index (TGI)) were the optimal variables. (2) The BPNN model established with optimal variables provided reliable estimates of soil fertility, with the determination coefficient (R2) of 0.66 and a root mean square error (RMSE) of 0.17. A nonlinear relation was found between soil fertility and the optimal crop spectral variables. (3) The BPNN model provides the potential for soil fertility mapping using Sentinel-2 images, with an R2 of 0.62 and an RMSE of 0.09 for the measured and estimated results. This study suggests that the proposed method is suitable for the estimation of soil fertility in paddy fields.