Work

Smart agriculture technology: Real-time generation method of local soil property distribution maps based on WGAN-GPM

Year: 2025

Type: article

Abstract: With the advancement of smart agriculture, precision variable-rate seeding requires high-resolution soil information. However, existing methods still fall short in generating localized soil property maps in real time, limiting inter-row seeding control for wide-span planters. To address this challenge, this paper proposes the Local Soil property distribution maps Generation Network (LSGN), based on the Wasserstein Generative Adversarial Network with Gradient Penalty and Mean squared error (WGAN-GPM). This proposed model integrates a Vision Transformer (ViT) encoder with convolutional and deconvolutional Residual Networks (ResNet), significantly improving feature extraction from discrete soil property data and enhancing the reconstruction accuracy of localized soil maps. The model adopts a two-stage training strategy. First, it performs self-supervised pre-training using local soil property maps with neighborhood information, enabling the network to learn spatial correlations and improve boundary prediction. Second, the pretrained weights are transferred into a WGAN-GPM adversarial training framework, which combines Wasserstein distance, gradient penalty, and Mean Squared Error (MSE) loss to jointly optimize the generator and discriminator. This ensures both pixel-level accuracy and distributional consistency. Compared to standard Generative Adversarial Networks (GANs), the WGAN-GPM-trained LSGN prediction reduces Relative Error Average (REA) by over 1.02 %, RMSE by over 0.16, and Kullback–Leibler Divergence (KLD) by over 1.76 × 10 −4 , while increasing Peak Signal-to-Noise Ratio (PSNR) by over 2.43. LSGN achieves REA values of 0.41 %, 1.19 %, and 1.80 % for planting widths of four, six, and eight rows, respectively, outperforming traditional generative models. Field cross-validation further shows that, relative to Kriging interpolation, LSGN reduces boundary region prediction errors by up to 2.42 % and central region errors by 0.97 %. Overall, the REA in local distribution maps decreases by more than 1.5 %, and RMSE is reduced by over 0.4. This study demonstrates that LSGN enables real-time high-precision soil mapping, providing a practical solution for precision seeding. • Proposed a variable seeding technology using real-time local soil property maps. • Proposed a network for generating local soil property distribution maps. • Improved training strategies of generative adversarial networks to enhance stability. • Generated multi-sized soil property maps to suit different wide-type corn seeders. • Provided technical support for improving variable seeding accuracy in corn.

Source: Artificial Intelligence in Agriculture

DOI: 10.1016/j.aiia.2025.10.014