Abstract
Exchangeable aluminum (Exc-Al), an often overlooked yet indispensable soil parameter, predominantly contributes to soil exchangeable acidity. In this study, we utilized data from 53 sets of surface and subsurface black soil characteristics, including Exc-Al, exchangeable acid (Exc-acid), pH, soil organic matter (SOM), and available and total nutrient levels, to develop a neural network prediction model for estimating Exc-Al and Exc-acid in the black soil area of northeast China. The deterministic neural network model (NNM) was employed to predict Exc-Al and Exc-acid contents in 690 sets of surface and subsurface farmland soil samples with unknown Exc-Al and Exc-acid values. Subsequently, a black soil exchangeable acidity map for northeast China was generated through spatial interpolation. Our results revealed that the average Exc-Al and Exc-acid contents in the 53 surface soils were 0.82 and 0.93 cmol kg−1, respectively, while those in the corresponding subsurface soils were 0.58 and 0.70 cmol kg−1, respectively. Multi-layer perceptron (MLP) neural networks effectively simulated Exc-Al and Exc-acid contents in the surface and subsurface black soils, with calibrated determination coefficients (Radj2) of 0.95–0.96, relative root mean square errors (rRMSE) of 17.3%–24.8%, and statistical significance α at 0.001. The MLP estimations and spatial interpolations revealed that 2.0% and 17.6% of the surface black soil area, and 0% and 3.7% of the subsurface soil area exhibited Exc-Al content exceeding 2.0 and 1.0 cmol kg−1, respectively. Furthermore, 6.7% and 24.9% of the surface black soil area, and 0% and 6.3% of the subsurface soil area showed Exc-acid content exceeding 2.0 and 1.0 cmol kg−1, respectively. These findings break the limitation of relying solely on soil pH as the unique indicator, enrich our knowledge of black soil exchangeable acidity, and enhance our understanding of the black soil acidity status in northeast China.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.