Coal mining has caused significant soil nitrogen loss in mining areas, limiting reclamation and reuse in agriculture. This article studies the effects of organic fertilizer, inorganic fertilizer, and the combined application of Pseudomonas fluorescens with the ability of nitrogen fixation on soil nitrogen accumulation and composition in the reclamation area of the Tunlan Coal Mine from 2016 to 2022 under the conditions of equal nitrogen application, providing a scientific basis for microbial fertilization and the rapid increase in nitrogen content in the reclaimed soil of mining areas. The results showed that as the reclamation time increased, the nitrogen content and the composition and structure of the soil treated with fertilization rapidly evolved toward normal farmland soil. The soil nitrogen content increased most rapidly in the presence of added P. fluorescens + organic fertilizer (MB). Compared to other treatments (inorganic fertilizer (CF), organic fertilizer (M), and P. fluorescens + inorganic fertilizer (CFB)), MB increased total nitrogen (TN) to normal farmland soil levels 1–3 years earlier. The comprehensive scores of MB and CFB on the two principal components increased by 1.58 and 0.79 compared to those of M and CF treatments, respectively. This indicates that the combination of P. fluorescens and organic fertilizer improves soil nitrogen accumulation more effectively than the combination of P. fluorescens and inorganic fertilizer. In addition, the application of P. fluorescens increases the content of unknown nitrogen (UN) in acid-hydrolysable nitrogen (AHN) and decreases the content of amino acid nitrogen (AAN) and ammonia nitrogen (AN). However, there was no significant effect on the content of ammonium nitrogen (NH₄⁺-N) and nitrate nitrogen (NO₃⁻-N) in soil-mineralized nitrogen (SMN). When combined with inorganic fertilizer, the contribution of SMN to TN increased by 14.78%, while when combined with organic fertilizer, the contribution of AHN to TN increased by 44.77%. In summary, the use of P. fluorescens is beneficial for nitrogen recovery in the reclaimed soil of coal-mining areas. The optimal fertilization method under the experimental conditions is the combination of P. fluorescens and organic fertilizer.

Quickly and accurately identifying weed areas is of great significance for improving weeding efficiency, reducing pesticide residues, protecting soil ecological environment, and increasing crop yield and quality. Targeting low detection efficiency in complex agricultural environments and inability of multispectral input in weed recognition of minor grain based on unmanned aerial vehicles (UAVs), a semantic segmentation model for buckwheat weeds based on MSU-Net (multispectral U-shaped network) was proposed to explore the influence of different band optimizations on recognition accuracy. Five spectral features—red (R), blue (B), green (G), red edge (REdge), and near-infrared (NIR)—were collected in August when the weeds were more prominent. Based on the U-net image semantic segmentation model, the input module was improved to adaptively adjust the input bands. The neuron death caused by the original ReLU activation function may lead to misidentification, so it was replaced by the Swish function to improve the adaptability to complex inputs. Five single-band multispectral datasets and nine groups of multi-band combined data were, respectively, input into the improved MSU-Net model to verify the performance of our method. Experimental results show that in the single-band recognition results, the B band performs better than other bands, with mean pixel accuracy (mPA), mean intersection over union (mIoU), Dice, and F1 values of 0.75, 0.61, 0.87, and 0.80, respectively. In the multi-band recognition results, the R+G+B+NIR band performs better than other combined bands, with mPA, mIoU, Dice, and F1 values of 0.76, 0.65, 0.85, and 0.78, respectively. Compared with U-Net, DenseASPP, PSPNet, and DeepLabv3, our method achieved a preferable balance between model accuracy and resource consumption. These results indicate that our method can adapt to multispectral input bands and achieve good results in weed segmentation tasks. It can also provide reference for multispectral data analysis and semantic segmentation in the field of minor grain crops.

Coal mining has caused a significant loss of nitrogen content of soil in mining areas. This article studies the effects of organic fertilizer, inorganic fertilizer, and combined application of Pseudomonas fluorescens with the ability of nitrogen fixation on soil nitrogen accumulation and composition in the reclamation area of Tunlan Coal Mine from 2016 to 2022 under the condition of equal nitrogen application, providing scientific basis for microbial fertilization and rapid increase of nitrogen content in the reclaimed soil of mining areas. The results showed that as the reclamation time increased, the nitrogen content and its composition structure of the soil treated with fertilization rapidly evolved towards normal farmland soil. The soil nitrogen content increased the fastest in the treatment of Pseudomonas fluorescens + organic fertilizer (MB), compared with inorganic fertilizer (CF), organic fertilizer (M), and Pseudomonas fluorescens + inorganic fertilizer (CFB) treatments, the treatment of Pseudomonas fluorescens + organic fertilizer (MB) can bring the total nitrogen (TN) content of the soil to normal farmland soil levels 1-3 years earlier. The comprehensive scores of Pseudomonas fluorescens + organic fertilizer (MB) and Pseudomonas fluorescens + inorganic fertilizer (CFB) on the two principal components were increased 1.58 and 0.79 than those of organic fertilizer (M) and inorganic fertilizer (CF) treatments, respectively. This further indicates that the combination of Pseudomonas fluorescens and organic fertilizer has a better effect on improving soil nitrogen accumulation than the combination of Pseudomonas fluorescens and inorganic fertilizer. At the same time, the application of Pseudomonas fluorescens will increase the content of unknown nitrogen (UN) in acid-hydrolysable nitrogen (AHN), and decrease the content of amino acid nitrogen (AAN) and ammonia nitrogen (AN), relatively. However, there was no significant effect on the content of ammonium nitrogen (NH4+-N) and nitrate nitrogen (NO3--N) in soil inorganic nitrogen (SMN). When combined with inorganic fertilizer, the contribution of soil mineralized nitrogen (SMN) to total nitrogen (TN) increased by 14.78%, while when combined with organic fertilizer, the contribution of acid-hydrolysable nitrogen (AHN) to total nitrogen (TN) increased by 44.77%. In summary, the use of Pseudomonas fluorescens is beneficial for nitrogen recovery in the reclaimed soil of coal mining areas. The optimal fertilization method under the experimental conditions is the combination of Pseudomonas fluorescens and organic fertilizer.