Muhammad Mubeen

Partial replacement of chemical fertilizers, particularly nitrogen fertilizers, with biological fertilizers is considered an effective strategy for reducing the negative environmental impacts associated with excessive fertilizer use. This study aimed to optimize N use through the application of bacterial-based biofertilizer, specifically plant growth-promoting rhizobacteria (PGPR), in different maize cultivars under semi-arid conditions. A randomized complete block design (RCBD) arranged in a split-plot arrangement was used, with the three hybrids (Shahkar, Bumbus and DK 7024) assigned to the main plots and different N treatments allocated to sub-plots. The field experiment was conducted during two consecutive spring seasons (Feb to June 2024 and 2025). The N treatments were defined as follows: control, 100% recommended N (200 kg/ha), 100% N with Pseudomonas stutzeri, 100% N with Bacillus subtilis, 100% N with Enterobacter sp., 50% N with Pseudomonas stutzeri, 50% N with Bacillus subtilis, 50% N with Enterobacter sp., 100% Pseudomonas stutzeri, 100% Bacillus subtilis, and 100% Enterobacter sp. The N treatments included synthetic fertilizer alone at the 100% recommended N rate and a combination of 100%, 50% and 0% of recommended levels with three N-fixing bacterial strains. Among the hybrids, DK 7024 exhibited the highest 1000-grain weight (349 g and 362.5 g), grain yield (6756 and 6971 kg ha⁻¹) and total dry matter (17,500 and 18,368 kg ha⁻¹) in 2024 and 2025, respectively. Among N levels, maximum 1000-grain weight, grain yield and total dry matter were noticed in 100% N with Enterobacter sp.: 402 g, 8446 kg ha⁻¹ and 21,656 kg ha⁻¹ in 2024 and 421 g, 8684 kg ha⁻¹ and 22,237 kg ha⁻¹ in 2025. Nitrogen application increased grain yield and total dry matter production; however, the treatment combined with 100% recommended synthetic N fertilizer with biofertilizer (Enterobacter sp.) showed superior performance compared with 100% N applied through only the synthetic fertilizer. The interaction between maize hybrids and N levels was statistically non-significant, suggesting that 100% N plus biofertilizers could be an effective strategy for achieving higher yields across different maize cultivars. Additionally, the beneficial effects of PGPR may contribute to sustainable agricultural practices. Further research is recommended to evaluate strategies involving reduced-N inputs combined with biological fertilizer, including the application of 100% N with biofertilizer. The present study suggests that N application in combination with biofertilizers has the potential to improve crop growth while promoting sustainable crop production.

Crop classification during the early stages is challenging because of the striking similarity in spectral and texture features among various crops. To improve classification accuracy, this study proposes a novel fusion-based deep learning approach. The approach integrates textural and spectral features from a fused dataset generated by merging Landsat 8–9 and Sentinel-2A data using the Gram-Schmidt fusion approach. The textural features were extracted using the multi-patch Gray Level Co-occurrence Matrix (GLCM) technique. The spectral features, namely the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI), were obtained using the spectral index method. The five machine learning methods (deep neural network, 1D convolutional neural network, decision tree, support vector machine, and random forest) were trained using textural and spectral parameters to develop classifiers. The proposed approach achieves promising results using deep neural network (DNN), with an accuracy of 0.89, precision of 0.88, recall of 0.91, and F1-score of 0.90. These results demonstrate the effectiveness of the fusion-based deep learning approach in enhancing classification accuracy for early-stage crops.