Multi-output neural network model for predicting biochar yield and composition.

In biomass pyrolysis for biochar production, existing prediction models face computational challenges and limited accuracy. This study curated a comprehensive dataset, revealing pyrolysis parameters' dominance in biochar yield (54.8 % importance). Pyrolysis temperature emerged as pivotal (PCC = -0.75), influencing yield significantly. Artificial Neural Network (ANN) outperformed Random Forest (RF) in testing set predictions (R2 = 0.95, RMSE = 3.6), making it apt for complex multi-output predictions and software development. The trained ANN model, employed in Partial Dependence Analysis, uncovered nonlinear relationships between biomass characteristics and biochar yield. Findings indicated optimization opportunities, correlating low pyrolysis temperatures, elevated nitrogen content, high fixed carbon, and brief residence times with increased biochar yields. A multi-output ANN model demonstrated optimal fit for biochar yield. A user-friendly Graphical User Interface (GUI) for biochar synthesis prediction was developed, exhibiting robust performance with a mere 0.52 % prediction error for biochar yield. This study showcases practical machine learning application in biochar synthesis, offering valuable insights and predictive tools for optimizing biochar production processes.

Noval bio-organic fertilizer containing Arthrobacter sp. DNS10 alleviates atrazine-induced growth inhibition on soybean by improving atrazine removal and nitrogen accumulation.

Herbicide atrazine restricts nutrient accumulation and thus inhibits the growth of sensitive crops. The application of organic fertilizer is a common measure that contributes to modulating abiotic tolerance of crops and providing nutrients, but its advantages in combination with atrazine degrading microorganisms as bio-organic fertilizer to alleviate atrazine stress on sensitive crops and the associated mechanisms are unknown. We investigated the beneficial effects of organic and bio-organic fertilizer (named DNBF10) containing Arthrobacter sp. DNS10 applications on growth, leaf nitrogen accumulation, root surface structure and root physiological properties of soybean seedlings exposed to 20 mg kg-1 atrazine in soil. Compared with organic fertilizer, bio-organic fertilizer DNBF10 exhibited more reduction in soil atrazine residue and plant atrazine accumulation, as well as alleviation in atrazine-induced root oxidative stress and damaged cells of soybean roots. Transcriptome analysis revealed that DNBF10 application enhanced nitrogen utilization by improving the expression of genes involved in nitrogen metabolism in soybean leaves. Besides, genes expression of cytochrome P450 and ABC transporters involved in atrazine detoxification and transport in soybean leaves were also down-regulated by DNBF10 to diminish phytotoxicity of atrazine to soybean seedlings. These results illustrate the molecular mechanism by which the application of DNBF10 alleviates soybean seedlings growth under atrazine stress, providing a step forward for mitigate the atrazine induced inhibition on soybean seedlings growth through decreasing atrazine residues as well as enhancing damaged root repair and nitrogen accumulation.

Mitigation of atrazine-induced oxidative stress on soybean seedlings after co-inoculation with atrazine-degrading bacterium Arthrobacter sp. DNS10 and inorganic phosphorus-solubilizing bacterium Enterobacter sp. P1.

Atrazine toxicity is one of the limiting factors inhibiting sensitive plant growth. Previous studies showed that atrazine-degrading bacteria could alleviate atrazine toxicity. However, there is limited information on how atrazine-degrading bacteria and plant growth-promote bacteria alleviate atrazine toxicity in soybeans. Therefore, the current study aimed to explore the atrazine removal, phosphorus utilization, and the oxidative stress alleviation of atrazine-degrading bacterium Arthrobacter sp. DNS10 and/or inorganic phosphorus-solubilizing bacterium Enterobacter sp. P1 in the reduction of atrazine toxicity in soybean. The results showed that atrazine exposure to soybean seedlings led to significant inhibition in growth, atrazine removal, and phosphorus utilization. However, the co-inoculatied strains significantly increased seedlings biomass, chlorophyll a/b contents, and total phosphorus in leaves accompanied by great reduction of the atrazine-induced antioxidant enzymes activities and malonaldehyde (MDA) contents, as well as atrazine contents in soil and soybeans under atrazine stress. Furthermore, transcriptome analysis highlighted that co-inoculated strains increased the expression levels of genes related to photosynthetic-antenna proteins, carbohydrate metabolism, and fatty acid degradation in leaves. All the results suggest that the co-inoculation mitigates atrazine-induced oxidative stress on soybean by accelerating atrazine removal from soil and phosphorus accumulation in leaves, enhancing the chlorophyll contents, and regulating plant transcriptome. It may be suggested that co-inoculation of atrazine-degrading bacteria and inorganic phosphorus-solubilizing bacteria can be used as a potential method to alleviate atrazine toxicity to the sensitive crops.