Attention-LSTM based prediction model for aircraft 4-D trajectory.

Aviation activities are constantly increasing as a result of the growth of the global economic system. How to increase airspace capacity within the limited airspace resources while ensuring smooth and safe aircraft operations is a challenge for civil aviation today. Air traffic safety is supported by accurate trajectory prediction. The way-points are relatively sparse, and there are many uncertain factors in the flight, which greatly increases the difficulty of trajectory prediction. So, it is vital to enhance trajectory prediction accuracy. An attention-LSTM trajectory prediction model is proposed in this paper, which is split into two parts. The time-series features of the flight trajectory are extracted in the initial stage using the long-short-term memory neural network (LSTM). In the second part, the attention mechanism is employed to process the extracted sequence features. The impact of secondary elements is reduced while the influence of primary ones is increased according to the attention mechanism. We used the advanced models in trajectory prediction as the comparison models, such as LSTM, support vector machine (SVM), back propagation (BP) neural network, Hidden Markov Model (HMM), and convolutional long-term memory neural network (CNN-LSTM). The model we proposed is superior to the model above based on quantitative analysis and comparison.

Maize and peanut intercropping improves the nitrogen accumulation and yield per plant of maize by promoting the secretion of flavonoids and abundance of Bradyrhizobium in rhizosphere.

Belowground interactions mediated by root exudates are critical for the productivity and efficiency of intercropping systems. Herein, we investigated the process of microbial community assembly in maize, peanuts, and shared rhizosphere soil as well as their regulatory mechanisms on root exudates under different planting patterns by combining metabolomic and metagenomic analyses. The results showed that the yield of intercropped maize increased significantly by 21.05% (2020) and 52.81% (2021), while the yield of intercropped peanut significantly decreased by 39.51% (2020) and 32.58% (2021). The nitrogen accumulation was significantly higher in the roots of the intercropped maize than in those of sole maize at 120 days after sowing, it increased by 129.16% (2020) and 151.93% (2021), respectively. The stems and leaves of intercropped peanut significantly decreased by 5.13 and 22.23% (2020) and 14.45 and 24.54% (2021), respectively. The root interaction had a significant effect on the content of ammonium nitrogen (NH4 +-N) as well as the activities of urease (UE), nitrate reductase (NR), protease (Pro), and dehydrogenase (DHO) in the rhizosphere soil. A combined network analysis showed that the content of NH4 +-N as well as the enzyme activities of UE, NR and Pro increased in the rhizosphere soil, resulting in cyanidin 3-sambubioside 5-glucoside and cyanidin 3-O-(6-Op-coumaroyl) glucoside-5-O-glucoside; shisonin were significantly up-regulated in the shared soil of intercropped maize and peanut, reshaped the bacterial community composition, and increased the relative abundance of Bradyrhizobium. These results indicate that interspecific root interactions improved the soil microenvironment, regulated the absorption and utilization of nitrogen nutrients, and provided a theoretical basis for high yield and sustainable development in the intercropping of maize and peanut.