Self-supervised acoustic representation learning via acoustic-embedding memory unit modified space autoencoder for underwater target recognition.

Since the expensive annotation of high-quality signals obtained from passive sonars and the weak generalization ability of the single feature in the ocean, this paper proposes the self-supervised acoustic representation learning under acoustic-embedding memory unit modified space autoencoder (ASAE) and performs the underwater target recognition task. In the manner of the animal-like acoustic auditory system, the first step is to design a self-supervised representation learning method called space autoencoder (SAE) to merge Mel filter-bank (FBank) with the acoustic discrimination and gammatone filter-bank (GBank) with the anti-noise robustness into SAE spectrogram (SAE Spec). Meanwhile, due to poor high-level semantic information in SAE Spec, an acoustic-embedding memory unit (AEMU) is introduced as the strategy of adversarial enhancement. During the auxiliary task, more negative samples are joined in the improved contrastive loss function to obtain adversarial enhanced features called ASAE spectrogram (ASAE Spec). Ultimately, the comprehensive contrast experiments and ablation experiments on two underwater datasets show that ASAE Spec increases by more than 0.96% in accuracy, convergence rate, and anti-noise robustness of other mainstream acoustic features. The results prove the potential value of ASAE in practical applications.

Effects of biological nitrification inhibitor in regulating NH3 volatilization and fertilizer nitrogen recovery efficiency in soils under rice cropping.

Biological nitrification inhibitors are exudates from plant roots that can inhibit nitrification, and have advantages over traditional synthetic nitrification inhibitors. However, our understanding of the effects of biological nitrification inhibitors on nitrogen (N) loss and fertilizer N recovery efficiency in staple food crops is limited. In this study, acidic and calcareous soils were selected, and rice growth pot experiments were conducted to investigate the effects of the biological nitrification inhibitor, methyl 3-(4-hydroxyphenyl) propionate (MHPP) and/or a urease inhibitor (N-[n-butyl], thiophosphoric triamide [NBPT]) on NH3 volatilization, N leaching, fertilizer N recovery efficiency under a 20% reduction of the conventional N application rate. Our results show that rice yield and fertilizer N recovery efficiency were more sensitive to reduced N application in the calcareous soil than in the acidic soil. MHPP stimulated NH3 volatilization by 13.2% in acidic soil and 9.06% in calcareous soil but these results were not significant. In the calcareous soil, fertilizer N recovery efficiency significantly increased by 19.3% and 44.4% in the MHPP and NBPT+MHPP groups, respectively, relative to the reduced N treatment, and the rice yield increased by 16.7% in the NBPT+MHPP treatment (P < 0.05). However, such effects were not significant in the acidic soil. MHPP exerted a significant effect on soil ammonia oxidizers, and the response of abundance and community structure of ammonia-oxidizing archaea, ammonia-oxidizing bacteria, and total bacteria to MHPP depended on the soil type. MHPP+NBPT reduced NH3 volatilization, N leaching, and maintaining rice yield for a 20% reduction in conventional N fertilizer application rate. This could represent a viable strategy for more sustainable rice production, despite the inevitable increase in cost for famers.