Crop disease classification has always been a critical and persistent problem in the field of agricultural and forestry sciences, where often we do not have access to a sufficient number of samples to know the distribution of real-world samples. How to make full use of the existing data is the starting point of our thinking. To address this problem, this paper proposes a supervised image augmentation method Negative Contrast, which uses the contrast images of existing disease samples after removing disease areas as negative samples for image augmentation when samples are relatively scarce. Numerous experiments have shown that several classical models using this augmentation method have improved in disease classification of four crops, rice, wheat, corn, and soybean, with a maximum accuracy improvement of 30.8%. In addition, the comparative analysis of attentional heat map shows that the model using Negative Contrast is more accurate and intense on the area of interest of diseases, and thus reflects better generalization ability in real-world disease classification. Our dataset and codes can be found in https://www.kaggle.com/datasets/w970704112/corn-wheat-rice-soybean and https://github.com/hiter0/contrastaug .

Connected and Autonomous Vehicle (CAV) combines technologies of autonomous vehicle (AV) and connected vehicles (CV) to develop quicker, more reliable and safer traffic. Artificial Intelligence (AI) based CAV solutions play significant roles in sustainable city. The convergence imposes stringent security requirements for CAV safety and reliability. In practice, vehicles are developed with increased automation and connectivity. Increased automation increases the reliance on the sensor-based technologies and decreases the reliance on driver; increased connectivity increases the exposures of vehicles vulnerability and increases the risk for an adversary to implement a cyber-attack. Much work has been dedicated to identifying the security vulnerabilities and recommending mitigation techniques associated with different sensors, controllers, and connection mechanisms, respectively. However, there is an absence of comprehensive and in-depth studies to identify how the cyber-attacks exploit the vehicles vulnerabilities to negatively impact the performance and operations of CAV. In this survey, we set out to thoroughly review the security issues introduced by AV and CV technologies, analyze how the cyber-attacks impact the performance of CAV, and summarize the solutions correspondingly. The impact of cyber-attacks on the performance of CAV is elaborated from both viewpoints of intra-vehicle system and inter-vehicle system. We pointed out that securing the perception and operations of CAV would be the top requirement to enable CAV to be applied safely and reliably in practice. Also, we suggested to utilize cloud and new AI methods to defend against smart cyber-attacks on CAV.

Comparison with conventional reservoirs, the prediction of pressure in ultra-deep tight sandstone formations is difficult. The prediction of seismic pressure is more challenging than well logging pressure prediction. The main methods for seismic pressure prediction include equivalent depth method, Eaton method, Fillippone formula, and its modified versions. Among them, the Eaton method is widely used and has good effectiveness. However, this method relies on difficult-to-obtain normal compaction trend line, which leads to low prediction accuracy in space. To address this issue, a method combining the Eaton method and Collocated cokriging is proposed. The Eaton formula is used to predict formation pressure at the well, with compressional wave velocity as the covariate for predicting the main variable, formation pressure. By simulating the shear wave velocity based on seismic compressional wave velocity, the influence of various parameters on the prediction results is analyzed, and the accuracy of this method is verified by comparing it with other methods. The proposed method is then applied to predict formation pressure in the ultra-deep formations of the Junggar Basin. The simulation results show that the Collocated cokriging method achieves higher planar accuracy and better matches the experimental expectations in terms of prediction results. The application results also demonstrate the scientific effectiveness of the combined method, which has achieved good results in practical production applications.

The degradation and detachment of the polyamide (PA) layer in thin-film composite (TFC) membranes due to chlorine based chemical cleaning and material difference of PA layer and substrate are two major bottlenecks of forward osmosis (FO) technology. In this study, a new type of FO membranes were prepared by controlling self-polymerization of dopamine (DA) in the aqueous phase and the reaction with trimesoyl chloride (TMC) during interfacial polymerization (IP) process. These membranes were characterized by attenuated total reflection Fourier transform infrared (ATR-FTIR), X-ray photoelectron spectroscopy (XPS), field-emission scanning electron microscopy (FESEM) and water contact angle measurements. The influence of synthesis parameters such as pH of the aqueous phase, reaction time, temperature, and monomer concentrations were systematically investigated. The optimized membrane showed enhanced structure stability in ethanol (7.1 times higher) and chlorine resistance (72.3 times higher) than the conventional Piperazine(PIP)/TMC membrane due to（poly-dopamine）PDA bio-adhesion and polyester groups in the membrane structure. In general, DA/TMC membranes could be an effective strategy to fabricate high-performance FO membranes with excellent structural stability and chlorine resistance.

The Chang’e-4 (CE-4) lunar rover, equipped with The Visible and Near-IR Imaging Spectrometer(VNIS) which based on acousto-optic tunable filter spectroscopy, was launched to the far side of the moon on December 8, 2018. The detection band of VNIS ranges from 0.45 to 2.4μm. Because of the weak reflection of infrared radiation from the lunar surface, a static electronic phase-locked acquisition method is adopted in the infrared channel for signal amplification. In this paper, full-link simulations and modeling are conducted of the infrared channel information flow of the instrument. The signal/noise characteristics of VNIS are analyzed in depth, and the signal-to-noise(SNR) ratio prediction and laboratory verification are presented. On January 4, 2019, the VNIS started working successfully and acquired high-resolution spectrum data of the far side of the moon for the first time. Through analysis, the SNR ratio is in line with predictions, and the data obtained by VNIS in orbit are consistent with the information model proposed in this paper.

Mancozeb is extensively used fungicide to prevent citrus melanose in most Asian countries, especially in China. So far, however, there have been no reports of thet effect of Mancozeb on the citrus rhizosphere bacterial community. Therefore, this comparative experiment defined the genomic and functional related to community and soil health of 2-years old Citrus unshiu Marc. rhizosphere through amplicon sequencing and chemical analysis. This study evaluated the effect of mancozeb on the chemical properties of citrus-cultivated soil and the richness and diversity of rhizosphere bacterial community. We also investigated the abundance response of rhizosphere bacterial groups to 0, 2, 4, 6 and 8 times application of 2 g mancozeb (active ingredient content, ai.) 600 times diluted with water. Our data revealed that the abundance of rhizosphere-associated bacterial species increased significantly after planting citrus. The relative abundance of Candidatus, Saccharibacteria, Parcubacteria, and Proteobacteria increased with the increase in mancozeb watering times. Meanwhile, the abundance of Nitrospirae decreased with the increase in mancozeb application times. The findings indicated that the chemical properties of the soil and the richness and diversity of rhizosphere bacterial community did not significantly differ across the mancozeb gradients in soil.

porous silicon-based photodetectors have attracted more researches due to their high luminous efficiency, good stability and low cost. In this paper, a PbS quantum dots/porous silicon hybrid structure has been fabricated. The PbS quantum dots (QDs) partly infiltrated into the porous silicon (PSi) layer and partly deposited on its surface, which could increase the absorption of near-infrared wavelength range and extend the light absorption in silicon for wavelengths longer than 1100 nm. After that, A metal-semiconductor-metal (MSM) device is fabricated and its response spectrum could extend to the 1200 nm at -3 V. As a silicon-based photodetector (PD), one can envision its role for operation from visible light to short-wavelength infrared range.

To analyse Xuanwei ham flavour quality at different post-ripening times, and to elucidate its microbial diversity, we studied free amino acids and volatile flavouring compounds (VOCs) and their relationships. We determined microbial community changes in Xuanwei ham at 1, 2, 3 and 4 years (W1-4) by high-throughput sequencing, and simultaneously, VOCs and free amino acid contents by gas chromatography-mass spectrometry (GC-MS) and liquid chromatography (LC), respectively. Then heatmap analysis was used to determine correlations between microbial communities, free amino acids and VOCs. A total of 25 free amino acids were detected, among which W3 contained the fewest and most were generally lower than in hams in the other three years. Fifty-nine VOCs were detected, among which were 17 esters, and the highest ester content was found in W4. Atotal of 87508391 reads were obtained from the samples, of which 812844 were clean reads, and the bacterial Chao1 index and Shannon index were significantly higher in W3 than in the other three ham years. In differetly-aged Xuanwei hams, Pseudomonadota was the dominant bacterial phylum, and the most abundant genera were Sarocladium, Klebsiella and Vibrio. Klebsiella was the most abundant genus in W1, and Vibrio in W3, and the second most abundant genera were Sarocladium and Gammaretrovirus. We elucidated differences in Xuanwei ham microflora structures in different years and the main flavor-related microorganisms, thus providing a theoretical basis for subsequent Xuanwei ham storage, quality and improvement.