SM-CycleGAN: crop image data enhancement method based on self-attention mechanism CycleGAN.

Crop disease detection and crop baking stage judgement require large image data to improve accuracy. However, the existing crop disease image datasets have high asymmetry, and the poor baking environment leads to image acquisition difficulties and colour distortion. Therefore, we explore the potential of the self-attention mechanism on crop image datasets and propose an innovative crop image data-enhancement method for recurrent generative adversarial networks (GANs) fused with the self-attention mechanism to significantly enhance the perception and information capture capabilities of recurrent GANs. By introducing the self-attention mechanism module, the cycle-consistent GAN (CycleGAN) is more adept at capturing the internal correlations and dependencies of image data, thus more effectively capturing the critical information among image data. Furthermore, we propose a new enhanced loss function for crop image data to optimise the model performance and meet specific task requirements. We further investigate crop image data enhancement in different contexts to validate the performance and stability of the model. The experimental results show that, the peak signal-to-noise ratio of the SM-CycleGAN for tobacco images and tea leaf disease images are improved by 2.13% and 3.55%, and the structural similarity index measure is improved by 1.16% and 2.48% compared to CycleGAN, respectively.

Multi-step prediction of carbon emissions based on a secondary decomposition framework coupled with stacking ensemble strategy.

Accurate prediction of carbon emissions is vital to achieving carbon neutrality, which is one of the major goals of the global effort to protect the ecological environment. However, due to the high complexity and volatility of carbon emission time series, it is hard to forecast carbon emissions effectively. This research offers a novel decomposition-ensemble framework for multi-step prediction of short-term carbon emissions. The proposed framework involves three main steps: (i) data decomposition. A secondary decomposition method, which is a combination of empirical wavelet transform (EWT) and variational modal decomposition (VMD), is used to process the original data. (ii) Prediction and selection: ten models are used to forecast the processed data. Then, neighborhood mutual information (NMI) is used to select suitable sub-models from candidate models. (iii) Stacking ensemble: the stacking ensemble learning method is innovatively introduced to integrate the selected sub-models and output the final prediction results. For illustration and verification, the carbon emissions of three representative EU countries are used as our sample data. The empirical results show that the proposed framework is superior to other benchmark models in predictions 1, 15, and 30 steps ahead, with the mean absolute percentage error (MAPE) of the proposed framework being as low as 5.4475% in Italy dataset, 7.3159% in France dataset, and 8.6821% in Germany dataset.

Microstructure and Friction Properties of CoCrFeMnNiTix High-Entropy Alloy Coating by Laser Cladding.

To enhance the friction and wear properties of 40Cr steel's surface, CoCrFeMnNi high-entropy alloy (HEA) coatings with various Ti contents were prepared using laser cladding. X-ray diffraction (XRD), scanning electron microscopy (SEM), and energy dispersive spectroscopy (EDS) were used to characterize the phase composition, microstructure, and chemical composition of the samples. The findings demonstrated that the CoCrFeMnNiTix HEA coatings formed a single FCC phase. Fe2Ti, Ni3Ti, and Co2Ti intermetallic compounds were discovered in the coatings when the molar ratio of Ti content was greater than 0.5. The EDS findings indicated that Cr and Co/Ni/Ti were primarily enriched in the dendrite and interdendrite, respectively. Ti addition can effectively enhance the coating's mechanical properties. The hardness test findings showed that when the molar ratio of Ti was 0.75, the coating's microhardness was 511 HV0.5, which was 1.9 times the hardness of the 40Cr (256 HV0.5) substrate and 1.46 times the hardness of the CrCrFeMnNi HEA coating (348 HV0.5). The friction and wear findings demonstrated that the addition of Ti can substantially reduce the coating's friction coefficient and wear rate. The coating's wear resistance was the best when the molar ratio of Ti was 0.75, the friction coefficient was 0.296, and the wear amount was 0.001 g. SEM and 3D morphology test results demonstrated that the coating's wear mechanism changed from adhesive wear and abrasive wear to fatigue wear and abrasive wear with the increase in Ti content.

Efficiently deep learning for monitoring Ipomoea cairica (L.) sweets in the wild.

Ipomoea cairica (L.) sweets are an invasive weed which has caused serious harm to the biodiversity and stability of the ecosystem. It is very important to accurately and rapidly identifying and monitoring Ipomoea cairica (L.) sweets in the wild for managements taking the necessary strategies to control the Ipomoea cairica (L.) sweets to rapidly grow in the wild. However, current approaches mainly depend on manual identification, which result in high cost and low efficiency. Satellite and manned aircraft are feasible assisting approaches, but the quality of the images collected by them is not well since the ground sampling resolution is low and cloud exists. In this study, we present a novel identifying and monitoring framework and method for Ipomoea cairica (L.) sweets based on unmanned aerial vehicle (UAV) and artificial intelligence (AI). In the proposed framework, we low-costly collected the images with 8256 × 5504 pixels of the monitoring area by the UAV and the collected images are split into more small sub-images with 224 × 224 pixels for identifying model. For identifying Ipomoea cairica (L.) sweets, we also proposed a novel deep convolutional neural network which includes 12 layers. Finally, the Ipomoea cairica (L.) sweets can be efficiently monitored by painting the area containing Ipomoea cairica (L.) sweets. In our experiments, we collected 100 raw images and generated 288000 samples, and made comparison with LeNet, AlexNet, GoogleNet, VGG and ResNet for validating our framework and model. The experimental results show the proposed method is excellent, the accuracy is 93.00% and the time cost is 7.439 s. The proposed method can achieve to an efficient balance between high accuracy and low complexity. Our method is more suitable for the identification of Ipomoea cairica (L.) sweets in the wild than other methods.

Facile synthetic routes for photocatalytic Pb3(BTC)2·H2O coordination polymers.

Herein, we report on the successful synthesis of photocatalytic Pb3(BTC)2·H2O polymers via different methods including the surfactant-assisted hydrothermal method, ultrasonic method and reflux method. As the crystal growth is subjected to preparation atmosphere, changes in reaction conditions do not alter the crystal structures of products, but vary their morphology. High ultraviolet-light-driven photocatalytic abilities are attributed to the stable Pb3(BTC)2·H2O, and the effective productions of h+ and ˙OH on the catalysts.

Synthesis of CdS-loaded (CuC10H26N6)3(PW12O40)2 for enhanced photocatalytic degradation of tetracycline under simulated solar light irradiation.

Largely discharged and excreted medical pollutants pose huge threats to ecosystems. However, typical photocatalysts, such as the Keggin-typed H3PW12O40, can hardly degrade these hazards under visible-light due to their broad bandgap and catalytic disability. In this work, the visible light harvesting was enabled by combining macrocyclic coordination compound CuC10H26N6Cl2O8 with H3PW12O40, and the resulting CuPW was loaded with CdS to reach robust catalytic ability to totally detoxify medicines. We prepared the CuPW-CdS composites through a facile precipitation method, and it showed excellent photocatalytic degradation for degrading tetracycline under visible-light irradiation. The (CuC10H26N6)3(PW12O40)2 with 10 wt% load of CdS shows the highest performance and is ∼6 times more efficient than the pure CuPW counterpart. The heterojunctional CuPW-CdS composites promote the separation of electrons and holes, and consequentially enhance photocatalytic activity. Thanks to migration of electrons from CdS to CuPW, the photocorrosion of CdS is prohibited, resulting in a high chemical stability during photocatalysis. In this work we design a new route to the multi-structural composite photocatalysts for practical applications in medical pollutant decontamination.

Optimizing the synthetic nitrogen rate to balance residual nitrate and crop yield in a leguminous green-manured wheat cropping system.

Nitrate that originates from agriculture is linked to a series of deleterious environmental consequences that are closely related to human health. Therefore, it is vital to design cropping systems that can produce acceptable crop yields while minimizing the impact of surplus soil nitrate. To develop quantitative estimations, data from 2008 to 2016 were evaluated using multiple regression models. A split-plot field experiment was conducted, with the main treatments of growing Huai bean, soybean and mung bean in summer as leguminous green manure (LGM) while fallow as the control. Four synthetic N rates (0, 108, 135 and 162kgha-1) were applied as sub-treatments at wheat seeding. The N accumulation for LGMs ranged from 61 to 90kgha-1, and that of Huai bean was 46% higher than the average value of soybean and mung bean (P<0.05). The threshold of total N for wheat to produce the highest yields was 141kgha-1. For the LGM treatments, residual nitrate accumulated below the root-zone soil was not significantly increased even when their total N inputs were higher than that of fallow with 162kgha-1 of synthetic N. The estimated nitrate-holding capacity of the root-zone soil for the LGM treatments ranged from 104 to 117kgha-1, and the corresponding synthetic N limits were 97-130kgha-1. Considering the target of producing high wheat yields while keeping the residual nitrate in the root-zone soil, the optimal synthetic N rates for LGM treatments were 52-80kgha-1. In conclusion, growing LGMs can maintain high crop yield and mitigate the environmental impact of residual nitrate by substantially replacing the synthetic N to avoid nitrate leaching to deeper soils.

Coupling life-cycle assessment and the RothC model to estimate the carbon footprint of green manure-based wheat production in China.

Reducing the carbon footprint (CF) of crop production is an efficient way to mitigate climate change. Growing legume green manure (LGM) instead of summer fallow may achieve this goal by lowering synthetic nitrogen (N) fertilizer needs and replenishing the depleted soil carbon (C) pool. The Rothamsted Carbon (RothC) model was incorporated into the Life-Cycle Assessment (LCA) to evaluate the present and projected CFs of green manure-based wheat production systems in dryland agriculture on the Loess Plateau of China. The field study included four main treatments (Huai bean, soybean and mung bean grown as green manure in summer and fallow as control) and four synthetic N rates (0, 108, 135 and 162kgNha-1) applied at wheat sowing. Soybean as LGM increased averaged wheat yield over 4 synthetic N rates by 8% compared with fallow (P<0.05), and synthetic N requirement was reduced by 33% without compromising the wheat yield for all the main treatments. Although LGM treatments had higher greenhouse gas (GHG) emissions from agricultural inputs, the greater amount of C inputs elevated the corresponding SOC stocks (SOCS) by 14-24% after 8years, thus significantly reducing the CF by 25-51% compared with fallow. The modelled SOCS equilibrium indicates that the CF for cropping systems with LGM will be 53-62% lower than fallow and 23-37% lower compared with their current level. In conclusion, introducing legume green manure instead of summer fallow is a highly efficient measure for persistent CF reduction, and coupling the RothC model and LCA is an alternative method to predict the long-term impact of different cropping systems on GHG emissions.

Soil Water Balance and Water Use Efficiency of Dryland Wheat in Different Precipitation Years in Response to Green Manure Approach.

Winter wheat (Triticum aestivum L.) monoculture is conventionally cultivated followed by two to three months of summer fallow in the Loess Plateau. To develop a sustainable cropping system, we conducted a six-year field experiment to investigate the effect of leguminous green manure (LGM) instead of bare fallow on the yield and water use efficiency (WUE) of winter wheat and the soil water balance (SWB) in different precipitation years in a semi-arid region of northwest China. Results confirmed that planting LGM crop consumes soil water in the fallow season can bring varied effects to the subsequent wheat. The effect is positive or neutral when the annual precipitation is adequate, so that there is no significant reduction in the soil water supplied to wheat. If this is not the case, the effect is negative. On average, the LGM crop increased wheat yield and WUE by 13% and 28%, respectively, and had considerable potential for maintaining the SWB (0-200 cm) compared with fallow management. In conclusion, cultivation of the LGM crop is a better option than fallow to improve the productivity and WUE of the next crop and maintain the soil water balance in the normal and wet years in the Loess Plateau.