Complexity Of Networks Research Articles

Response Characteristics and Community Assembly Mechanisms of nirS-Type Denitrifiers in the Alpine Wetland under Simulated Precipitation Conditions.

The nitrogen cycling process in alpine wetlands is profoundly affected by precipitation changes, yet the dynamic response mechanism of denitrifiers to long-term precipitation shifts in the alpine wetland of the Qinghai-Tibet Plateau remains enigmatic. Utilizing high-throughput sequencing analysis of nirS-type functional genes, this study delved into the dynamic response mechanism of nirS-type denitrifiers to precipitation changes in the alpine wetland of Qinghai Lake. The findings revealed that nirS-type denitrifiers in the alpine wetland of Qinghai Lake were primarily Proteobacteria, and Alpha diversity exhibited a negative correlation with the precipitation gradient, with deterministic processes predominating in the community assembly of denitrifying microbes. A 50% increase in rainfall shifted the community assembly process of denitrifiers from deterministic to stochastic. Dominant microflora at the genus level responded significantly to precipitation changes, with aerobic bacteria comprising the majority of differentially abundant taxa (55.56%). As precipitation increased, the complexity of the microbial interaction network decreased, and a 25% reduction in precipitation notably elevated the relative abundance of three key functional groups: chemoheterotrophic, aerobic chemoheterotrophic, and nitrogen fixation. Precipitation notably emerged as the primary regulator of nirS-type denitrifiers in the alpine wetland of Qinghai Lake, accounting for 51% of the variation in community composition. In summary, this study offers a fresh perspective for investigating the ecological processes of nitrogen cycling in alpine ecosystems by examining the diversity and community composition of nirS-type denitrifiers in response to precipitation changes.

Lightweight cattle pose estimation with fusion of reparameterization and an attention mechanism.

Heatmap-based cattle pose estimation methods suffer from high network complexity and low detection speed. Addressing the issue of cattle pose estimation for complex scenarios without heatmaps, an end-to-end, lightweight cattle pose estimation network utilizing a reparameterized network and an attention mechanism is proposed to improve the overall network performance. The EfficientRepBiPAN (Efficient Representation Bi-Directional Progressive Attention Network) module, incorporated into the neck network, adeptly captures target features across various scales while also mitigating model redundancy. Moreover, a 3D parameterless SimAM (Similarity-based Attention Mechanism) attention mechanism is introduced into the backbone to capture richer directional and positional feature information. We constructed 6846 images to evaluate the performance of the model. The experimental results demonstrate that the proposed network outperforms the baseline method with a 4.3% increase in average accuracy at OKS = 0.5 on the test set. The proposed network reduces the number of floating-point computations by 1.0 G and the number of parameters by 0.16 M. Through comparative evaluations with heatmap and regression-based models such as HRNet, HigherHRNet, DEKR, DEKRv2, and YOLOv5-pose, our method improves AP0.5 by at least 0.4%, reduces the number of parameters by at least 0.4%, and decreases the amount of computation by at least 1.0 GFLOPs, achieving a harmonious balance between accuracy and efficiency. This method can serve as a theoretical reference for estimating cattle poses in various livestock industries.

Macro-Nutrient Prediction of Paddy Field Soil Using Artificial Neural Network and NIR Spectroscopy

Understanding soil fertility, influenced by macronutrients like nitrogen, phosphorus, and potassium, is essential for adaptive agriculture implementation based on various soil conditions. Near-infrared spectroscopy technology provides non-destructive, rapid soil property measurements without chemicals, applicable both in-field and in-laboratory. However, the wide NIR spectrum range and neural network complexities can hinder Artificial Neural Network (ANN) training and inference, leading to time and resource inefficiency, especially without sophisticated computing devices. This study examines data reduction methods to enhance ANN performance in predicting soil macronutrients using NIR spectra. Multiple Linear Regression (MLR) and Principal Component Analysis (PCA) were applied to select wavelengths from the 1000–2500 nm for ANN input, comparing their performance. About 237 NIR reflectance data from paddy soil were transformed into absorbance data. MLR used forward selection to identify wavelengths with correlations higher than 0.9, while PCA selected wavelengths corresponding to the loading factor peaks for each principal component. These selected wavelengths served as inputs for the ANN model. The ANN’s performance was assessed using correlation and determination coefficients, RMSE, RPD, and model consistency. For nitrogen, the PCA+ANN model with reflectance spectra performed better (RPD 2.4-4.8) than the MLR+ANN model (RPD 2.2-2.6) using fewer wavelengths (5-9 for PCA+ANN vs. 9-12 for MLR+ANN). For phosphorus estimation, the PCA+ANN model also excelled (RPD 2.3-7.0 vs. 2.3-2.4) with fewer wavelengths (4-7 vs. 7). For potassium estimation, the PCA+ANN model showed superior performance (RPD 4.3-9.5 vs. 4.2-4.4), using the same number of wavelengths (4-8 vs. 4-6).

Bacterial Communities Associated with the Leaves and the Roots of Salt Marsh Plants of Bayfront Beach, Mobile, Alabama, USA.

Salt marshes are highly dynamic and biologically diverse ecosystems that serve as natural habitats for numerous salt-tolerant plants (halophytes). We investigated the bacterial communities associated with the roots and leaves of plants growing in the coastal salt marshes of the Bayfront Beach, located in Mobile, Alabama, United States. We compared external (epiphytic) and internal (endophytic) communities of both leaf and root plant organs. Using 16S rDNA amplicon sequencing methods, we identified 10 bacterial phyla and 59 different amplicon sequence variants (ASVs) at the genus level. Bacterial strains belonging to the phyla Proteobacteria, Bacteroidetes, and Firmicutes were highly abundant in both leaf and root samples. At the genus level, sequences of the genus Pseudomonas were common across all four sample types, with the highest abundance found in the leaf endophytic community. Additionally, Pantoea was found to be dominant in leaf tissue compared to roots. Our study revealed that plant habitat (internal vs. external for leaves and roots) was a determinant of the bacterial community structure. Co-occurrence network analyses enabled us to discern the intricate characteristics of bacterial taxa. Our network analysis revealed varied levels of ASV complexity in the epiphytic networks of roots and leaves compared to the endophytic networks. Overall, this study advances our understanding of the intricate composition of the bacterial microbiota in habitats (epiphytic and endophytic) and organs (leaf and root) of coastal salt marsh plants and suggests that plants might recruit habitat- and organ-specific bacteria to enhance their tolerance to salt stress.

Fungal community determines soil multifunctionality during vegetation restoration in metallic tailing reservoir

Microorganisms are pivotal in sustaining soil functions, yet the specific contributions of bacterial and fungal succession on the functions during vegetation restoration in metallic tailing reservoirs remains elusive. Here, we explored bacterial and fungal succession and their impacts on soil multifunctionality along a ∼50-year vegetation restoration chronosequence in China’s largest vanadium titano-magnetite tailing reservoir. We found a significant increase in soil multifunctionality, an index comprising factors pertinent to soil fertility and microbially mediated nutrient cycling, along the chronosequence. Despite increasing heavy metal levels, both bacterial and fungal communities exhibited significant increase in richness and network complexity over time. However, fungi demonstrated a slower succession rate and more consistent composition than bacteria, indicating their relatively higher resilience to environmental changes. Soil multifunctionality was intimately linked to bacterial and fungal richness or complexity. Nevertheless, when scrutinizing both richness and complexity concurrently, the correlations disappeared for bacteria but remained robust for fungi. This persistence reveals the critical role of the fungal community resilience in sustaining soil multifunctionality, particularly through their stable interactions with powerful core taxa. Our findings highlight the importance of fungal succession in enhancing soil multifunctionality during vegetation restoration in metallic tailing reservoirs, and manipulating fungal community may expedite ecological recovery of areas polluted with heavy metals.

Organic substitution contrasting direct fertilizer reduction increases wheat productivity, soil quality, microbial diversity and network complexity

Excessive use of chemical fertilizers negatively impacts crop productivity and farmland ecosystem, impeding sustainable agricultural progress. Consequently, there is an immediate need for a chemical fertilizer reduction strategy that ensures crop productivity and improves soil quality and the ecological environment of farmland. This study implemented a three-year (2018–2020) field experiment with two chemical fertilizer reduction methods (direct fertilizer reduction and organic substitution) to investigate their effects on wheat productivity, soil quality, heavy metal pollution risk and microbial characteristics. The results showed that organic substitution treatments (OF1, OF2 and OF3) improved most wheat plant (nutrient uptake and yield and its components) and soil properties (soil nutrients and carbon and nitrogen fractions), leading to increased crop productivity index (CPI, by 9.18 %-16.39 % and 14.14 %-23.36 %) and soil quality index (SQI, by 84.67 %-138.86 % and 104.11 %-175.91 %) compared to conventional fertilization (CF) and direct fertilizer reduction treatments (RF1, RF2 and RF3) in 2019 and 2020. Additionally, organic substitution enhanced the diversity and network complexity of bacterial community, while raising the soil pollution index (SPI, by 9.30 %-12.84 % and 12.20 %-18.49 %) without causing soil heavy metal pollution. Thus, it is recommended to adopt organic fertilizer substitution as the primary chemical fertilizer reduction strategy for wheat production. This approach will ensure crop yield, and improve soil quality and microbial characteristics, but its long-term application requires monitoring changes in soil heavy metals. Overall, this study provides guidelines for implementing scientific fertilization in agricultural practices, thus contributing to the health and sustainability of farmland ecosystems.

Metabolic Network Analysis Reveals Human Impact on Urban Nitrogen Cycles

Human interactions have led to the emergence of a higher complexity of urban metabolic networks; hence, traditional natural- or agriculture-oriented biogeochemical models might not be transferred well to urban environments. Increasingly serious environmental problems require the development of new concepts and models. Here, we propose a basic paradigm for urban–rural complex nitrogen (N) metabolic network reconstruction (NMNR) by introducing new concepts and methodologies from systems biology at the molecular scale, analyzing both local and global structural properties and exploring optimization and regulation methods. Using the Great Hangzhou Areas System (GHA) as a case study, we revealed that pathway fluxes follow a power law distribution, which indicates that human-dominated pathways constitute the principal part of the functions of the whole network. However, only 1.16% of the effective cycling pathways and an average hamming distance of only 5.23 between the main pathways indicate that the network lacks diverse pathways and feedback loops, which could lead to low robustness. Furthermore, more than half of the N fluxes did not pass through core metabolism, causing waste and pollution. We also provided strategies to design network structures and regulate system function: improving robustness and reducing pollution by referring to the characteristics of biochemical metabolic networks (e.g., the bow-tie structure). This method can be used to replace the trial-and-error method in system regulation and design. By decomposing the GHA N metabolic network into 4398 metabolic pathways and the corresponding fluxes with a power law distribution, NMNR helps us quantify the vulnerability in the current urban nitrogen cycle. The basic ideas and methodology in NMNR can be applied to coupled human and natural systems to advance global sustainable development studies, and they can also extend systems biology from the molecule to complex ecosystems and lead to the development of multi-scale unified theory in systems biology.

The Spatiotemporal Matching Relationship between Metro Networks and Urban Population from an Evolutionary Perspective: Passive Adaptation or Active Guidance?

With the operation of the first route in Xi’an City, the matching relationship between the metro networks and the urban population is a root factor affecting the utilization of rail transit facilities. The mismatch between the metro networks and the urban population has led to an imbalance between the supply and demand for rail transport, resulting in wasted urban infrastructure. Based on this issue, the research objective is to focus on the spatiotemporal variations of the matching relationship. Firstly, the topological network model abstractly extracted metro spatial distribution features, and the spatial autocorrelation model was adopted to identify the evolution characteristics of the metro networks and urban population. Secondly, this paper adopted a time-lagged regression model to demonstrate the action relationship from 2011 to 2021. Then, the compositive coordination index was utilized to assess the variation of the global matching relationship. Finally, the paper explored spatial heterogeneity through the coupling coherence degree attached to grid cells. The research results indicate that the Moran’s I value of metro elements decreased from 0.782 to 0.510 with the further complexity of topological networks, while the population was consistently high in spatial dependence with a Moran’s I value of around 0.75 during the decade. Based on the regression coefficients and significance, this paper verified the hypothesis that the metro networks and urban population had a positive time-lagged feedback effect in urban development. From 2011 to 2021, the compositive coordination index symbolizing the global matching relationship increased from 0.29 to 0.90, but the coupling coherence degree shows significant spatial heterogeneity in different grid units. Differentiated spatial planning strategies were proposed for varied areas to efficiently utilize rail transit, which may provide a reference for other cities with the same reality problem.

Machine Learning Big Data Set Analysis Reveals C-C Electro-Coupling Mechanism.

Carbon-carbon (C-C) coupling is essential in the electrocatalytic reduction of CO2 for the production of green chemicals. However, due to the complexity of the reaction network, there remains controversy regarding the underlying reaction mechanisms and the optimal direction for catalyst material design. Here, we present a global perspective to establish a comprehensive data set encompassing all C-C coupling precursors and catalytic active site compositions to explore the reaction mechanisms and screen catalysts via big data set analysis. The 2D-3D ensemble machine learning strategy, developed to target a variety of adsorption configurations, can quickly and accurately expand quantum chemical calculation data, enabling the rapid acquisition of this extensive big data set. Analyses of the big data set establish that (1) asymmetric coupling mechanisms exhibit greater potential efficiency compared to symmetric coupling, with the optimal path involving the coupling CHO with CH or CH2, and (2) C-C coupling selectivity of Cu-based catalysts can be enhanced through bimetallic doping including CuAgNb sites. Importantly, we experimentally substantiate the CuAgNb catalyst to demonstrate actual boosted performance in C-C coupling. Our finding evidence the practicality of our big data set generated from machine learning-accelerated quantum chemical computations. We conclude that combining big data with complex catalytic reaction mechanisms and catalyst compositions will set a new paradigm for accelerating optimal catalyst design.

BWO-BiLSTM & CNN composite model for prediction of atmospheric particulate matter mass concentration

Accurate prediction of the mass concentration of atmospheric particulate matter is of great significance for the rational formulation of atmospheric environment management strategies and the study of the spatial and temporal evolution of atmospheric pollutants. In order to solve the problems of low prediction accuracy and low efficiency of traditional prediction models, aiming at the nonlinear and stochastic characteristics of atmospheric particulate matter mass concentration changes, a composite prediction model based on Random Forest (RF) feature selection, Beluga Whale Optimization (BWO) algorithm, Convolutional Neural Network (CNN) and Bidirectional Long and Short-Term Storage Memory Neural Network (BiLSTM) is proposed in this paper. In this composite prediction model, the input variables are adjusted and screened through RF algorithm to reduce the network complexity. The weights and thresholds of CNN-BiLSTM are optimized using BWO to improve the prediction accuracy of the model. The publicly mass concentration data and Aerodynamic Particle Size Spectrometer (APS) measurements are used to train and compare with the predicted data. The experimental results indicate that this composite model has better prediction performance and prediction accuracy compared with the traditional single and the combined model. The fitting coefficient (R2) of PM2.5 prediction using publicly data and APS data can reach 0.8842 and 0.9762, respectively. The R2 for the prediction of PM10 using publicly data and APS data can reach 0.8635 and 0.976, respectively. It indicates that the model proposed in this paper has better generalization and robustness.

A Novel Model Combining Transformer and Bi-LSTM for News Categorization

News categorization (NC), the aim of which is to identify distinct categories of news through analyzing the contents, has acquired substantial progress since deep learning was introduced into the natural language processing (NLP) field. As a state-of-art model, transformer’s classification performance is not satisfied compared with recurrent neural network (RNN) and convolutional neural network (CNN) if it does not get pretrained. Based on the transformer model, this article proposes a novel framework that combines bidirectional long short-term memory (Bi-LSTM) network and transformer to solve this problem. In the suggested framework, the self-attention mechanism is substituted with Bi-LSTM to capture the semantic information from sentences. Meanwhile, an attention mechanism model is applied to focus on those important words and adjust their weights to solve the problem of long-distance information loss. With pooling network, the network complexity can be reduced and the main features can be highlighted by halving the dimension of the hidden state. Finally, after acquiring the hidden representation by the above structures, we utilize a contraction network to further capture the long-range associations from a text. Experiments on three large-scale corpora were performed to evaluate the suggested framework, and the results demonstrate that our model outperforms other models such as deep pyramid CNN (DPCNN), transformer.

Tab-Cox: An Interpretable Deep Survival Analysis Model for Patients With Nasopharyngeal Carcinoma Based on TabNet.

The nutritional status of cancer patients is closely associated with the clinical progression of the disease. A survival analysis model combined with a neural network can predict future disease trends in patients, facilitating early prevention and assisting physicians in making diagnoses. However, the complexity of neural networks and their incompatibility with medical tabular data can reduce the interpretability of the model. To address this issue, thr paper propose a novel survival analysis model called Tab-Cox, which combines TabNet and Cox models. This model is specifically designed to predict the survival outcomes of patients with nasopharyngeal carcinoma. The model utilizes TabNet's sequential attention mechanism to extract more interpretable features, providing an interpretable method for identifying disease risk factors. Consequently, the model ensures accurate survival prediction while also making the results more comprehensible for both patients and doctors. The paper tested the efficacy of the model by conducting experiments on various diverse datasets in comparison with other commonly used survival models. The results showed that the proposed model delivered the highest or second-highest accuracy across all datasets. Furthermore, the paper conducted a comparative interpretability analysis against the classical Cox model. In addition and compare the interpretability of the Tab-Cox model with the classical Cox model and discuss the advantages and disadvantages of its interpretability. This demonstrates that Tab-Cox can assist doctors in identifying risk factors that are challenging to capture using artificial methods.

Dynamic simulation of policy-driven green technology innovation networks: Digital empowerment and collaborative efficiency

To delve into the intricate dynamics of green innovation, it is imperative to establish a policy-driven green innovation network and optimize its multi-entity collaborative mechanism. Given the dynamic complexity of a technological innovation network composed of multiple entities, this paper examines the interactions among four subsystems based on system dynamics (SD) simulation: resource input, innovation performance, policy-driven, and digital empowerment subsystem. Furthermore, we analyze the combined effects of policy-driven initiatives and the role of digital platforms in facilitating innovation efficiency based on empirical evidence. The results indicate that: (1) Government can effectively promote green development by enforcing stronger environmental regulations, such as increasing carbon trading price, while enhancing the emission reduction efficiency of innovative products. (2) Increased per capita R&D investment, along with financial, tax, fiscal incentives for innovation investment, will increase the rate of innovation achievements. (3) Government should strengthen talent policy during anticipated increases in talent numbers and reduce the intensity of introductions during expected declines. (4) By implementing incentive policies to develop S&T platforms, government can broaden innovation network cooperation, promotes resource aggregation, and leverages multi-entity cohort effects.

Salivary IL-1β, IL-6, and IL-10 Are Key Biomarkers of Periodontitis Severity.

To explore severity and progression biomarkers, we examined the clinical relevance of multiple cytokines and mediators involved in the inflammatory response in periodontitis. A cohort of 68 patients was enrolled in the study and periodontal status assessed by the current classification of periodontal diseases. Immune mediators present in saliva, of both patients and healthy controls, were quantified using a Legendplex-13 panel. Clinic parameters were significantly higher in PD patients compared with HC, with a strong significant association with the disease severity (stage) (p < 0.001), but not with progression (grade). The panel of immune mediators evidenced elevated levels of pro-inflammatory cytokines IL-6 and IL-1β as disease established (p < 0.01). IL-1β/IL-1RA ratio was increased in PD patients, being associated with disease stage. An anti-inflammatory response was spotted by higher IL-10. Lower levels of IL-23 and IP-10 were associated with disease severity. No significant statistical differences were found by grade classification. Moreover, salivary IL-1β and IL-6 exhibited significant positive correlations with several clinical measurements (PI, BOP, PPD, CAL), while IP-10 showed a statistical negative correlation with BOP, PPD, and CAL. These insights highlight the complexity of the periodontitis inflammatory network and the potential of cytokines as biomarkers for refined diagnostic and therapeutic strategies.

Association between plant microbiota and cadmium uptake under the influence of microplastics with different particle sizes

Plant microbiota are an important factor impacting plant cadmium (Cd) uptake. However, little is known about how plant microbiota affects the Cd uptake by plants under the influence of microplastics (MPs) with different particle sizes. In this study, bacterial structure and assembly in the rhizosphere and endosphere in pakchoi were analyzed by amplicon sequencing of 16S rRNA genes under the influence of different particle sizes of polystyrene microplastics (PS-MPs) combined with Cd treatments. Results showed that there were no significant differences observed in the shoot endophytes among different treatments. However, compared to Cd treatment, larger-sized PS-MPs (2 and 20 μm) significantly increased community diversity and altered the structural composition of rhizosphere bacteria and root endophytes, while smaller-sized PS-MPs (0.2 μm) did not. Under the treatment of larger-sized PS-MPs, the niche breadth of rhizosphere bacteria and root endophytes were significantly increased. And larger-sized PS-MPs also maintained stability and complexity of bacterial co-occurrence networks, while smaller-sized PS-MPs reduced them. Furthermore, compared to Cd treatment, the addition of larger particle size PS-MPs decreased the proportion of homogeneous section, while increased the proportion of drift in root endophytic bacterial community assembly. The role of larger-sized MPs in the community assembly of rhizosphere bacteria was opposite. Using random forest and structural equation models, the study found that larger-sized PS-MPs can promote the colonization of specific bacterial taxa, such as Brevundimonas, AKAU4049, SWB02, Ellin6055, Porphyrobacter, Sphingorhabdus, Rhodobacter, Erythrobacter, Devosia and some other bacteria belonging to Alphaproteobacteria, in the rhizosphere and root endosphere. The colonization of these taxa can may induce the formation of biofilms in the roots, immobilize heavy metals through oxidation processes, and promote plant growth, thereby reducing Cd uptake by pakchoi. The findings of this study provide important insights into the microbial mechanisms underlying the influence of MPs with different particle sizes on plant Cd uptake.

Beyond Inca roads: the Redes Andinas project explores complex palimpsests of Andean road networks

AbstractThe Redes Andinas (Andean Networks) project assesses the complexity of ancient road networks in the archaeological record in the Andes, beyond the Inca roads system. A multiscale methodological approach allows us to characterise the transformation and resilience of the road networks over the past millennium, in the context of the 18°South parallel's vertical transect.

Enhanced nutrient supply promotes mutualistic interactions between cyanobacteria and bacteria in oligotrophic ocean.

Cyanobacteria can form complex interactions with heterotrophic microorganisms, but this relationship is susceptible to nutrient concentrations. Disentangling the cyanobacteria-bacteria interactions in relation to nutrient supply is essential to understanding their roles in geochemical cycles under global change. We hypothesize that enhanced nutrient supply in oligotrophic oceans can promote interactions among cyanobacteria and bacteria. Therefore, we investigated the planktonic bacteria and their interactions with cyanobacteria in relation to elevated nutrients caused by enhanced upwelling around a shallow and a deep seamount in the tropical western Pacific Ocean. We found obviously higher complexity of network occurred with significantly more cyanobacteria in the deep chlorophyll maximum layer ofthe shallow seamount when compared with that ofthe deep seamount. Cyanobacteria can shape bacterial interaction and community evenness in response to relatively high nutrient concentrations. The effects of the nutrients on cyanobacteria-related networks were further estimated based on the Tara Oceans data. Statistical analyses further showed a facilitative effect of nitrate concentrations on cyanobacteria-bacteria mutualistic interactions in the global oligotrophic ocean. By analysing the Tara Ocean macrogenomic data, we detected functional genes related to cyanobacteria-bacteria interactions in all samples, indicating the existence of a mutualistic relationship. Our results reveal cyanobacteria-bacteria interaction in response to nutrient elevation in oligotrophic ocean and highlight the potentially negative effects of global change on the bacterial community from the view of the bio-interaction.

Neural Network Models for Ionospheric Electron Density Prediction at a Fixed Altitude Using Neural Architecture Search

AbstractSpecification and forecast of ionospheric parameters, such as ionospheric electron density (Ne), have been an important topic in space weather and ionospheric research. Neural networks (NNs) emerge as a powerful modeling tool for Ne prediction. However, heavy manual adjustments are time consuming to determine the optimal NN structures. In this work, we propose to use neural architecture search (NAS), an automatic machine learning method, to mitigate this problem. NAS aims to find the optimal network structure through the alternate optimization of the hyperparameters and the corresponding network parameters within a pre‐defined hyperparameter search space. A total of 16‐year data from Millstone Hill incoherent scatter radar (ISR) are used for the NN models. One single‐layer NN (SLNN) model and one deep NN (DNN) model are both trained with NAS, namely SLNN‐NAS and DNN‐NAS, for Ne prediction and compared with their manually tuned counterparts (SLNN and DNN) based on previous studies. Our results show that SLNN‐NAS and DNN‐NAS outperformed SLNN and DNN, respectively. These NN predictions of Ne daily variation patterns reveal a 27‐day mid‐latitude topside Ne variation, which cannot be reasonably represented by traditional empirical models developed using monthly averages. DNN‐NAS yields the best prediction accuracy measured by quantitative metrics and rankings of daily pattern prediction, especially with an improvement in mean absolute error more than 10% compared to the SLNN model. The limited improvement of NAS is likely due to the network complexity and the limitation of fully connected NN without the time histories of input parameters.

Spartina alterniflora invasion reduces soil microbial diversity and weakens soil microbial inter-species relationships in coastal wetlands.

Soil microorganisms play a crucial role in the plant invasion process, acting as both drivers of and responders to plant invasion. However, the effects of plant invasion on the complexity and stability of co-occurrence networks of soil microbial communities remain unclear. Here, we investigated how the invasion of Spartina alterniflora affected the diversity, composition, and co-occurrence networks of soil bacterial and fungal communities in the Yellow River Delta, China. Compared to the native plant (Suaeda salsa), S. alterniflora invasion decreased the α-diversity of soil bacterial communities but did not affect that of fungal communities. The β-diversity of soil bacterial and fungal communities under S. salsa and S. alterniflora habitats also differed dramatically. S. alterniflora invasion increased the relative abundance of the copiotrophic phylum Bacteroidota, whereas decreased the relative abundances of the oligotrophic phyla Acidobacteriota and Gemmatimonadota. Additionally, the relative abundance of Chytridiomycota, known for its role in degrading recalcitrant organic matter, increased substantially within the soil fungal community. Functional predictions revealed that S. alterniflora invasion increased the relative abundance of certain soil bacteria involved in carbon and nitrogen cycling, including aerobic chemoheterotrophy, nitrate reduction, and nitrate respiration. More importantly, S. alterniflora invasion reduced the complexity and stability of both soil bacterial and fungal community networks. The shifts in soil microbial community structure and diversity were mainly induced by soil available nutrients and soil salinity. Overall, our study highlights the profound impacts of S. alterniflora invasion on soil microbial communities, which could further indicate the modification of ecosystem functioning by invasive species.

Singular value decomposition for single-phase flow and cluster identification in heterogeneous pore networks

Pore networks play a key role in understanding and quantifying flow and transport processes in complex porous media. Realistic pore-spaces may be characterized by singular regions, that is, isolated subnetworks that do not connect inlet and outlet, resulting from unconnected porosity or multiphase configurations. The robust identification of these features is critical for the characterization of network topology and for the solution of the set of linear equations of flow and transport. We propose a robust method based on singular value decomposition to solve for network flow and locate isolated subnetworks simultaneously. The performance of the method is demonstrated for pore networks of different complexity.