Multiscale Process Research Articles

3D printed feathers with embedded aerodynamic sensing.

Bird flight is often characterized by outstanding aerodynamic efficiency, agility and adaptivity in dynamic conditions. Feathers play an integral role in facilitating these aspects of performance, and the benefits feathers provide largely derive from their intricate and hierarchical structures. Although research has been attempted on developing membrane-type artificial feathers for bio-inspired aircraft and micro air vehicles (MAVs), fabricating anatomically accurate artificial feathers to fully exploit the advantages of feathers has not been achieved. Here, we present our 3D printed artificial feathers consisting of hierarchical vane structures with feature dimensions spanning from 10-2 to 102 mm, which have remarkable structural, mechanical and aerodynamic resemblance to natural feathers. The multi-step, multi-scale 3D printing process used in this work can provide scalability for the fabrication of artificial feathers tailored to the specific size requirements of aircraft wings. Moreover, we provide the printed feathers with embedded aerodynamic sensing ability through the integration of customized piezoresistive and piezoelectric transducers for strain and vibration measurements, respectively. Hence, the 3D printed feather transducers combine the aerodynamic advantages from the hierarchical feather structure design with additional aerodynamic sensing capabilities, which can be utilized in future biomechanical studies on birds and can contribute to advancements in high-performance adaptive MAVs.&#xD.

Seeing the Big‐ to Fine‐Grained Picture: Exploring the Baseline Status of Mammal Occupancy Across Myanmar Using Scale‐Optimised Modelling

ABSTRACTAimMyanmar, an Indo‐Burmese biodiversity hotspot, lacks baseline data on species occurrence and distribution. This hinders biodiversity monitoring and optimisation of conservation and development plans. We aim to document baseline mammal occupancy, interactions with environmental factors and scale‐dependent responses.LocationHkakaborazi National Park, Htamanthi Wildlife Sanctuary, Alaungdaw Kathapa National Park, Rakhine Yoma Elephant Range, Say Taung and Myinmoletkhat Key Biodiversity Areas distributed across Myanmar.MethodsCamera trap data throughout Myanmar were used to analyse species occupancy. We conducted a multiscale hierarchical spatial modelling process, using local and pooled data across Myanmar. We also optimised spatial scale across five scales and six predictors, using univariate occupancy models. We then selected scale‐optimised variables for multivariate modelling, repeating this process for each species across local, regional and national datasets.ResultsThe study identified 47 terrestrial species and observed strong scale‐dependent nonstationarity in occupancy estimates. Relationships with environmental variables differed among species and were highly scale dependent. Importantly, occupancy estimates produced by pooling data across sites were greatly different from any of the estimates for the individual sites, suggesting that high heterogeneity in occurrence and abundance across sites among species requires local or nested occupancy estimates to account for spatial heterogeneity and variation.Main ConclusionsFuture conservation efforts should focus on Northern Myanmar if range‐restricted and rare species are to be protected, while focus should still be given to common species which serve as potential indicators of overall community structure. The nonstationarity of occupancy results from different datasets underscores the potential for misleading interpretations from aggregated data in nonstationary ecological systems. Metareplicated analyses of local, geographically and ecologically proximal regional datasets provide an important view of spatial variation in occupancy patterns guiding conservation design and improving understanding of the drivers of biodiversity patterns and change across large regions, such as Southeast Asia.

Multiscale Processes Drive Formation of Logjam Habitats and Use by Juvenile Chinook Salmon Across a Boreal Stream Network in Alaska

Multiscale Processes Drive Formation of Logjam Habitats and Use by Juvenile Chinook Salmon Across a Boreal Stream Network in Alaska

Phase unwrapping via fully exploiting global and local spatial dependencies

Phase unwrapping (PU) is the process of extracting the authentic phase image from its noisy wrapped measurements, playing a crucial role in scientific imaging techniques. PU requires solving a challenging non-linear ill-posed problem, particularly in the presence of noticeable noise. In recent years, deep learning has emerged as a promising approach for PU. Inspired by the success of convolutional neural networks (CNNs) in image restoration, many existing works trained CNNs for PU. However, due to the locality of convolutional kernels, CNNs are not efficient in capturing global spatial dependencies, a critical cue for PU. As an alternate, recent studies employed recurrent neural networks (RNNs) defined on handcrafted pixel paths. Nonetheless, a limited number of pre-defined pixel paths cannot fully exploit global spatial dependencies existing in complex phase structures. In this paper, we introduce a vision transformer (ViT) model that effectively captures both global and local spatial dependencies using a hierarchical structure with a multi-scale process. The proposed ViT model employs a series of global transformer blocks to capture global spatial dependencies at the roughest scale. The resulting global features are used to guide a set of local transformer blocks to analyze local spatial dependencies in a coarse-to-fine progressive manner for unwrapping. Extensive experiments show that, our proposed ViT model produces higher-quality unwrapped phases over existing CNN/RNN-based methods, while maintaining a lightweight nature.

Simulation of the pulsed streamer discharge in water considering the effect of hydrostatic pressure

Streamer discharge is a very complex multi-scale and multi-physics coupling process, and there is no accurate model that can describe its development. In this paper, a two-dimensional axisymmetric fluid model is established in COMSOL to simulate and study the effects of the applied voltage amplitude, the discharge gap distance, the rising edge of pulse voltage, and hydrostatic pressure on the development of the positive streamer discharge at a needle-plate electrode in water under a nanosecond pulse voltage. The results show that increasing the voltage amplitude, decreasing the pulse rise time, and narrowing the discharge gap all increase the electric field strength of the streamer, thereby affecting the electron density of the plasma channel, among which changing the discharge gap has the greatest effect on the electron density. And under the gap of 3 mm, the peak electron density can reach 3.76 × 1023 m−3; if the discharge gap is narrowed to 1 mm, the peak electron density is reduced to 1.20 × 1023 m−3. In addition, hydrostatic pressure and water molecule spacing are closely linked. Increasing the hydrostatic pressure decreases the electric field strength and the peak electron density in the plasma channel, and its effect on the peak electron density saturates with increasing hydrostatic pressure.

Hybrid multiscale computational approach for heat transfer in GaN semiconductors

Abstract With ongoing advancements in semiconductor technology, understanding thermal transport in semiconductor devices—where phonons are the primary charge carriers—is crucial. This involves a multiscale process in which phenomena at different scales are governed by distinct control equations, necessitating various numerical methods. In this context, this paper introduces a novel multiscale simulation method called the Second-Order Reconstruction Operator Finite Difference Lattice Boltzmann Method (ROsFDLBM). This method effectively combines the Lattice Boltzmann Method (LBM) with the Finite Difference Method (FDM). ROsFDLBM employs reconstruction operators to accurately map the relationship between distribution functions and macroscopic physical quantities, significantly reducing errors caused by the transmission of interface information. The efficacy of this coupling scheme has been confirmed through an interface-coupled thermal diffusion model. Comparative analyses have revealed that the relative error of ROsFDLBM does not exceed 1.2%, demonstrating its superior accuracy. Further simulations of GaN devices have confirmed that traditional macroscopic methods tend to underestimate the temperature in the heat source area at micro-nano scales, with discrepancies reaching up to 60.9 K. Overall, the ROsFDLBM aligns with current research findings and offers an accurate and efficient simulation strategy for addressing complex heat transfer problems.

Regime-Dependent Characteristics and Predictability of Cold-Season Precipitation Events in the St. Lawrence River Valley

Abstract The St. Lawrence River Valley experiences a variety of precipitation types (p-types) during the cold season, such as rain, freezing rain, ice pellets, and snow. These varied precipitation types exert considerable impacts on aviation, road transportation, power generation and distribution, and winter recreation and are shaped by diverse multiscale processes that interact with the region’s complex topography. This study utilizes ERA5 reanalysis data, surface cyclone climatology, and hourly station observations from Montréal, Québec, and Burlington, Vermont, during October–April 2000–18 to investigate the spectrum of synoptic-scale weather regimes that induce cold-season precipitation across the St. Lawrence River Valley. In particular, k-means clustering and self-organizing maps (SOMs) are used to classify cyclone tracks passing near the St. Lawrence River Valley, and their accompanying thermodynamic profiles, into a set of event types that include a U.S. East Coast track, a central U.S. track, and two Canadian clipper tracks. Composite analyses are subsequently performed to reveal the synoptic-scale environments and the characteristic p-types that most frequently accompany each event type. Global Ensemble Forecast System version 12 (GEFSv12) reforecasts are then used to examine the relative predictability of cyclone characteristics and the local thermodynamic profile associated with each event type at 0–5-day forecast lead times. The analysis suggests that forecasted cyclones near the St. Lawrence River Valley develop too quickly and are located left-of-track relative to the reanalysis on average, which has implications for forecasts of the local thermodynamic profile and p-type across the region when the temperature is near 0°C. Significance Statement Diverse precipitation types are observed when near-surface temperatures approach 0°C during the cold season, especially across the St. Lawrence River Valley in southern Québec. This study classifies cold-season precipitation events impacting the St. Lawrence River Valley based on the track of storm systems across the region and quantifies the average meteorological characteristics and predictability of each track. Our analysis reveals that forecasted low pressure systems develop too quickly and are left of their observed track 0–5 days prior to an event on average, which has implications for forecasted temperatures and the type of precipitation observed across the region. Our results can inform future operational forecasts of cold-season precipitation events by providing a storm-focused perspective on forecast errors during these impactful events.

Relationships between crayfish population genetic diversity, species richness, and abundance within impounded and unimpounded streams in Alabama, USA.

Understanding the relationship between multi-scale processes driving community- and population-level diversity can guide conservation efforts. While the importance of population-level genetic diversity is widely recognized, it is not always assessed for conservation planning, and positive correlations with community-level diversity are sometimes assumed, such that only the latter is measured. We surveyed species richness and cumulative multispecies abundance of crayfishes in impounded and unimpounded streams in the southern Appalachian Mountains (Alabama, USA). We simultaneously assessed levels of population genetic diversity within two focal crayfishes (Faxonius validus and F. erichsonianus) using nuclear (nDNA; inter-simple sequence repeat (ISSR)) and mitochondrial DNA (mtDNA; mitochondrial DNA cytochrome oxidase subunit I (mtCOI)) markers. We then tested for species-genetic diversity correlations (SGDCs), species diversity-abundance correlations (i.e., more individuals hypothesis, MIH), and abundance-genetic diversity correlations (AGDCs) across sites. We also examined the relationship between each of the three different types of correlation (i.e., species richness, cumulative multispecies abundance, and population genetic diversity) and stream habitat characteristics and fragmentation. Surprisingly, based on F. validus mtDNA data, sites with the greatest multispecies abundance had the lowest genetic diversity, indicating a negative AGDC. However, no AGDC was evident from nDNA. There was no evidence of SGDCs for F. validus based on either of the two genetic data types. For F. erichsonianus, there was no evidence for SGDC or AGDC. When considering the community-level data only, there was no support for the MIH. Stream width was positively correlated with F. validus genetic diversity, but negatively correlated with multispecies abundance. Similarly, species richness was positively correlated with stream width in unimpounded streams but negatively correlated with width in impounded streams. These findings indicate that community-level diversity cannot be indiscriminately used as a proxy for population-level diversity without empirically testing this correlation on the focal group. As such, community- and population-level assessments for multiple crayfish species are needed to better understand drivers of diversity and eco-evolutionary processes which will aid in the conservation of this vulnerable taxonomic group.

Multi-Scale Meteorological Impact on PM2.5 Pollution in Tangshan, Northern China.

Tangshan, a major industrial and agricultural center in northern China, frequently experiences significant PM2.5 pollution events during winter, impacting its large population. These pollution episodes are influenced by multi-scale meteorological processes, though the complex mechanisms remain not fully understood. This study integrates surface PM2.5 concentration data, ground-based and upper-air meteorological observations, and ERA5 reanalysis data from 2015 to 2019 to explore the interactions between local planetary boundary layer (PBL) structures and large-scale atmospheric processes driving PM2.5 pollution in Tangshan. The results indicate that seasonal variations in PM2.5 pollution levels are closely linked to changes in PBL thermal stability. During winter, day-to-day increases in PM2.5 concentrations are often tied to atmospheric warming above 1500 m, as enhanced thermal inversions and reduced PBL heights lead to pollutant accumulation. Regionally, this aloft warming is driven by a high-pressure system at 850 hPa over the southern North China Plain, accompanied by prevailing southwesterly winds. Additionally, southwesterly winds within the PBL can transport pollutants from the adjacent Beijing-Tianjin-Hebei region to Tangshan, worsening pollution. Simulations from the chemical transport model indicate that regional pollutant transport can contribute to approximately half of the near-surface PM2.5 concentration under the unfavorable synoptic conditions. These findings underscore the importance of multi-scale meteorology in predicting and mitigating severe wintertime PM2.5 pollution in Tangshan and surrounding regions.

Multi-scale processes of the Kelvin-Helmholtz instability at Earth’s magnetopause

The Kelvin-Helmholtz Instability (KHI) is a large scale convective instability which occurs anywhere the velocity shear between two fluids is large, such as Earth’s magnetopause where the fast flowing magnetosheath abuts the relatively stagnant outer magnetosphere. The KHI was initially believed to contribute only to energy and momentum transfer from the solar wind to the magnetosphere, but was eventually shown to support mass transport and plasma heating. Recent advancements in in-situ observational capabilities and high scale computer modeling have once again shifted our understanding of the KHI from a large scale process, to an active environment which connects the global and kinetic scales through a variety of multi-scale processes and phenomena. In this mini-review, we provide an update on the latest findings in Kelvin-Helmholtz (KH) related processes at kinetic scales and the effects of the global environment on KH development.

A novel non-invasive method for measuring the spatial kinematic behavior of cardiomyocytes regulated by mechanical cues

The intact heart undergoes complex and multiscale mechanical remodeling processes. Measuring rhythmic spatial contraction of the myocardium is crucial for assessing mechanical durability and the ability to mount coordinated responses to pressure, electrical, and hemodynamic signals. However, current cardiomyocyte measurement platforms typically focus on action potentials and XY-plane contractions. Therefore, effective evaluation methods for studying the influence of mechanical cues on the spatial dynamic contraction of cardiomyocytes are still lacking. In this study, we developed a topographic guiding combined with an optical spatial motion tracking method to provide controllable mechanical stimulation for inducing directed contraction of cardiomyocytes and obtaining spatial motion information in vitro. We first performed a detailed investigation of cell connections and cytoskeleton orientations by combining the proposed method with immunofluorescence. Next, spatial constrictive modes, features, and key parameters of microgroove-guided cardiomyocytes were studied. Finally, the three-dimensional (3D) motions of the cardiomyocytes at different positions on the structure were compared. We found that the XY-plane contraction of cardiomyocytes typically has only one direction and shows a significant phase delay compared to the axial motion. In addition, cardiomyocytes located near the edges of the microgrooves were restricted by stronger mechanical forces, resulting in a significant height change reduction. These results provide new perspectives for structural and functional research on cardiomyocytes under long-term mechanical regulation. Overall, this study provides a highly precise and convenient method for evaluating the 3D cardiomyocyte motion under mechanical induction. This method is expected to enhance understanding of cardiomyocyte development and be useful for research on cardiac mechanics and functions.

Scale-specific controls of monthly suspended sediment load in a typical inland river

Sediment transport is a multi-scale and non-linear process controlled by multiple variables. Given the intricate nature of sediment transport mechanisms and the overlap of different factors’ effects on it at various time scales, unraveling the relationship between sediment load and its influencing factors is challenging. This study aimed to elucidate the multi-timescale effects of factors on monthly suspended sediment load in a seasonal inland river. In this study, monthly sediment loads measured by the depth-integrating method were obtained from the Tabu River Basin in northern China from 2007 to 2021, alongside data on four controlling factors: runoff, precipitation, water surface evaporation, and the normalized difference vegetation index (NDVI). The results showed that sediment load, runoff, and precipitation showed strong variability during 2007–2021, while water surface evaporation and NDVI exhibited moderate variability. Multivariate empirical mode decomposition (MEMD) decomposed the temporal patterns of sediment load and associated variables into five intrinsic mode functions (IMF) and a residue. IMF1 (4.7 months), IMF2 (9.0 months) and IMF3 (14.2 months) collectively explained 115.88 %, 91.73 %, 91.28 %, 107.69 %, and 106.09 % of the total variability in sediment load, runoff, precipitation, water surface evaporation, and NDVI, respectively. Subsequently, the time-dependent intrinsic correlation (TDIC) was utilized to illustrate the inherent relationships between sediment load and its controlling factors across various time scales. The associations between sediment load and the controlling factors changed significantly with the scale. Runoff was the dominant factor controlling sediment load at IMF1 (4.7 months), IMF2 (9.0 months), IMF3 (14.2 months), and IMF4 (25.1 months). Water surface evaporation controlled the sediment transport process at IMF5 (63.6 months). The prediction of sediment load on the measurement scale, using scale-specific controls analyzed with MEMD (R2 = 0.993), demonstrated superior performance compared to traditional multiple linear regression prediction (R2 = 0.748). This study will provide a theoretical basis for effective prevention and control of soil erosion and watershed management in inland river basins.

Construction of a Fine Extraction Process for Seismic Methane Anomalies Based on Remote Sensing: The Case of the 6 February 2023, Türkiye–Syria Earthquake

Identifying seismic CH4 anomalies via remote sensing has been verified as a legitimate method. However, there are still some problems, such as unknown reliability due to the complex characteristics of seismic anomalies. In this study, a multi-dimensional and multi-scale methane seismic anomaly extraction process for remote sensing was constructed with the Robust Satellite Technique (RST) based on the Atmospheric Infrared Sounder (AIRS) CH4 data and then applied to the 2023 Türkiye–Syria earthquake. This study obtained the two-dimensional temporal–spatial distribution of methane anomalies and temporal variation in the anomaly index. Based on this, the three-dimensional profile structure of the 8-day methane anomaly was extracted to determine the reliability of the anomaly. Finally, based on the daily methane anomaly, combined with atmospheric circulation and backward trajectory analysis as auxiliary tools, the influence of air mass migration was excluded to enhance the accuracy of CH4 anomaly determination. The results show that the three-dimensional anomalous structure is consistent with the geological characteristics of tectonic activities, and it appears as a “pyramid” or “inverted pyramid” type in a three-dimensional space. The anomalies caused by air mass migration can be eliminated by combining them with synoptic-scale circulation motion. The time series calculated at the epicenter or a certain point in a region may not accurately reflect the influence of regional or specific tectonic activity in the atmosphere. Thus, the optimal determination of the range and magnitude of atmospheric anomalies caused by tectonic activities is a difficult task for future research.

Disruptions in thermohaline staircases caused by subsurface mesoscale eddies in the eastern Caribbean Sea

Thermohaline staircases and mesoscale eddies play crucial roles in the transport of heat, salt, and nutrients in the ocean, yet their complex relationship remains unclear due to the limitations in observational resolution and lateral range. Here, utilizing high spatial resolution seismic images with a total length of 2518 km, we show the widespread occurrence of thermohaline staircases in the eastern Caribbean Sea and demonstrate their three-dimensional distribution. These staircases occupy about 70% of the total length of the seismic lines, with the remaining 30% occupied by six subsurface mesoscale eddies. These staircases are disrupted and interrupted due to the enhanced turbulent diffusivity driven by the vertical shear of these eddies. The numerous high-resolution seismic observations presented herein enhance our comprehension of the interplay between staircases and multiscale oceanic dynamical processes.

The impact of evolving synoptic weather patterns on multi-scale transport and sources of persistent high-concentration ozone pollution event in the Yangtze River Delta, China

High-concentration ozone pollution pose threats to ecosystems and human health. However, there is limited research on the impact of the alternating evolution of synoptic weather patterns (SWPs) on the multi-scale transport processes and sources of ozone. From June 14 to 18, 2018, a rare consecutive ozone pollution plagued in Hefei and broader Yangtze River Delta region (YRD). This study investigates the meteorological factors and sources using in-situ observational data and WRF-Chem model simulations. Analysis reveals a northeastern low-pressure system moving from north to south generated a cold front. This moving cold front facilitated the vertical transport of warm air masses carrying high-concentration ozone originating from North China. Subsequently, Ozone-rich air masses (ORMs) were transported over the YRD, influenced by the eastward movement of the Mongolian high-pressure system. Based on WRF-Chem model with NOx tagging mechanisms and WRF-FLEXPART backward simulations, it is confirmed that a notable atmospheric transport originated from North China region (NCR) to Hefei, especially on June 15. As the Mongolian high-pressure weakens and shifts east-southward, it carried ORMs generated by NOx emissions from the YRD, accumulating over the sea within the range of 120°E to 126°E and 25°N to 30°N. Both WRF-chem model results and TRopospheric Ozone and Precursors from Earth System Sounding (TROPESS) Chemistry Reanalysis dataset Version 2 (TCR-2) revealed the existence of ORMs in this geographic range. Subsequently, the ORMs carried out to sea by the weakened high-pressure system were reintroduced inland, influenced by southeast winds brought about by the peripheral circulation of typhoon “Gaemi”. In summary, the alternating evolution of SWPs significantly influences multi-scale ozone transport from both the NCR and the YRD regions, making substantial contributions to this prolonged episode. These findings offer valuable insights for improving regional ozone pollution prevention and control mechanisms.

Influence of sand particle size on the erosion-corrosion resistance of Ni2FeCrMo0.2 HEA in seawater: Particle-surface-electrochemistry interaction

The erosion-corrosion mechanism in rotary flowing seawater is hugely complicated due to the multiscale coupling processes of particle-surface impact, ion mass transfer, and interface electrochemistry. Therefore, developing erosion-corrosion resistant material and exploring the synergistic mechanism between sand erosion and electrochemical corrosion is vital. This study conducted the erosion-corrosion test on Ni2FeCrMo0.2 high-entropy alloy under the particle-seawater flow. Based on a coupled analysis of multi-component weight loss, electrochemical behavior, and microscopic damage morphology, the multiscale coupling processes of sand transportation, particle-surface impact, ion mass transfer, and interface electrochemistry were revealed. The present study found that with the increase of sand size, the energy carried by the particles promoted impact erosion. Additionally, particle movement enhanced ion mass transfer through turbulent effects, and the impact behavior disrupted the passivation film to promote electrochemical processes by reducing the thickness of the passivation film, leading to an increase in the erosion-corrosion rate. However, when the particle size continued to increase to a certain extent, the impact frequency decreased, reducing the erosion-corrosion rate. As the sand size grew, the dominant damage mechanism transitioned from pure corrosion (100 μm) to synergistic effects (200 μm, 400 μm) and then to pure erosion (800 μm). This study provides an in-depth understanding of the erosion-corrosion mechanism in seawater from the perspective of particle-ion-fluid-surface interaction by multi-element characterization.

Digital twinning, prediction and multi-objective optimization of an azeotrope system separation process in pharmaceutical manufacturing process

Digital twin is to make full use of the physical model, sensor update, operation history and other data to integrate multidisciplinary, multi-physical quantity, multi-scale and multi-probability simulation process, and to complete the full life cycle process of the corresponding physical equipment in the virtual space. In this paper, digital twin technology was used to simulate the production process of a pharmaceutical workshop, thus realizing solvent recovery by an azeotrope system separation process. The separation was optimized by multi-objective genetic algorithm. separation process, wherein the polynomial curve fitting and entropy-weighted TOPSIS data evaluation algorithms were combined to optimize the operating parameters, then the solvent purity and yield reach 99.96 % and 77.9 %, respectively, which is much higher than the corporate requirements. In addition, the effectiveness of the digital twin in providing data-driven prediction capability was verified by a CNN-LSTM-based regression prediction model, and the CNN-LSTM model has an accuracy of more than 98.9 % for all prediction results. Finally, a 3D visualization model was built using the Unity engine, enabling researchers to visualize and explore changes in key metrics during the separation process. This study can provide some guidance for digital transformation and intelligent development in pharmaceutical industry.

Multiscale dimensions of the foreign working citizens participation to the Italian labour market: intra-regional heterogeneities across the North–South divide

This article delves into the distinctive intra- and interregional geographical heterogeneity of Italy, emphasizing demographic and socio-economic variations and the role of foreign employment, considering the labour market as a fundamental driver for migration and local inclusion. The article identifies a gap in understanding the employed foreign population as a multiscale process in Lombardy and Campania, representative regions as case studies from the North and South divide using a MGWR approach. The results reveal contrasting effects of the Italian labour force’s unemployment rate (URI). In Lombardy, a positive effect suggests working competition between labour force components while, in Campania, the relation is less clear. The analysis underscores significant local heterogeneity, emphasizing the importance and urgency of employing local scale analysis for accurate statistics. The study emphasizes the multiscale nature of the analysed process, demonstrating variable effects across different regional contexts. While the study is limited to two regions and cross-sectional data, it marks the first attempt in Italy to address the foreign presence as a multiscale process, highlighting the need for localized and multiscale approaches in understanding spatial processes related to demography and population issues.

Transformer-based cross-modality interaction guidance network for RGB-T salient object detection

Exploring more effective multimodal fusion strategies is still challenging for RGB-T salient object detection (SOD). Most RGB-T SOD methods tend to focus on the strategy of acquiring modal complementary features by utilizing foreground information while ignoring the importance of background information for salient object localization. In addition, feature fusion without information filtering may introduce more noise. To solve these problems, this paper proposes a new cross-modal interaction guidance network (CIGNet) for RGB-T saliency object detection. Specifically, we construct a transformer-based dual-stream encoder to extract multimodal features. In the decoder, we propose an attention mechanism-based modal information complementary module (MICM) for capturing cross-modal complementary information for global comparison and salient object localization. Based on the MICM features, we design a multi-scale adaptive fusion module (MAFM) to find the optimal salient region of the multi-scale fusion process and reduce redundant features. In order to enhance the completeness of salient features after multi-scale feature fusion, this paper proposes the saliency region mining module (SRMM), which corrects the features in the boundary neighborhood by exploiting the differences between foreground and background pixels and the boundary. Comparisons with other state-of-the-art methods on three RGB-T datasets and five RGB-D datasets, the experimental results demonstrate the superiority and extensiveness of the proposed CIGNet.

Predicting air quality using a multi-scale spatiotemporal graph attention network

As urbanization accelerates, air quality has become a pressing concern. Accurate air quality prediction is essential for informed governmental decision-making and for protecting public health. Variations in air quality are influenced by complex multi-scale spatiotemporal processes. Existing research primarily relies on capturing single spatiotemporal features of air quality to predict changes. Meanwhile, when constructing spatiotemporal dynamic graphs, the inherent characteristics of the input data and the comprehensive effects of both global and local influences are not fully considered. To address these problems, we propose a graph-attention-based approach, named Multi-scale Spatiotemporal Graph Attention Network (MSTGAN). MSTGAN addresses the intricate spatiotemporal patterns of air quality across various scales through three key components: (1) a multistation transformer to model the temporal patterns of air quality at individual monitoring stations; (2) a bilinear spatiotemporal attention mechanism to capture the spatiotemporal dynamic global dependencies among all stations in a region; and (3) a set of spatiotemporal dependence graph-coupled Chebyshev graph convolution gate recurrent units to extract and aggregate the local spatiotemporal features of interrelated stations. Experiments conducted on three real-world datasets demonstrated that MSTGAN achieved significant improvements of 4.2%, 3.9%, and 7.8% in the mean absolute error, root mean square error, and R2 evaluation metrics, respectively, compared to seven state-of-the-art time-series forecasting methods. This code is publicly available at https://github.com/HPSCIL/MSTGAN-airquality-prediction.