Spatial Continuity Research Articles

Novel View Synthesis with Depth Priors Using Neural Radiance Fields and CycleGAN with Attention Transformer

Novel view synthesis aims to generate new perspectives from a limited number of input views. Neural Radiance Field (NeRF) is a key method for this task, and it produces high-fidelity images from a comprehensive set of inputs. However, a NeRF’s performance drops significantly with sparse views. To mitigate this, depth information can be used to guide training, with coarse depth maps often readily available in practical settings. We propose an improved sparse view NeRF model, ATGANNeRF, which integrates an enhanced U-Net generator with a dual-discriminator framework, CBAM, and Multi-Head Self-Attention mechanisms. The symmetric design enhances the model’s ability to capture and preserve spatial relationships, ensuring a more consistent generation of novel views. Additionally, local depth ranking is employed to ensure depth consistency with coarse maps, and spatial continuity constraints are introduced to synthesize novel views from sparse samples. SSIM loss is also added to preserve local structural details like edges and textures. Evaluation on LLFF, DTU, and our own datasets shows that ATGANNeRF significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.

Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network

Recent developments in spatially resolved transcriptomics (SRT) enable the characterization of spatial structures for different tissues. Many decomposition methods have been proposed to depict the cellular distribution within tissues. However, existing computational methods struggle to balance spatial continuity in cell distribution with the preservation of cell-specific characteristics. To address this, we propose Spall, a novel decomposition network that integrates scRNA-seq data with SRT data to accurately infer cell type proportions. Spall introduced the GATv2 module, featuring a flexible dynamic attention mechanism to capture relationships between spots. This improves the identification of cellular distribution patterns in spatial analysis. Additionally, Spall incorporates skip connections to address the loss of cell-specific information, thereby enhancing the prediction capability for rare cell types. Experimental results show that Spall outperforms the state-of-the-art methods in reconstructing cell distribution patterns on multiple datasets. Notably, Spall reveals tumor heterogeneity in human pancreatic ductal adenocarcinoma samples and delineates complex tissue structures, such as the laminar organization of the mouse cerebral cortex and the mouse cerebellum. These findings highlight the ability of Spall to provide reliable low-dimensional embeddings for downstream analyses, offering new opportunities for deciphering tissue structures.

Specific Response Assembly of 3D Space-Confined DNA Nanoaggregates for Rapid and Sensitive Detection of DNA Methyltransferase.

Rapid and sensitive detection of DNA adenine methyltransferase (Dam) activity is crucial for both research and clinical applications. Herein, we utilize two types of spherical nucleic acids (SNAs) to specific response assemble into 3D space-confined DNA nanoaggregates that enable the rapid and sensitive detection of Dam activity. The SNAs feature 3D order DNA scaffolds that serve as cores for anchoring signal hairpin probes (S-HPs) and target hairpin probes (T-HPs). Specifically, two distinct S-HPs are labeled with FAM fluorophores and BHQ1 quenchers and share identical hairpin sequences, while two types of T-HPs are designed with different linking sequences and specific recognition regions, resulting in the formation of two types of SNAs (SNA1 and SNA2). In the presence of Dam, the recognition region of the T-HPs is methylated and subsequently cleaved by auxiliary endonuclease, releasing the loop of the T-HP as a walking strand and exposing the linking sequence on the SNAs. Notably, the prior design of complementary linking sequences in the two types of SNAs facilitates their assembly into 3D DNA nanoaggregates, creating a confined space for walking strands to recover fluorescent signals. The 3D DNA nanoaggregate system not only provides highly ordered tracks but also enhances the spatial continuity of the walking strands, greatly improving the reaction kinetics for detecting Dam activity. This strategy enables the rapid and sensitive detection of Dam activity within 105 min, achieving a limit of detection of 2.9 × 10-4 U mL-1, demonstrating significant potential for advancing research in DNA methylation.

Spatiotemporal Multivariate Weather Prediction Network Based on CNN-Transformer.

Weather prediction is of great significance for human daily production activities, global extreme climate prediction, and environmental protection of the Earth. However, the existing data-based weather prediction methods cannot adequately capture the spatial and temporal evolution characteristics of the target region, which makes it difficult for the existing methods to meet practical application requirements in terms of efficiency and accuracy. Changes in weather involve both strongly correlated spatial and temporal continuation relationships, and at the same time, the variables interact with each other, so capturing the dynamic correlations among space, time, and variables is particularly important for accurate weather prediction. Therefore, we designed a spatiotemporal coupled prediction network based on convolution and Transformer for weather prediction from the perspective of multivariate spatiotemporal fields. First, we designed a spatial attention encoder-decoder to comprehensively explore spatial representations for extracting and reconstructing spatial features. Then, we designed a multi-scale spatiotemporal evolution module to obtain the spatiotemporal evolution patterns of weather using inter- and intra-frame computations. After that, in order to ensure that the model has better prediction ability for global and local hotspot areas, we designed a composite loss function based on MSE and SSIM to focus on the global and structural distribution of weather to achieve more accurate multivariate weather prediction. Finally, we demonstrated the excellent effect of STWPM in multivariate spatiotemporal field weather prediction by comprehensively evaluating the proposed algorithm with classical algorithms on the ERA5 dataset in a global region.

An Efficient OCT Fingerprint Antispoofing Method Based on ResMamba

Optical coherence tomography (OCT), known for its noncontact and 3D imaging capabilities, has found widespread application in fingerprint antispoofing detection. However, the existing methods rely heavily on single-frame B-scan images, underutilizing the 3D spatial information inherent in OCT volume data. High computational costs further limit its practical applications. Thus, this study proposes an efficient fingerprint antispoofing method which leverages the spatial continuity of OCT volume data to enhance both the accuracy and computational efficiency. Using an OCT system, we collected 320 real fingerprints and 320 spoofed fingerprints. Then, to distinguish between genuine and spoofed fingerprints, we developed the proposed ResMamba model, which is based on an enhanced 3D convolutional network integrated with a state space model (SSM). We extracted regions of interest (ROIs) from B-scan images and segmented them into volume slices for training and classification. The experimental results demonstrate that ResMamba achieved a 0.56% error rate (ERR) and 99.22% area under the curve (AUC), with an inference time of just 11 ms. Furthermore, compared to the existing models, ResMamba effectively balances its accuracy, inference speed, and model size. Ablation studies confirm that integrating the SIC module enhances the model’s robustness. Overall, ResMamba offers an efficient and reliable fingerprint antispoofing solution, outperforming the traditional methods in terms of its accuracy and performance.

Identification of Spatial Specific Lipid Metabolic Signatures in Long-Standing Diabetic Kidney Disease.

Background: Diabetic kidney disease (DKD) is a major complication of diabetes leading to kidney failure. Methods: This study investigates lipid metabolism profiles of long-standing DKD (LDKD, diabetes duration > 10 years) by integrative analysis of available single-cell RNA sequencing and spatial multi-omics data (focusing on spatial continuity samples) from the Kidney Precision Medicine Project. Results: Two injured cell types, an injured thick ascending limb (iTAL) and an injured proximal tubule (iPT), were identified and significantly elevated in LDKD samples. Both iTAL and iPT exhibit increased lipid metabolic and biosynthetic activities and decreased lipid and fatty acid oxidative processes compared to TAL/PT cells. Notably, compared to PT, iPT shows significant upregulation of specific injury and fibrosis-related genes, including FSHR and BMP7. Meanwhile, comparing iTAL to TAL, inflammatory-related genes such as ANXA3 and IGFBP2 are significantly upregulated. Furthermore, spatial metabolomics analysis reveals regionally distributed clusters in the kidney and notably differentially expressed lipid metabolites, such as triglycerides, glycerophospholipids, and sphingolipids, particularly pronounced in the inner medullary regions. Conclusions: These findings provide an integrative description of the lipid metabolism landscape in LDKD, highlighting injury-associated cellular processes and potential molecular mechanisms.

Electrical resistivity tomography inversion combining deep variational autoencoder and stochastic adaptive sampling

Geophysical methods, such as electrical resistivity tomography (ERT), can be used to imaging the near-surface electrical resistivity as field measurements depend on the subsurface porosity, water saturation and fluid salinity. ERT has been widely applied to investigate mineral and groundwater resources, and in archaeological, environmental, and engineering studies. The prediction of subsurface electrical conductivity from ERT data requires solving a geophysical inverse problem. For near-surface characterization studies, this is often accomplished with deterministic inverse methods. These methods linearize the problem around an initial solution, and their smoothness depends on an imposed a priori spatial regularization term. Depending on this parameterization, these methodologies might struggle to capture the natural variability of the subsurface. Moreover, deterministic solutions have limited capabilities for uncertainty assessment. On the contrary, stochastic inverse methods can assess uncertainties by predicting multiple model realizations that fit similarly the recorded ERT data. However, they are often more computationally expensive than deterministic solutions. Deep learning algorithms based on deep generative models have been used to re-parametrize model and data spaces into low-dimensional domains and efficiently solve geophysical inverse problems. However, within this context, uncertainty assessment is challenging. We propose a deep convolutional variational autoencoder (VAE) coupled with stochastic adaptive optimization to perform stochastic ERT inversion. Geostatistical simulations of electrical resistivity are used as training data set of the VAE. After training, the VAE generates electrical resistivity models that reproduce the statistics and spatial continuity patterns of the training data set. Then, the VAE latent space is iteratively perturbed and updated with adaptive stochastic sampling based on the misfit between observed and predicted ERT data. The proposed methodology is illustrated in two-dimensional synthetic and real data sets to illustrate the ability of the proposed method to predict reliable electrical resistivity models while generating multiple possible scenarios for uncertainty assessment.

Interactions between the fovea and the periphery shape misbinding of visual features in a continuous report paradigm

Human object perception depends on the proper integration of multiple visual features, such as color and motion. When features are integrated incorrectly, they are perceptually misbound and can cause illusions. This study investigates the phenomenon of continuous misbinding of color and motion features in peripheral vision, addressing the role of spatial continuity and color configuration in binding processes. Using a novel continuous report task, human subjects reported the perceived movement direction of color-coded dots in the peripheral visual field that were either congruent or incongruent with a foveal stimulus. Results indicate that spatial continuity is crucial for feature misbinding, with a marked decrease in peripheral perceptions bound to match foveal perception when the foveal and peripheral stimuli are spatially disjointed. Additionally, performance improved significantly when peripheral and foveal features were aligned, suggesting a ‘positive illusion’ effect where congruent features enhance perceptual accuracy. This effect was independent of the color pairings used, challenging the notion that color processing discrepancies might drive erroneous perception in this stimulus. These findings highlight the complex interplay between spatial configuration and perceptual accuracy in visual feature integration, with implications for understanding the neural basis of vision and developing applications to address perceptual inaccuracies in visual disorders.

Nonlinear Isogeometric Analyses of Instabilities in Thin Elastic Shells Exhibiting Combined Bending and Stretching

Abstract Thin structures like shells are highly susceptible to mechanical instabilities. They can undergo large nonlinear elastic deformations while exhibiting combined bending and stretching modes of deformation. Here, we propose a new displacement-based finite element (FE) formulation based on the isogeometric discretization of Koiter’s nonlinear shell theory and use of the method of dynamic relaxation (DR) to solve equilibrium configurations of problems involving fine-scale and hierarchical wrinkling and buckling. No imperfection seeding is required to trigger instabilities. The use of the NURBS basis provides a rotation-free, conforming, higher-order spatial continuity such that curvatures and membrane strains can be computed directly from interpolating the position vectors of the control points using spatial finite differences. The pseudo-dissipative FE dynamical system is updated through explicit time integration and made scalable for parallel computing using a message passing interface (MPI). The proposed FE method is successfully benchmarked against several numerical and experimental results.

Research and application of joint-constrained inversion of transient electromagnetic multivariate parameter

Due to the phenomena of stratigraphic inclination, complex structure, and lateral discontinuity of resistivity or layer thickness in most of the coal seams, the traditional one-dimensional transient electromagnetic inversion method has limitations in interpretation accuracy. In addition, two- and three-dimensional inversion and artificial intelligence inversion have problems of large computation and large sample size, respectively, which limit their application in small- and medium-sized engineering exploration. To improve the inversion effect, this study proposes a method of joint-constrained inversion of transient electromagnetic multivariate parameters. This method achieves the joint constraint inversion of the transient electromagnetic multi-parameter by making full use of the geological data and a priori information to construct the initial model and adding the constraints such as the resistivity, the thickness, and the layer interface of each layer in the inversion objective function, and at the same time, taking into account the spatial correlation of the stratigraphic structure between the neighboring measurement points, as well as the transverse and vertical constraints between the measurement points along the direction of the survey line and perpendicular to the survey line. First, a series of typical geoelectric models are established and numerically simulated, and the results are compared with those of the traditional inversion method to verify the applicability and effectiveness of the method. Then, the constrained inversion is carried out on the physical simulation and measured data, and the results are in good agreement with the actual geological conditions. The numerical simulation, physical simulation and measured data inversion results consistently prove that this method can effectively reduce the uncertainty of the inversion at the isolated measuring points, improve the spatial continuity of the formation boundary, and better reflect the actual geoelectric characteristics of the formation.

Attention mechanism‐assisted recurrent neural network for well log lithology classification

AbstractLithology classification is a fundamental aspect of reservoir classification. Due to the limited availability of core samples, computational modelling methods for lithology classification based on indirect measurements are required. The main challenge for standard clustering methods is the complex vertical dependency of sedimentological sequences as well as the spatial coupling of well logs. Machine learning methods, such as recurrent neural networks, long short‐term memory and bidirectional long short‐term memory, can account for the spatial correlation of the measured data and the predicted model. Based on these developments, we propose a novel approach using two distinct models: a self‐attention‐assisted bidirectional long short‐term memory model and a multi‐head attention‐based bidirectional long short‐term memory model. These models consider spatial continuity and adaptively adjust the weight in each step to improve the classification using the attention mechanism. The proposed method is tested on a set of real well logs with limited training data obtained from core samples. The prediction results from the proposed models and the benchmark one are compared in terms of the accuracy of lithology classification. Additionally, the weight matrices from both attention mechanisms are visualized to elucidate the correlations between depth steps and to help analyse how these mechanisms contribute to improved prediction accuracy. The study shows that the proposed multi‐head attention‐based bidirectional long short‐term memory model improves classification, especially for thin layers.

Infrared and Visible Image Fusion via Sparse Representation and Guided Filtering in Laplacian Pyramid Domain

The fusion of infrared and visible images together can fully leverage the respective advantages of each, providing a more comprehensive and richer set of information. This is applicable in various fields such as military surveillance, night navigation, environmental monitoring, etc. In this paper, a novel infrared and visible image fusion method based on sparse representation and guided filtering in Laplacian pyramid (LP) domain is introduced. The source images are decomposed into low- and high-frequency bands by the LP, respectively. Sparse representation has achieved significant effectiveness in image fusion, and it is used to process the low-frequency band; the guided filtering has excellent edge-preserving effects and can effectively maintain the spatial continuity of the high-frequency band. Therefore, guided filtering combined with the weighted sum of eight-neighborhood-based modified Laplacian (WSEML) is used to process high-frequency bands. Finally, the inverse LP transform is used to reconstruct the fused image. We conducted simulation experiments on the publicly available TNO dataset to validate the superiority of our proposed algorithm in fusing infrared and visible images. Our algorithm preserves both the thermal radiation characteristics of the infrared image and the detailed features of the visible image.

Unsupervised learning bioreactor regimes

Efficient operation of bioreactors is crucial for the success of biomanufacturing processes. Traditional Computational Fluid Dynamics (CFD) simulations provide detailed insights but often involve lengthy computation times and complexity, hindering their practicality for real-time applications. This study introduces a novel multivariate unsupervised learning algorithm that clusters bioreactors into physically meaningful regions based on CFD-generated and real-world data. These clusters not only facilitate the determination of internal reactor regimes but also serve as a foundational step for developing compartment models. Our approach utilizes a custom k-means clustering algorithm, which ensures spatial continuity of clusters by incorporating geometric data, and optimizes the number of compartments to maximize physical significance and data retention. This optimization is guided by a Pareto front analysis, balancing the need for clear compartment definition with the preservation of maximum information from the dataset. The effectiveness and versatility of this methodology were verified through case studies involving a 202 m³ Rushton impeller bioreactor (steady state simulation) and an 840 m³ airlift reactor (dynamic simulation). In the airlift reactor, the clustering algorithm accounted for dynamic fluctuations by averaging the simulation results, providing a robust method for incorporating temporal variations into the compartment analysis. The findings highlight the advantages of 3-D compartmentalization in capturing the intricate dynamics of fluid motion and cellular activities, thereby advancing the design of bioreactors and scaling down experiments for more efficient industrial applications.

A geometric view of seismic wavefields: implications for imaging dense clusters of events

SUMMARY Imaging dense clusters of seismicity is crucial to many problems in seismology: to delineate complex systems of faults, provide constraints on the causes of volcanic and cryogenic swarms, and to shed light on possible means to prevent damaging induced seismicity in mining, geothermal, and oil and gas extraction activities. Current imaging methods rely upon high-resolution relative location techniques, commonly requiring arrival-time picks for seismic phases. This paper examines an alternative approach, based upon concepts drawn from differential geometry, that images directly from waveform data. It relies upon the common assumption of spatial continuity of seismic wavefield observations, which implies that a differentiable map exists between the source region to be imaged and waveform observations considered as elements of a vector space. The map creates an image of event clusters on a Riemannian manifold embedded in that vector space. The image can be visualized by projecting the observations into a tangent space of the manifold and is a distorted rendering of cluster geometry. However, the distortion can be predicted and removed if a model for wavefield propagation is available. This visualization approach is applicable to clusters of uniform events with highly similar waveforms, such as are commonly acquired with correlation detectors or other pattern matching techniques. To assess its performance, it is applied to the closely related reciprocal problem of imaging the (known) geometry of an array from observations by the array of several regional events. Differences between the original problem and its reciprocal analogue are noted and controlled for in the analysis. Chief among the differences is the necessity for aligning the waveforms in the original problem, which, to maintain consistency with the original problem, is solved in the reciprocal problem by a generalization of the VanDecar–Crosson algorithm. The VanDecar–Crosson algorithm exhibits a bias, shown through an analysis of the situation when the observed wavefields are adequately modelled as plane waves. In that circumstance, the bias can be predicted and removed. In a test using a portion of a large-N array, this imaging approach is shown to successfully reconstruct the array geometry. The method is applicable directly to infinitesimal array apertures, but is extended to a larger aperture by partitioning the image into local, effectively infinitesimal overlapping subsets. These are inverted, then assembled into a global picture of the array geometry using constraints provided by the overlapped regions. Although demonstrated in a reciprocal array context, the method appears viable for imaging clusters of events with highly similar source mechanisms and time histories.

Generation and evaluation of energy and water fluxes from the HOLAPS framework: Comparison with satellite-based products during extreme hot weather

Improving our understanding of the energy and water exchanges between the land surface and the lower atmosphere (i.e. land–atmosphere interactions), and how climate change may affect them, is crucial to predict changes in temperature and precipitation extremes. Observations of energy and water fluxes at the land surface are typically retrieved from the eddy covariance method, which presents limitations related to spatial and temporal gaps, and the non-closure of the energy and water balances. Meanwhile, soil moisture (SM) products derived from satellite data have been widely used at regional and global scales, but they are limited to capture only surface soil water content and variations. The combination of remote sensing (RS) data and modelling frameworks is called to be the solution to improve the spatial coverage and vertical resolution of land–atmosphere interactions data, ensuring the energy and water balance closure. Here, we explore the combination of remote sensing and meteorological data with a physical-based modelling framework, the High resOlution Land Atmosphere Parameters from Space (HOLAPS). We used HOLAPS to produce hourly consistent estimates of energy and water fluxes over Europe at 5 km resolution. HOLAPS and other satellite-based evapotranspiration and sensible heat flux products from the literature are evaluated against the water balance method and eddy covariance measurements. HOLAPS SM estimates together with other RS-modelling products are also evaluated against ground-based measurements at the surface and in the root zone. The evaluation of HOLAPS ET estimates show similar performance to the other products with Kling–Gupta efficiency (KGE) ¿ -0.41 in comparison with eddy covariance measurements from FLUXNET in all seasons but in boreal winter. The simulation of H is more uncertain than for ET with KGE values ranging from -2.5 to 0.8 along the products and stations at monthly scales. HOLAPS reaches slightly better results than the rest of ET and H products at daily scales in summer (KGE ¿ 0.3 for ET and KGE ¿ 0.0 for H) and during hot conditions (KGE ¿ 0.2 for ET and KGE ¿-0.2 for H), while the state-of-the-art products show KGE ¿ 0.1 for ET and KGE ¿ -0.41 for H in summer and KGE ¿ -0.1 for ET and KGE ¿ -0.6 for H during hot conditions. All products evaluated here yield a reasonable performance (KGE ¿-0.41 at most sites) in simulating SM at the surface and in the root zone. Our results expose the need for further investigating and improving product performances during extreme conditions. The good performance of HOLAPS together with its inherent advantages (RS data driven, high temporal and spatial resolution, spatial and temporal continuity, soil moisture at different depths and long-term consistent evapotranspiration and sensible heat flux estimates) support its use for agricultural and forest management activities as well as to study land–atmosphere interactions based on Earth Observations.

Advancements in coupled processes numerical models: Upscaling aperture fields using spatial continuity

Fluid flow through fractured geological media is crucial in addressing the challenges posed by climate change, resource management, and energy exploration. Numerical models commonly employ fracture surface representations and aperture distribution models to simulate these processes. However, conventional statistical approaches often overlook the inherent spatial continuity and directionality within fracture data, impacting the accuracy of aperture geometry and subsequent flow simulations. This study investigates the benefits of incorporating spatial continuity information, derived from semi-variogram analysis, into numerical models. A Freiberg gneiss fracture aperture field was upscaled using both spatial continuity-informed and traditional arithmetic averaging methods. The comparative analysis reveals that incorporating spatial continuity during the upscaling process yields notable improvements in the accuracy of flow simulations, particularly when employing coarser mesh resolutions. This approach presents a promising alternative for enhancing the representation of fracture and aperture fields in numerical modeling across diverse applications, promoting a deeper understanding of fluid flow behavior in complex geological systems.

Two-stage estimation of hourly diffuse solar radiation across China using end-to-end gradient boosting with sequentially boosted features

Diffuse solar radiation (DR) constitutes a vital component of solar energy reaching the surface of the Earth. The demand for extensive temporal and spatial coverage of DR data has intensified in the realms of solar energy harvesting, agriculture, and climate change. However, until now, long-term DR observations have only been available from 17 stations across mainland China. Consequently, there is a pressing need to estimate spatially continuous, high-temporal-resolution DR for large-scale regions in China. The current hindrance to DR estimations stems from the scarcity of stations equipped with DR observations. This study proposes a two-stage strategy to efficiently estimate seamless DR in 2019 at a national scale, leveraging both DR and total solar radiation (TR) observations from numerous stations. In the first stage, the approach generates virtual DR at TR stations by establishing a learned relationship between DR and TR observations. Subsequently, in the second stage, these virtual DR data, in conjunction with satellite and reanalysis datasets, are utilized to estimate national-scale DR. Additionally, a novel model, End-to-end Gradient Boosting with Shortcuts and Feature selection (EGB-SF), is introduced to estimate DR over China. One advantage of this model is its consideration of the impact of sequentially boosted features and their interactions. Embedded shortcut connections fully exploit the influence of existing features on newly introduced ones during the learning process. Beyond enhancing the accuracy of DR estimation, the EGB-SF algorithm can also elucidate the relative importance levels of input features to the model. Moreover, the two-stage strategy outperforms the method of estimating national DR using only DR observations, as evidenced by its superior spatial generalization abilities. Statistical evaluation, collaborative analysis with influencing factors, and comparisons with related products confirm the accuracy and spatial continuity of the DR estimations in this study. These results furnish reliable DR data across China for research in agriculture, climate, solar radiation, and related fields.

Geostatistical Simulation of Daily Rainfall Fields—Performance Assessment for Extremes in West Africa

Abstract The spatial description of high-resolution extreme daily rainfall fields is challenging because of the high spatial and temporal variability of rainfall, particularly in tropical regions due to the stochastic nature of convective rainfall. Geostatistical simulations offer a solution to this problem. In this study, a stochastic geostatistical simulation technique based on the spectral turning bands method is presented for modeling daily rainfall extremes in the data-scarce tropical Ouémé River basin (Benin). This technique uses meta-Gaussian frameworks built on Gaussian random fields, which are transformed into realistic rainfall fields using statistical transfer functions. The simulation framework can be conditioned on point observations and is computationally efficient in generating multiple ensembles of extreme rainfall fields. The results of tests and evaluations for multiple extremes demonstrate the effectiveness of the simulation framework in modeling more realistic rainfall fields and capturing their variability. It successfully reproduces the empirical cumulative distribution function of the observation samples and outperforms classical interpolation techniques like ordinary kriging in terms of spatial continuity and rainfall variability. The study also addresses the challenge of dealing with uncertainty in data-poor areas and proposes a novel approach for determining the spatial correlation structure even with low station density, resulting in a performance boost of 9.5% compared to traditional techniques. Additionally, we present a low-skill reference simulation method to facilitate a comprehensive comparison of the geostatistical simulation approaches. The simulations generated have the potential to provide valuable inputs for hydrological modeling.

Spatial patterns and effects of invasive plants on soil microbial activity and diversity along river corridors

Abstract Background and aims Invasive species represent a threat to the conservation of biological systems. Riparian ecosystems are vulnerable to plant invasions, as waterflow facilitates the dispersal of plant propagules, while invasive species may subsequently impact soil, including soil microbial communities. Downstream connectivity among disparate riverine segments is expected to cause spatial continuity of abiotic and biotic components of riparian ecosystems. Methods We studied diversity of microbial communities in three headwater streams in Central Europe. Plant diversity, soil properties and soil microbiota were assessed on 20 sample plots per river. Soil microbial activity and community-level physiological profiling were used to study the soil microbial community. Results While the α-diversity of plants and soil microbiota was similar among rivers, plant communities were substantially more differentiated than microbial communities. Richness in alien and invasive plants significantly differed among rivers, which was reflected in different spatial patterns of microbial activity and diversity. A high level of spatial continuity was observed in the Kysuca river with straightened riverbed and artificial surfaces in the adjacent areas. The cover of invasive plants affects the composition of microbial functional groups of riverbed soils. Conclusion The expectation of spatial continuity of riverbed soil properties including those of soil microbiota caused by connectivity between different river segments was only partially fulfilled. Spatial continuity strongly depends on the environmental setting and stream characteristics of a particular river. The presence of invasive herbs affected the functional composition of soil microbiota but had no effect on microbial activity and diversity.

Assessing the Potential of UAV for Large-Scale Fractional Vegetation Cover Mapping with Satellite Data and Machine Learning

Fractional vegetation cover (FVC) is an essential metric for valuating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R2 values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R2 of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology.