Search

Globally, ocean dumping of chemical waste is a common method of disposal and relies on the assumption that dilution, diffusion, and dispersion at ocean scales will mitigate human exposure and ecosystem impacts. In southern California, extensive dumping of agrochemical waste, particularly chlorinated hydrocarbon contaminants such as DDT, via sewage outfalls and permitted offshore barging occurred for most of the last century. This study compiled a database of existing sediment and fish DDT measurements to examine how this unique legacy of regional ocean disposal translates into the contemporary contamination of the coastal ocean. We used spatiotemporal modeling to derive continuous estimates of sediment DDT contamination and show that the spatial signature of disposal (i.e., high loadings near historic dumping sites) is highly conserved in sediments. Moreover, we demonstrate that the proximity of fish to areas of high sediment loadings explained over half of the variation in fish DDT concentrations. The relationship between sediment and fish contamination was mediated by ecological predictors (e.g., species, trophic ecology, habitat use), and the relative influence of each predictor was context-dependent, with habitat exhibiting greater importance in heavily contaminated areas. Thus, despite more than half a century since the cessation of industrial dumping in the region, local ecosystem contamination continues to mirror the spatial legacy of dumping, suggesting that sediment can serve as a robust predictor of fish contamination, and general ecological characteristics offer a predictive framework for unmeasured species or locations.

Urban air pollution can vary sharply in space and time. However, few monitoring strategies can concurrently resolve spatial and temporal variation at fine scales. Here, we present a new measurement-driven spatiotemporal modeling approach that transcends the individual limitations of two complementary sampling paradigms: mobile monitoring and fixed-site sensor networks. We develop, validate, and apply this model to predict black carbon (BC) using data from an intensive, 100-day field study in West Oakland, CA. Our spatiotemporal model exploits coherent spatial patterns derived from a multipollutant mobile monitoring campaign to fill spatial gaps in time-complete BC data from a low-cost sensor network. Our model performs well in reconstructing patterns at fine spatial and temporal resolution (30 m, 15 min), demonstrating strong out-of-sample correlations for both mobile (Pearson's R ∼ 0.77) and fixed-site measurements (R ∼ 0.95) while revealing features that are not effectively captured by a single monitoring approach in isolation. The model reveals sharp concentration gradients near major emission sources while capturing their temporal variability, offering valuable insights into pollution sources and dynamics.

Accurate station-level numerical weather predictions are critical for disaster prevention and mitigation, with error correction playing an essential role. However, existing correction models struggle to effectively handle the high-dimensional features and complex dependencies inherent in meteorological data. To address these challenges, this paper proposes the dual-branch residual-guided multi-view attention fusion network (DRAF-Net), a novel deep learning-based correction model. DRAF-Net introduces two key innovations: (1) a dual-branch residual structure that enhances the spatial sensitivity of deep high-dimensional features and improves output stability by connecting raw data and shallow features to deep features, respectively; and (2) a multi-view attention fusion mechanism that models spatiotemporal influences, temporal dynamics, and spatial associations, significantly improving the representation of complex dependencies. The effectiveness of DRAF-Net was validated on two real-world datasets comprising observations and predictions from Chinese meteorological stations. It achieved an average RMSE reduction of 83.44% and an average MAE reduction of 84.21% across all eight variables, significantly outperforming other methods. Moreover, extensive studies confirmed the critical contributions of each key component, while visualization results highlighted the model's ability to eliminate anomalous values and improve prediction consistency. The code will be made publicly available to support future research and development. [ABSTRACT FROM AUTHOR]

Estimating surface-level PM2.5 concentrations at any given location is crucial for public health monitoring and cohort studies. Existing models and datasets for this purpose have limited precision, especially on high-concentration days. Additionally, due to the lack of open-source code, generating estimates for other areas and time periods remains cumbersome. We developed a novel deep learning-based model that improves the surface-level PM2.5 concentration estimates by capitalizing on the temporal dynamics of air quality. Specifically, we improve the estimation precision by developing a Long Short-Term Memory (LSTM) network with Attention and integrating multiple data sources, including in situ measurements, remotely sensed data, and wildfire smoke density observations, which improve the model's ability to capture high-concentration events. We rigorously evaluate the model against existing products, demonstrating a 2.2% improvement in overall RMSE, and a 9.8% reduction in RMSE on high-concentration days, highlighting the superior performance of our approach, particularly on high-concentration days. Using the model, we have produced a comprehensive dataset of PM2.5 estimates from 2005 to 2021 for the contiguous United States and are releasing an open-source framework to ensure reproducibility and facilitate further adaptation in air quality studies. [ABSTRACT FROM AUTHOR]

Fish spawning phenology is a major concern for conservation and fisheries management. New intensive data sources, such as GPS-based tracking data and high-resolution catch declaration data, are becoming increasingly available in the field of marine ecology. These data benefit from high spatiotemporal resolution and open new research avenues for investigating the interannual variability in fish phenology. In this paper, we demonstrate how an integrated species distribution model informed by commercial catch data combined with spatiotemporal dimension reduction methods known as empirical orthogonal functions (EOFs) can be used to synthesize spatiotemporal signals in fish reproduction phenology. Specifically, we address the following questions: (1) Can we identify seasonal spatial patterns that can be interpreted in terms of reproductive phenology and essential habitats? (2) Can we identify changes in reproductive phenology over time? (3) Are these changes related to environmental drivers? The analysis illustrates the reproductive phenology of three key commercial species in the Bay of Biscay (sole, hake, and sea bass). The EOF analysis emphasized strong seasonal spatiotemporal patterns that correspond to reproduction patterns and feeding patterns. Based on this methodology, we identified seasonal variations in the timing of reproduction, and we related these variations to sea surface temperature, a key driver of fish reproduction. [ABSTRACT FROM AUTHOR]

In video action recognition, effective spatiotemporal modeling is crucial. However, traditional two-stream methods face challenges in integrating spatial information from RGB images and temporary information from optical flow without long-range temporal modelling. To address these limitations, we propose the Deep Fusion Module (DFM), which focuses on the deep fusion of spatial and temporal information and consists of two components. First, we propose an Attention Fusion Module (AFM) to effectively fuse the shallow features obtained from a two-stream network, thereby facilitating the integration of spatial and temporal information. Next, we incorporate a SpatioTemporal Module (STM), comprising a ConvGRU and a 1×1 convolution, to model long-range temporal dependency and fuse spatial-temporal features. Experiments on the UCF101 dataset show that our method achieves 96.5% accuracy, outperforming baseline two-stream models by 0.3%. [ABSTRACT FROM AUTHOR]

French Guiana lacks a dedicated model for developing an early warning system tailored to its entomological contexts. We employed a spatiotemporal modeling approach to predict the risk of Aedes aegypti larvae presence in local households in French Guiana. The model integrated field data on larvae, environmental data obtained from very high-spatial-resolution Pleiades imagery, and meteorological data collected from September 2011 to February 2013 in an urban area of French Guiana. The identified environmental and meteorological factors were used to generate dynamic maps with high spatial and temporal resolution. The study collected larval data from 261 different surveyed houses, with each house being surveyed between one and three times. Of the observations, 41% were positive for the presence of Aedes aegypti larvae. We modeled the Aedes larvae risk within a radius of 50 to 200 m around houses using six explanatory variables and extrapolated the findings to other urban municipalities during the 2020 dengue epidemic in French Guiana. This study highlights the potential of spatiotemporal modeling approaches to predict and monitor the evolution of vector-borne disease transmission risk, representing a major opportunity to monitor the evolution of vector risk and provide valuable information for public health authorities. [ABSTRACT FROM AUTHOR]

Developing a precise and interpretable spatiotemporal model is need for establishing evidence-based adaptation strategies on climate change-driven disasters. This study introduced a diagnostic prediction concept as a generalized modeling framework for enhancing modeling precision and interpretability and demonstrate a case study of estimating forest net primary production (NPP) in a mid-latitude region (MLR) by developing a diagnostic NPP diagnostic prediction model (DNPM). The diagnostic prediction concept starts with modeling meteorology and static environmental data, referred as a prognostic prediction part. Then, its outcome is refined with spatiotemporal residual calibration in the diagnostic prediction part, of which result undergo spatial, temporal, and spatiotemporally explicit validation methods. For the case of DNPM, a prognostic NPP prediction model (PNPM) was set, using a multilinear regression on SPEI 3, temperature, and static environmental features extracted from topography and soil by a random forest. Subsequently, during the diagnostic process of DNPM, we calibrated the primary outcome based on the temporal pattern captured at the time-series residual of PNPM. The results highlighted the superiority of the DNPM over the PNPM. Spatiotemporal validation showed that the DNPM achieved higher accuracy, with Pearson correlation coefficients ([Formula: see text]) ranging from 0.975 to 0.992 and root mean squared error (RMSE) between 38.99 and 70.23 gC/m2/year across all climate zones. Similarly, temporal validation indicated that DNPM outperformed the PNPM, with [Formula: see text] values of 0.233 to 0.494 and RMSE of 46.01 to 70.75 gC/m2/year, compared to the PNPM’s [Formula: see text] values of 0.192 to 0.406 and RMSE of 55.23 to 89.31 gC/m2/year. This study showed enhanced diagnostic prediction concept can be applied to diverse environmental modeling approaches, offering valuable insights for climate adaptation and forest policy formulation. By accurately predicting various environmental targets, including drought and forest NPP, this approach aids in making informed policy decisions across different scales.

We evaluated the spatiotemporal clustering of rapid diagnostic test−positive cholera cases in Uvira, eastern Democratic Republic of the Congo. We detected spatiotemporal clusters that consistently overlapped with major rivers, and we outlined the extent of zones of increased risk that are compatible with the radii currently used for targeted interventions.

This paper presents a systematic literature review, providing a comprehensive taxonomy of Data Augmentation (DA), Transfer Learning (TL), and Self-Supervised Learning (SSL) techniques within the context of Few-Shot Learning (FSL) for EEG signal classification. EEG signals have shown significant potential in various paradigms, including Motor Imagery, Emotion Recognition, Visual Evoked Potentials, Steady-State Visually Evoked Potentials, Rapid Serial Visual Presentation, Event-Related Potentials, and Mental Workload. However, challenges such as limited labeled data, noise, and inter/intra-subject variability have impeded the effectiveness of traditional machine learning (ML) and deep learning (DL) models. This review methodically explores how FSL approaches, incorporating DA, TL, and SSL, can address these challenges and enhance classification performance in specific EEG paradigms. It also delves into the open research challenges related to these techniques in EEG signal classification. Specifically, the review examines the identification of DA strategies tailored to various EEG paradigms, the creation of TL architectures for efficient knowledge transfer, and the formulation of SSL methods for unsupervised representation learning from EEG data. Addressing these challenges is crucial for enhancing the efficacy and robustness of FSL-based EEG signal classification. By presenting a structured taxonomy of FSL techniques and discussing the associated research challenges, this systematic review offers valuable insights for future investigations in EEG signal classification. The findings aim to guide and inspire researchers, promoting advancements in applying FSL methodologies for improved EEG signal analysis and classification in real-world settings. [ABSTRACT FROM AUTHOR]

This work introduces an unsupervised framework for video anomaly detection, leveraging a hybrid deep learning model that combines a vision transformer (ViT) with a convolutional spatiotemporal relationship (STR) attention block. The proposed model addresses the challenges of anomaly detection in video surveillance by capturing both local and global relationships within video frames, a task that traditional convolutional neural networks (CNNs) often struggle with due to their localized field of view. We have utilized a pre-trained ViT as an encoder for feature extraction, which is then processed by the STR attention block to enhance the detection of spatiotemporal relationships among objects in videos. The novelty of this work is utilizing the ViT with the STR attention to detect video anomalies effectively in large and heterogeneous datasets, an important thing given the diverse environments and scenarios encountered in real-world surveillance. The framework was evaluated on three benchmark datasets, i.e., the UCSD-Ped2, CHUCK Avenue, and ShanghaiTech. This demonstrates the model's superior performance in detecting anomalies compared to state-of-the-art methods, showcasing its potential to significantly enhance automated video surveillance systems by achieving area under the receiver operating characteristic curve (AUC ROC) values of 95.6, 86.8, and 82.1. To show the effectiveness of the proposed framework in detecting anomalies in extra-large datasets, we trained the model on a subset of the huge contemporary CHAD dataset that contains over 1 million frames, achieving AUC ROC values of 71.8 and 64.2 for CHAD-Cam 1 and CHAD-Cam 2, respectively, which outperforms the state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Sea Surface Temperature (SST) is of great importance to study several major phenomena due to ocean interactions with other earth systems. Previous studies on SST based on statistical inference methods were less accurate for longer prediction lengths. A considerable number of studies in recent years involve machine learning for SST modeling. These models were able to mitigate this problem to some length by modeling SST patterns and trends. Sequence analysis by decomposition is used for SST forecasting in several studies. Ensemble Empirical Mode Decomposition (EEMD) has been proven in previous studies as a useful method for this. The application of EEMD in spatiotemporal modeling has been introduced as Multidimensional EEMD (MEEMD). The aim of this study is to employ fast MEEMD methods to decompose the SST spatiotemporal dataset and apply a Convolutional Long Short-Term Memory (ConvLSTM)-based model to model and forecast SST. The results show that the fast MEEMD method is capable of enhancing spatiotemporal SST modeling compared to the Linear Inverse Model (LIM) and ConvLSTM model without decomposition. The model was further validated by making predictions from April to May 2023 and comparing them to original SST values. There was a high consistency between predicted and real SST values. [ABSTRACT FROM AUTHOR]

Short-term residential load forecasting (STRLF) holds great significance for the stable and economic operation of distributed power systems. Different households in the same region may exhibit similar consumption patterns owing to the analogous environmental parameters. Incorporating the spatiotemporal correlations can enhance the load forecasting performance of individual households. To this end, a spatiotemporal graph attention (STGA)-enabled Transformer is proposed for multivariate, multi-step residential load forecasting in this paper. Specifically, the multiple residential loads are cast to a graph and a Transformer with a graph sequence-to-sequence (Seq2Seq) structure is employed to model the multi-step load forecasting problem. Gated fusion-based STGA blocks are embedded in the encoder and decoder of the Transformer to extract dynamic spatial correlations and non-linear temporal patterns among multiple residential loads. A transform attention block is further designed to transfer historical graph observations into future graph predictions and alleviate the error propagation between the encoder and decoder. The embedding of multiple attention modules in the Seq2Seq framework allows us to capture the spatiotemporal correlations between residents and achieve confident inference of load values several steps ahead. Numerical simulations on residential data from three different regions demonstrate that the developed Transformer method improves multi-step load forecasting by 14.7% at least, compared to the state-of-the-art benchmarks.

Predicting the trajectory of geographical events, such as wildfire spread, presents a formidable task due to the dynamic associations among influential biophysical factors. Geo-events like wildfires frequently display short and long-range spatial and temporal correlations. Short-range effects are the direct contact and near-contact spread of the fire front. Long-range effects are represented by processes such as spotting, where firebrands carried by the wind ignite fires distant from the flaming front, altering the shape and speed of an advancing fire front. This study addresses these modeling challenges by clearly defining and analyzing the scale-dependent spatiotemporal dynamics that influence wildfire spread, focusing on the interplay between biophysical factors and fire behavior. We propose two unique attention-based spatiotemporal models using Convolutional Long Short-Term Memory (ConvLSTM) networks. These models are designed to learn and capture a range of local to global and short and long-range spatiotemporal correlations. The proposed models were tested on two datasets: a high-resolution wildfire spread dataset produced with a semi-empirical percolation model and a satellite observed wildfire spread data in California 2012–2021. Results indicate that attention-based models accurately predict fire front movements that are consistent with known wildfire spread-biophysical dynamics. Our research suggests there is considerable potential for attention mechanisms to capture the spatiotemporal behavior of wildfire spread, with model transferability, that can guide rapid deployment of wildfire management operations. We also highlight directions for future studies that focus on how the self-attention mechanism could enhance model performance for a range of geospatial applications.

The article presents results of using remote sensing images and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Land potential here refers to the potential vegetation productivity in the hypothetical absence of short-term anthropogenic influence, such as intensive agriculture and urbanization. Knowledge on this ecological land potential could support the assessment of levels of land degradation as well as restoration potentials. Monthly aggregated FAPAR time-series of three percentiles (0.05, 0.50 and 0.95 probability) at 250 m spatial resolution were derived from the 8-day GLASS FAPAR V6 product for 2000-2021 and used to determine long-term trends in FAPAR, as well as to model potential FAPAR in the absence of human pressure. CCa 3 million training points sampled from 12,500 locations across the globe were overlaid with 68 bio-physical variables representing climate, terrain, landform, and vegetation cover, as well as several variables representing human pressure including: population count, cropland intensity, nightlights and a human footprint index. The training points were used in an ensemble machine learning model that stacks three base learners (extremely randomized trees, gradient descended trees and artificial neural network) using a linear regressor as meta-learner. The potential FAPAR was then projected by removing the impact of urbanization and intensive agriculture in the covariate layers. The results of strict cross-validation show that the global distribution of FAPAR can be explained with an R2 of 0.89, with the most important covariates being growing season length, forest cover indicator and annual precipitation. From this model, a global map of potential monthly FAPAR for the recent year (2021) was produced, and used to predict gaps in actual vs. potential FAPAR. The produced global maps of actual vs. potential FAPAR and long-term trends were each spatially matched with stable and transitional land cover classes. The assessment showed large negative FAPAR gaps (actual lower than potential) for classes: urban, needle-leave deciduous trees, and flooded shrub or herbaceous cover, while strong negative FAPAR trends were found for classes: urban, sparse vegetation and rainfed cropland. On the other hand, classes: irrigated or post-flooded cropland, tree cover mixed leaf type, and broad-leave deciduous showed largely positive trends. The framework allows land managers to assess potential land degradation from two aspects: as an actual declining trend in observed FAPAR and as a difference between actual and potential vegetation FAPAR. [ABSTRACT FROM AUTHOR]

The most often utilized construction material worldwide is concrete. Extensive experiments are carried out each year to study the physical, mechanical, and chemical properties of concrete, which are costly and time-consuming. This study focuses on avoiding redundant tests by applying the machine learning (ML) method to predict temperature-dependent polymer concrete qualities. In this work, as a strong tool of the ML method, a deep neural network (DNN) is used to examine the five temperature-dependent mechanical characteristics of concrete, including Poisson's ratio, Young's modulus, specific heat, coefficient of thermal expansion, and thermal conductivity. A 5-fold cross-validation method was used to verify the strategy in this research and get rid of split bias in testing and training. This study demonstrates the material properties of temperature-dependent polymer concrete followed by mathematical modeling of a steel-polymer concrete panel used for various civil applications. Temperature-dependent equations are determined using constitutive heat transfer and Cartesian coordinates. In addition, a thermal shock load acts on the upper part, and the lower part becomes an isothermal state with no heat flow. In order to account for the limited speed at which temperature waves travel, two distinct theories of generalized thermoelasticity are employed: the Lord-Shulman (LS) and the Green-Lindsay (GL) theories. The Fast Laplace Inverse Transform Method (FLITM) is used to transfer the results from the Laplace domain to the time domain. In addition, a three-dimensional differential quadrature approach (3D-DQA) using three Chebyshev-Gaussian-Robat functions for solving temperature-dependent equations is presented. In conclusion, some suggestions for improving the stability of polymer concrete panels are detailed and will be compiled in a future manual.

Existing regulatory pollutant monitoring networks rely on a small number of centrally located measurement sites that are purposefully sited away from major emission sources. While informative of general air quality trends regionally, these networks often do not fully capture the local variability of air pollution exposure within a community. Recent technological advancements have reduced the cost of sensors, allowing air quality monitoring campaigns with high spatial resolution. The 100×100 black carbon (BC) monitoring network deployed 100 low-cost BC sensors across the 15 km2 West Oakland, CA community for 100 days in the summer of 2017, producing a nearly continuous site-specific time series of BC concentrations which we aggregated to one-hour averages. Leveraging this dataset, we employed a hierarchical spatio-temporal model to accurately predict local spatio-temporal concentration patterns throughout West Oakland, at locations without monitors (average cross-validated hourly temporal R 2=0.60). Using our model, we identified spatially varying temporal pollution patterns associated with small-scale geographic features and proximity to local sources. In a sub-sampling analysis, we demonstrated that fine scale predictions of nearly comparable accuracy can be obtained with our modeling approach by using ~30% of the 100×100 BC network supplemented by a shorter-term high-density campaign.

The article presents results of using remote sensing images and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Land potential here refers to the potential vegetation productivity in the hypothetical absence of short–term anthropogenic influence, such as intensive agriculture and urbanization. Knowledge on this ecological land potential could support the assessment of levels of land degradation as well as restoration potentials. Monthly aggregated FAPAR time-series of three percentiles (0.05, 0.50 and 0.95 probability) at 250 m spatial resolution were derived from the 8-day GLASS FAPAR V6 product for 2000–2021 and used to determine long-term trends in FAPAR, as well as to model potential FAPAR in the absence of human pressure. CCa 3 million training points sampled from 12,500 locations across the globe were overlaid with 68 bio-physical variables representing climate, terrain, landform, and vegetation cover, as well as several variables representing human pressure including: population count, cropland intensity, nightlights and a human footprint index. The training points were used in an ensemble machine learning model that stacks three base learners (extremely randomized trees, gradient descended trees and artificial neural network) using a linear regressor as meta-learner. The potential FAPAR was then projected by removing the impact of urbanization and intensive agriculture in the covariate layers. The results of strict cross-validation show that the global distribution of FAPAR can be explained with an R2 of 0.89, with the most important covariates being growing season length, forest cover indicator and annual precipitation. From this model, a global map of potential monthly FAPAR for the recent year (2021) was produced, and used to predict gaps in actual vs. potential FAPAR. The produced global maps of actual vs. potential FAPAR and long-term trends were each spatially matched with stable and transitional land cover classes. The assessment showed large negative FAPAR gaps (actual lower than potential) for classes: urban, needle-leave deciduous trees, and flooded shrub or herbaceous cover, while strong negative FAPAR trends were found for classes: urban, sparse vegetation and rainfed cropland. On the other hand, classes: irrigated or post-flooded cropland, tree cover mixed leaf type, and broad-leave deciduous showed largely positive trends. The framework allows land managers to assess potential land degradation from two aspects: as an actual declining trend in observed FAPAR and as a difference between actual and potential vegetation FAPAR.

Focused Ultrasound (FUS)-triggered nano-sized drug delivery, as a smart stimuli-responsive system for treating solid tumors, is computationally investigated to enhance localized delivery of drug and treatment efficacy. Integration of thermosensitive liposome (TSL), as a doxorubicin (DOX)-loaded nanocarrier, and FUS, provides a promising drug delivery system. A fully coupled partial differential system of equations, including the Helmholtz equation for FUS propagation, bio-heat transfer, interstitial fluid flow, drug transport in tissue and cellular spaces, and a pharmacodynamic model is first presented for this treatment approach. Equations are then solved by finite element methods to calculate intracellular drug concentration and treatment efficacy. The main objective of this study is to present a multi-physics and multi-scale model to simulate drug release, transport, and delivery to solid tumors, followed by an analysis of how FUS exposure time and drug release rate affect these processes. Our findings not only show the capability of model to replicate this therapeutic approach, but also confirm the benefits of this treatment with an improvement of drug aggregation in tumor and reduction of drug delivery in healthy tissue. For instance, the survival fraction of tumor cells after this treatment dropped to 62.4%, because of a large amount of delivered drugs to cancer cells. Next, a combination of three release rates (ultrafast, fast, and slow) and FUS exposure times (10, 30, and 60 min) was examined. Area under curve (AUC) results show that the combination of 30 min FUS exposure and rapid drug release leads to a practical and effective therapeutic response. [ABSTRACT FROM AUTHOR]

Accurate PM2.5 concentration prediction is essential for environmental control management, therefore numerous air quality monitoring stations have been established, which generate multiple time series with spatio-temporal correlation. However, the statistical distribution of data from different monitoring stations varies widely, which needs to provide higher flexibility in the feature extraction stage. Moreover, the spatio-temporal correlation and mutation characteristics of the time series are difficult to capture. To this end, an adaptive spatio-temporal prediction network (ASTP-NET) is proposed, in which the encoder adaptively extracts the input data features, then captures the spatio-temporal dependencies and dynamic changes of the time series, the decoder part maps the encoded features into a predicted future time series representation, while an objective function is proposed to measure the overall fluctuations of the model's multi-step prediction. In this paper, ASTP-NET is evaluated based on the Xi'an air quality dataset, and the results show that the model outperforms other baseline methods. [ABSTRACT FROM AUTHOR]

Although increasing hidden layers can improve the ability of a neural network in modeling complex nonlinear relationships, deep layers may result in degradation of accuracy due to the problem of vanishing gradient. Accuracy degradation limits the applications of deep neural networks to predict continuous variables with a small sample size and/or weak or little invariance to translations. Inspired by residual convolutional neural network in computer vision, we developed an encoder-decoder full residual deep network to robustly regress and predict complex spatiotemporal variables. We embedded full shortcuts from each encoding layer to its corresponding decoding layer in a systematic encoder-decoder architecture for efficient residual mapping and error signal propagation. We demonstrated, theoretically and experimentally, that the proposed network structure with full residual connections can successfully boost the backpropagation of signals and improve learning outcomes. This novel method has been extensively evaluated and compared with four commonly used methods (i.e., plain neural network, cascaded residual autoencoder, generalized additive model, and XGBoost) across different testing cases for continuous variable predictions. For model evaluation, we focused on spatiotemporal imputation of satellite aerosol optical depth with massive nonrandomness missingness and spatiotemporal estimation of atmospheric fine particulate matter [Formula: see text] (PM2.5). Compared with the other approaches, our method achieved the state-of-the-art accuracy, had less bias in predicting extreme values, and generated more realistic spatial surfaces. This encoder-decoder full residual deep network can be an efficient and powerful tool in a variety of applications that involve complex nonlinear relationships of continuous variables, varying sample sizes, and spatiotemporal data with weak or little invariance to translation.

French Guiana lacks a dedicated model for developing an early warning system tailored to its entomological contexts. We employed a spatiotemporal modeling approach to predict the risk of Aedes aegypti larvae presence in local households in French Guiana. The model integrated field data on larvae, environmental data obtained from very high-spatial-resolution Pleiades imagery, and meteorological data collected from September 2011 to February 2013 in an urban area of French Guiana. The identified environmental and meteorological factors were used to generate dynamic maps with high spatial and temporal resolution. The study collected larval data from 261 different surveyed houses, with each house being surveyed between one and three times. Of the observations, 41% were positive for the presence of Aedes aegypti larvae. We modeled the Aedes larvae risk within a radius of 50 to 200 m around houses using six explanatory variables and extrapolated the findings to other urban municipalities during the 2020 dengue epidemic in French Guiana. This study highlights the potential of spatiotemporal modeling approaches to predict and monitor the evolution of vector-borne disease transmission risk, representing a major opportunity to monitor the evolution of vector risk and provide valuable information for public health authorities.

Land use regression (LUR) models are widely used in epidemiological and environmental studies to estimate humans’ exposure to air pollution within urban areas. However, the early models, developed using linear regressions and data from fixed monitoring stations and passive sampling, were primarily designed to model traditional and criteria air pollutants and had limitations in capturing high-resolution spatiotemporal variations of air pollution. Over the past decade, there has been a notable development of multi-source observations from low-cost monitors, mobile monitoring, and satellites, in conjunction with the integration of advanced statistical methods and spatially and temporally dynamic predictors, which have facilitated significant expansion and advancement of LUR approaches. This paper reviews and synthesizes the recent advances in LUR approaches from the perspectives of the changes in air quality data acquisition, novel predictor variables, advances in model-developing approaches, improvements in validation methods, model transferability, and modeling software as reported in 155 LUR studies published between 2011 and 2023. We demonstrate that these developments have enabled LUR models to be developed for larger study areas and encompass a wider range of criteria and unregulated air pollutants. LUR models in the conventional spatial structure have been complemented by more complex spatiotemporal structures. Compared with linear models, advanced statistical methods yield better predictions when handling data with complex relationships and interactions. Finally, this study explores new developments, identifies potential pathways for further breakthroughs in LUR methodologies, and proposes future research directions. In this context, LUR approaches have the potential to make a significant contribution to future efforts to model the patterns of long- and short-term exposure of urban populations to air pollution.

House price prediction has traditionally been approached using linear or spatial linear hedonic models and focused on big cities. In this study, we developed a flexible spatiotemporal model (FSTM) to explore the spatiotemporal characteristics of the residential house price and the impact factors in middle-small cities. The FSTM integrated both spatial and temporal components of the residential house price, accounted for its spatiotemporal characteristics, and reproduced its spatial variability and temporal trends. The results showed that the governmental policy had a significant influence on the house price and led to the characteristics being different from those in big cities. The significant factors also included the density of roads, the density of banks, density of supermarkets, the area used by public and user shared area within a building. This study implied that FSTM provided the potential for spatiotemporal prediction of the residential house price in the middle-small cities.

This paper develops an extension of spatiotemporal models that handle count data using nonhomogeneous Poisson processes. In this new proposal, we incorporate a seasonal cycle component in the definition of the intensity function to control possible effects produced by the occurrence of the event of interest in regular periods. The seasonal cycle can cause problems in estimating the shape parameter of the Weibull and generalized Goel intensity functions. This shape parameter serves to confront the research hypothesis that seeks to identify a trend in the occurrence rate of an event of interest. In the case of the Weibull intensity function, a value significantly equal to one of the shape parameters indicates a constant rate of occurrence, less than one indicates a decreasing rate, and greater than one indicates an increasing rate. In the case of the Goel intensity function, parameter values less than or equal to one indicate a decreasing occurrence rate, and values greater than one indicate the presence of a change point. We also built a spatial model using the Musa-Okumoto intensity function as an alternative to approximate counting processes for which there is a decreasing trend in the occurrence rate of the event of interest. We estimated the parameters of the proposed method from a Bayesian perspective. Finally, we fitted the proposed model and compared it with other approximations to analyze the frequency of extreme rainfall in the northern region of the states of Maranhão and Piauí in northeastern Brazil over ten years. Among the main results, we found that (1) the proposed method has proven superior in terms of fit and prediction performance than the other models, and (2) unlike other approximations, the proposed model does not detect changes in the rate of extreme rainfall occurrences. [ABSTRACT FROM AUTHOR]

In 2022, the 22nd International Conference on Aquatic Invasive Species returned to Europe as a hybrid event. The conference welcomed representatives from 41 countries, including the largest group of students and early career professionals of any ICAIS conference. The theme of the conference was "Global Climate Change Amplifies Aquatic Invasive Species Impacts." Keynote speakers discussed ongoing invasions and the damaging synergy between climate change and invasions, presented on the value of risk assessment, outreach, and education, highlighted new ways to estimate the economic costs of invasions, and told attendees about some of the work of NGOs in managing invasions. This special issue includes a selection of papers that were presented at the conference, along with a few related papers that were not presented which touch on the risk of specific vectors, improvements in survey techniques to detect new or spreading invaders, and advances in management approaches to control AIS. [ABSTRACT FROM AUTHOR]

Functional data are generally curves indexed over a time domain, and land-use regression (LUR) is a promising spatial technique for generating high-resolution spatial estimation of retrospective long-term air pollutants. We developed a methodology for the novel functional land-use regression (FLUR) model, which provides high-resolution spatial and temporal estimations of retrospective pollutants. Long-term fine particulate matter (PM2.5) in the megacity of Tehran, Iran, was used as the practical example. The hourly measured PM2.5 concentrations were averaged for each hour and in each air monitoring station. Penalized smoothing was employed to construct the smooth PM2.5 diurnal curve using averaged hourly data in each of the 30 stations. Functional principal component analysis (FPCA) was used to extract FPCA scores from pollutant curves, and LUR models were fitted on FPCA scores. The mean of all PM2.5 diurnal curves had a maximum of 39.58 µg/m3 at 00:26 a.m. and a minimum of 29.27 µg/m3 at 3:57 p.m. The FPCA explained about 99.5% of variations in the observed diurnal curves across the city using just three components. The evaluation of spatially predicted long-term PM2.5 diurnal curves every 15 min provided a series of 96 high-resolution exposure maps. The presented methodology and results could benefit future environmental epidemiological studies. [ABSTRACT FROM AUTHOR]

Complex nonlinear distributed parameter systems (DPSs) exist widely in advanced industrial thermal processes. The modeling of such highly nonlinear systems is a challenge for traditional time/space-separation-based methods since they employ linear methods for the model reduction and spatiotemporal reconstruction, which may lead to an inefficient application of the nonlinear spatial structure features represented by the spatial basis functions. To overcome this problem, a novel spatiotemporal modeling framework composed of nonlinear temporal domain transformation and nonlinear spatiotemporal domain reconstruction is proposed in this paper. Firstly, local nonlinear dimension reduction based on the locally linear embedding technique is utilized to perform nonlinear temporal domain transformation of the spatiotemporal output of nonlinear DPSs. In this step, the original spatiotemporal data can be directly transformed into low-order time coefficients. Then, the extreme learning machine (ELM) method is utilized to establish a temporal model. Finally, through the spatiotemporal domain reconstruction based on the kernel-based ELM method, the prediction of the temporal dynamics obtained from the temporal model can be reconstructed back to the spatiotemporal output. The effectiveness and performance of the proposed method are demonstrated in experiments on the thermal processes of a snap curing oven and a lithium-ion battery. [ABSTRACT FROM AUTHOR]

This study presents a deep-learning-based forecast model for spatial and temporal prediction of pluvial flooding. The developed model can produce the flooding situation for the upcoming time steps as a sequence of flooding maps. Thus, a dynamic overview of the forthcoming flooding situation is generated to support the decision of crisis management actors. The influence of different input data, data formats, and model setups on the prediction results was investigated. Data from multiple sources were considered as follows: precipitation information, spatial information, and an overflow forecast. In addition, models with different layers and network architectures such as convolutional layers, graph convolutional layers, or generative adversarial networks (GANs) were considered and evaluated. The data required to train and test the models were generated using a coupled hydrodynamic 1D/2D model. The model setup with the inclusion of all available input variables and an architecture with graph convolutional layers presented, in general, the best results in terms of root mean square error (RMSE) and critical success index (CSI). The prediction results of the final model showed a high agreement with the simulation results of the hydrodynamic model, with drastic reductions in computation time, making this model suitable for integration into an early warning system for pluvial flooding. [ABSTRACT FROM AUTHOR]

Temporally and spatially resolved data on wind power generation are very useful for studying the technical and economic aspects of this variable renewable energy at local and regional levels. Due to the lack of disaggregated electricity data from onshore and offshore turbines in Germany, it is necessary to use numerical simulations to calculate the power generation for a given geographic area and time period. This study shows how such a simulation model, which uses freely available plant and weather data as input variables, can be developed with the help of basic atmospheric laws and specific power curves of wind turbines. The wind power model is then applied to ensembles of nearly 28,000 onshore and 1500 offshore turbines to simulate the wind power generation in Germany for the years 2019 and 2020. For both periods, the obtained and spatially aggregated time series are in good agreement with the measured feed-in patterns for the whole of Germany. Such disaggregated simulation results can be used to analyze the power generation at any spatial scale, as each turbine is simulated separately with its location and technical parameters. This paper also presents the daily resolved wind power generation and associated indicators at the federal state level. [ABSTRACT FROM AUTHOR]

Abstract Background Image segmentation in fluorescence microscopy is often based on spectral separation of fluorescent probes (color-based segmentation) or on significant intensity differences in individual image regions (intensity-based segmentation). These approaches fail, if dye fluorescence shows large spectral overlap with other employed probes or with strong cellular autofluorescence. Results Here, a novel model-free approach is presented which determines bleaching characteristics based on dynamic mode decomposition (DMD) and uses the inferred photobleaching kinetics to distinguish different probes or dye molecules from autofluorescence. DMD is a data-driven computational method for detecting and quantifying dynamic events in complex spatiotemporal data. Here, DMD is first used on synthetic image data and thereafter used to determine photobleaching characteristics of a fluorescent sterol probe, dehydroergosterol (DHE), compared to that of cellular autofluorescence in the nematode Caenorhabditis elegans. It is shown that decomposition of those dynamic modes allows for separating probe from autofluorescence without invoking a particular model for the bleaching process. In a second application, DMD of dye-specific photobleaching is used to separate two green-fluorescent dyes, an NBD-tagged sphingolipid and Alexa488-transferrin, thereby assigning them to different cellular compartments. Conclusions Data-based decomposition of dynamic modes can be employed to analyze spatially varying photobleaching of fluorescent probes in cells and tissues for spatial and temporal image segmentation, discrimination of probe from autofluorescence and image denoising. The new method should find wide application in analysis of dynamic fluorescence imaging data.

The current research attempts to present a modeling framework for determining soil moisture conditions by using remotely sensed imagery products. In this way, identifying various pixels with similar patterns from satellite images could be a reliable method to have an appropriate view over the soil moisture condition of a particular region. In this context, an artificial intelligence-based self-organizing map (SOM) method is employed to classify homogenous pixels over Phoenix, which is located in the south of Arizona, utilizing parameters extracted from satellite images. The central pixels of clusters are selected as the cluster indicator, with one from each cluster. Then, feed-forward neural networks (FFNNs) consisting of three layers of input, hidden, and output are trained by employing the extracted satellite images time series of the central pixels of the clusters. Finally, the soil moisture conditions of the representative pixels of the clusters are simulated by the trained models. The results reveal the suitability of SOM-based clustering to identify the specific points by which soil moisture can represent the soil moisture condition over the related regions. The proposed methodology and obtained results can be further used to provide a cost-effective method to determine the soil moisture condition of the region by reducing the costs of monitoring. HIGHLIGHTS An SOM is used to cluster homogenous pixels.; The soil moisture conditions of the representative pixel for each cluster are simulated by using an ANN.; The results reveal the suitability of the SOM clustering method to identify the specific points by which the soil moisture can represent the soil moisture condition.;

Quantifying the impacts of disturbances such as oil spills on marine species can be challenging. Natural environmental variability, human responses to the disturbance (e.g., fisheries closures), the complex life histories of the species being monitored, and limited pre-spill data can make detection of effects of oil spills difficult. Using long-term monitoring data from the state of Louisiana (USA), we applied novel spatiotemporal approaches to identify anomalies in species occurrence and catch rates. We included covariates (salinity, temperature, turbidity) to help isolate unusual events. While some species showed evidence of unlikely temporal anomalies in occurrence or catch rates, we found that the majority of the observed anomalies were also before the Deepwater Horizon event. Several species-gear combinations suggested upticks in the spatial variability immediately following the spill, but most species indicated no trend. Across species-gear combinations, there was no clear evidence for synchronous or asynchronous responses in occurrence or catch rates across sites following the spill. Our results are in general agreement to other analyses of monitoring data that detected small impacts, but in contrast to recent results from ecological modeling that showed much larger effects of the oil spill on fish and shellfish.

We developed a novel approach in the field of spatiotemporal modeling, based on the spatialisation of time, the Timescape algorithm. It is especially aimed at sparsely distributed datasets in ecological research, whose spatial and temporal variability is strongly entangled. The algorithm is based on the definition of a spatiotemporal distance that incorporates a causality constraint and that is capable of accommodating the seasonal behavior of the modeled variable as well. The actual modeling is conducted exploiting any established spatial interpolation technique, substituting the ordinary spatial distance with our Timescape distance, thus sorting, from the same input set of observations, those causally related to each estimated value at a given site and time. The notion of causality is expressed topologically and it has to be tuned for each particular case. The Timescape algorithm originates from the field of stable isotopes spatial modeling (isoscapes), but in principle it can be used to model any real scalar random field distribution.

Numerous clinical investigations require understanding changes in anatomical shape over time, such as in dynamic organ cycle characterization or longitudinal analyses (e.g., for disease progression). Spatiotemporal statistical shape modeling (SSM) allows for quantifying and evaluating dynamic shape variation with respect to a cohort or population of interest. Existing data-driven SSM approaches leverage information theory to capture population-level shape variations by learning correspondence-based (landmark) representations of shapes directly from data using entropy-based optimization schemes. These approaches assume sample independence and thus are unsuitable for sequential dynamic shape observations. Previous methods for adapting entropy-based SSM optimization schemes for the spatiotemporal case either utilize a cross-sectional design (ignoring within-subject correlation) or impose other limiting assumptions, such as the linearity of shape dynamics. Here, we present a principled approach to spatiotemporal SSM that relaxes these assumptions to correctly capture population-level shape variation over time. We propose to incorporate modeling the underlying time dependency into correspondence optimization via a regularized principal component polynomial regression. This approach is flexible enough to capture non-linear temporal dynamics while encoding population-specific spatial regularity. We demonstrate our method’s efficacy on synthetic data and left atrium segmented from cardiac MRI scans. Our approach better captures the population modes of variation and a statistically significant time dependency than existing methods.

Ultraviolet radiation (UVR) exposure is the major risk factor for melanoma. However, epidemiologic studies on UVR and noncutaneous cancers have reported inconsistent results, with some suggesting an inverse relationship potentially mediated by vitamin D. To address this, we examined 3 US prospective cohorts, the Health Professionals Follow-up Study (HPFS) (1986) and Nurses' Health Study (NHS) I and II (1976 and 1989), for associations between cumulative erythemal UVR and incident cancer risk, excluding nonmelanoma skin cancer. We used a validated spatiotemporal model to calculate erythemal UVR. Participants (47,714 men; 212,449 women) were stratified into quintiles by cumulative average erythemal UVR, using the first quintile as referent, for Cox proportional hazards regression analysis. In the multivariable-adjusted meta-analysis of all cohorts, compared with the lowest quintile, risk of any cancer was slightly increased across all other quintiles (highest quintile hazard ratio (HR) = 1.04, 95% confidence interval (CI): 1.01, 1.07; P for heterogeneity = 0.41). All UVR quintiles were associated with similarly increased risk of any cancer excluding melanoma. As expected, erythemal UVR was positively associated with risk of melanoma (highest quintile HR = 1.17, 95% CI: 1.04, 1.31; P for heterogeneity = 0.83). These findings suggest that elevated UVR is associated with increased risk of both melanoma and noncutaneous cancers. [ABSTRACT FROM AUTHOR]

The impact of COVID-19 across the United States (US) has been heterogeneous, with rapid spread and greater mortality in some areas compared with others. We used geographically-linked data to test the hypothesis that the risk for COVID-19 was defined by location and sought to define which demographic features were most closely associated with elevated COVID-19 spread and mortality. We leveraged geographically-restricted social, economic, political, and demographic information from US counties to develop a computational framework using structured Gaussian process to predict county-level case and death counts during the pandemic's initial and nationwide phases. After identifying the most predictive information sources by location, we applied an unsupervised clustering algorithm and topic modeling to identify groups of features most closely associated with COVID-19 spread. Our model successfully predicted COVID-19 case counts of unseen locations after examining case counts and demographic information of neighboring locations, with overall Pearson's correlation coefficient and the proportion of variance explained as 0.96 and 0.84 during the initial phase and 0.95 and 0.87 during the nationwide phase, respectively. Aside from population metrics, presidential vote margin was the most consistently selected spatial feature in our COVID-19 prediction models. Urbanicity and 2020 presidential vote margins were more predictive than other demographic features. Models trained using death counts showed similar performance metrics. Topic modeling showed that counties with similar socioeconomic and demographic features tended to group together, and some of these feature sets were associated with COVID-19 dynamics. Clustering of counties based on these feature groups found by topic modeling revealed groups of counties that experienced markedly different COVID-19 spread. We conclude that topic modeling can be used to group similar features and identify counties with similar features in epidemiologic research. [ABSTRACT FROM AUTHOR]

Numerical weather prediction (NWP) provides the future state of the atmosphere and is a major tool for weather forecasting. However, NWP has inevitable errors and requires bias correction to obtain more accurate forecasts. NWP is based on discrete numerical calculations, which inevitably result in a loss in resolution, and downscaling provides important support for obtaining detailed weather forecasts. In this paper, based on the spatio-temporal modeling approach, the Spatio-Temporal Transformer U-Net (ST-UNet) is constructed based on the U-net framework using the swin transformer and convolution to perform bias correction and temporal downscaling. The encoder part extracts features from the multi-time forecasts, and the decoder part uses the features from the encoder part and the constructed query vector for feature reconstruction. Besides, the query builder block generates different query vectors to accomplish different tasks. Multi-time bias correction was conducted for the 2-m temperature and the 10-m wind component. The results showed that the deep learning model significantly outperformed the anomaly numerical correction with observations, and ST-UNet also outperformed the U-Net model for single-time bias correction and the 3-dimensional U-Net (3D-UNet) model for multi-time bias correction. Forecasts from ST-UNet obtained the smallest root mean square error and the largest accuracy and correlation coefficient on both the 2-m temperature and 10-m wind component experiments. Meanwhile, temporal downscaling was performed to obtain hourly forecasts based on ST-UNet, which increased the temporal resolution and reduced the root mean square error by 0.78 compared to the original forecasts. Therefore, our proposed model can be applied to both bias correction and temporal downscaling tasks and achieve good accuracy.

Future weather conditions can be obtained based on numerical weather prediction (NWP); however, NWP is unsatisfied with precise local weather prediction. In this study, we propose a spatiotemporal convolutional network (STCNet) based on spatiotemporal modeling for local weather prediction post-processing. To model the spatiotemporal information, we use a convolutional neural network and an interactive convolutional module, which use two-dimensional convolution for spatial feature extraction and one-dimensional convolution for time-series processing, respectively. We performed experiments at several stations, and the results show that our model considerably outperforms the traditional recurrent neural network–based Seq2Seq model while demonstrating the effectiveness of the fusion of observation and forecast data. By investigating the influences of seasonal changes and station differences, we conclude that the STCNet model has high prediction accuracy and stability. Finally, we completed the hour-by-hour local weather prediction using the 3-h forecast data and attained similar results to the 3-h local weather prediction that efficiently compensated for the temporal resolution of the forecast data. Thus, our model can enhance the spatial and temporal resolutions of forecast data and achieve remarkable local weather prediction.

Time/space separation-based methods have been extensively employed in modeling the lithium-ion battery (LIB) thermal process. However, these methods often adopt linear separation and reconstruction models that heavily depend on spatial basis functions to separate and reconstruct the spatiotemporal domain of the thermal process, which fails to handle highly nonlinear thermal dynamics. To cope with this problem, a nonlinear spatiotemporal modeling method combined with t-distributed stochastic neighbor embedding (t-SNE) and broad learning system (BLS) is presented in this paper. First, a parametric t-SNE is designed to transform the spatiotemporal domain of the LIB thermal process into the time domain. Compared with traditional linear separation models, the proposed t-SNE can better preserve the nonlinear information of spatiotemporal temperature data. Then, BLS is utilized for dynamic temporal model construction. Finally, BLS is also employed to establish a nonlinear reconstruction model for the spatiotemporal domain. To improve the modeling accuracy and reduce the structural complexity of these two BLS-based models, a two-stage selection strategy of activation functions is designed. Since both t-SNE and BLS can handle nonlinear complexity, the proposed method provides significant benefits for nonlinear modeling. The efficiency of the proposed method is demonstrated by experimental findings on a 32 Ah ternary LIB. • A novel temperature distribution estimation method for batteries is proposed. • t-SNE is introduced to realize spatiotemporal decoupling. • Broad learning system is designed to enhance the modeling performance. • Experimental results on a battery confirm the effectiveness of this model. [ABSTRACT FROM AUTHOR]

Predicting the trajectory of geographical events, such as wildfire spread, presents a formidable task due to the dynamic associations among influential biophysical factors. Geo-events like wildfires frequently display short and long-range spatial and temporal correlations. Short-range effects are the direct contact and near-contact spread of the fire front. Long-range effects are represented by processes such as spotting, where firebrands carried by the wind ignite fires distant from the flaming front, altering the shape and speed of an advancing fire front. This study addresses these modeling challenges by clearly defining and analyzing the scale-dependent spatiotemporal dynamics that influence wildfire spread, focusing on the interplay between biophysical factors and fire behavior. We propose two unique attention-based spatiotemporal models using Convolutional Long Short-Term Memory (ConvLSTM) networks. These models are designed to learn and capture a range of local to global and short and long-range spatiotemporal correlations. The proposed models were tested on two datasets: a high-resolution wildfire spread dataset produced with a semi-empirical percolation model and a satellite observed wildfire spread data in California 2012–2021. Results indicate that attention-based models accurately predict fire front movements that are consistent with known wildfire spread-biophysical dynamics. Our research suggests there is considerable potential for attention mechanisms to capture the spatiotemporal behavior of wildfire spread, with model transferability, that can guide rapid deployment of wildfire management operations. We also highlight directions for future studies that focus on how the self-attention mechanism could enhance model performance for a range of geospatial applications. [Display omitted] • Tackles predicting wildfire spread by linking biophysical factors and spatial-temporal correlations. • Introduces two novel attention-based ConvLSTM models for dynamic wildfire analysis. • Models capture short and long-range effects like direct spread and spotting. • Tested on high-resolution data, models accurately predict wildfire dynamics. [ABSTRACT FROM AUTHOR]

Background: Image segmentation in fluorescence microscopy is often based on spectral separation of fluorescent probes (color-based segmentation) or on significant intensity differences in individual image regions (intensity-based segmentation). These approaches fail, if dye fluorescence shows large spectral overlap with other employed probes or with strong cellular autofluorescence. Results: Here, a novel model-free approach is presented which determines bleaching characteristics based on dynamic mode decomposition (DMD) and uses the inferred photobleaching kinetics to distinguish different probes or dye molecules from autofluorescence. DMD is a data-driven computational method for detecting and quantifying dynamic events in complex spatiotemporal data. Here, DMD is first used on synthetic image data and thereafter used to determine photobleaching characteristics of a fluorescent sterol probe, dehydroergosterol (DHE), compared to that of cellular autofluorescence in the nematode Caenorhabditis elegans. It is shown that decomposition of those dynamic modes allows for separating probe from autofluorescence without invoking a particular model for the bleaching process. In a second application, DMD of dye-specific photobleaching is used to separate two green-fluorescent dyes, an NBD-tagged sphingolipid and Alexa488-transferrin, thereby assigning them to different cellular compartments. Conclusions: Data-based decomposition of dynamic modes can be employed to analyze spatially varying photobleaching of fluorescent probes in cells and tissues for spatial and temporal image segmentation, discrimination of probe from autofluorescence and image denoising. The new method should find wide application in analysis of dynamic fluorescence imaging data. [ABSTRACT FROM AUTHOR]

The irregular timing and spatial variation in the zoonotic arbovirus spillover from vertebrate hosts to humans and livestock present challenges to predicting spillover occurrence over time and across broader geographic areas, compromising effective prevention and control strategies. The objective of this study was to quantify the effects of the landscape composition and configuration and dynamic weather events on the 2018 spatiotemporal distribution of eastern equine encephalitis virus (EEEV) (Togaviridae, Alphavirus) and West Nile virus (WNV) (Flaviviridae, Flavivirus) sentinel chicken seroconversion in northeastern Florida. We used a modeling framework that explicitly accounts for joint spatial and temporal effects and incorporates key EO (Earth Observation) information on the climate and landscape in order to more accurately quantify the environmental effects on the transmission to sentinel chickens. We investigated the environmental effects using Bernoulli generalized linear mixed effects models (GLMMs), including a site-level random effect, and then added spatial random effects and spatiotemporal random effects in subsequent runs. The models were executed using an integrated nested Laplace approximation (INLA) and a stochastic partial differential equation (SPDE) approach in R-INLA. The GLMMs that included a spatiotemporal random effect performed better relative to models that included only spatial random effects and also performed better than non-spatial models. The results indicated a strong spatiotemporal structure in the seroconversion for both viruses, but EEEV exhibited a more punctuated and compact structure at the beginning of the sampling season, while WNV exhibited a more gradual and diffuse structure across the study area toward the end of the sampling season. The percentage of cypress–tupelo wetland land cover within 3500 m of coop sites and the edge density of the forest land cover within 500 m had a strong positive effect on the EEEV seroconversion, while the best fitting model for WNV was the intercept-only model with spatiotemporal random effects. The lagged climatic variables included in our study did not have a strong effect on the seroconversion for either virus when accounting for temporal autocorrelation, demonstrating the utility of capturing this structure to avoid type I errors. The predictive accuracy for out-of-sample data for the EEEV seroconversion demonstrates the potential to develop a framework that incorporates temporal dynamics in order to better predict arbovirus transmission. [ABSTRACT FROM AUTHOR]

This article describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species (Abies alba Mill., Castanea sativa Mill., Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., Prunus avium L., Quercus cerris L., Quercus ilex L., Quercus robur L., Quercus suber L. and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data for a total of three million of points was used to train different algorithms: random forest, gradient-boosted trees, generalized linear models, k-nearest neighbors, CART and an artificial neural network. A stack of 305 coarse and high resolution covariates representing spectral reflectance, different biophysical conditions and biotic competition was used as predictors for realized distributions, while potential distribution was modelled with environmental predictors only. Logloss and computing time were used to select the three best algorithms to tune and train an ensemble model based on stacking with a logistic regressor as a meta-learner. An ensemble model was trained for each species: probability and model uncertainty maps of realized distribution were produced for each species using a time window of 4 years for a total of six distribution maps per species, while for potential distributions only one map per species was produced. Results of spatial cross validation show that the ensemble model consistently outperformed or performed as good as the best individual model in both potential and realized distribution tasks, with potential distribution models achieving higher predictive performances (TSS = 0.898, R²logloss = 0.857) than realized distribution ones on average (TSS = 0.874, R²logloss = 0.839). Ensemble models for Q. suber achieved the best performances in both potential (TSS = 0.968, R²logloss = 0.952) and realized (TSS = 0.959, R²logloss = 0.949) distribution, while P. sylvestris (TSS = 0.731, 0.785, R²logloss = 0.585, 0.670, respectively, for potential and realized distribution) and P. nigra (TSS = 0.658, 0.686, R²logloss = 0.623, 0.664) achieved the worst. Importance of predictor variables differed across species and models, with the green band for summer and the Normalized Difference Vegetation Index (NDVI) for fall for realized distribution and the diffuse irradiation and precipitation of the driest quarter (BIO17) being the most frequent and important for potential distribution. On average, fine-resolution models outperformed coarse resolution models (250 m) for realized distribution (TSS = +6.5%, R²logloss = +7.5%). The framework shows how combining continuous and consistent Earth Observation time series data with state of the art machine learning can be used to derive dynamic distribution maps. The produced predictions can be used to quantify temporal trends of potential forest degradation and species composition change. [ABSTRACT FROM AUTHOR]