Dynamic Prediction Research Articles

Assimilation of Satellite-Derived Reservoir Storage Data to Improve Global Hydrodynamic Modeling

In this study, we explore the potential of assimilating satellite-derived reservoir storage data into the global-scale hydrodynamic model CaMa-Flood, focusing on the Yangtze River basin. We evaluated three data assimilation (DA) methods: direct assimilation (DIR), anomaly based assimilation (ANO), and normalized assimilation (NOM). Our results show that the DIR method achieved the most significant improvements in reservoir storage and downstream discharge simulations. DIR reduced the average relative root mean square error (rRMSE) of reservoir storage estimates by 80.5%, and increased discharge correlation (ΔCC) by 78.6% in the 14 validated discharge stations. ANO, while effective in certain cases, led to mixed results, with 56.4% of the 39 assimilated dams showing improved storage estimates and a modest 7.8% reduction in average RMSE. NOM had minimal impact, with negligible changes in RMSE or discharge correlation (ΔCC). The direct assimilation method (DIR) consistently outperformed the others, improving both reservoir storage and downstream discharge estimates. However, the magnitude of improvement varied across locations, highlighting the need for the further refinement of DA techniques and input data, especially for regions with complex reservoir operations. Our findings enhance reservoir representation in global hydrodynamic models and improve the predictability of river dynamics and water resource management.

Impact of broader ecological and socio-environmental components on Aedes mosquito population dynamics: a spatial-temporal longitudinal study.

The increasing spread of mosquito-borne diseases is a significant problem globally, but mosquito management strategies are less efficient. Therefore, a comprehensive understanding of the population dynamics of Aedes mosquito is essential for improving mosquito management strategies. Constructing a model to understand Aedes mosquito development in response to environmental factors is crucial to addressing these challenges. An extensive data set on Aedes spp. mosquito populations was constructed, considering the environmental factors temperature, water vapor pressure, wind speed, daylength, and rainfall. This data set, compiled from mosquito collections over a period of four years across multiple locations in Alabama, USA, facilitated the prediction of mosquito dynamics. The random forest model was used to explain mosquito population changes in response to these factors. These findings indicated that temperature, daylength, and water vapor pressure had the most significant impacts on mosquito population dynamics. The model also allowed predictions of mosquito population changes over time and across different geographic regions, extending beyond Alabama to the southeastern USA. This study provided valuable insights into the impacts of environmental factors on mosquito populations. This novel approach using machine learning and the random forest model will enable researchers to predict future mosquito populations and contribute to developing more-effective strategies for mosquito management. © 2024 Society of Chemical Industry. Published by John Wiley & Sons Ltd.

Groundwater dynamics clustering and prediction based on grey relational analysis and LSTM model: A case study in Beijing Plain, China

Study regionBeijing Plain, China Study focusThe traditional zoning of groundwater systems relies on lithological characteristics and hydraulic connections. However, the influence of climate change and human activities has led to the emergence of diverse dynamic patterns within these systems. Additionally, the differences in groundwater dynamic characteristics are often ignored when modeling with machine learning methods. In this study, a new clustering method named GRA-CLU was proposed to classify dynamic types of groundwater. Then, regional models are built using LSTM based on the dynamic zoning, aiming to incorporate hydrogeological significance into the pure data-driven model.New hydrological insights for the region: The GRA-CLU method classified the study area into six groundwater dynamic types. Compared with the traditional hydrogeological units, the new zoning result identified two dynamic types that have never been considered: urban influence zone and mountain-plain junction zone where surface water interacts with groundwater. Through analysis, the significant rise of groundwater levels in 2021 was more influenced by heavy rainfall events rather than human activities. This study further explored the performance of LSTM regional models based on the six dynamic zones. The results indicated that the NSE of models increased by 5.7–50.0 %, the improvement was more obvious in zones with irregular fluctuations. The RMSE decreased by 31.5–59.8 %, particularly noticeable in zones with regular annual fluctuations and large samples.

RNALocate v3.0: Advancing the Repository of RNA Subcellular Localization with Dynamic Analysis and Prediction.

Subcellular localization of RNA is a crucial mechanism for regulating diverse biological processes within cells. Dynamic RNA subcellular localizations are essential for maintaining cellular homeostasis; however, their distribution and changes during development and differentiation remain largely unexplored. To elucidate the dynamic patterns of RNA distribution within cells, we have upgraded RNALocate to version 3.0, a repository for RNA-subcellular localization (http://www.rnalocate.org/ or http://www.rna-society.org/rnalocate/). RNALocate v3.0 incorporates and analyzes RNA subcellular localization sequencing data from over 850 samples, with a specific focus on the dynamic changes in subcellular localizations under various conditions. The species coverage has also been expanded to encompass mammals, non-mammals, plants and microbes. Additionally, we provide an integrated prediction algorithm for the subcellular localization of seven RNA types across eleven subcellular compartments, utilizing convolutional neural networks(CNNs) and transformer models. Overall, RNALocate v3.0 contains a total of 1 844 013 RNA-localization entries covering 26 RNA types, 242 species and 177 subcellular localizations. It serves as a comprehensive and readily accessible data resource for RNA-subcellular localization, facilitating the elucidation of cellular function and disease pathogenesis.

MODELS FOR REAL-TIME TRAFFIC FLOW MANAGEABILITY AND DECISION-MAKING IN INTELLIGENT TRANSPORTATION SYSTEMS

This article explores models in Intelligent Transportation Systems for real-time traffic flow manageability, focusing on decision-making processes. It covers forecasting, planning, implementing, and controlling strategies to manage traffic flow and ease congestion. Traffic flow prediction models, like dynamic route guidance and traffic flow prediction, utilize historical data and real-time inputs for proactive decision-making. Traffic flow planning models, such as dynamic route guidance index and route efficiency factor, aid in route selection and signal timing optimization. In order to streamline the boundless complexity, the authors assume that it is effective to delineate the managerial capacity paradigm of intelligent transportation systems into the two separate scenarios of “stable and known situation” and “unstable and with large uncertainty situation”. The article proposes a hypothesis to improve the decision-making process in traffic flow. The distinction between these two situations is essential for the smooth running of the business and requires a thorough understanding of the traffic flow in real time, making decisions in intelligent transport systems in order to direct the traffic. The article focuses on data-driven decisions for smoother traffic flow.

Dynamic Response Prediction Model for Jack-Up Platform Pile Legs Based on Random Forest Algorithm

Jack-up offshore platforms are widely used in many fields, and it is of great importance to quickly and accurately predict the dynamic response of platform pile leg structures in real time. The current analytical techniques are founded upon numerical modelling of the platform structure. Although these methods can be used to accurately analyze the dynamic response of the platform, they require a large quantity of computational resources and cannot meet the requirements of real-time prediction. A predictive model for the dynamic response of the pile leg of a jack-up platform based on the random forest algorithm is proposed. Firstly, a pile leg dynamic response database is established based on high-fidelity numerical model simulation calculations. The data are subjected to cleaning and dimensional reduction in order to facilitate the training of the random forest model. Cross-checking and Bayesian optimization algorithms are used for the selection of random forest parameters. The results show that the prediction model is capable of outputting response results for new environmental load inputs within a few milliseconds, and the prediction results remain highly accurate and perform well at extreme values.

Study of Molecular Docking, Molecular Dynamics, Pharmacokinetics and Toxicity Prediction: Compounds from Nigella sativa Linn, Andrographis paniculata Nees, and Propolis as Inhibitors of Mycobacterium tuberculosis Growth

Background: Tuberculosis (TB) is caused by *Mycobacterium tuberculosis*, and Multiple Drug-Resistant Tuberculosis (MDR-TB) arises from resistance to first-line treatments like Rifampicin and Isoniazid. Since current TB medications have been used for over four decades, discovering new drug candidates is critical. This research focuses on herbal compounds—Black cumin (*Nigella sativa*), Sambiloto (*Andrographis paniculata*), and propolis—as potential inhibitors of *M. tuberculosis* by targeting DHFR. The objective of the study is to predict the activity of these herbal compounds prior to in vitro and in vivo testing. Methods: This study employed computational tools, including Molegro Virtual Docking (MVD) and Molecular Dynamics (MD), to assess the interactions of the herbal compounds with DHFR (PDB ID: 2CIG). Pharmacokinetic predictions were also conducted to evaluate the absorption and toxicity of the compounds. Results: Molecular docking and MD simulations indicated that Andrographolide, Thymoquinone, and Caffeic Acid Phenethyl Ester effectively inhibited the growth of *M. tuberculosis*. The analysis revealed favorable binding interactions and conformational changes in DHFR, with significant activity observed for Thymoquinone. Conclusion: This study suggests that Andrographolide, Thymoquinone, and Caffeic Acid Phenethyl Ester may serve as promising candidates for further development as anti-tuberculosis drugs. Subsequent in vitro and in vivo studies are warranted to validate their therapeutic potential.

Seasonality in Sonoran pronghorn survival and movement within a managed rangeland

AbstractThe endangered Sonoran pronghorn (Antilocapra americana sonoriensis) has a large portion of its range within a military operations area in southwestern Arizona, USA. Sonoran pronghorn have been actively managed in this region for more than 20 years. Recovery efforts have included release of captive‐born pronghorn into areas both currently and historically occupied by wild pronghorn. These areas provide habitat for federally endangered essential and experimental non‐essential, referred to as 10(j), pronghorn populations. More than 20 years of monitoring efforts have resulted in a large dataset on their spatial occurrence and movement within these areas. To synthesize long‐term trends and seasonality in Sonoran pronghorn movement and mortality, we employed a suite of quantitative analyses that characterized the pronghorns' 1) individual and population‐level home ranges, 2) occurrence near active military targets, 3) trends in seasonal group sizes and composition, 4) sex‐ and group‐specific survivorship, and 5) changes in movement‐based behavior following release from captivity. We found strong seasonal trends throughout, including sex‐specific differences in seasonal movement rates, home ranges, survival, and group composition. Further, captive‐born pronghorn released into the endangered population exhibited markedly higher survival compared to those released in 10(j) areas. Captive‐born pronghorn exhibited significant seasonal use of active military target areas. These analyses, which represent the most comprehensive analysis of Sonoran pronghorn movement and survival to date, have important implications for the future conservation and management of this endangered species. Our results indicate that active management of endangered Sonoran pronghorn has successfully increased survival, and we recommend maintaining or increasing current recovery efforts, such as captive breeding and placement of supplemental resources throughout their range (e.g., freestanding water and supplemental forage), to further boost the survivorship of both wild‐ and captive‐born pronghorn. Moreover, future management efforts could use our seasonality results to create dynamic prediction models of when and where pronghorn are likely to overlap with military activities to best manage interactions. Our methods have added application to other mobile species of conservation interest occurring in disturbed and resource‐limited landscapes.

Intelligent Evaluation and Dynamic Prediction of Oysters Freshness with Electronic Nose Non-Destructive Monitoring and Machine Learning.

Physiological and environmental fluctuations in the oyster cold chain can lead to quality deterioration, highlighting the importance of monitoring and evaluating oyster freshness. In this study, an electronic nose was developed using ten partially selective metal oxide-based gas sensors for rapid freshness assessment. Simultaneous analyses, including GC-MS, TVBN, microorganism, texture, and sensory evaluations, were conducted to assess the quality status of oysters. Real-time electronic nose measurements were taken at various storage temperatures (4 °C, 12 °C, 20 °C, 28 °C) to thoroughly investigate quality changes under different storage conditions. Principal component analysis was utilized to reduce the 10-dimensional vectors to 3-dimensional vectors, enabling the clustering of samples into fresh, sub-fresh, and decayed categories. A GA-BP neural network model based on these three classes achieved a test data accuracy rate exceeding 93%. Expert input was solicited for performance analysis and optimization suggestions enhanced the efficiency and applicability of the established prediction system. The results demonstrate that combining an electronic nose with quality indices is an effective approach for diagnosing oyster spoilage and mitigating quality and safety risks in the oyster industry.

Dynamic Link Prediction in Jujube Sales Market: Innovative Application of Heterogeneous Graph Neural Networks

Dynamic Link Prediction in Jujube Sales Market: Innovative Application of Heterogeneous Graph Neural Networks

Data-driven predictor of control-affine nonlinear dynamics: Finite discrete-time bilinear approximation of koopman operator

This paper introduces a novel and efficient data-driven approach for approximating a finite discrete-time bilinear model of control affine nonlinear dynamical systems with a tunable parameter that balances model dimension and prediction accuracy. An approximation of the Koopman operator based on the evolutions of the nonlinear system measurements used to lift a control-affine nonlinear system to a higher dimensional model. However, higher dimensional spaces can result in a long learning time and the curse of dimensionality in control analysis. The proposed approach addresses these challenges by introducing a convex optimization which identifies informative observable functions. This technique allows for the adjustment of a parameter to strike a balance between model dimension and accuracy in prediction. The main contribution of this study is to introduce a reduced dimensional bilinear model for a nonlinear complex system. This achievement is made possible by implementing convex sparse optimization, enabling the exploration of informative estimated Koopman eigenfunctions while minimizing the number of system measurements required. The optimization problem is solved using the alternating direction method of multipliers. The effectiveness of the proposed method is evaluated on three different nonlinear systems: a numerical nonlinear system, a Van der Pol oscillator, and a Duffing oscillator. In the last simulation, an estimation of the Koopman linear model is considered as a special case, and the policy iteration algorithm is employed to evaluate optimal control designed for different reduced-dimensional models.

TdCoxSNN: Time-dependent Cox survival neural network for continuous-time dynamic prediction

Abstract The aim of dynamic prediction is to provide individualized risk predictions over time, which are updated as new data become available. In pursuit of constructing a dynamic prediction model for a progressive eye disorder, age-related macular degeneration (AMD), we propose a time-dependent Cox survival neural network (tdCoxSNN) to predict its progression using longitudinal fundus images. tdCoxSNN builds upon the time-dependent Cox model by utilizing a neural network to capture the nonlinear effect of time-dependent covariates on the survival outcome. Moreover, by concurrently integrating a convolutional neural network with the survival network, tdCoxSNN can directly take longitudinal images as input. We evaluate and compare our proposed method with joint modelling and landmarking approaches through extensive simulations. We applied the proposed approach to two real datasets. One is a large AMD study, the Age-Related Eye Disease Study, in which more than 50,000 fundus images were captured over a period of 12 years for more than 4,000 participants. Another is a public dataset of the primary biliary cirrhosis disease, where multiple laboratory tests were longitudinally collected to predict the time-to-liver transplant. Our approach demonstrates commendable predictive performance in both simulation studies and the analysis of the two real datasets.

Seasonally varying contributions of contemporaneous and lagged sources of instream total nitrogen and phosphorus load across the Illinois River basin

Quantifying nutrient sources in streams, their temporal and spatial variability, and drivers of that variability can support effective water resources management. Yet a lack of data and modeling capabilities has previously prevented comprehensive quantification across both space and time. Here a dynamic SPARROW (Spatially Referenced Regressions on Watershed attributes) model that accounts for a lagged delivery of nutrients to streams was developed and applied to simulate seasonal and source-specific total nitrogen (TN) and total phosphorus (TP) loads in streams across the Illinois River basin (IRB). Dynamic load predictions from 2000 through 2020 revealed that a third of the TN and a quarter of the TP instream load originated from non-point sources that were lagged in their delivery from land-application to streams by more than a season. This lagged mass was the largest overall TN source—which was estimated as a lagged expression of previous seasonal non-point sources including fertilizer, manure, atmospheric deposition and fixation, and urban land use. Treated wastewater effluent was the largest TP source exported from the basin, contributing 39 % of the TP load and 15 % of the TN load, and dominated the load in the upper Illinois River near Chicago. Loads in the lower river during this period, conversely, were attributed primarily to a mix of agricultural sources and their lagged fractions from headwater tributaries. Instream processes removed 10 % of the TN load while only 4 % of the TP load was removed during instream transport. With appropriate datasets, the models could be extended to other basins or time periods and used to forecast future seasonal nutrient loads.

Delayed gastric emptying risk stratification in patients with pancreatic ductal adenocarcinoma after pancreatoduodenectomy: An international validation cohort study.

Currently, there is still a lack of an accurate predictive model for delayed gastric emptying (DGE) following pancreaticoduodenectomy (PD) in patients with pancreatic ductal adenocarcinoma (PDAC). The aim of this study was to develop a concise model that could effectively predict the risk of DGE. This retrospective cohort study included a training cohort of 1251 consecutive PDAC patients who underwent PD from the US multicenter ACS-NSQIP database. Additionally, a validation cohort of 934 consecutive PDAC patients who underwent PD was included from the National Cancer Center in China. A total of 46 perioperative indicators were incorporated in the analysis. The DGE risk stratification (DGERS) model was then developed and validated using Lasso-logistic regression. After screening using Lasso-logistic regression, we identified four independent predictors that were significantly correlated with DGE: days to pancreatic drain removal (HR, 1.05; 95% CI, 1.02-1.08; p<0.001), pancreatic fistula (HR, 2.61; 95% CI, 1.65-4.12; p<0.001), sepsis/septic shock (HR, 2.46; 95% CI, 1.52-3.91; p<0.001), and reoperation (HR, 4.16; 95% CI, 2.27-7.57; p<0.001). Based on these factors, we developed a nomogram to predict postoperative DGE. The model demonstrated excellent calibration and optimal performance in the validation cohorts (AUC, 0.73; 95% CI, 0.67-0.73). In the validation cohort, the DGERS exhibited significant risk stratification ability, with AUC values of 0.7, 0.61, and 0.74 for the low-, moderate-, and high-risk groups, respectively. This study identified four factors that independently increased the occurrence of DGE in patients with PDAC after PD, including days to pancreatic drain removal, pancreatic fistula, sepsis/septic shock, and reoperation. Based on these findings, we developed a personalized and straightforward DGERS that enables dynamic and precise prediction of DGE risk, allowing for effective stratification of individuals based on their risk profiles.

T-Cell Dynamics Predicts Prognosis of Patients with Hepatocellular Carcinoma Receiving Atezolizumab Plus Bevacizumab.

Atezolizumab and bevacizumab show promise for treating hepatocellular carcinoma (HCC), but identifying responsive patients remains challenging, due to tumor heterogeneity. This study explores immune dynamics following this combination therapy. Between 2020 and 2023, 29 patients with advanced HCC who received atezolizumab plus bevacizumab at Severance Hospital, Seoul, were enrolled in this study. Peripheral blood mononuclear cells were analyzed using flow cytometry and statistical methods to assess immune alterations and identify biomarkers. Baseline characteristics showed a diverse HCC cohort with a mean age of 64 years and 82.8% male predominance. Absence of extrahepatic metastasis was associated with better overall survival. Immune responses revealed distinct CD4+ T-cell phenotypes between the 'partial response (PR) + stable disease (SD)' and 'progressive disease (PD)' groups, with an overall increase in CD8+ T-cell phenotypes. Patients with higher frequencies of CD8+PD-1+Ki-67+ T cells experienced significantly improved overall survival, while those with lower frequencies of CD4+Foxp3+PD-1+LAG3+ T cells also had notable survival benefits. These findings enhance the overall understanding of immune responses to this combination therapy, facilitating improved patient stratification and personalized therapeutic approaches for HCC.

Dynamic Response Prediction of Railway Bridges Considering Train Load Duration Using the Deep LSTM Network

Dynamic Response Prediction of Railway Bridges Considering Train Load Duration Using the Deep LSTM Network

Numerical method for dynamic prediction of temperature field in aviation gear profile grinding

Numerical method for dynamic prediction of temperature field in aviation gear profile grinding

Warming and disturbances affect Arctic-boreal vegetation resilience across northwestern North America.

Rapid warming and increasing disturbances in high-latitude regions have caused extensive vegetation shifts and uncertainty in future carbon budgets. Better predictions of vegetation dynamics and functions require characterizing resilience, which indicates the capability of an ecosystem to recover from perturbations. Here, using temporal autocorrelation of remotely sensed greenness, we quantify time-varying vegetation resilience during 2000-2019 across northwestern North American Arctic-boreal ecosystems. We find that vegetation resilience significantly decreased in southern boreal forests, including forests showing greening trends, while it increased in most of the Arctic tundra. Warm and dry areas with high elevation and dense vegetation cover were among the hotspots of reduced resilience. Resilience further declined both before and after forest losses and fires, especially in southern boreal forests. These findings indicate that warming and disturbance have been altering vegetation resilience, potentially undermining the expected long-term increase of high-latitude carbon uptake under future climate.

Exploring the potential of forest snow modeling at the tree and snowpack layer scale

Abstract. Boreal and sub-alpine forests host seasonal snow for multiple months per year; however, snow regimes in these environments are rapidly changing due to rising temperatures and forest disturbances. Accurate prediction of forest snow dynamics, relevant for ecohydrology, biogeochemistry, cryosphere, and climate sciences, requires process-based models. While snow schemes that track the microstructure of individual snow layers have been proposed for avalanche research, so far, tree-scale processes resolving canopy representations only exist in a few snow-hydrological models. A framework that enables layer- and microstructure-resolving forest snow simulations at the meter scale is lacking to date. To fill this research gap, this study introduces the forest snow modeling framework FSMCRO, which combines two detailed, state-of-the art model components: the canopy representation from the Flexible Snow Model (FSM2) and the snowpack representation of the Crocus ensemble model system (ESCROC). We apply FSMCRO to discontinuous forests at boreal and sub-alpine sites to showcase how tree-scale forest snow processes affect layer-scale snowpack properties. Simulations at contrasting locations reveal marked differences in stratigraphy throughout the winter. These arise due to different prevailing processes at under-canopy versus gap locations and due to variability in snow metamorphism dictated by a spatially variable snowpack energy balance. Ensemble simulations allow us to assess the robustness and uncertainties of simulated stratigraphy. Spatially explicit simulations unravel the dependencies of snowpack properties on canopy structure at a previously unfeasible level of detail. Our findings thus demonstrate how hyper-resolution forest snow simulations can complement observational approaches to improve our understanding of forest snow dynamics, highlighting the potential of such models as research tools in interdisciplinary studies.

Integrating Flow Field Dynamics and Chemical Atmosphere Predictions for Enhanced Sulfur Corrosion Risk Assessment in Power Boilers.

In this work, we attempt to explain the phenomenon of sulfur corrosion of power boiler water walls under the conditions of large fluctuations in carbon monoxide concentrations. To assess the conditions required for corrosion formation, a criterion based on the chemical and flow field parameters of the flue gas is proposed. The formulated sulfur corrosion criterion is based on the mixture fraction variance and the turbulence time scale. Numerical modeling of coal combustion in a 250 MW power boiler is performed using ANSYS. Two cases of combustion in a boiler are analyzed, with the first simulating the boiler operated using classic high-swirl burners and the second one accounting for boiler operation with modified low-swirl burners. Calculations of pulverized coal combustion are performed using the standard k-ε turbulence model and the combustion described by the mixture fraction. The simulation results reveal that the low-swirl burner is characterized by higher values of the mixture fraction variance and a higher frequency of fluctuation of the velocity field, which is strongly related to an increased corrosion rate. The study outcomes show the validity of using the criterion of the mixture fraction variance and velocity field fluctuations to determine the areas at risk of sulfur corrosion.