Statistical Model Research Articles

Two decades of data on the neurotoxic Gymnodinium catenatum dynamics and paralytic shellfish toxins contamination of molluscs in the southwestern Mediterranean: What have we learned?

Harmful algal blooms have been documented in the Moroccan Western Mediterranean region since 1993, primarily associated with the presence of paralytic shellfish toxins (PSTs) produced by the dinoflagellate Gymnodinium catenatum. The proliferation of this neurotoxic species has led to recurring bans on the harvesting of molluscs, resulting in significant socio-economic repercussions and threats to human health. In the present study, we examine the dynamics of G. catenatum and mollusc PST contamination patterns over a 20-year period (2002−2021) in two distinct marine ecosystems: M'diq Bay and the Oued Laou Estuary. For the PST contamination, we considered two commercially important shellfish species: the smooth clam, Callista Chione, and the cockle, Acanthocardia tuberculata. The highest G. catenatum abundances were consistently observed from November to February in both sites. Our data revealed inter-annual variations in G. catenatum abundance, peaking at 91,840 cells.L−1 in November 2011. PST contamination levels in A. tuberculata were significantly higher than those observed in C. chione. Furthermore, we identified a significant correlation (Pearson, P-value <0.05) between PST contamination of smooth clams and the abundance of G. catenatum. The contamination of A. tuberculata by PSTs reached very high levels, with up to 13,500 μg STX di-HCl eq. kg−1 of shellfish meat, exceeding the established safety thresholds by 16-fold. Additionally, there has been an increase in the prevalence and incidence of PSTs over the years. Notably, we observed a substantial increase in G. catenatum blooms and PST events in the Western Mediterranean during the last decade (2010−2021). The examined data suggest that rainfall could play a pivotal role in G. catenatum bloom dynamics by enriching marine waters with nutrients. The statistical model selection approaches indicated that nutrient concentrations (i.e., nitrate and phosphorus) were the most significant parameters for G. catenatum blooms in the studied area.

Scalable spatiotemporal prediction with Bayesian neural fields

Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in diverse applications, such as air pollution monitoring, disease tracking, and cloud-demand forecasting. As the scale of modern datasets increases, there is a growing need for statistical methods that are flexible enough to capture complex spatiotemporal dynamics and scalable enough to handle many observations. This article introduces the Bayesian Neural Field (BayesNF), a domain-general statistical model that infers rich spatiotemporal probability distributions for data-analysis tasks including forecasting, interpolation, and variography. BayesNF integrates a deep neural network architecture for high-capacity function estimation with hierarchical Bayesian inference for robust predictive uncertainty quantification. Evaluations against prominent baselines show that BayesNF delivers improvements on prediction problems from climate and public health data containing tens to hundreds of thousands of measurements. Accompanying the paper is an open-source software package (https://github.com/google/bayesnf) that runs on GPU and TPU accelerators through the Jax machine learning platform.

Development of mixed linear models to analyze and describe the impact of malathion on the larval growth of Megaselia scalaris (Diptera: Phoridae) under various feeding media and environmental conditions.

Forensic entomology plays a crucial role in estimating the minimum postmortem interval through the study of insect larvae found at crime scenes. The precision of this estimation relies on various biotic and abiotic elements that simultaneously influence insect growth and development, encompassing factors such as temperature, humidity, photoperiod, diet, and the existence of xenobiotics in decomposing tissues. Despite numerous studies on the influence of these factors, including the impact of xenobiotics, there are currently no robust tools available for making corrections to this estimation considering concurrently all variables. In an attempt to propose an exploratory and descriptive statistical model to analyze the simultaneous effect and interaction of different variables on larval growth, this study aimed to compare the effect of malathion on the growth of Megaselia scalaris (Loew, 1866) (Diptera: Phoridae) raised in malathion-spiked porcine muscle, under controlled and uncontrolled temperature and humidity conditions (environmental conditions). Larvae were also reared using various growth media. A split-plot design that combined crossed and nested factors was employed; 2 linear mixed models were developed to assess the relationships between the variables. The model provides valuable insights into the complex interactions among xenobiotics, growth media, and environmental conditions in the size and development of M. scalaris.

Rapid LA-REIMS-based metabolic fingerprinting of serum discriminates aflatoxin-exposed from non-exposed pregnant women: a prospective cohort from the Butajira Nutrition, Mental Health, and Pregnancy (BUNMAP) Study in rural Ethiopia

To date, the changes in maternal metabolic response associated with prenatal aflatoxin exposure remain largely unknown. This study investigated the effects of prenatal aflatoxin exposure on the maternal serum metabolome in rural Ethiopia. A total of 309 pregnant women were enrolled prospectively, and their serum aflatoxin concentrations were measured using targeted liquid chromatography coupled to tandem mass spectrometry (LC–MS/MS). Serum metabolic fingerprints were obtained using laser-assisted rapid evaporative ionization mass spectrometry (LA-REIMS), followed by combination of univariate and multivariate statistical modelling to evaluate changes in circulating metabolic features between aflatoxin-exposed and unexposed mothers and to select discriminatory metabolic features. The analysis revealed that 81.8% of women were exposed to aflatoxins, with a median concentration of 12.9 pg/mg albumin. The orthogonal partial least square discriminant analysis (OPLS-DA) regression model demonstrated significant disparities in the serum metabolome when comparing Ethiopian pregnant women with low vs high aflatoxin exposure. Thirty-two differentially expressed metabolic features were identified, affecting aminoacyl-tRNA biosynthesis pathway. Several discriminatory metabolites have been identified, including glutamine, tryptophan, tyrosine, carnosine, and 1-methylnicotinamide. In conclusion, our findings indicate that aflatoxin exposure during pregnancy have shown disparities in the maternal serum metabolome, primarily affecting protein synthesis. Further research is needed to identify specific metabolite biomarkers and elucidate the underlying mechanisms.

Storylines of projected summer warming in Iberia using atmospheric circulation, soil moisture and sea surface temperature as drivers of uncertainty

This study explores the uncertainty of future summer warming over Iberia using storylines constructed from climate model simulations of the Climate Model Intercomparison Project Phase 6. Unlike prior storyline approaches focusing on remote drivers and global teleconnections of atmospheric circulation, we use regional factors that directly influence summer temperatures: ridging activity, soil moisture and Mediterranean sea surface temperature. These drivers explain a substantial portion of the observed variability across climate models, with ridging activity and soil moisture showing the strongest influence on Iberian warming. Under a high radiative forcing scenario (SSP5–8.5), the storylines of Iberian warming based on these two drivers range between 7 and 9 °C for the end of the 21st century. The storyline leading to the largest warming is characterised by a drying out of the soil conditions and an increase in the anticyclonic activity over Iberia. We find similar conclusions for simple extreme heat indicators, though the approach struggles with more complex heatwave metrics. We also propose a novel modification of the storyline approach to increase the data sample of climate responses by using different time intervals throughout the 21st century. This modification would allow the application of more complex statistical models, the exploration of non-linear relationships and the identification of other drivers shaping the regional climate projections.

Response Surface Design Models to Predict the Strength of Iron Tailings Stabilized with an Alkali-Activated Cement

Tailing storage facilities are very complex structures whose failure generally leads to catastrophic consequences in terms of casualties, serious environmental impacts on local biodiversity, and disruptions in the mineral supply. For this reason, structures at risk must be reinforced or decommissioned. One possible option is its reinforcement with compacted filtered tailings stabilized with binders. Alkali-activated binders provide a more sustainable solution than ordinary Portland cement but require an optimization of the tailing–binder mixture, which, in some cases, can lead to a substantial experimental effort. Statistical models have been used to reduce the number of those experiments, but a rational design methodology is still lacking. This methodology to define the right mixture for a required strength should consider both the mixture components and in situ conditions. In this paper, response surface methods were used to plan and interpret unconfined compression strength test results on an iron tailing stabilized with alkali-activated binders. It was concluded that the fly ash content was the most important parameter, followed by the liquid content and sodium hydroxide concentration. From the obtained results, several statistical models were defined and compared according to the definition of a strength prediction model based on a mixture index parameter. It was interesting to observe that models with the porosity cement index still provide reasonable adjustment even when different tailings’ water contents are considered.

Development of Statistical Downscaling Model Based on Volterra Series Realization, Principal Components, Climate Classification, and Ridge Regression

This paper applied the fuzzy function approach, combined with the ridge regression model, to produce daily rainfall projections from large-scale climate variables. This study developed a statistical downscaling model based on principal components, c-means fuzzy clustering, Volterra series, and ridge regression. The model is known, hereafter as SDC2R2. In the developed downscaling model, the use of ridge regression, instead of multiple linear regression, is proposed to downscale daily rainfall with wide range (WR) predictors. The WR predictors were applied to sufficiently incorporate climate change signals. The developed model also captured the non-linear interactions of the climate variables by applying the transformation of Volterra series realization over WR predictors. This transformation was performed by applying principal components as orthogonal filters. Further, these principal components were clustered by using c-means clustering and non-linear transformations were applied on these membership functions, to improve the prediction ability of the model. The reanalysis of climate data from the National Centres for Environmental Prediction (NCEP) was used to develop the model and was validated by using the Global Climate Model (GCM) for four locations in the Manawatu River basin. The developed model was used to obtain future daily rainfall projections from three Representative Concentrative Pathways (RCP 2.6, RCP 4.5, and RCP 8.5) scenarios from the Canadian Earth System Model (CanESM2) GCM. The performance of the model was compared with a widely used statistical downscaling model (SDSM). It was observed that the model performed better than SDSM in downscaling rainfall on a daily basis. Every scenario indicated that there is a probability of obtaining high future rainfall frequency. The results of this study provide valuable information for decision-makers since climate change may potentially impact the Manawatu basin.

Methodological Challenges when Using Routinely Collected Health Data for Research: A scoping review.

Routinely collected health data (RCD) including electronic health records, disease registries, health administrative data and wearables data are not specifically collected for research purposes. Analysis of these data poses unique methodological challenges that must be addressed when conducting research, particularly as availability and use increase. This scoping review aimed to identify methodological challenges in research using RCD from existing literature (registered protocol: https://doi.org/10.17605/OSF.IO/EBM4D). We searched 6 electronic databases, including medical, health economics, nursing and psychology research databases, between Jan 2015 and Jan 2023, combining multiple “RCD” and “research” search terms (e.g., epidemiologic, informatics, pharmaceutical research). After screening abstracts and full-texts, we doubly extracted methodological themes, categorizing them into different study stages. We screened more than 23,000 records and included 430 papers. Bias and confounding were the most common methodological issues identified, discussed in relation to both study design and data analysis. Data quality, including data accuracy, validation, completeness, timeliness and cleaning, also posed substantial challenges, particularly during data processing stage. Record linkage and conducting analyses using distributed health networks also pose unique methodological challenges. Heterogeneity, incorporating social determinants of health and statistical models that address methodological challenges are also described in the literature. External validity and reporting are important considerations for RCD research. Our review identified several methodological challenges facing researchers using RCD. These issues should be addressed to ensure methodologically sound research. These findings will inform the development of a standardized protocol template and accompanying educational platform aimed at enhancing methodological quality and transparency when conducting research using RCD.

Enhancing Manufacturing Processing Stability and Efficiency with Linear-Regression Analysis: Modeling on a Flow-Drill Screw (FDS) Joining Process

The instability (in processing time) in the flow-drill screwing process is undesired but inescapable due to variations in material property, gauge, and process parameters. A substantial number of materials and lab labor need to be used to test and control the variability of the real manufacturing joining process. To enhance the stability and efficiency of the screwing process, this study seeks multi-disciplinary collaboration by applying linear-regression modeling. Six hundred and forty-eight data points were collected and split into an 80% training set for model building and a 20% test set for model validation. A multiple linear-regression model was built. The results indicated that, compared to variable base level (6000 rpm rotational speed and 1100 N downforce), higher rotational speed (8000 rpm, 7000 rpm), greater downforce (1200 N, 1300 N), and their interaction were significantly associated with passage (processing) time, while the switch point did not significantly affect passage time. The interaction plot and effect size were adopted to provide measurements of the effect magnitude on processing time. The coefficient of determination indicated that 86% of the variability in the passage time can be explained by this model. Statistical analysis, such as data visualization, statistical modeling, and other data-driven analysis methods, can be used to detect underlying relationships between variables, investigate variations, and make predictions in the manufacturing process. The outcomes from the data-driven analysis can benefit from improving the economical manufacturing system, refining the processing setting, and reducing test material costs, labor, and lead time.

Exploration of a model driven by climate to simulate pond water temperature in aquaculture systems

IntroductionInterannual climate variability in the Asian mega deltas has been posing a wide range of climate risks in the aquaculture systems of the region. Water temperature variation is one of the key risks related to disease outbreak, fish health, and loss and damage in fish production. However, Climate information can improve the ability to predict changes in pond water quality parameters at the farm level using publicly available weather and climate data. Little research has been done to translate weather data into water temperature forecasts using mechanistic models in order to provide farmers with relevant forecasting information in the context of climate services.MethodsThe advantage of mechanistic models over statistical models is that they are based on physical processes and can therefore be used in a wider range of environmental conditions. In this study, we used an energy balance model to investigate its ability to simulate pond water temperature at daily and seasonal timescales in the southwest and northeast regions of Bangladesh. The model was able to adequately simulate pond water temperature at a daily timescale using publicly available weather data, and the accuracy of the model was lower at the study site with very heavy rainfall events.ResultsSensitivity analyses showed that the model was also able to simulate the impact of air temperature cold and hot spells on the pond water temperature. Connecting the model with seasonal air temperature forecasts resulted in very small variations in the forecasted seasonal pond water temperature, in large part due to the low variability observed in water temperature at seasonal scale in the study sites.DiscussionClimate information can improve the ability to predict changes in pond water quality parameters at the farm level using publicly available weather and climate data. Hence, these improved predictions are important to help fish-farmers make informed decisions for managing associated climate risks.

Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models

Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.

Improving sub-seasonal extreme precipitation forecasts over China through a hybrid statistical-dynamical framework

Skillful and reliable sub-seasonal extreme precipitation forecasts are crucial for disaster prevention and mitigation. In this study, we introduce a hybrid statistical-dynamical framework to predict monthly maximum one-day precipitation (Rx1D) and monthly maximum five-day precipitation (Rx5D) over China from May to October. In the hybrid statistical-dynamical framework, the ECMWF forecasts of precipitation and boreal summer intraseasonal oscillation (BSISO) indices are used as predictors to establish calibration model and bridging models, separately. The calibration model and bridging models are then merged to generate probabilistic forecasts of Rx1D and Rx5D. Our results suggest that the bridging models show better performance in predicting Rx1D and Rx5D than calibration model in May, June, and July when the BSISO indices are used as predictors. The forecast skill of calibration model is higher compared to bridging models in August, September, and October. The BMA merged forecasts take advantage of both calibration model and bridging models, and can provide skilful and reliable forecasts for both Rx1D and Rx5D prediction. To have a more comprehensive assessment, we also evaluate the prediction skill of the occurrence of extreme precipitation events with exceedance probabilities of 50%, 20%, and 5% for both Rx1D and Rx5D. The Brier skill score of merged forecasts indicates that the hybrid statistical-dynamical framework can also provide skilful forecasts for the occurrence of extreme precipitation events greater than one-in-5-year return value of Rx1D (5Rx1D) and one-in-5-year return value of Rx5D (5Rx5D) in comparison to long-term climatology. These findings demonstrate the great potential of combining dynamical models and statistical models in improving sub-seasonal extreme precipitation forecasts.

Application of geometric deep learning in disease-gene relationship prediction

The correlation between diseases and genetic factors represents a pivotal challenge in the biomedical field, often conceptualized as a task of link prediction. Conventional methods employed for prediction, such as statistical models and various machine learning algorithms, frequently fall short in terms of accuracy when confronted with the intricacies of biological network data. These methods also tend to inadequately represent the complex relationships inherent in such data. In contrast, recent advances in geometric deep learning have introduced a powerful tool within artificial intelligence, particularly adept at processing non-Euclidean data structures. This study delves into the potential of leveraging geometric deep learning techniques to enhance the prediction of disease-gene associations. Initially, we conduct a thorough review of existing research related to link prediction, encompassing both traditional approaches and contemporary methods grounded in deep learning. Subsequently, we propose a geometric deep learning framework, incorporating Graph Convolutional Networks (GCN) and Graph Auto-Encoder (GAE), to develop and assess our predictive model. The results of our experiments demonstrate that the proposed geometric deep learning model surpasses conventional techniques in accurately predicting disease-gene associations. In conclusion, we evaluate the implications of our findings, discuss their practical applications in the biomedical domain, and suggest possible avenues for future research.

Dynamic density functional theory of polymers with salt in electric fields.

We present a dynamic density functional theory for modeling the effects of applied electric fields on the local structure of polymers with added salt (polymer electrolytes). Time-dependent equations for the local electrostatic potential and volume fractions of polymer, cation, and anion of added salt are developed using the principles of linear irreversible thermodynamics. For such a development, a field theoretic description of the free energy of polymer melts doped with salts is used, which captures the effects of local variations in the dielectric function. Connections of the dynamic density functional theory with experiments are established by relating the three phenomenological Onsager's transport coefficients of the theory to the mutual diffusion of electrolyte, ionic conductivity, and transference number of one of the ions. The theory is connected with a statistical mechanical model developed by Bearman and Kirkwood [J. Chem. Phys. 28, 136 (1958)] after relating the three transport coefficients to friction coefficients. The steady-state limit of the dynamic density functional theory is used to understand the effects of dielectric inhomogeneity on the phase separation in polymer electrolytes. The theory developed here provides not only a way to connect with experiments but also to develop multi-scale models for studying connections between local structure and ion transport in polymer electrolytes.

Ethical considerations of use of hold-out sets in clinical prediction model management

AbstractClinical prediction models are statistical or machine learning models used to quantify the risk of a certain health outcome using patient data. These can then inform potential interventions on patients, causing an effect called performative prediction: predictions inform interventions which influence the outcome they were trying to predict, leading to a potential underestimation of risk in some patients if a model is updated on this data. One suggested resolution to this is the use of hold-out sets, in which a set of patients do not receive model derived risk scores, such that a model can be safely retrained. We present an overview of clinical and research ethics regarding potential implementation of hold-out sets for clinical prediction models in health settings. We focus on the ethical principles of beneficence, non-maleficence, autonomy and justice. We also discuss informed consent, clinical equipoise, and truth-telling. We present illustrative cases of potential hold-out set implementations and discuss statistical issues arising from different hold-out set sampling methods. We also discuss differences between hold-out sets and randomised control trials, in terms of ethics and statistical issues. Finally, we give practical recommendations for researchers interested in the use hold-out sets for clinical prediction models.

Artificial Intelligence in Predicting the Mode of Delivery: A Systematic Review.

The integration of artificial intelligence (AI) into obstetric care offers significant potential to enhance clinical decision-making and optimize maternal and neonatal outcomes. Traditional prediction methods for mode of delivery often rely on subjective clinical judgment and limited statistical models, which may not fully capture complex patient data. This systematic review aims to evaluate the current state of research on AI applications in predicting the mode of delivery, comparing the performance of AI models with traditional methods, and identifying gaps for future research. A comprehensive literature search was conducted across PubMed, Google Scholar, Web of Science, and Scopus databases, covering publications from January 2010 to July 2024. Inclusion criteria were studies employing AI techniques to predict the mode of delivery, published in peer-reviewed journals, and involving human subjects. Studies were assessed for quality using the Prediction Model Risk of Bias Assessment Tool (PROBAST), and data were synthesized narratively due to heterogeneity. In total, 18 studies met the inclusion criteria, employing various AI models such as logistic regression, random forest, gradient boosting, and neural networks. Sample sizes ranged from 40 to 94,480 participants across diverse geographic settings. AI models demonstrated high accuracy rates, often exceeding 90%, and strong predictive metrics (area under the curve (AUC) values from 0.745 to 0.932). Key predictors included maternal age, gravidity, parity, gestational age, labor induction type, and fetal weight. Notable models like the Adana Systemand Categorical Boosting (CatBoost, Yandex LLC, Moscow, Russia) highlighted the effectiveness of AI in enhancing prediction accuracy and supporting clinical decisions. AI models significantly outperform traditional statistical methods in predicting the mode of delivery, providing a robust tool for obstetric care. Future research should focus on standardizing data collection, improving model interpretability, addressing ethical concerns, and ensuring fairness in AI predictions to enhance clinical trust and application.

Predicting the Representative Elementary Volume by determining the evolution law of the convergence cone

In order to characterise a rock formation prior to subsurface operations, it is required to find a microscale rock volume for which the homogenised property does not fluctuate when the size of the sample is increased; the Representative Elementary Volume (REV). Its determination usually comes at the cost of a large number of simulations, making it overall a computationally expensive process. Therefore, many scientific studies have been dedicated to optimising the process of finding REV. Using statistical numerical methods, it is shown that the fluctuation of the effective property corresponds overall to a cone-like shape convergence. We suggest determining the generic evolution law of the cone of convergence, which can be used to predict the size of the REV and the effective physical property. This study is based on simulations of Stokes flow through idealised microstructures from which the permeability is upscaled. By tracing and plotting the convergence of permeability for multiple samples, the full cone of convergence appears. The cone shows exponential growth and decay, converging towards the effective permeability of the microstructure. By fitting a log-normal distribution on the collected data points, we show that the generic evolution law of the cone of convergence can always be described with two parameters, independently of the porosity. We show that the determined law of the cone also applies to real microstructures, despite the presence of natural heterogeneities. The new method allows us to reduce the computational costs of finding all characteristics related to REV by simulating several subsamples rather than the full-sized sample, unlocking thereby high-resolution samples which are often too computationally expensive. The use of a statistical model provides quantification of the precision level we can obtain on the REV determination.

BayesianSSA: a Bayesian statistical model based on structural sensitivity analysis for predicting responses to enzyme perturbations in metabolic networks

BackgroundChemical bioproduction has attracted attention as a key technology in a decarbonized society. In computational design for chemical bioproduction, it is necessary to predict changes in metabolic fluxes when up-/down-regulating enzymatic reactions, that is, responses of the system to enzyme perturbations. Structural sensitivity analysis (SSA) was previously developed as a method to predict qualitative responses to enzyme perturbations on the basis of the structural information of the reaction network. However, the network structural information can sometimes be insufficient to predict qualitative responses unambiguously, which is a practical issue in bioproduction applications. To address this, in this study, we propose BayesianSSA, a Bayesian statistical model based on SSA. BayesianSSA extracts environmental information from perturbation datasets collected in environments of interest and integrates it into SSA predictions.ResultsWe applied BayesianSSA to synthetic and real datasets of the central metabolic pathway of Escherichia coli. Our result demonstrates that BayesianSSA can successfully integrate environmental information extracted from perturbation data into SSA predictions. In addition, the posterior distribution estimated by BayesianSSA can be associated with the known pathway reported to enhance succinate export flux in previous studies.ConclusionsWe believe that BayesianSSA will accelerate the chemical bioproduction process and contribute to advancements in the field.

Influences of Central and Eastern Atlantic Niño on the West African and South American summer monsoons

The rainfall variabilities of the West African and South American summer monsoons, pivotal for local and global climate systems, are strongly influenced by tropical Atlantic sea surface temperature anomalies. This study investigates the impacts of two recently identified Atlantic Niño types, central and eastern Atlantic Niño (CAN and EAN), on these monsoon systems using observational data and numerical experiments. During boreal summer, EAN events exhibit increased rainfall over West Africa compared to CAN events, indicating a strengthened West African summer monsoon. Enhanced moisture flux convergence from eastern Atlantic warming drives these wetting conditions during EAN events. Conversely, CAN events have a more pronounced influence on South American monsoon rainfall during austral summer, causing a rainfall anomaly dipole between the Amazon and eastern Brazil, suggesting an eastward shift in the South American summer monsoon rainfall belt. These rainfall changes are linked to cyclonic circulation anomalies over the southwest Atlantic Ocean, attributed to central Atlantic warming during CAN events. Furthermore, a statistical model assesses hindcast skills of rainfall variability in the two summer monsoon regions, affirming the benefits of separating Atlantic Niño into CAN and EAN events for improved seasonal climate predictions.

Applications of satellite platforms and machine learning for mapping and monitoring grasslands and pastures: A systematic and comprehensive review

Grasslands and pastures are critical ecosystems globally, essential for their agricultural and environmental roles. Extensive research from 2000 to 2022, comprising 504 articles, has explored the integration of remote sensing and statistical modelling for mapping and monitoring grassland and pasture ecosystems. These articles were sourced from the SCOPUS database and analysed using text mining and natural language processing techniques to investigate the evolution of publication trends over the past twenty-two years. The number of publications per year on this topic has grown consistently in the considered period, from 3 in 2000 to 93 in 2022, doubling their weight compared to the total number of Scopus publications. The quantitative analysis of satellite platform utilisation revealed the increasing importance of Sentinel-2, even though MODIS remained the most utilised satellite platform throughout the study period. The increasing availability of big data has helped spread the utilisation of machine learning algorithms, mostly in the last ten years. Among these, random forest appeared to be the most widespread for grassland and pasture studies. Researchers' primary interest in this field centres on the technologies and their applications. This is evidenced by cluster analysis, which reveals a dominant focus on terms related to the 'Instruments' (25.8 %) and 'Parameters' (24.9 %) categories. This analysis aims to outline the progression of research, offering insights that could be useful in forecasting future trends and facilitating stakeholder engagement in this sector.