Search

Species distribution models (SDMs) are extensively used to estimate species–environment relationships (SERs) and predict species distribution across space and time. For this purpose, it is key to choose relevant spatial grains for predictor and response variables at the onset of the modelling process. However, environmental variables are often derived from large‐scale climate models at a grain that can be coarser than the one of the response variable. Such area‐to‐point spatial misalignment can bias estimates of SER and jeopardise the robustness of predictions. We used a virtual species approach, running simulations across different levels of area‐to‐point spatial misalignment to seek statistical solutions to this problem. We specifically compared accuracy of SER estimates and predictive performances, assessed across different degrees of spatial heterogeneity in environmental conditions, of three SDMs: a GLM, a spatial GLM and a Berkson error model (BEM) that accounts for fine‐grain environmental heterogeneity within coarse‐grain cells. Only the BEM accurately estimates SER from relatively coarse‐grain environmental data (up to 50 times coarser than the response grain), while the two GLMs provide flattened SER. However, all three models perform poorly when predicting from coarse‐grain data, particularly in environments that are more heterogeneous than the training conditions. Conversely, decreasing environmental heterogeneity relative to the training dataset reduces the predictive biases. Because predictions are made from covariate‐grain data, the BEM displays lower predictive performance than the two GLMs. Thus, standard model selection methods would fail to select the model that best estimates SERs (here, the BEM), which could lead to false interpretations about the environmental drivers of species distributions. Overall, we conclude that the BEM, because it can robustly estimate SER at the response grain, holds great promise to overcome area‐to‐point misalignment. [ABSTRACT FROM AUTHOR]

Real-time monitoring using in-situ sensors is becoming a common approach for measuring water-quality within watersheds. High-frequency measurements produce big datasets that present opportunities to conduct new analyses for improved understanding of water-quality dynamics and more effective management of rivers and streams. Of primary importance is enhancing knowledge of the relationships between nitrate, one of the most reactive forms of inorganic nitrogen in the aquatic environment, and other water-quality variables. We analysed high-frequency water-quality data from in-situ sensors deployed in three sites from different watersheds and climate zones within the National Ecological Observatory Network, USA. We used generalised additive mixed models to explain the nonlinear relationships at each site between nitrate concentration and conductivity, turbidity, dissolved oxygen, water temperature, and elevation. Temporal auto-correlation was modelled with an auto-regressive–moving-average (ARIMA) model and we examined the relative importance of the explanatory variables. Total deviance explained by the models was high for all sites (99%). Although variable importance and the smooth regression parameters differed among sites, the models explaining the most variation in nitrate contained the same explanatory variables. This study demonstrates that building a model for nitrate using the same set of explanatory water-quality variables is achievable, even for sites with vastly different environmental and climatic characteristics. Applying such models will assist managers to select cost-effective water-quality variables to monitor when the goals are to gain a spatial and temporal in-depth understanding of nitrate dynamics and adapt management plans accordingly. [ABSTRACT FROM AUTHOR]

Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing compositional data imbalance, this paper proposes an adaptation of the original Synthetic Minority Oversampling TEchnique (SMOTE) to deal with compositional data imbalance. The new approach, called SMOTE for Compositional Data (SMOTE-CD), generates synthetic examples by computing a linear combination of selected existing data points, using compositional data operations. The performance of the SMOTE-CD is tested with three different regressors (Gradient Boosting tree, Neural Networks, Dirichlet regressor) applied to two real datasets and to synthetic generated data, and the performance is evaluated using accuracy, cross-entropy, F1-score, R2 score and RMSE. The results show improvements across all metrics, but the impact of oversampling on performance varies depending on the model and the data. In some cases, oversampling may lead to a decrease in performance for the majority class. However, for the real data, the best performance across all models is achieved when oversampling is used. Notably, the F1-score is consistently increased with oversampling. Unlike the original technique, the performance is not improved when combining oversampling of the minority classes and undersampling of the majority class. The Python package smote-cd implements the method and is available online. [ABSTRACT FROM AUTHOR]

Aim: Optimum shifts in species–environment relationships are intensively studied in a wide range of ecological topics, including climate change and species invasion. Numerous statistical methods are used to study optimum shifts, but, to our knowledge, none explicitly estimate it. We extended an existing model to explicitly estimate optimum shifts for multiple species having symmetrical response curves. We called this new Bayesian hierarchical model the Explicit Hierarchical Model of Optimum Shifts (EHMOS). Location: All locations. Taxon: All taxa. Methods: In a simulation study, we compared the accuracy of EHMOS to a mean comparison method and a Bayesian generalized linear mixed model (GLMM). Specifically, we tested if the accuracy of the methods was sensitive to (1) sampling design, (2) species optimum position and (3) species ecological specialization. In addition, we compared the three methods using a real dataset of investigated optimum shifts in 24 Orthopteran species between two time periods along an elevation gradient. Results: Of all the simulated scenarios, EHMOS was the most accurate method. GLMM was the most sensitive method to species optimum position, providing unreliable estimates in the presence of marginal species, that is, species with an optimum close to a sampling boundary. The mean comparison method was also sensitive to species optimum position and ecological specialization, especially in an unbalanced sampling design, with high negative bias and low interval coverage compared to EHMOS. The case study results obtained with EHMOS were consistent with what is expected considering ongoing climate change, with mostly upward shifts, which further improved confidence in the accuracy of the EHMOS method. Main Conclusions: Explicit Hierarchical Model of Optimum Shifts could be used for a wide range of topics and extended to produce new insights, especially in climate change studies. Explicit estimation of optimum shifts notably allows investigation of ecological assumptions that could explain interspecific variability of these shifts. [ABSTRACT FROM AUTHOR]

Several R packages have been developed to study cross-phenotypes associations (or pleiotropy) at the SNP-level, based on summary statistics data from genome-wide association studies (GWAS). However, none of them allow for consideration of the underlying group structure of the data. We developed an R package, entitled GCPBayes (Group level Bayesian Meta-Analysis for Studying Cross-Phenotype Genetic Associations), introduced by Baghfalaki et al. (2021), that implements continuous and Dirac spike priors for group selection, and also a Bayesian sparse group selection approach with hierarchical spike and slab priors, to select important variables at the group level and within the groups. The methods use summary statistics data from association studies or individual level data as inputs, and perform Bayesian meta-analysis approaches across multiple phenotypes to detect pleiotropy at both group-level (e.g., at the gene or pathway level) and within group (e.g., at the SNP level). [ABSTRACT FROM AUTHOR]

Semi-Markov models are widely used for survival analysis and reliability analysis. In general, there are two competing parameterizations and each entails its own interpretation and inference properties. On the one hand, a semi-Markov process can be defined based on the distribution of sojourn times, often via hazard rates, together with transition probabilities of an embedded Markov chain. On the other hand, intensity transition functions may be used, often referred to as the hazard rates of the semi-Markov process. We summarize and contrast these two parameterizations both from a probabilistic and an inference perspective, and we highlight relationships between the two approaches. In general, the intensity transition based approach allows the likelihood to be split into likelihoods of two-state models having fewer parameters, allowing efficient computation and usage of many survival analysis tools. Nevertheless, in certain cases the sojourn time based approach is natural and has been exploited extensively in applications. In contrasting the two approaches and contemporary relevant R packages used for inference, we use two real datasets highlighting the probabilistic and inference properties of each approach. This analysis is accompanied by an R vignette. [ABSTRACT FROM AUTHOR]

Abstract Background Multistate models have become increasingly useful to study the evolution of a patient’s state over time in intensive care units ICU (e.g. admission, infections, alive discharge or death in ICU). In addition, in critically-ill patients, data come from different ICUs, and because observations are clustered into groups (or units), the observed outcomes cannot be considered as independent. Thus a flexible multi-state model with random effects is needed to obtain valid outcome estimates. Methods We show how a simple multi-state frailty model can be used to study semi-competing risks while fully taking into account the clustering (in ICU) of the data and the longitudinal aspects of the data, including left truncation and right censoring. We suggest the use of independent frailty models or joint frailty models for the analysis of transition intensities. Two distinct models which differ in the definition of time t in the transition functions have been studied: semi-Markov models where the transitions depend on the waiting times and nonhomogenous Markov models where the transitions depend on the time since inclusion in the study. The parameters in the proposed multi-state model may conveniently be computed using a semi-parametric or parametric approach with an existing R package FrailtyPack for frailty models. The likelihood cross-validation criterion is proposed to guide the choice of a better fitting model. Results We illustrate the use of our approach though the analysis of nosocomial infections (ventilator-associated pneumonia infections: VAP) in ICU, with “alive discharge” and “death” in ICU as other endpoints. We show that the analysis of dependent survival data using a multi-state model without frailty terms may underestimate the variance of regression coefficients specific to each group, leading to incorrect inferences. Some factors are wrongly significantly associated based on the model without frailty terms. This result is confirmed by a short simulation study. We also present individual predictions of VAP underlining the usefulness of dynamic prognostic tools that can take into account the clustering of observations. Conclusions The use of multistate frailty models allows the analysis of very complex data. Such models could help improve the estimation of the impact of proposed prognostic features on each transition in a multi-centre study. We suggest a method and software that give accurate estimates and enables inference for any parameter or predictive quantity of interest.

An increasing number of genome‐wide association studies (GWAS) summary statistics is made available to the scientific community. Exploiting these results from multiple phenotypes would permit identification of novel pleiotropic associations. In addition, incorporating prior biological information in GWAS such as group structure information (gene or pathway) has shown some success in classical GWAS approaches. However, this has not been widely explored in the context of pleiotropy. We propose a Bayesian meta‐analysis approach (termed GCPBayes) that uses summary‐level GWAS data across multiple phenotypes to detect pleiotropy at both group‐level (gene or pathway) and within group (eg, at the SNP level). We consider both continuous and Dirac spike and slab priors for group selection. We also use a Bayesian sparse group selection approach with hierarchical spike and slab priors that enables us to select important variables both at the group level and within group. GCPBayes uses a Bayesian statistical framework based on Markov chain Monte Carlo (MCMC) Gibbs sampling. It can be applied to multiple types of phenotypes for studies with overlapping or nonoverlapping subjects, and takes into account heterogeneity in the effect size and allows for the opposite direction of the genetic effects across traits. Simulations show that the proposed methods outperform benchmark approaches such as ASSET and CPBayes in the ability to retrieve pleiotropic associations at both SNP and gene‐levels. To illustrate the GCPBayes method, we investigate the shared genetic effects between thyroid cancer and breast cancer in candidate pathways. [ABSTRACT FROM AUTHOR]

Summary: Identification of biomarkers is an emerging area in oncology. In this article, we develop an efficient statistical procedure for the classification of protein markers according to their effect on cancer progression. A high‐dimensional time‐course dataset of protein markers for 80 patients motivates us for developing the model. The threshold value is formulated as a level of a marker having maximum impact on cancer progression. The classification algorithm technique for high‐dimensional time‐course data is developed and the algorithm is validated by comparing random components using both proportional hazard and accelerated failure time frailty models. The study elucidates the application of two separate joint modeling techniques using auto regressive‐type model and mixed effect model for time‐course data and proportional hazard model for survival data with proper utilization of Bayesian methodology. Also, a prognostic score is developed on the basis of few selected genes with application on patients. This study facilitates to identify relevant biomarkers from a set of markers. [ABSTRACT FROM AUTHOR]

Anticipating future changes of an ecosystem's dynamics requires knowledge of how its key communities respond to current environmental regimes. The Great Barrier Reef (GBR) is under threat, with rapid changes of its reef‐building hard coral (HC) community structure already evident across broad spatial scales. While several underlying relationships between HC and multiple disturbances have been documented, responses of other benthic communities to disturbances are not well understood. Here we used statistical modelling to explore the effects of broad‐scale climate‐related disturbances on benthic communities to predict their structure under scenarios of increasing disturbance frequency. We parameterized a multivariate model using the composition of benthic communities estimated by 145,000 observations from the northern GBR between 2012 and 2017. During this time, surveyed reefs were variously impacted by two tropical cyclones and two heat stress events that resulted in extensive HC mortality. This unprecedented sequence of disturbances was used to estimate the effects of discrete versus interacting disturbances on the compositional structure of HC, soft corals (SC) and algae. Discrete disturbances increased the prevalence of algae relative to HC while the interaction between cyclones and heat stress was the main driver of the increase in SC relative to algae and HC. Predictions from disturbance scenarios included relative increases in algae versus SC that varied by the frequency and types of disturbance interactions. However, high uncertainty of compositional changes in the presence of several disturbances shows that responses of algae and SC to the decline in HC needs further research. Better understanding of the effects of multiple disturbances on benthic communities as a whole is essential for predicting the future status of coral reefs and managing them in the light of new environmental regimes. The approach we develop here opens new opportunities for reaching this goal. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the objective function and deflation process for sparse Partial Least Squares (PLS) regression with multiple components. While many have considered variations on the objective for sparse PLS, the deflation process for sparse PLS has not received as much attention. Our work highlights a flaw in the Statistically Inspired Modification of Partial Least Squares (SIMPLS) deflation method when applied in sparse PLS regression. We also consider the Nonlinear Iterative Partial Least Squares (NIPALS) deflation in sparse PLS regression. To remedy the flaw in the SIMPLS method, we propose a new sparse PLS method wherein the direction vectors are constrained to be sparse and lie in a chosen subspace. We give insight into this new PLS procedure and show through examples and simulation studies that the proposed technique can outperform alternative sparse PLS techniques in coefficient estimation. Moreover, our analysis reveals a simple renormalization step that can be used to improve the estimation of sparse PLS direction vectors generated using any convex relaxation method. [ABSTRACT FROM AUTHOR]

Objectives: We sought to evaluate the impact of later menarche on the risk of operative delivery.Population: We studied 38,069 eligible women (first labors at term with a singleton infant in a cephalic presentation) from the Norwegian Mothers and Child Cohort Study. The main exposures were the age at menarche and the duration of the interval between menarche and the first birth.Methods: Poisson's regression with a robust variance estimator.Main Outcome Measures: Operative delivery, defined as emergency cesarean or assisted vaginal delivery (ventouse extraction or forceps).Results: A 5 year increase in age at menarche was associated with a reduced risk of operative delivery (risk ratio [RR] 0.84, 95%CI 0.78, 0.89; p < .001). Adjustment for the age at first birth slightly strengthened the association (RR 0.79, 95%CI 0.74, 0.84; p < .001). However, the association was lost following adjustment for the menarche to birth interval (RR 0.99, 95%CI 0.93, 1.06; p = .81). A 5 years increase in menarche to birth interval was associated with an increased risk of operative delivery (RR 1.26, 95%CI 1.23, 1.28; p < .001). This was not materially affected by adjustment for an extensive series of maternal characteristics (RR 1.23, 95%CI 1.20, 1.25; p < .001).Conclusions: Later menarche reduces the risk of an operative first birth through shortening the menarche to birth interval. This observation is consistent with the hypothesis that the pattern and/or duration of prepregnancy exposure of the uterus to estrogen and progesterone contributes to uterine aging. [ABSTRACT FROM AUTHOR]

Multiple endpoints are increasingly used in clinical trials. The significance of some of these clinical trials is established if at least r null hypotheses are rejected among m that are simultaneously tested. The usual approach in multiple hypothesis testing is to control the family-wise error rate, which is defined as the probability that at least one type-I error is made. More recently, the q-generalized family-wise error rate has been introduced to control the probability of making at least q false rejections. For procedures controlling this global type-I error rate, we define a type-II r-generalized family-wise error rate, which is directly related to the r-power defined as the probability of rejecting at least r false null hypotheses. We obtain very general power formulas that can be used to compute the sample size for single-step and step-wise procedures. These are implemented in our R package rPowerSampleSize available on the CRAN, making them directly available to end users. Complexities of the formulas are presented to gain insight into computation time issues. Comparison with Monte Carlo strategy is also presented. We compute sample sizes for two clinical trials involving multiple endpoints: one designed to investigate the effectiveness of a drug against acute heart failure and the other for the immunogenicity of a vaccine strategy against pneumococcus. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

In humans, the risk of operative first delivery increases linearly with maternal age. We previously hypothesized that prolonged, cyclical, prepregnancy exposure to estrogen and progesterone contributes to uterine aging. Here, we test this hypothesis. Myometrium was obtained from four groups of virgin mice: (i) 10- to 12-week- and 28- to 30-week-old mice; (ii) 10- to 12-week- and 38- to 40-week-old mice; (iii) 38-week-old mice that had an ovariectomy or sham operation early in life; (iv) 38-week-old mice that had been treated with progesterone or vehicle containing implants from 8 to 36 weeks. Transcript profiling was carried out using Affymetrix Gene ST 1.1 arrays, and data were normalized. We identified 60 differentially regulated transcripts associated with advancing age (group 1). We validated these changes in group 2 ( P for overlap = 5.8 × 10−46). Early ovariectomy prevented the age-related changes in myometrial transcript profile. Similarly, progesterone-mediated long-term ovarian suppression prevented the age-related changes in myometrial transcript profile. Interferon regulatory factor 7 (Irf7) mRNA was regulated by age and hormonal exposure, and was identified as a predicted regulator of the other differentially expressed transcripts by both promoter sequence and canonical pathway activation analysis ( P = 8.47 × 10−5 and P < 10−10, respectively). Immunohistochemistry demonstrated IRF7 in both mouse and human myometrium. We conclude the following: (i) Myometrial aging in mice is associated with reproducible changes in transcript profile; (ii) these changes can be prevented by interventions which inhibit cyclical changes in the female sex hormones; and (iii) IRF7 may be an important regulator of myometrial function and aging. [ABSTRACT FROM AUTHOR]

Selection of estimators is an essential task in modeling. A general framework is that the estimators of a distribution are obtained by minimizing a function (the estimating function) and assessed using another function (the assessment function). A classical case is that both functions estimate an information risk (specifically cross-entropy); this corresponds to using maximum likelihood estimators and assessing them by Akaike information criterion (AIC). In more general cases, the assessment risk can be estimated by leave-one-out cross-validation. Since leave-one-out cross-validation is computationally very demanding, we propose in this paper a universal approximate cross-validation criterion under regularity conditions (UACVR). This criterion can be adapted to different types of estimators, including penalized likelihood and maximum a posteriori estimators, and also to different assessment risk functions, including information risk functions and continuous rank probability score (CRPS). UACVR reduces to Takeuchi information criterion (TIC) when cross-entropy is the risk for both estimation and assessment. We provide the asymptotic distributions of UACVR and of a difference of UACVR values for two estimators. We validate UACVR using simulations and provide an illustration on real data both in the psychometric context where estimators of the distributions of ordered categorical data derived from threshold models and models based on continuous approximations are compared. [ABSTRACT FROM AUTHOR]

The use of two or more primary correlated endpoints is becoming increasingly common. A mandatory approach when analyzing data from such clinical trials is to control the family-wise error rate (FWER). In this context, we provide formulas for computation of sample size and for data analysis. Two approaches are discussed: an individual method based on a union–intersection procedure and a global procedure, based on a multivariate model that can take into account adjustment variables. These methods are illustrated with simulation studies and applications. AnRpackage known asrPowerSampleSizeis also available. [ABSTRACT FROM AUTHOR]

Background: In statistical modeling, finding the most favorable coding for an exploratory quantitative variable involves many tests. This process involves multiple testing problems and requires the correction of the significance level. Methods: For each coding, a test on the nullity of the coefficient associated with the new coded variable is computed. The selected coding corresponds to that associated with the largest statistical test (or equivalently the smallest pvalue). In the context of the Generalized Linear Model, Liquet and Commenges (Stat Probability Lett,71:33-38,2005) proposed an asymptotic correction of the significance level. This procedure, based on the score test, has been developed for dichotomous and Box-Cox transformations. In this paper, we suggest the use of resampling methods to estimate the significance level for categorical transformations with more than two levels and, by definition those that involve more than one parameter in the model. The categorical transformation is a more flexible way to explore the unknown shape of the effect between an explanatory and a dependent variable. Results: The simulations we ran in this study showed good performances of the proposed methods. These methods were illustrated using the data from a study of the relationship between cholesterol and dementia. Conclusion: The algorithms were implemented using R, and the associated CPMCGLM R package is available on the CRAN. [ABSTRACT FROM AUTHOR]

Genome-wide association studies (GWAS) yielded significant advances in defining the genetic architecture of complex traits and disease. Still, a major hurdle of GWAS is narrowing down multiple genetic associations to a few causal variants for functional studies. This becomes critical in multi-phenotype GWAS where detection and interpretability of complex SNP(s)-trait(s) associations are complicated by complex Linkage Disequilibrium patterns between SNPs and correlation between traits. Here we propose a computationally efficient algorithm (GUESS) to explore complex genetic-association models and maximize genetic variant detection. We integrated our algorithm with a new Bayesian strategy for multi-phenotype analysis to identify the specific contribution of each SNP to different trait combinations and study genetic regulation of lipid metabolism in the Gutenberg Health Study (GHS). Despite the relatively small size of GHS (n = 3,175), when compared with the largest published meta-GWAS (n>100,000), GUESS recovered most of the major associations and was better at refining multi-trait associations than alternative methods. Amongst the new findings provided by GUESS, we revealed a strong association of SORT1 with TG-APOB and LIPC with TG-HDL phenotypic groups, which were overlooked in the larger meta-GWAS and not revealed by competing approaches, associations that we replicated in two independent cohorts. Moreover, we demonstrated the increased power of GUESS over alternative multi-phenotype approaches, both Bayesian and non-Bayesian, in a simulation study that mimics real-case scenarios. We showed that our parallel implementation based on Graphics Processing Units outperforms alternative multi-phenotype methods. Beyond multivariate modelling of multi-phenotypes, our Bayesian model employs a flexible hierarchical prior structure for genetic effects that adapts to any correlation structure of the predictors and increases the power to identify associated variants. This provides a powerful tool for the analysis of diverse genomic features, for instance including gene expression and exome sequencing data, where complex dependencies are present in the predictor space. [ABSTRACT FROM AUTHOR]

Attributable risk has become an important concept in clinical epidemiology. In this paper, we suggest to estimate the attributable risk of nosocomial infections using a multistate approach. Recently, a multistate model (called progressive disability model in the literature) has been developed in order to take into consideration both the time-dependency of the risk factor (e.g., nosocomial infections) and the presence of competing risks (e.g., death and discharge) at each time point. However, this approach does not take into account the possible heterogeneity of the study population. In this paper, we investigate an extension of this model and suggest an adjusted disability multistate model including covariates in each transition. This new multistate model has led us to define the concepts of overall and profiled attributable risk. We use a classical semiparametric approach to estimate the model and the new attributable risk. A simulation study is investigated and we show, in particular, that neglecting the presence of covariates when estimating the model can lead to an important bias. The methodology developed in this paper is applied to data on ventilator-associated pneumonia in 12 French intensive care units. [ABSTRACT FROM AUTHOR]

Background: High throughput 'omics' experiments are usually designed to compare changes observed between different conditions (or interventions) and to identify biomarkers capable of characterizing each condition. We consider the complex structure of repeated measurements from different assays where different conditions are applied on the same subjects. Results: We propose a two-step analysis combining a multilevel approach and a multivariate approach to reveal separately the effects of conditions within subjects from the biological variation between subjects. The approach is extended to two-factor designs and to the integration of two matched data sets. It allows internal variable selection to highlight genes able to discriminate the net condition effect within subjects. A simulation study was performed to demonstrate the good performance of the multilevel multivariate approach compared to a classical multivariate method. The multilevel multivariate approach outperformed the classical multivariate approach with respect to the classification error rate and the selection of relevant genes. The approach was applied to an HIV-vaccine trial evaluating the response with gene expression and cytokine secretion. The discriminant multilevel analysis selected a relevant subset of genes while the integrative multilevel analysis highlighted clusters of genes and cytokines that were highly correlated across the samples. Conclusions: Our combined multilevel multivariate approach may help in finding signatures of vaccine effect and allows for a better understanding of immunological mechanisms activated by the intervention. The integrative analysis revealed clusters of genes, that were associated with cytokine secretion. These clusters can be seen as gene signatures to predict future cytokine response. The approach is implemented in the R package mixOmics (http://cran.r-project.org/) with associated tutorials to perform the analysisa. [ABSTRACT FROM AUTHOR]

Data about storm impacts are essential for the disaster risk reduction process, but unlike data about storm characteristics, they are not routinely collected. In this paper, we demonstrate the high potential of convolutional neural networks to automatically constitute storm impact database using timestacks images provided by coastal video monitoring stations. Several convolutional neural network architectures and methods to deal with class imbalance were tested on two sites (Biarritz and Zarautz) to find the best practices for this classification task. This study shows that convolutional neural networks are well adapted for the classification of timestacks images into storm impact regimes. Overall, the most complex and deepest architectures yield better results. Indeed, the best performances are obtained with the VGG16 architecture for both sites with F-scores of 0.866 for Biarritz and 0.858 for Zarautz. For the class imbalance problem, the method of oversampling shows best classification accuracy with F-scores on average 30% higher than the ones obtained with cost sensitive learning. The transferability of the learning method between sites is also investigated and shows conclusive results. This study highlights the high potential of convolutional neural networks to enhance the value of coastal video monitoring data that are routinely recorded on many coastal sites. Furthermore, it shows that this type of deep neural network can significantly contribute to the setting up of risk databases necessary for the determination of storm risk indicators and, more broadly, for the optimization of risk-mitigation measures. [ABSTRACT FROM AUTHOR]

Commonly, when studies deal with the effects of climate change on biodiversity, mean value is used more than other parameters. However, climate change also leads to greater temperature variability, and many papers have demonstrated its importance in the implementation of biodiversity response strategies. We studied the spatio-temporal variability of activity time and persistence index, calculated from operative temperatures measured at three sites over three years, for a mountain endemic species. Temperatures were recorded with biomimetic loggers, an original remote sensing technology, which has the same advantages as these tools but is suitable for recording biological organisms data. Among the 42 tests conducted, 71% were significant for spatial variability and 28% for temporal variability. The differences in daily activity times and in persistence indices demonstrated the effects of the micro-habitat, habitat, slope, altitude, hydrography, and year. These observations have highlighted the great variability existence in the environmental temperatures experienced by lizard populations. Thus, our study underlines the importance to implement multi-year and multi-site studies to quantify the variability and produce more representative results. These studies can be facilitated by the use of biomimetic loggers, for which a user guide is provided in the last part of this paper. [ABSTRACT FROM AUTHOR]

Climate fluctuations affect a wide range of environmental factors that may impact fish populations with various response mechanisms. For a major part of world fisheries stocks, only abundance time-series are available. Relations between abundance of these species and ocean variables, including long term trends and patterns of seasonal change, remain sparsely documented. The main aim of our work is to determine to what extent effects of inter-annual and seasonal changes in environmental factors can be identified and quantified on a selected time-series of abundance data-set: the striped red mullet population within the Bay of Biscay. 8 Landings per unit of effort (LPUE) for striped red mullet data are compared with environmental covariates extracted from the Copernicus web database. Our strategy is to decompose the patterns of change in fish populations into long-term and seasonal components and to analyse the possible dependency of both components on environmental factors. The overall tendencies are a decrease of the long-term component and a modification of the seasonality, with additional spatial variability. The observed tendencies and seasonal changes are discussed against the spatio-temporal patterns of change in environmental factors. High spatial heterogeneity within the Bay of Biscay was found, both for striped red mullet long-term trends and seasonal changes. Most inter-annual and seasonal changes in striped red mullet abundance can be related to environmental factors. In addition to the well-known annual fluctuation, most coastal sites revealed a bi-annual seasonality possibly related to the recruitment process. [ABSTRACT FROM AUTHOR]

• Machine learning algorithms applied to minimize systematic errors of wave models. • Random forest and gradient boosting are used for the first time to predict errors. • Better results with these algorithms than with commonly used neural networks. • Assessment of the relevance by application to a study site on the Basque coast. The main objective is to present alternative algorithms to neural networks when improving sea state forecast by numerical models considering main spectral bulk parameters at a specific location, namely significant wave height, peak wave period and peak wave direction. The two alternatives are random forest and gradient boosting trees. To our knowledge, they have never been used for error prediction method. Therefore, their performances are compared with the performances of the usual choice in the literature: neural networks. We showed that the RMSE of the variables updated with gradient boosting trees and random forest are respectively 20 and 10% lower than the RMSE obtained with neural networks. A secondary objective is to show how to tune the hyperparameter values of machine learning algorithms with Bayesian Optimization. This step is essential when using machine learning algorithms and can improve the results significantly. Indeed, after a fine hyperparameter tuning with Bayesian optimization, gradient boosting trees yielded RMSE values in average 8% to 11% lower for the correction of significant wave height and peak wave period. Lastly, the potential benefits of such corrections in real life application are investigated by computing the extreme wave run-up (R 2%) at the study site (Biarritz, France) using the data corrected by the different algorithms. Here again, the corrections made by random forest and gradient boosting trees provide better results than the corrections made by neural networks. [ABSTRACT FROM AUTHOR]