Explore the vast range of titles available.

Statistical landslide susceptibility mapping is a topic in complete and constant evolution, especially since the introduction of machine learning (ML) methods. A new methodological approach is here presented, based on the ensemble of artificial neural network, generalized boosting model and maximum entropy ML algorithms. Such approach has been tested in the Monterosso al Mare area, Cinque Terre National Park (Northern Italy), severely hit by landslides in October 2011, following an extraordinary precipitation event, which caused extensive damage at this World Heritage site. Thirteen predisposing factors were selected and assessed according to the main characteristics of the territory and through variance inflation factor, whilst a database made of 260 landslides was adopted. Four different Ensemble techniques were applied, after the averaging of 300 stand-alone methods, each one providing validation scores such as ROC (receiver operating characteristics)/AUC (area under curve) and true skill statistics (TSS). A further model performance evaluation was achieved by assessing the uncertainty through the computation of the coefficient of variation (CV). Ensemble modelling thus showed improved reliability, testified by the higher scores, by the low values of CV and finally by a general consistency between the four Ensemble models adopted. Therefore, the improved reliability of Ensemble modelling confirms the efficacy and suitability of the proposed approach for decision-makers in land management at local and regional scales.

Global change is expected to expand and shrink species' distributions in complex ways beyond just retraction at warm edges and expansion at cool ones. Detecting these changes is complicated by the need for robust baseline data for comparison. For instance, gaps in species' distributions may reflect long‐standing patterns, recent shifts, or merely insufficient sampling effort. We investigated an apparent gap in the distribution of the American pika, Ochotona princeps, along the North American Sierra Nevada. Historical records from this region are sparse, with ~100 km separating previously documented pika‐occupied sites. Surveys during 2014–2023 confirmed that the gap is currently unoccupied by pikas, and evidence of past occurrence indicates that the gap has expanded over time, likely due to contemporary global change. Sites lacking evidence of past pika occurrence were climatically and geographically more distant from sites with signs of recent (former) occurrence and currently occupied sites. Formerly and currently occupied sites were partially climatically distinct, suggesting either metapopulation‐like dynamics or an extinction debt that may eventually result in further population losses at the edge of suitable climate space. The Feather River gap aligns with one of several “low points” in the otherwise continuous boreal‐like conditions spanning the Cascade Range and Sierra Nevada and is coincident with discontinuities in ranges of other mammals. These results highlight the potential for climate‐driven fragmentation and range retraction in regions considered climatically and geographically interior to a species' overall distribution.

The aim of this work is to explore the effectiveness of theoretical information approaches for the reduction of data complexity in multimodel ensemble systems. We first exploit a weak form of independence, i.e. uncorrelation, as a mechanism for detecting linear relationships. Then, stronger and more general forms of independence measure, such as mutual information, are used to investigate dependence structures for model selection. A distance matrix, measuring the interdependence between data, is derived for the investigated measures, with the scope of clustering correlated/dependent models together. Redundant information is discarded by selecting a few representative models from each cluster. We apply the clustering analysis in the context of atmospheric dispersion modeling, by using the ETEX‐1 data set. We show how the selection of a small subset of models, according to uncorrelation or mutual information distance criteria, usually suffices to achieve a statistical performance comparable to, or even better than, that achieved from the whole ensemble data set, thus providing a simpler description of ensemble results without sacrificing accuracy. Key Points New insights into ensemble data analysis Improved atmospheric dispersion predictions Ensemble data complexity reduction

Predicting contemporary and future species distributions is relevant for science and decision making, yet the development of high‐resolution spatial predictions for numerous taxonomic groups and regions is limited by the scalability of available modelling tools. Uniting species distribution modelling (SDM) techniques into one high‐performance computing (HPC) pipeline, we developed N‐SDM, an SDM platform aimed at delivering reproducible outputs for standard biodiversity assessments. N‐SDM was built around a spatially‐nested framework, intended at facilitating the combined use of species occurrence data retrieved from multiple sources and at various spatial scales. N‐SDM allows combining two models fitted with species and covariate data retrieved from global to regional scales, which is useful for addressing the issue of spatial niche truncation. The set of state‐of‐the‐art SDM features embodied in N‐SDM includes a newly devised covariate selection procedure, five modelling algorithms, an algorithm‐specific hyperparameter grid search, and the ensemble of small‐models approach. N‐SDM is designed to be run on HPC environments, allowing the parallel processing of thousands of species at the same time. All the information required for installing and running N‐SDM is openly available on the GitHub repository https://github.com/N‐SDM/N‐SDM.

A major challenge of the 21st century is to achieve food supply security under a changing climate and roughly a doubling in food demand by 2050 compared to present, the majority of which needs to be met by the cereals wheat, rice, maize, and barley. Future harvests are expected to be especially threatened through increased frequency and severity of extreme events, such as heat waves and drought, that pose particular challenges to plant breeders and crop scientists. Process-based crop models developed for simulating interactions between genotype, environment, and management are widely applied to assess impacts of environmental change on crop yield potentials, phenology, water use, etc. During the last decades, crop simulation has become important for supporting plant breeding, in particular in designing ideotypes, i.e. ‘model plants’, for different crops and cultivation environments. In this review we (i) examine the main limitations of crop simulation modelling for supporting ideotype breeding, (ii) describe developments in cultivar traits in response to climate variations, and (iii) present examples of how crop simulation has supported evaluation and design of cereal cultivars for future conditions. An early success story for rice demonstrates the potential of crop simulation modelling for ideotype breeding. Combining conventional crop simulation with new breeding methods and genetic modelling holds promise to accelerate delivery of future cereal cultivars for different environments. Robustness of model-aided ideotype design can further be enhanced through continued improvements of simulation models to better capture effects of extremes and the use of multi-model ensembles.

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence-only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence-only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well-established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point-process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision-recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible.

Aim Advances in ecological and environmental modelling offer new opportunities for estimating dynamic habitat suitability for highly mobile species and supporting management strategies at relevant spatiotemporal scales. We used an ensemble modelling approach to predict daily, year‐round habitat suitability for a migratory species, the blue whale (Balaenoptera musculus), and demonstrate an application for evaluating the spatiotemporal dynamics of their exposure to ship strike risk. Location The California Current Ecosystem (CCE) and the Southern California Bight (SCB), USA. Methods We integrated a long‐term (1994–2008) satellite tracking dataset on 104 blue whales with data‐assimilative ocean model output to assess year‐round habitat suitability. We evaluated the relative utility of ensembling multiple model types compared to using single models, and selected and validated candidate models using multiple cross‐validation metrics and independent observer data. We quantified the spatial and temporal distribution of exposure to ship strike risk within shipping lanes in the SCB. Results Multi‐model ensembles outperformed single‐model approaches. The final ensemble model had high predictive skill (AUC = 0.95), resulting in daily, year‐round predictions of blue whale habitat suitability in the CCE that accurately captured migratory behaviour. Risk exposure in shipping lanes was highly variable within and among years as a function of environmental conditions (e.g., marine heatwave). Main conclusions Daily information on three‐dimensional oceanic habitats was used to model the daily distribution of a highly migratory species with high predictive power and indicated that management strategies could benefit by incorporating dynamic environmental information. This approach is readily transferable to other species. Dynamic, high‐resolution species distribution models are valuable tools for assessing risk exposure and targeting management needs.

A novel sub‐sampling method has been used to isolate the dynamic effects of the response of the North Atlantic Oscillation (NAO) and the Siberian High (SH) from the total response to projected Arctic sea‐ice loss under 2°C global warming above preindustrial levels in very large initial‐condition ensemble climate simulations. Thermodynamic effects of Arctic warming are more prominent in Europe while dynamic effects are more prominent in Asia/East Asia. This explains less‐severe cold extremes in Europe but more‐severe cold extremes in Asia/East Asia. For Northern Eurasia, dynamic effects overwhelm the effect of increased moisture from a warming Arctic, leading to an overall decrease in precipitation. We show that the response scales linearly with the dynamic response. However, caution is needed when interpreting inter‐model differences in the response because of internal variability, which can largely explain the inter‐model spread in the NAO and SH response in the Polar Amplification Model Intercomparison Project. Plain Language Summary The projected loss of Arctic sea‐ice under 2°C global warming will cause large warming in the Arctic region and climate and weather anomalies outside the Arctic. The warming in the Arctic will mean warmer airmasses coming from the Arctic and also more moisture from the open Arctic Ocean. Furthermore, it will also change atmospheric circulation. These effects together will determine the impacts of Arctic warming. In this study, we introduce a novel sub‐sampling method to isolate atmospheric circulation change in response to the Arctic warming. The method involves selecting members of simulations from the experiment with future Arctic sea‐ice conditions, the average of which is equal to the average of the members of simulations in the experiment with present‐day Arctic sea‐ice conditions. We found that atmospheric circulation change in European regions is relatively weak so that warming effects will dominate the climate and weather response there. On the other hand, atmospheric circulation change will dominate the climate and weather response in East Eurasia. We also found that stronger atmospheric circulation changes will generally increase the response to the Arctic warming. We suggest caution when assessing whether different responses in different models can be interpreted as true differences in model physics. Key Points A novel sub‐sampling method is introduced to isolate the role of dynamics in the response to projected Arctic sea‐ice loss A dynamical Siberian High response dominates the temperature response over East Eurasia while that of the North Atlantic Oscillation is weak Inter‐model differences in Polar Amplification Model Intercomparison Project likely contain a large fraction of internal variability due to the unconstrained dynamic effects

Aim Cacao (Theobroma cacao L.) is expected to be vulnerable to climate change. The objectives of this study were to (a) assess the future impact of climate change on cacao in Peru and (b) identify areas where climate change‐tolerant genotypes are potentially present. Location Peru Methods Drawing on 19,700 and 1,200 presence points of cultivated and wild cacao, respectively, we modelled their suitability distributions using multiple ensemble models constructed based on both random and target group selection of pseudo‐absence points and different resolutions of spatial filtering. To estimate the uncertainty of future predictions, we generated future projections for all the ensemble models. We investigated the potential emergence of novel climates, determined expected changes in ecogeographical zones (zones representative for particular sets of growth conditions) and carried out an outlier analysis based on the environmental variables most relevant for climate change adaptation to identify areas where climate change‐tolerant genotypes are potentially present. Results We found that the best modelling approaches differed between cultivated and wild cacao and that the resolution of spatial filtering had a strong impact on future suitability predictions, calling for careful evaluation of the effect of model selection on modelling results. Overall, our models foresee a contraction of suitable area for cultivated cacao while predicting a more positive future for wild cacao in Peru. Ecogeographical zones are expected to change in 8%–16% of the distribution of cultivated and wild cacao. We identified several areas where climate change‐tolerant genotypes may be present in Peru. Main conclusions Our results indicate that tolerant genotypes will be required to facilitate the adaptation of cacao cultivation under climate change. The identified cacao populations will be target of collection missions.

The aim of this research was to evaluate the predictive performances of frequency ratio (FR), logistic regression (LR) and weight of evidence (WoE), in flood susceptibility mapping in China. In addition, the ensemble WoE and LR and ensemble FR and LR techniques were applied and used in the evaluation. The flood inventory map, consisting of 196 flood locations, was extracted from a number of sources. The flood inventory data were randomly divided into a testing data-set, allocating 70% for training, and the remaining 30% for validation. The 15 flood conditioning factors included in the spatial database were altitude, slope, aspect, geology, distance from river, distance from road, distance from fault, soil type, land use/cover, rainfall, Normalized Difference Vegetation Index, Stream Power Index, Topographic Wetness Index, Sediment Transport Index and curvature. For validation, success and prediction rate curves were developed using area under the curve (AUC) method. The results indicated that the highest prediction rate of 90.36% was achieved using the ensemble technique of WoE and LR. The standalone WoE produced the highest prediction rate among the individual methods. It can be concluded that WoE offers a more advanced method of mapping prone areas, compared with the FR and LR methods.