Ensemble Modeling Approach Research Articles

Evaluation and uncertainty assessment of wheat yield prediction by multilayer perceptron model with bayesian and copula bayesian approaches

An accurate crop yield forecast is vital for sustaining food security and preventing famine. Artificial intelligence provides a robust tool for integrating environmental, physiological, and management data and predicting crop yield. In this study, we used a Multilayer Perceptron (MLP) model in its default and hybrid learning modes to predict wheat yield. In its default mode, MLP was trained with the backpropagation algorithm, and in the hybrid mode, MLP was trained with the Water Striders Algorithm (WSA), Sine-Cosine Algorithm (SCA), and Genetic Algorithm (GA). We further considered two ensemble modeling approaches, including the Bayesian Model Averaging (BMA) and Copula-based Bayesian Model Averaging (CBMA). The study area was classified into four homogenous wheat cultivation regions using the Fuzzy clustering approach, and for each region, the models were trained based on 30 years of fertilizer information, harvested yield, and climatic data. Our results showed that hybridizing MLP with an optimization algorithm provides more accurate yield predictions than its default mode. WSA required the lowest computational time, and its combination with MLP resulted in a more accurate yield prediction compared to other optimization algorithms. The accuracy of yield predictions was further improved when ensemble modeling was implemented. Accordingly, the CBMA approach generated the most accurate result with the lowest uncertainty range. The mean absolute error (MAE) of the CBMA was 0.026, 0.058, 0.088, 0.133, and 0.0201 lower than that of the BMA, MLP-WSA, MLP-SCA, MLP-GA, and MLP models. GLUE uncertainty analysis verified the superiority of the hybrid models and ensemble approaches. The predicted yield by CBMA, BMA, and MLP-WSA covered 94 %, 92 %, and 89 % of the observations, respectively.

On the rise: Climate change in New Zealand will cause sperm and blue whales to seek higher latitudes

Climate impacts affect marine ecosystems worldwide with island nations such as New Zealand being extremely vulnerable because of their socio-economic and cultural dependence on the marine and costal environment. Cetaceans are ideal indicator species of ecosystem change and ocean health given their extended life span and cosmopolitan distribution, but limited data availability prevents anticipating change in distribution under future climate changes. We projected the range shifts of a key odontocete and mysticete species (Physeter macrocephalus and Balaenoptera musculus) in 2100 relative to present day in New Zealand waters, using an ensemble modelling approach, under three climate change scenarios of different severity.The results show a latitudinal shift in suitable habitat for both whale species, increasing in magnitude with severity of sea surface temperature warming. The most severe climate change scenario tested generated 61% and 42% loss and decrease of currently suitable habitat for sperm and blue whales, respectively, mostly in New Zealand’s northern waters. These predicted changes will have a strong impact on the ecosystem functioning and services in New Zealand’s northern waters but also in coastal areas (critical for the species’ foraging and survival). Not only do these simulated range shifts help to identify future potential climate refugia to mitigate a global warming, they also generate a range of socioeconomic consequences for island nations relying on wildlife tourism, industry, and environmental protection.

Climate change-induced distributional change of medicinal and aromatic plants in the Nepal Himalaya.

Medicinal and aromatic plants (MAPs) contribute to human well‐being via health and economic benefits. Nepal has recorded 2331 species of MAPs, of which around 300 species are currently under trade. Wild harvested MAPs in Nepal are under increasing pressure from overexploitation for trade and the effects of climate change and development. Despite some localized studies to examine the impact of climate change on MAPs, a consolidated understanding is lacking on how the distribution of major traded species of MAPs will change with future climate change. This study identifies the potential distribution of 29 species of MAPs in Nepal under current and future climate using an ensemble modeling and hotspot approach. Future climate change will reduce climatically suitable areas of two‐third of the studied species and decrease climatically suitable hotspots across elevation, physiography, ecoregions, federal states, and protected areas in Nepal. Reduction in climatically suitable areas for MAPs might have serious consequences for the livelihood of people that depend on the collection and trade of MAPs as well as Nepal's national economy. Therefore, it is imperative to consider the threats that future climate change may have on distribution of MAPs while designing protected areas and devising environmental conservation and climate adaptation policies.

Effects of stochastic wave forcing on probabilistic equilibrium shoreline response across the 21st century including sea-level rise

Coastal communities are currently facing the challenge of climate change and coastal retreat. While scientists are moving towards ensemble-modelling approaches to address uncertainties on shoreline evolution predictions, they rarely account for the stochastic nature of wave conditions across a variety of temporal scales (e.g., daily, weekly, seasonal, and interannual). In this contribution, we investigate the effects of the inherent variability of wave conditions on past and future multi-decadal shoreline evolution at the cross-shore transport dominated beach of Truc Vert (France). Using a climate-based wave emulator and variance decomposition method, we address the relative impacts of uncertain wave chronology, sea-level rise and model free parameters on modelled shoreline change, while accounting for possible correlations and interactions among the input variables. This work is done for two different wave-driven equilibrium models. The results show that the equilibrium shoreline models respond differently to the ensemble wave forcing, so that the choice of the modelling approach is critical to long-term modelled shoreline variations and the related uncertainties. We find that the modelled shoreline variance is primarily driven by the uncertain wave chronology until mid-21st century, while the uncertainties on future sea-level rise become dominant after 2060 in all the simulated scenarios. We also found that interactions and correlations among the uncertain variables can affect the estimation of shoreline predictions uncertainties. Finally, we provide a perspective on the application of non-stationary wave-related model parameters as a future research avenue for understanding uncertainties in modelled shoreline position.

Decline in the suitable habitat of dominant Abies species in response to climate change in the Hindu Kush Himalayan region: insights from species distribution modelling.

Reliable predictions of future distribution ranges of ecologically important species in response to climate change are required for developing effective management strategies. Here we used an ensemble modelling approach to predict the distribution of three important species of Abies namely, Abies pindrow, Abies spectabilis and Abies densa in the Hindu Kush Himalayan region under the current and two shared socioeconomic pathways (SSP245 and SSP585) and time periods of 2050 and 2090s. A correlative ensemble model using presence/absence data of the three Abies species and 22 environmental variables, including 19 bioclimatic variables and 3 topographic variables, from known distributions was built to predict the potential current and future distribution of these species. The individual models used to build the final ensemble performed well and provided reliable results for both the current and future distribution of all three species. For A. pindrow, precipitation of the driest month (Bio14) was the most important environmental variable with 83.3% contribution to model output while temperature seasonality (Bio4) and annual mean diurnal range (Bio2) were the most important variables for A. spectabilis and A. densa with 48.4% and 46.1% contribution to final model output, respectively. Under current climatic conditions, the ensemble models projected a total suitable habitat of about 433,003 km2, 790,837 km2 and 676,918 km2 for A. pindrow, A. spectabilis and A. densa, respectively, which is approximately 10.36%, 18.91% and 16.91% of the total area of Hindu Kush Himalayan region. Projections of habitat suitability under future climate scenarios for all the shared socioeconomic pathways showed a reduction in potentially suitable habitats with a maximum overall loss of approximately 14% of the total suitable area of A. pindrow under SSP 8.5 by 2090. A decline in total suitable habitat is predicted to be 9.6% in A. spectabilis by 2090 under the SSP585 scenario while in A. densa 6.67% loss in the suitable area is expected by 2050 under the SSP585 scenario. Furthermore, there is no elevational change predicted in the case of A. pindrow while A. spectabilis is expected to show an upward shift by about 29m per decade and A. densa is showing a downward shift at a rate of 11m per decade. The results are interesting, and intriguing given the occurrence of these species across the Hindu Kush Himalayan region. Thus, our study underscores the need for consideration of unexpected responses of species to climate change and formulation of strategies for better forest management and conservation of important conifer species, such as A. pindrow, A. spectabilis and A. densa.

What drives spatially varying ecological relationships in a wide‐ranging species?

AbstractAimDecades of research on species distributions has revealed geographic variation in species‐environment relationships for a given species. That is, the way a species uses the local environment varies across geographic space. However, the drivers underlying this variation are contested and still largely unexplored. Niche traits that are conserved should reflect the evolutionary history of a species whereas more flexible ecological traits could vary at finer scales, reflecting local adaptation.LocationNorth America.MethodsWe used mammal observations during a 5‐year period from the iNaturalist biodiversity database and a local ensemble modelling approach to explore spatial variation in American black bear (Ursus americanus) relationships with eight ecological correlates. We tested four biologically driven hypotheses to explain the patterns of local adaptation. We evaluated non‐stationarity in ecological relationships using a Stationarity Index and tested predictive performance using an independent, national‐level animal occurrence data set.ResultsWe documented considerable spatial non‐stationarity in all eight environmental relationships, with the greatest spatial variation occurring in bear's relationship to climatic factors. Notably, the greatest variation in environmental relationships tended to occur along the current boundaries of the species' range, potentially representing the ecological limits to the species geographic range. We additionally documented that spatial variation in relationships with land cover and anthropogenic factors were best explained by niche conservatism at the subspecies level, whereas climatic relationships were better explained by local adaptation.Main ConclusionsBased on these results, we propose that the current distribution of American black bear is determined by an evolutionary legacy of habitat relationships unique to each subspecies combined with more fine‐scale local adaptation to climatic conditions. This result suggests that black bears should be adaptable to climatic changes over the 21st century and that management of habitat and human‐bear relationships could be considered at the subspecies level.

Expected contraction in the distribution ranges of demersal fish of high economic value in the Mediterranean and European Seas

Fisheries and aquaculture are facing many challenges worldwide, especially adaptation to climate change. Investigating future distributional changes of largely harvested species has become an extensive research topic, aiming at providing realistic ecological scenarios on which to build management measures, to help fisheries and aquaculture adapt to future climate-driven changes. Here, we use an ensemble modelling approach to estimate the contemporary and future distributional range of eight demersal fish species of high economic value in the Mediterranean Sea. We identify a cardinal influence of (i) temperature on fish species distributions, all being shaped by yearly mean and seasonality in sea bottom temperature, and (ii) the primary production. By assessing the effects of changes in future climate conditions under three Representative Concentration Pathway (RCP2.6, RCP4.5 and RCP8.5) scenarios over three periods of the twenty-first century, we project a contraction of the distributional range of the eight species in the Mediterranean Sea, with a general biogeographical displacement towards the North European coasts. This will help anticipating changes in future catch potential in a warmer world, which is expected to have substantial economic consequences for Mediterranean fisheries.

The possible future changes in potential suitable habitats of Tetrastigma hemsleyanum (Vitaceae) in China predicted by an ensemble model

Tetrastigma hemsleyanum ( Vitaceae ) is an endangered subtropical herbaceous perennial climbing liana mainly distributed south of the Yangtze River (China). It is widely used in medical and phylogeographic applications, and its growth is restricted to certain climate conditions. In this study, we applied ensemble modeling approaches to investigate the possible changes in potential suitable habitats of T. hemsleyanum in the future under all shared socioeconomic pathway (SSP) scenarios. The results showed that the mean diurnal range (bio2) and precipitation of the warmest quarter (bio18) were the most important variables affecting the potential suitable habitats of T. hemsleyanum . Currently, the area of highly suitable habitat for T. hemsleyanum is approximately 1.38 × 10 6 km 2 . The ensemble model predicted that the highly suitable habitat of T. hemsleyanum will contract under all future SSP scenarios and that the more severe the global warming is, the more highly suitable habitats will be lost. The contracted high suitable habitats ranged from 20% (SSP126, best case) to 90% (SSP585, worst case) at the end of this century. The results of this work may provide useful information for formulating conservation and natural resource management policies for T. hemsleyanum . The remained high suitable habitats under SSP585 at the end of this century projected by the current work can be selected as nature reserves.

Habitat suitability of neotenic net‐winged beetles (Coleoptera: Lycidae) in China using combined ecological models, with implications for biological conservation

AbstractAimChina has dozens of well‐recognized biodiversity hotspots, but many more potential areas have not been estimated thoroughly, which is unfavourable for biodiversity conservation. Neotenic net‐winged beetles with limited dispersal ability generally occur in restricted ranges but rarely occur in China, which makes them ideal models for biogeographical studies to define biodiversity hotspots. This study will explore the potential distribution patterns of neotenic Lycidae in China to provide basic data for the implementation of biological conservation.LocationChina.MethodsWe conducted maximum entropy (MaxEnt) and random forest (RF) modelling to simulate the habitat suitability for neotenic Lycidae occurring in China under different climate scenarios by using all available distribution information in Southeast Asia (a total of 305 occurrence records) and several environmental variables. The dynamic changes in the potentially suitable habitats and centroids of neotenic Lycidae were simulated under all climate scenarios.ResultsThe results indicated that potentially suitable habitats for neotenic Lycidae were mostly located in the montane areas and mountainous islands in southern China, including the eastern Himalayas, Gaoligong Mountains, Ailao Mountains, Hengduan Mountains, Wumeng Mountains, Miaoling Mountains, Daba Mountains, Wu Mountains, Yunkai Mountains, Wuzhi Mountains and Central Mountains. In addition, the dynamic analyses showed that their changes also occurred in montane areas, whose affinity and significance were confirmed in the biological conservation.Main conclusionsTaking the unique neotenic Lycidae as the subject, we verify that several montane areas are biodiversity hotspots that have already been well‐recognized, while it is determined that some additional mountains could be potential hotspots. Therefore, more attention and biological conservation efforts should be used in these areas. In addition, using the ensemble modelling approach to identify potential distributions is a helpful tool to develop strategies for biological conservation, even if it has several limitations.

Large-scale hydrological modeling in a multi-objective uncertainty framework – Assessing the potential for managed aquifer recharge in the North China Plain

The region studied is the 137.000 km2 North China Plain (NCP). A region with high population density and a major agricultural production leading to unsustainable exploitation of groundwater resources.Previous modeling studies in the region have utilized simplified representations of model boundary fluxes, both regarding lateral inflows from surface and groundwater and related to water demands and consumptions. The current study focusses on developing a hydrological modeling framework, with better spatial descriptions of major water balance components regarding water demands, model boundary conditions of surface and groundwater inflows and evaporative losses due to irrigation. Compared to previous efforts, the modeling framework utilizes a novel multi-objective parameter optimization strategy combined with an ensemble modeling approach to illuminate optimization trade-offs and impacts of parameter uncertainty.Groundwater storage declines are estimated to be in the order of 25–55 mm/y for the period 2000–2013. The impacts of water management strategies are explored using the model ensemble and show that this decline can be counterbalanced by approximately 15–20 mm/y by substantial reductions in irrigation (20%) or implementation of planned inter-basin water transfers. Managed aquifer recharge in the form of infiltrating excess river peak flows, can only reduce groundwater storage declines to a limited degree. However, at the local to regional scale storage decline reductions from MAR are in the same order of magnitude as other extensive water management strategies.

Retreat of Major European Tree Species Distribution under Climate Change—Minor Natives to the Rescue?

Climate change is projected to trigger strong declines in the potential distribution of major tree species in Europe. While minor natives have moved into the spotlight as alternatives, their ecology is often poorly understood. We use an ensemble species distribution modelling approach on a set of promising native tree species to gain insights into their distribution potential under different climate change scenarios. Moreover, we identify the urgency and potential of altered species distributions in favor of minor natives by comparing the niche dynamics of five major native tree species with the set of six minor natives in a case study. Our models project stark range contractions and range shifts among major tree species, strongly amplified under high emission scenarios. Abies alba, Picea abies and Fagus sylvatica are affected the strongest. While also experiencing range shifts, the minor European natives Castanea sativa, Sorbus torminalis, and Ulmus laevis all considerably expand their range potential across climate change scenarios. Accompanied by Carpinus betulus, with a stable range size, they hold the potential to substantially contribute to sustainably adapting European forest to climate change.

Global burden of gallbladder and biliary diseases: A systematic analysis for the Global Burden of Disease Study 2019.

Gallbladder and biliary diseases (GBDs) are one of the most prevalent medical issues in the digestive system. This study was designed to describe the characteristics of prevalence, death, and disability-adjusted life years (DALYs) of GBDs during 1990-2019 using data from the Global Burden of Diseases, Injuries, and Risk Factors Study 2019. Prevalence, death, and DALYs for GBDs in different locations, years, sex, and age groups were estimated using DisMod-MR 2.1 and a generic Cause of Death Ensemble Modeling approach. Countries and territories were categorized according to socio-demographic index (SDI) quintiles. The prevalence cases (127345732 to 193493378), death cases (82430 to 124941), and DALYs (4604821 to 6352738) of GBDs increased from 1990 to 2019. However, the age-standardized rates of indicators decreased over the 30-year period (prevalence, 2851.84 to 2350.78 per 100000 population; death, 2.40 to 1.65 per 100000 population; DALYs, 106.76 to 78.25 per 100000 population). In 2019, the high and middle-high SDI regions had higher age-standardized prevalence rates, the low SDI region had the highest age-standardized death rate, and the middle SDI region had the highest DALYs and age-standardized DALYs rate of GBDs. Being female, older age, and high body mass index were important risk factors for the burden of GBDs. Globally, there were improvements in overall health with regard to GBDs over the 30years. However, the prevention of GBDs should be promoted in middle, middle-high, and high SDI regions, while more medical resources should be provided to improve treatment levels in low SDI region.

Prediction of topsoil organic carbon content with Sentinel-2 imagery and spectroscopic measurements under different conditions using an ensemble model approach with multiple pre-treatment combinations

Estimating soil organic carbon (SOC) using visible near infrared (Vis-NIR) spectroscopy has proven to be a rapid and reliable approach. However, when working across large geographical scales, remote sensing may be more suitable. Acquiring these spectra data normally under different measurement conditions could introduce artefacts that reduce SOC prediction accuracy. A common procedure has been using calibration or multivariate techniques in conjunction with one or more pre-treatment algorithms. The results of several comparative studies based on these predictive calibration techniques used alone were inconsistent. Moreover, protocols to select the most appropriate pre-treatment algorithms rarely exist. This study combines predictions from different techniques into a single model based on an ensemble learning approach. The main objective is to improve the accuracy of SOC prediction by assessing the effectiveness of using different calibration techniques individually against an ensemble model consisting of one statistical method, which includes partial least squares regression (PLSR), and three machine learning (ML) algorithms, including random forest (RF), support vector machine regression (SVMR), and Cubist. Several pre-treatment algorithms were also employed to improve the spectral data before prediction. Spectra data were collected from three different agricultural fields (with different soil types), under different spectral measurement conditions (field, wet and dry). Additionally, Sentinel-2 (S2) data was collected from one of these fields. Furthermore, to ascertain the effectiveness of the developed model on regional scale dataset, two options were employed: (1) merged data from all fields, and (2) merged data from fields measured under the same spectral measurement conditions. The models were evaluated using root mean square error of prediction (RMSEPCV), the coefficient of determination (R²CV), the ratio of performance to interquartile range (RPIQ), the ratio of performance to deviation (RPD) and BIAS. The results show that, across the three agricultural fields, the ensemble model predicted SOC more accurately than each of the individual calibration techniques (R2CV = 0.92, RMSEPCV (g/kg) = 1.00, RPD = 3.06, RPIQ = 3.74, BIAS (g/kg) = 0.067). The models derived from merged data (regional dataset) show that the ensemble approach predicted SOC more accurately with option 2 than option 1. Finally, while the ensemble model improves SOC accuracy with S2 data, the final output was poor. Further research to determine the underlying problem is strongly recommended. Nonetheless, these results indicate that the ensemble model is advantageous because it improved the prediction accuracy of SOC and reduced the error margin.

An ensemble approach to understand predation mortality for groundfish in the Gulf of Alaska

There is increasing consensus of the need for ecosystem-based fisheries management (EBFM), which accounts for trophic interactions and environmental conditions when managing exploited marine resources. Continued development and testing of analytical tools that are expected to address EBFM needs are essential for guiding the management of fisheries resources in achieving and balancing multiple social, economic, and conservation objectives. To address these needs, we present and compare alternative climate-informed multi-species statistical catch-at-age models to account for spatio-temporal differences in stock distributions, with application to four groundfish species (walleye pollock Gadus chalcogrammus, Pacific cod Gadus macrocephalus, arrowtooth flounder Atheresthes stomias, and Pacific halibut Hippoglossus stenolepis) in the Gulf of Alaska, USA. We integrate across multiple forms of uncertainty regarding the data and distribution of Pacific halibut using an ensemble modelling approach. Models developed here can be used to supplement current tactical fisheries management and inform on the trade-offs between harvesting across groundfish in the Gulf of Alaska. This approach may be applicable for other situations where spatial and temporal overlap is extensive among closely coupled species.

Genetic Lineage Distribution Modeling to Predict Epidemics of a Conifer Disease

A growing body of evidence suggests that climate change is altering the epidemiology of many forest diseases. Nothophaeocryptopus gaeumannii (Rhode) Petrak, an ascomycete native to the Pacific Northwest and the causal agent of the Swiss needle cast (SNC) disease of Douglas-fir [Pseudotsuga menziesii (Mirbel) Franco], is no exception. In the past few decades, changing climatic conditions have coincided with periodic epidemics of SNC in coastal forests and plantations from Southwestern British Columbia (B.C.) to Southwestern Oregon, wherein an increase in the colonization of needles by N. gaeumanii causes carbon starvation, premature needle shedding and a decline in growth. Two major sympatric genetic lineages of N. gaeumannii have been identified in the coastal Pacific Northwest. Past research on these lineages suggests they have different environmental tolerance ranges and may be responsible for some variability in disease severity. In this study, we examined the complex dynamics between biologically pertinent short- and long-term climatic and environmental factors, phylogenetic lineages of N. gaeumannii and the severity patterns of the SNC disease. Firstly, using an ensemble species distribution modeling approach using genetic lineage presences as model inputs, we predicted the probability of occurrence of each lineage throughout the native range of Douglas-fir in the present as well as in 2050 under the “business as usual” (RCP8.5) emissions scenario. Subsequently, we combined these model outputs with short-term climatic and topographic variables and colonization index measurements from monitoring networks across the SNC epidemic area to infer the impacts of climate change on the SNC epidemic. Our results suggest that the current environmental tolerance range of lineage 1 exceeds that of lineage 2, and we expect lineage 1 to expand inland in Washington and Oregon, while we expect lineage 2 will remain relatively constrained to its current range with some slight increases in suitability, particularly in coastal Washington and Oregon. We also found that disease colonization index is associated with the climatic suitability of lineage 1, and that the suitability of the different lineages could impact the vertical patterns of colonization within the crown. We conclude that unabated climate change could cause the SNC epidemic to intensify.

Exploring the effects of land management change on productivity, carbon and nutrient balance: Application of an Ensemble Modelling Approach to the upper River Taw observatory, UK

Agriculture is challenged to produce healthy food and to contribute to cleaner energy whilst mitigating climate change and protecting ecosystems. To achieve this, policy-driven scenarios need to be evaluated with available data and models to explore trade-offs with robust accounting for the uncertainty in predictions. We developed a novel model ensemble using four complementary state-of-the-art agroecosystems models to explore the impacts of land management change. The ensemble was used to simulate key agricultural and environmental outputs under various scenarios for the upper River Taw observatory, UK. Scenarios assumed (i) reducing livestock production whilst simultaneously increasing the area of arable where it is feasible to cultivate (PG2A), (ii) reducing livestock production whilst simultaneously increasing bioenergy production in areas of the catchment that are amenable to growing bioenergy crops (PG2BE) and (iii) increasing both arable and bioenergy production (PG2A + BE). Our ensemble approach combined model uncertainty using the tower property of expectation and the law of total variance. Results show considerable uncertainty for predicted nutrient losses with different models partitioning the uncertainty into different pathways. Bioenergy crops were predicted to produce greatest yields from Miscanthus in lowland and from SRC-willow (cv. Endurance) in uplands. Each choice of management is associated with trade-offs; e.g. PG2A results in a significant increase of edible calories (6736 Mcal ha−1) but reduced soil C (−4.32 t C ha−1). Model ensembles in the agroecosystem context are difficult to implement due to challenges of model availability and input and output alignment. Despite these challenges, we show that ensemble modelling is a powerful approach for applications such as ours, offering benefits such as capturing structural as well as data uncertainty and allowing greater combinations of variables to be explored. Furthermore, the ensemble provides a robust means for combining uncertainty at different scales and enables us to identify weaknesses in system understanding.

Improving forecasts of sockeye salmon (Oncorhynchus nerka) with parametric and nonparametric models

Accurate forecasts of sockeye salmon (Oncorhynchus nerka) in Bristol Bay, Alaska, play an important role in management and harvesting decisions for this culturally and ecologically vital species. We used a suite of parametric and nonparametric models to assess the frontiers in forecast accuracy of Bristol Bay sockeye salmon possible given currently available data. In retrospective performance testing individual models were capable of reducing pre-season forecast error at the river system level by on average 15% relative to a benchmark model. We used an ensemble modeling approach to produce pre-season forecasts based on historical performance of individual models. This ensemble model reduced river system forecast error by 13% on average in 5 of the 7 evaluated river systems, though it increased forecast error by 39% on average in the remaining 2 systems. We found potential for modest improvements in forecast accuracy across a variety of scales. However, all tested models failed to accurately predict certain periods in the historical salmon return patterns, indicating that further forecast improvements likely depend on novel data rather than more flexible models.

Developing a prediction model for low-temperature fracture energy of asphalt mixtures using machine learning approach

ABSTRACTThis paper presents an augmented full quadratic model (AFQM), artificial neural network (ANN) and an innovative machine learning technique called self-validated ensemble modelling (SVEM) approaches to predict low-temperature fracture energy of asphalt mixtures. An experimental database including 852 fracture energy values obtained from low temperature disk-shaped compact tension (DCT) testing was utilised to develop the prediction models. The fracture energy was predicted in terms of several variables that are available during the mix design process. The collected data were categorised into three groups based on the availability of the data at different points during the mix design process. A sensitivity analysis was conducted to assess the impact of the design variables on fracture energy. Based on the model development results, both ANN and SVEM methods showed higher prediction accuracy than AFQM. Prediction models based on the ANN were time-consuming and computationally expensive due to the optimum model architecture. The SVEM technique was found to be a reliable prediction method with high prediction reliability even with a limited amount of data. Based on the sensitivity analysis, design traffic level, PG low temperature (PGLT) binder grade, amount of aggregate passing 9.5 mm sieve, and the voids in mineral aggregate (VMA) are the most effective factors impacting low-temperature asphalt mixture fracture energy. A web-based prediction model platform was developed using prediction models based on the SVEM technique which can be utilised as a predesign tool to evaluate low-temperature fracture energy of asphalt mixtures when laboratory testing is not feasible.

Mapping environmental suitability of Haemagogus and Sabethes spp. mosquitoes to understand sylvatic transmission risk of yellow fever virus in Brazil.

BackgroundYellow fever (YF) is an arboviral disease which is endemic to Brazil due to a sylvatic transmission cycle maintained by infected mosquito vectors, non-human primate (NHP) hosts, and humans. Despite the existence of an effective vaccine, recent sporadic YF epidemics have underscored concerns about sylvatic vector surveillance, as very little is known about their spatial distribution. Here, we model and map the environmental suitability of YF’s main vectors in Brazil, Haemagogus spp. and Sabethes spp., and use human population and NHP data to identify locations prone to transmission and spillover risk.Methodology/Principal findingsWe compiled a comprehensive set of occurrence records on Hg. janthinomys, Hg. leucocelaenus, and Sabethes spp. from 1991–2019 using primary and secondary data sources. Linking these data with selected environmental and land-cover variables, we adopted a stacked regression ensemble modelling approach (elastic-net regularized GLM, extreme gradient boosted regression trees, and random forest) to predict the environmental suitability of these species across Brazil at a 1 km x 1 km resolution. We show that while suitability for each species varies spatially, high suitability for all species was predicted in the Southeastern region where recent outbreaks have occurred. By integrating data on NHP host reservoirs and human populations, our risk maps further highlight municipalities within the region that are prone to transmission and spillover.Conclusions/SignificanceOur maps of sylvatic vector suitability can help elucidate potential locations of sylvatic reservoirs and be used as a tool to help mitigate risk of future YF outbreaks and assist in vector surveillance. Furthermore, at-risk regions identified from our work could help disease control and elucidate gaps in vaccination coverage and NHP host surveillance.

An update on the distribution of the coypu, Myocastor coypus, in Asia and Africa through published literature, citizen-science and online platforms

The coypu, Myocastor coypus, has been introduced worldwide for fur farming and is widely recognized as one of the most invasive alien mammals of the world, affecting natural ecosystems, crops and possibly human health. Here we present a comprehensive up-to-date review of its distribution and status in Asia and Africa. Using a multi-source approach, we collected occurrences from published literature as well as from online biodiversity platforms (e.g. GBIF, iNaturalist), video sharing platforms, and local experts. Additionally, we used an ensemble modelling approach to predict the climatic suitability across Africa and Asia. We present an updated distribution map, including a total of 1506 spatially explicit records from 1973 to 2021, covering 1 African and 16 Asian countries. We find evidence for current populations in Kenya and five new countries since the last review of (Carter and Leonard, Wildl Soc Bull 30:162–175, 2002): Iran, Jordan, Lebanon, Uzbekistan, and Vietnam, and identify main clusters of coypu occurrence in Western (including Transcaucasia) and East Asia. We show that warm temperate and Mediterranean areas on both continents are predicted to be climatically suitable for the coypu and highlight not only areas of possible spread, but also potential data gaps, i.e. with high suitability and low availability of concrete information (e.g. China, Southern Russia). We emphasize the importance of citizen involvement and the urgency for coypu-targeted studies in data-poor regions to obtain a clear picture of the geographical distribution and to better address management strategies.