Performance analysis of real-time plant species recognition using bilateral network combined with machine learning classifier

A real-time plant species recognition under an unconstrained environment is a challenging and time-consuming process. The recognition model should cope up with the computer vision challenges such as scale variations, illumination changes, camera viewpoint or object orientation changes, cluttered backgrounds and structure of leaf (simple or compound). In this paper, a bilateral convolutional neural network (CNN) with machine learning classifiers are investigated in relation to the real-time implementation of plant species recognition. The CNN models considered are MobileNet, Xception and DenseNet-121. In the bilateral CNNs (Homogeneous/Heterogeneous type), the models are connected using the cascade early fusion strategy. The Bilateral CNN is used in the process of feature extraction. Then, the extracted features are classified using different machine learning classifiers such as Linear Discriminant Analysis (LDA), multinomial Logistic Regression (MLR), Naïve Bayes (NB), k-Nearest Neighbor (k−NN), Classification and Regression Tree (CART), Random Forest Classifier (RF), Bagging Classifier (BC), Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). From the experimental investigation, it is observed that the multinomial Logistic Regression classifier performed better compared to other classifiers, irrespective of the bilateral CNN models (Homogeneous - MoMoNet, XXNet, DeDeNet; Heterogeneous - MoXNet, XDeNet, MoDeNet). It is also observed that the MoDeNet + MLR model attained the state-of-the-art results (Flavia: 98.71%, Folio: 96.38%, Swedish Leaf: 99.41%, custom created Leaf-12: 99.39%), irrespective of the dataset. The number of misprediction/class is highly reduced by utilizing the MoDeNet + MLR model for real-time plant species recognition.     

Top-down effects of an invasive omnivore: detection in long-term monitoring of large-river reservoir chlorophyll-a

Elevation represents an important selection agent on self-maintenance traits and correlated life histories in birds, but no study has analysed whether life-history variation along this environmental cline is consistent among and within species. In a sympatric community of passerines, we analysed how the average adult survival of 25 open-habitat species varied with their elevational distribution and how adult survival varied with elevation at the intra-specific level. For such purpose, we estimated intra-specific variation in adult survival in two mountainous species, the Water pipit (Anthus spinoletta) and the Northern wheatear (Oenanthe oenanthe) in NW Spain, by means of capture–recapture analyses. At the inter-specific level, high-elevation species showed higher survival values than low elevation ones, likely because a greater allocation to self-maintenance permits species to persist in alpine environments. At the intra-specific level, the magnitude of survival variation was lower by far. Nevertheless, Water pipit survival slightly decreased at high elevations, while the proportion of transient birds increased. In contrast, no such relationships were found in the Northern wheatear. Intra-specific analyses suggest that living at high elevation may be costly, such as for the Water pipit in our case study. Therefore, it seems that a species can persist with viable populations in uplands, where extrinsic mortality is high, by increasing the investment in self-maintenance and prospecting behaviours.     

Testing whether ensemble modelling is advantageous for maximising predictive performance of species distribution models

Predictive performance is important to many applications of species distribution models (SDMs). The SDM ‘ensemble’ approach, which combines predictions across different modelling methods, is believed to improve predictive performance, and is used in many recent SDM studies. Here, we aim to compare the predictive performance of ensemble species distribution models to that of individual models, using a large presence–absence dataset of eucalypt tree species. To test model performance, we divided our dataset into calibration and evaluation folds using two spatial blocking strategies (checkerboard-pattern and latitudinal slicing). We calibrated and cross-validated all models within the calibration folds, using both repeated random division of data (a common approach) and spatial blocking. Ensembles were built using the software package ‘biomod2’, with standard (‘untuned’) settings. Boosted regression tree (BRT) models were also fitted to the same data, tuned according to published procedures. We then used evaluation folds to compare ensembles against both their component untuned individual models, and against the BRTs. We used area under the receiver-operating characteristic curve (AUC) and log-likelihood for assessing model performance. In all our tests, ensemble models performed well, but not consistently better than their component untuned individual models or tuned BRTs across all tests. Moreover, choosing untuned individual models with best cross-validation performance also yielded good external performance, with blocked cross-validation proving better suited for this choice, in this study, than repeated random cross-validation. The latitudinal slice test was only possible for four species; this showed some individual models, and particularly the tuned one, performing better than ensembles. This study shows no particular benefit to using ensembles over individual tuned models. It also suggests that further robust testing of performance is required for situations where models are used to predict to distant places or environments.     

Interspecific Response to Playback of Bird Song

Responses to bird song have usually only been studied at the intraspecific level. I experimentally tested whether playback of the song of the black wheatear Oenanthe leucura in an area in S Spain resulted in responses from conspecifics as well as heterospecific birds by comparing the numbers of individuals singing before and after playback. The number of singing male black wheatears increased considerably, but also the number of singing males of five other passerine species increased significantly. The heterospecific response to playback may be due (1) to interspecific territoriality, (2) to black wheatear song signalling the absence of predators, or (3) to heterospecifics confusing the species-identity of the singer. The second alternative is considered more likely, since an ecologically wide array of species increased their song rate following playback. The conspicuous dawn (and dusk) chorus of bird song may be augmented by social facilitation due to the singing of conspecifics as well as heterospecifics.     

Background sampling for multi-scale ensemble habitat selection modeling: Does the number of points matter?

Ensemble habitat selection modeling is becoming a popular approach among ecologists to answer different questions. Since we are still in the early stages of development and application of ensemble modeling, there remain many questions regarding performance and parameterization. One important gap, which this paper addresses, is how the number of background points used to train models influences the performance of the ensemble model. We used an empirical presence-only dataset and three different selections of background points to train scale-optimized habitat selection models using six modeling algorithms (GLM, GAM, MARS, ANN, Random Forest, and MaxEnt). We tested four ensemble models using different combinations of the component models: (a) equal numbers of background points and presences, (b) background points equaled ten times the number of presences, (c) 10,000 background points, and (d) optimized background points for each component model. Among regression-based approaches, MARS performed best when built with 10,000 background points. Among machine learning models, RF performed the best when built with equal presences and background points. Among the four ensemble models, AUC indicated that the best performing model was the ensemble with each component model including the optimized number of background points, while TSS increased as the number of background points models increased. We found that an ensemble of models, each trained with an optimal number of background points, outperformed ensembles of models trained with the same number of background points, although differences in performance were slight. When using a single modeling method, RF with equal number of presences and background points can perform better than an ensemble model, but the performance fluctuates when the number of background points is not properly selected. On the other hand, ensemble modeling provides consistently high accuracy regardless of background point sampling approach. Further, optimizing the number of background points for each component model within an ensemble model can provide the best model improvement. We suggest evaluating more models across multiple species to investigate how background point selection might affect ensemble models in different scenarios.     

Prediction of wild pistachio ecological niche using machine learning models

Observing vegetation dynamics and determining optimum conditions for tree species are important for the long-term habitat conservation. In this study we evaluate the environmental drivers that may explain the development and geographic distribution of Pistacia atlantica Desf. (wild pistachio) in Northeastern Iran. The study uses seven machine learning models to predict the habitats of P. atlantica: multivariate adaptive regression splines (MARS), flexible discriminant analysis (FDA), boosted regression tree (BRT), maximum entropy (MaxEnt), random forest (RF), support vector machine (SVM), generalized linear model (GLM), and their ensembles (ESMs). In total, 1477 P. atlantica sites were identified, described and mapped. The most relevant determinants of the species habitat were included as 28 bioclimatic, topographic, edaphic, and geologic components. While all the models returned high accuracies, the ESMs achieved the highest AUC, TSS, and Kappa values, suggesting a good predictive performance. The most important parameters explaining the species habitat were found to be the mean diurnal temperature range, annual precipitation and slope. These results support the higher performance of ESMs to predict the spatial distribution of P. atlantica. In turn, this model may support species conservation and decision-making at the regional and national levels.     

Parallel plumage colour evolution and introgressive hybridization in wheatears

Genetic and phenotypic mosaics, in which various phenotypes and different genomic regions show discordant patterns of species or population divergence, offer unique opportunities to study the role of ancestral and introgressed genetic variation in phenotypic evolution. Here, we investigated the evolution of discordant phenotypic and genetic divergence in a monophyletic clade of four songbird taxa—pied wheatear (O. pleschanka), Cyprus wheatear (Oenanthe cypriaca), and western and eastern subspecies of black‐eared wheatear (O. h. hispanica and O. h. melanoleuca). Phenotypically, black back and neck sides distinguish pied and Cyprus wheatears from the white‐backed/necked black‐eared wheatears. Meanwhile, mitochondrial variation only distinguishes western black‐eared wheatear. In the absence of nuclear genetic data, and given frequent hybridization among eastern black‐eared and pied wheatear, it remains unclear whether introgression is responsible for discordance between mitochondrial divergence patterns and phenotypic similarities, or whether plumage coloration evolved in parallel. Multispecies coalescent analyses of about 20,000 SNPs obtained from RAD data mapped to a draft genome assembly resolve the species tree, provide evidence for the parallel evolution of colour phenotypes and establish western and eastern black‐eared wheatears as independent taxa that should be recognized as full species. The presence of the entire admixture spectrum in the Iranian hybrid zone and the detection of footprints of introgression from pied into eastern black‐eared wheatear beyond the hybrid zone despite strong geographic structure of ancestry proportions furthermore suggest a potential role for introgression in parallel plumage colour evolution. Our results support the importance of standing heterospecific and/or ancestral variation in phenotypic evolution.     

Do Stacked Species Distribution Models Reflect Altitudinal Diversity Patterns?

The objective of this study was to evaluate the performance of stacked species distribution models in predicting the alpha and gamma species diversity patterns of two important plant clades along elevation in the Andes. We modelled the distribution of the species in the Anthurium genus (53 species) and the Bromeliaceae family (89 species) using six modelling techniques. We combined all of the predictions for the same species in ensemble models based on two different criteria: the average of the rescaled predictions by all techniques and the average of the best techniques. The rescaled predictions were then reclassified into binary predictions (presence/absence). By stacking either the original predictions or binary predictions for both ensemble procedures, we obtained four different species richness models per taxa. The gamma and alpha diversity per elevation band (500 m) was also computed. To evaluate the prediction abilities for the four predictions of species richness and gamma diversity, the models were compared with the real data along an elevation gradient that was independently compiled by specialists. Finally, we also tested whether our richness models performed better than a null model of altitudinal changes of diversity based on the literature. Stacking of the ensemble prediction of the individual species models generated richness models that proved to be well correlated with the observed alpha diversity richness patterns along elevation and with the gamma diversity derived from the literature. Overall, these models tend to overpredict species richness. The use of the ensemble predictions from the species models built with different techniques seems very promising for modelling of species assemblages. Stacking of the binary models reduced the over-prediction, although more research is needed. The randomisation test proved to be a promising method for testing the performance of the stacked models, but other implementations may still be developed.     

Validation of X-ray Crystal Structure Ensemble Representations of SARS-CoV-2 Main Protease by Solution NMR Residual Dipolar Couplings

Considerable debate has focused on whether sampling of molecular dynamics trajectories restrained by crystallographic data can be used to develop realistic ensemble models for proteins in their natural, solution state. For the SARS-CoV-2 main protease, M^pro, we evaluated agreement between solution residual dipolar couplings (RDCs) and various recently reported multi-conformer and dynamic-ensemble crystallographic models. Although Phenix-derived ensemble models showed only small improvements in crystallographic R_free, substantially improved RDC agreement over fits to a conventionally refined 1.2-Å X-ray structure was observed, in particular for residues with above average disorder in the ensemble. For a set of six lower resolution (1.55–2.19 Å) M^pro X-ray ensembles, obtained at temperatures ranging from 100 to 310 K, no significant improvement over conventional two-conformer representations was found. At the residue level, large differences in motions were observed among these ensembles, suggesting high uncertainties in the X-ray derived dynamics. Indeed, combining the six ensembles from the temperature series with the two 1.2-Å X-ray ensembles into a single 381-member “super ensemble” averaged these uncertainties and substantially improved agreement with RDCs. However, all ensembles showed excursions that were too large for the most dynamic fraction of residues. Our results suggest that further improvements to X-ray ensemble refinement are feasible, and that RDCs provide a sensitive benchmark in such endeavors. Remarkably, a weighted ensemble of 350 PDB M^pro X-ray structures provided slightly better cross-validated agreement with RDCs than any individual ensemble refinement, implying that differences in lattice confinement also limit the fit of RDCs to X-ray coordinates.     

Using a multi‐model ensemble approach to determine biodiversity hotspots with limited occurrence data in understudied areas: An example using freshwater mussels in México

Species distribution models (SDMs) are an increasingly important tool for conservation particularly for difficult‐to‐study locations and with understudied fauna. Our aims were to (1) use SDMs and ensemble SDMs to predict the distribution of freshwater mussels in the Pánuco River Basin in Central México; (2) determine habitat factors shaping freshwater mussel occurrence; and (3) use predicted occupancy across a range of taxa to identify freshwater mussel biodiversity hotspots to guide conservation and management. In the Pánuco River Basin, we modeled the distributions of 11 freshwater mussel species using an ensemble approach, wherein multiple SDM methodologies were combined to create a single ensemble map of predicted occupancy. A total of 621 species‐specific observations at 87 sites were used to create species‐specific ensembles. These predictive species ensembles were then combined to create local diversity hotspot maps. Precipitation during the warmest quarter, elevation, and mean temperature were consistently the most important discriminatory environmental variables among species, whereas land use had limited influence across all taxa. To the best of our knowledge, our study is the first freshwater mussel‐focused research to use an ensemble approach to determine species distribution and predict biodiversity hotspots. Our study can be used to guide not only current conservation efforts but also prioritize areas for future conservation and study.     

气候变化对物种分布影响模拟中的不确定性组分分割与制图——以油松为例

物种分布模型是预测评估气候变化对物种分布影响的主要工具。为了降低物种分布模型在预测过程中的不确定性,近期有学者提出了采用组合预测的新方法,即采用多套建模数据、模型技术,模型参数,以及环境情景数据对物种分布进行预测,构成物种分布预测集合。但是,组合预测中各组分对变异的贡献还知之甚少,因此有必要把变异组分来源进行分割,以更有效地利用组合预测方法来降低模型预测中的不确定性。以油松为例,采用8个生态位模型,9套模型训练数据,3个GCM模型和一个SRES(A2)排放情景,模型分析了油松当前(1961-1990年)和未来气候条件下3个时间段(2010-2039年,2040-2069年,2070-2099年)的潜在分布。共计得到当前分布预测数据72套,未来每个时间段分布数据216套。采用开发的ClimateChina软件进行当前和未来气候数据的降尺度处理。采用Kappa、真实技巧统计方法(TSS)和接收机工作特征曲线下的面积(AUC)对模型预测能力进行评估。结果表明,随机森林(RF)、广义线性模型(GLM),广义加法模型(GAM)、多元自适应样条函数(MARS)以及助推法(GBM)预测效果较好,几乎不受建模数据之间差异的影响。混合判别分析模型(MDA)对建模数据之间的差异非常敏感,甚至出现建模失败现象。采用三因素方差分析方法对组合预测中的不确定性来源进行变异分割,结果表明,模型之间的差异对模拟预测结果不确定性的贡献最大且所占比例极高,而建模数据之间的差异贡献最小,GCM贡献居中。研究将有助于加深对物种分布模拟预测中不确定性的认识。     

The Impact of Increased Food Availability on Reproduction in a Long-Distance Migratory Songbird: Implications for Environmental Change?

Many populations of migratory songbirds are declining or shifting in distribution. This is likely due to environmental changes that alter factors such as food availability that may have an impact on survival and/or breeding success. We tested the impact of experimentally supplemented food on the breeding success over three years of northern wheatears (Oenanthe oenanthe), a species in decline over much of Europe. The number of offspring fledged over the season was higher for food-supplemented birds than for control birds. The mechanisms for this effect were that food supplementation advanced breeding date, which, together with increased resources, allowed further breeding attempts. While food supplementation did not increase the clutch size, hatching success or number of chicks fledged per breeding attempt, it did increase chick size in one year of the study. The increased breeding success was greater for males than females; males could attempt to rear simultaneous broods with multiple females as well as attempting second broods, whereas females could only increase their breeding effort via second broods. Multiple brooding is rare in the study population, but this study demonstrates the potential for changes in food availability to affect wheatear breeding productivity, primarily via phenotypic flexibility in the number of breeding attempts. Our results have implications for our understanding of how wheatears may respond to natural changes in food availability due to climate changes or changes in habitat management.     

Intelligent Bayes Classifier (IBC) for ENT infection classification in hospital environment

Electronic Nose based ENT bacteria identification in hospital environment is a classical and challenging problem of classification. In this paper an electronic nose (e-nose), comprising a hybrid array of 12 tin oxide sensors (SnO₂) and 6 conducting polymer sensors has been used to identify three species of bacteria, Escherichia coli (E. coli), Staphylococcus aureus (S. aureus), and Pseudomonas aeruginosa (P. aeruginosa) responsible for ear nose and throat (ENT) infections when collected as swab sample from infected patients and kept in ISO agar solution in the hospital environment. In the next stage a sub-classification technique has been developed for the classification of two different species of S. aureus, namely Methicillin-Resistant S. aureus (MRSA) and Methicillin Susceptible S. aureus (MSSA). An innovative Intelligent Bayes Classifier (IBC) based on "Baye's theorem" and "maximum probability rule" was developed and investigated for these three main groups of ENT bacteria. Along with the IBC three other supervised classifiers (namely, Multilayer Perceptron (MLP), Probabilistic neural network (PNN), and Radial Basis Function Network (RBFN)) were used to classify the three main bacteria classes. A comparative evaluation of the classifiers was conducted for this application. IBC outperformed MLP, PNN and RBFN. The best results suggest that we are able to identify and classify three bacteria main classes with up to 100% accuracy rate using IBC. We have also achieved 100% classification accuracy for the classification of MRSA and MSSA samples with IBC. We can conclude that this study proves that IBC based e-nose can provide very strong and rapid solution for the identification of ENT infections in hospital environment.     

Prediction of Higher Heating Value of Solid Biomass Fuels Using Artificial Intelligence Formalisms

The higher heating value (HHV) is an important property defining the energy content of biomass fuels. A number of proximate and/or ultimate analysis based predominantly linear correlations have been proposed for predicting the HHV of biomass fuels. A scrutiny of the relationships between the constituents of the proximate and ultimate analyses and the corresponding HHVs suggests that all relationships are not linear and thus nonlinear models may be more appropriate. Accordingly, a novel artificial intelligence (AI) formalism, namely genetic programming (GP) has been employed for the first time for developing two biomass HHV prediction models, respectively using the constituents of the proximate and ultimate analyses as the model inputs. The prediction and generalization performance of these models was compared rigorously with the corresponding multilayer perceptron (MLP) neural network based as also currently available high-performing linear and nonlinear HHV models. This comparison reveals that the HHV prediction performance of the GP and MLP models is consistently better than that of their existing linear and/or nonlinear counterparts. Specifically, the GP- and MLP-based models exhibit an excellent overall prediction accuracy and generalization performance with high (>0.95) magnitudes of the coefficient of correlation and low (<4.5 %) magnitudes of mean absolute percentage error in respect of the experimental and model-predicted HHVs. It is also found that the proximate analysis-based GP model has outperformed all the existing high-performing linear biomass HHV prediction models. In the case of ultimate analysis-based HHV models, the MLP model has exhibited best prediction accuracy and generalization performance when compared with the existing linear and nonlinear models. The AI-based models introduced in this paper due to their excellent performance have the potential to replace the existing biomass HHV prediction models.     

In silico prediction of splice-altering single nucleotide variants in the human genome

In silico tools have been developed to predict variants that may have an impact on pre-mRNA splicing. The major limitation of the application of these tools to basic research and clinical practice is the difficulty in interpreting the output. Most tools only predict potential splice sites given a DNA sequence without measuring splicing signal changes caused by a variant. Another limitation is the lack of large-scale evaluation studies of these tools. We compared eight in silico tools on 2959 single nucleotide variants within splicing consensus regions (scSNVs) using receiver operating characteristic analysis. The Position Weight Matrix model and MaxEntScan outperformed other methods. Two ensemble learning methods, adaptive boosting and random forests, were used to construct models that take advantage of individual methods. Both models further improved prediction, with outputs of directly interpretable prediction scores. We applied our ensemble scores to scSNVs from the Catalogue of Somatic Mutations in Cancer database. Analysis showed that predicted splice-altering scSNVs are enriched in recurrent scSNVs and known cancer genes. We pre-computed our ensemble scores for all potential scSNVs across the human genome, providing a whole genome level resource for identifying splice-altering scSNVs discovered from large-scale sequencing studies.     

Innate sex differences in the timing of spring migration in a songbird

In migrating animals protandry is the phenomenon whereby males of a species arrive at the breeding grounds earlier than females. In the present study we investigated the proximate causes of protandry in a migratory songbird, the northern wheatear Oenanthe oenanthe. Previous experiments with caged birds revealed that males and females show differentiated photoperiod-induced migratory habits. However, it remained open whether protandry would still occur without photoperiodic cues. In this study we kept captive first-year birds under constant photoperiod and environmental conditions in a "common garden" experiment. Male northern wheatears started their spring migratory activity earlier than females, even in the absence of environmental cues. This indicates that protandry in the northern wheatear has an endogenous basis with an innate earlier spring departure of males than females.     

Reweighting of molecular simulations with explicit-solvent SAXS restraints elucidates ion-dependent RNA ensembles

Small-angle X-ray scattering (SAXS) experiments are increasingly used to probe RNA structure. A number of forward models that relate measured SAXS intensities and structural features, and that are suitable to model either explicit-solvent effects or solute dynamics, have been proposed in the past years. Here, we introduce an approach that integrates atomistic molecular dynamics simulations and SAXS experiments to reconstruct RNA structural ensembles while simultaneously accounting for both RNA conformational dynamics and explicit-solvent effects. Our protocol exploits SAXS pure-solute forward models and enhanced sampling methods to sample an heterogenous ensemble of structures, with no information towards the experiments provided on-the-fly. The generated structural ensemble is then reweighted through the maximum entropy principle so as to match reference SAXS experimental data at multiple ionic conditions. Importantly, accurate explicit-solvent forward models are used at this reweighting stage. We apply this framework to the GTPase-associated center, a relevant RNA molecule involved in protein translation, in order to elucidate its ion-dependent conformational ensembles. We show that (a) both solvent and dynamics are crucial to reproduce experimental SAXS data and (b) the resulting dynamical ensembles contain an ion-dependent fraction of extended structures.     

A meta-learning approach for B-cell conformational epitope prediction

Background

One of the major challenges in the field of vaccine design is identifying B-cell epitopes in continuously evolving viruses. Various tools have been developed to predict linear or conformational epitopes, each relying on different physicochemical properties and adopting distinct search strategies. We propose a meta-learning approach for epitope prediction based on stacked and cascade generalizations. Through meta learning, we expect a meta learner to be able integrate multiple prediction models, and outperform the single best-performing model. The objective of this study is twofold: (1) to analyze the complementary predictive strengths in different prediction tools, and (2) to introduce a generic computational model to exploit the synergy among various prediction tools. Our primary goal is not to develop any particular classifier for B-cell epitope prediction, but to advocate the feasibility of meta learning to epitope prediction. With the flexibility of meta learning, the researcher can construct various meta classification hierarchies that are applicable to epitope prediction in different protein domains.

Results

We developed the hierarchical meta-learning architectures based on stacked and cascade generalizations. The bottom level of the hierarchy consisted of four conformational and four linear epitope prediction tools that served as the base learners. To perform consistent and unbiased comparisons, we tested the meta-learning method on an independent set of antigen proteins that were not used previously to train the base epitope prediction tools. In addition, we conducted correlation and ablation studies of the base learners in the meta-learning model. Low correlation among the predictions of the base learners suggested that the eight base learners had complementary predictive capabilities. The ablation analysis indicated that the eight base learners differentially interacted and contributed to the final meta model. The results of the independent test demonstrated that the meta-learning approach markedly outperformed the single best-performing epitope predictor.

Conclusions

Computational B-cell epitope prediction tools exhibit several differences that affect their performances when predicting epitopic regions in protein antigens. The proposed meta-learning approach for epitope prediction combines multiple prediction tools by integrating their complementary predictive strengths. Our experimental results demonstrate the superior performance of the combined approach in comparison with single epitope predictors.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0378-y) contains supplementary material, which is available to authorized users.     

A Statistical Comparison between Less and Common Applied Models to Estimate Geographical Distribution of Endangered Species (<Emphasis Type="Italic">Felis margarita</Emphasis>) in Central Iran

Species distribution in space is important in habitat conservation and biodiversity protection, so gaining knowledge about species range would be worthwhile to rescue endangered species and plan conservation policy. This study evaluates and compares the performance of an array of Species Distribution Models (SDMs), namely RF, SVM, MaxEnt, GLMNET, and MARS, in predicting rare sand cat distribution across a large unprotected sand dune area in central Iran. Due to absence of reliable data and difficulties in recording the species itself, the SDMs were challenged by limited data including 55 absence (background) and 40 presence points as well as nine climatic and geological parameters that influence on species distribution, including humidity, maximum, minimum and mean temperature, precipitation, amount of sunshine, ground water level, aspect, and DEM. Moreover, each model was replicated 20 times and the statistics including TSS, AUC, COR and Deviance were computed. Then, based on computed statistics, the model performances were evaluated by TUKEY and ANOVA. Finally, ensemble map was obtained by weighted approach using AUC. The results of this study showed that complex machine learning methods, like SVM, RF, and MaxEnt are more outperformed to predict the distribution of rare species.     

Assessing uncertainties in crop and pasture ensemble model simulations of productivity and N2O emissions

Simulation models are extensively used to predict agricultural productivity and greenhouse gas emissions. However, the uncertainties of (reduced) model ensemble simulations have not been assessed systematically for variables affecting food security and climate change mitigation, within multi‐species agricultural contexts. We report an international model comparison and benchmarking exercise, showing the potential of multi‐model ensembles to predict productivity and nitrous oxide (N₂O) emissions for wheat, maize, rice and temperate grasslands. Using a multi‐stage modelling protocol, from blind simulations (stage 1) to partial (stages 2–4) and full calibration (stage 5), 24 process‐based biogeochemical models were assessed individually or as an ensemble against long‐term experimental data from four temperate grassland and five arable crop rotation sites spanning four continents. Comparisons were performed by reference to the experimental uncertainties of observed yields and N₂O emissions. Results showed that across sites and crop/grassland types, 23%–40% of the uncalibrated individual models were within two standard deviations (SD) of observed yields, while 42 (rice) to 96% (grasslands) of the models were within 1 SD of observed N₂O emissions. At stage 1, ensembles formed by the three lowest prediction model errors predicted both yields and N₂O emissions within experimental uncertainties for 44% and 33% of the crop and grassland growth cycles, respectively. Partial model calibration (stages 2–4) markedly reduced prediction errors of the full model ensemble E‐median for crop grain yields (from 36% at stage 1 down to 4% on average) and grassland productivity (from 44% to 27%) and to a lesser and more variable extent for N₂O emissions. Yield‐scaled N₂O emissions (N₂O emissions divided by crop yields) were ranked accurately by three‐model ensembles across crop species and field sites. The potential of using process‐based model ensembles to predict jointly productivity and N₂O emissions at field scale is discussed.