Comparing machine learning classifiers in potential distribution modelling

Species` potential distribution modelling consists of building a representation of the fundamental ecological requirements of a species from biotic and abiotic conditions where the species is known to occur. Such models can be valuable tools to understand the biogeography of species and to support the prediction of its presence/absence considering a particular environment scenario. This paper investigates the use of different supervised machine learning techniques to model the potential distribution of 35 plant species from Latin America. Each technique was able to extract a different representation of the relations between the environmental conditions and the distribution profile of the species. The experimental results highlight the good performance of random trees classifiers, indicating this particular technique as a promising candidate for modelling species` potential distribution. (C) 2010 Elsevier Ltd. All rights reserved.

Implementing new northernmost records to modelling the distribution of Hypsiboas caingua (Anura: Hylidae) in South America

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Using individual tracking data to validate the predictions of species distribution models

The authors would like to thank the College of Life Sciences of Aberdeen University and Marine Scotland Science which funded CP's PhD project. Skate tagging experiments were undertaken as part of Scottish Government project SP004. We thank Ian Burrett for help in catching the fish and the other fishermen and anglers who returned tags. We thank José Manuel Gonzalez-Irusta for extracting and making available the environmental layers used as environmental covariates in the environmental suitability modelling procedure. We also thank Jason Matthiopoulos for insightful suggestions on habitat utilization metrics as well as Stephen C.F. Palmer, and three anonymous reviewers for useful suggestions to improve the clarity and quality of the manuscript.

Data to Decision in a Dynamic Ocean: Robust Species Distribution Models and Spatial Decision Frameworks

Human use of the oceans is increasingly in conflict with conservation of endangered species. Methods for managing the spatial and temporal placement of industries such as military, fishing, transportation and offshore energy, have historically been post hoc; i.e. the time and place of human activity is often already determined before assessment of environmental impacts. In this dissertation, I build robust species distribution models in two case study areas, US Atlantic (Best et al. 2012) and British Columbia (Best et al. 2015), predicting presence and abundance respectively, from scientific surveys. These models are then applied to novel decision frameworks for preemptively suggesting optimal placement of human activities in space and time to minimize ecological impacts: siting for offshore wind energy development, and routing ships to minimize risk of striking whales. Both decision frameworks relate the tradeoff between conservation risk and industry profit with synchronized variable and map views as online spatial decision support systems.

For siting offshore wind energy development (OWED) in the U.S. Atlantic (chapter 4), bird density maps are combined across species with weights of OWED sensitivity to collision and displacement and 10 km2 sites are compared against OWED profitability based on average annual wind speed at 90m hub heights and distance to transmission grid. A spatial decision support system enables toggling between the map and tradeoff plot views by site. A selected site can be inspected for sensitivity to a cetaceans throughout the year, so as to capture months of the year which minimize episodic impacts of pre-operational activities such as seismic airgun surveying and pile driving.

Routing ships to avoid whale strikes (chapter 5) can be similarly viewed as a tradeoff, but is a different problem spatially. A cumulative cost surface is generated from density surface maps and conservation status of cetaceans, before applying as a resistance surface to calculate least-cost routes between start and end locations, i.e. ports and entrance locations to study areas. Varying a multiplier to the cost surface enables calculation of multiple routes with different costs to conservation of cetaceans versus cost to transportation industry, measured as distance. Similar to the siting chapter, a spatial decisions support system enables toggling between the map and tradeoff plot view of proposed routes. The user can also input arbitrary start and end locations to calculate the tradeoff on the fly.

Essential to the input of these decision frameworks are distributions of the species. The two preceding chapters comprise species distribution models from two case study areas, U.S. Atlantic (chapter 2) and British Columbia (chapter 3), predicting presence and density, respectively. Although density is preferred to estimate potential biological removal, per Marine Mammal Protection Act requirements in the U.S., all the necessary parameters, especially distance and angle of observation, are less readily available across publicly mined datasets.

In the case of predicting cetacean presence in the U.S. Atlantic (chapter 2), I extracted datasets from the online OBIS-SEAMAP geo-database, and integrated scientific surveys conducted by ship (n=36) and aircraft (n=16), weighting a Generalized Additive Model by minutes surveyed within space-time grid cells to harmonize effort between the two survey platforms. For each of 16 cetacean species guilds, I predicted the probability of occurrence from static environmental variables (water depth, distance to shore, distance to continental shelf break) and time-varying conditions (monthly sea-surface temperature). To generate maps of presence vs. absence, Receiver Operator Characteristic (ROC) curves were used to define the optimal threshold that minimizes false positive and false negative error rates. I integrated model outputs, including tables (species in guilds, input surveys) and plots (fit of environmental variables, ROC curve), into an online spatial decision support system, allowing for easy navigation of models by taxon, region, season, and data provider.

For predicting cetacean density within the inner waters of British Columbia (chapter 3), I calculated density from systematic, line-transect marine mammal surveys over multiple years and seasons (summer 2004, 2005, 2008, and spring/autumn 2007) conducted by Raincoast Conservation Foundation. Abundance estimates were calculated using two different methods: Conventional Distance Sampling (CDS) and Density Surface Modelling (DSM). CDS generates a single density estimate for each stratum, whereas DSM explicitly models spatial variation and offers potential for greater precision by incorporating environmental predictors. Although DSM yields a more relevant product for the purposes of marine spatial planning, CDS has proven to be useful in cases where there are fewer observations available for seasonal and inter-annual comparison, particularly for the scarcely observed elephant seal. Abundance estimates are provided on a stratum-specific basis. Steller sea lions and harbour seals are further differentiated by ‘hauled out’ and ‘in water’. This analysis updates previous estimates (Williams & Thomas 2007) by including additional years of effort, providing greater spatial precision with the DSM method over CDS, novel reporting for spring and autumn seasons (rather than summer alone), and providing new abundance estimates for Steller sea lion and northern elephant seal. In addition to providing a baseline of marine mammal abundance and distribution, against which future changes can be compared, this information offers the opportunity to assess the risks posed to marine mammals by existing and emerging threats, such as fisheries bycatch, ship strikes, and increased oil spill and ocean noise issues associated with increases of container ship and oil tanker traffic in British Columbia’s continental shelf waters.

Starting with marine animal observations at specific coordinates and times, I combine these data with environmental data, often satellite derived, to produce seascape predictions generalizable in space and time. These habitat-based models enable prediction of encounter rates and, in the case of density surface models, abundance that can then be applied to management scenarios. Specific human activities, OWED and shipping, are then compared within a tradeoff decision support framework, enabling interchangeable map and tradeoff plot views. These products make complex processes transparent for gaming conservation, industry and stakeholders towards optimal marine spatial management, fundamental to the tenets of marine spatial planning, ecosystem-based management and dynamic ocean management.

Applying fuzzy logic to comparative distribution modelling: a case study with two sympatric amphibians.

We modelled the distributions of two toads (Bufo bufo and Epidalea calamita) in the Iberian Peninsula using the favourability function, which makes predictions directly comparable for different species and allows fuzzy logic operations to relate different models. The fuzzy intersection between individual models, representing favourability for the presence of both species simultaneously, was compared with another favourability model built on the presences shared by both species. The fuzzy union between individual models, representing favourability for the presence of any of the two species, was compared with another favourabilitymodel based on the presences of either or both of them. The fuzzy intersections between favourability for each species and the complementary of favourability for the other (corresponding to the logical operation “A and not B”) were compared with models of exclusive presence of one species versus the exclusive presence of the other. The results of modelling combined species data were highly similar to those of fuzzy logic operations between individual models, proving fuzzy logic and the favourability function valuable for comparative distribution modelling. We highlight several advantages of fuzzy logic over other forms of combining distribution models, including the possibility to combine multiple species models for management and conservation planning.

New status, species, distribution records and phylogeny for Australian mandibulate Chironomidae (Diptera)

All life-history stages of the Australian Podonominae (Chironomidae) genus Archaeochlus Brundin are revised, providing evidence for recognition of a separate clade, named here as Austrochlus Cranston. Based on molecular and morphological evidence, the clade contains two additional species: Austrochlus parabrundini Cranston, Edward and Cook sp. n. is described from Western Australia where its granite outcrop seepage habitat and geographical range is almost identical to that of the type species Austrochlus brundini Cranston, Edward and Colless (n. comb); Austrochlus centralaustralis Cranston, Edward and Cook sp. n. is described from ephemeral seepage/flows in the MacDonnell and James Ranges of central Australia. Molecular studies reported here confirm species distinctions, relationships to African taxa, and basal relationships within the Chironomidae. Modelled distributions provide evidence for range restriction by seasonal rainfall patterns.

Candidemia in a Brazilian tertiary care hospital: species distribution and antifungal susceptibility patterns

Recent studies have shown differences in the epidemiology of invasive infections caused by Candida species worldwide. In the period comprising August 2002 to August 2003, we performed a study in Santa Casa Complexo Hospitalar, Brazil, to determine Candida species distribution associated with candidemia and their antifungal susceptibility profiles to amphotericin B, fluconazole and itraconazole. Antifungal susceptibility was tested according to the broth microdilution method described in the NCCLS (M27A-2 method). Only one sample from each patient was analyzed (the first isolate). Most of the episodes had been caused by species other than C. albicans (51.6%), including C. parapsilosis (25.8%), C. tropicalis (13.3%), C. glabrata (3.3%), C. krusei (1.7%), and others (7.5%). Dose-dependent susceptibility to itraconazole was observed in 14.2% of strains, and dose-dependent susceptibility to fluconazole was found in 1.6%. Antifungal resistance was not found, probably related to low use of fluconazole. Further epidemiological surveillance is needed.

Candida esophagitis: species distribution and risk factors for infection

Although Candida albicans is the main cause of fungal esophagitis, other species such as C. tropicalis, C. krusei and C. stellatoidea have also been implicated. Several studies have identified risk factors for C. albicans esophagitis. However, data for non-C. albicans species is still sparse. The aim of this study was to determine the etiology of Candida esophagitis in our medical centre over an 18-month period. Additionally, we aimed to investigate predisposing conditions for esophageal candidosis caused by different Candida species. A total of 21,248 upper gastroscopies were performed in Santa Casa Complexo Hospitalar between January 2005 and July 2006. The prevalence of Candida esophagitis was 0.74% (n = 158). C. albicans caused the vast majority of infections (96.2%), followed by C. tropicalis (2.5%), C. lusitaniae (0.6%) and C. glabrata (0.6%). There were 81 women (51.3%) and 77 men (48.7%). No case of mixed infection occurred. Concomitant oral candidosis was documented for 10.8% (n = 17). Most of cases (55.1%) involved outpatients. Around one fifth of patients in our cohort had no identifiable risk factors for esophageal candidosis (20.8%). Since nearly all infections were caused by C. albicans we were not able to determine risk factors for esophagitis caused by other Candida species.

Species distribution and in vitro fluconazole susceptibility of clinical Candida isolates in a Brazilian tertiary-care hospital over a 3-year period

INTRODUCTION: In this study, we aimed at identifying Candida isolates obtained from blood, urine, tracheal secretion, and nail/skin lesions from cases attended at the Hospital Universitário de Londrina over a 3-year period and at evaluating fluconazole susceptibilities of the isolates. METHODS: Candida isolates were identified by polymerase chain reaction (PCR) using species-specific forward primers. The in vitro fluconazole susceptibility test was performed according to EUCAST-AFST reference procedure. RESULTS: Isolates were obtained from urine (53.4%), blood cultures (19.2%), tracheal secretion (17.8%), and nail/skin lesions (9.6%). When urine samples were considered, prevalence was similar in women (45.5%) and in men (54.5%) and was high in the age group >61 years than that in younger ones. For blood samples, prevalence was high in neonates (35%) and advanced ages (22.5%). For nail and skin samples, prevalence was higher in women (71.4%) than in men (28.6%). Candida albicans was the most frequently isolated in the hospital, but Candida species other than C. albicans accounted for 64% of isolates, including predominantly Candida tropicalis (33.2%) and Candida parapsilosis (19.2%). The trend for non-albicans Candida as the predominant species was noted from all clinical specimens, except from urine samples. All Candida isolates were considered susceptible in vitro to fluconazole with the exception of isolates belonging to the intrinsically less-susceptible species C. glabrata. CONCLUSIONS: Non-albicans Candida species were more frequently isolated in the hospital. Fluconazole resistance was a rare finding in our study.

Cross-scale determinants of palm species distribution

We investigate palm species distribution, richness and abundance along the Mokoti, a seasonally-dry river of southeastern Amazon and compare it to the patterns observed at a large scale, comprising the entire Brazilian territory. A total of 694 palms belonging to 10 species were sampled at the Mokoti River basin. Although the species showed diverse distribution patterns, we found that local palm abundance, richness and tree basal area were significantly higher from the hills to the bottomlands of the study region, revealing a positive association of these measures with moisture. The analyses at the larger spatial scale also showed a strong influence of vapor pressure (a measure of moisture content of the air, in turn modulated by temperature) and seasonality in temperature: the richest regions were those where temperature and humidity were simultaneously high, and which also presented a lower degree of seasonality in temperature. These results indicate that the distribution of palms seems to be strongly associated with climatic variables, supporting the idea that, by 'putting all the eggs in one basket' (a consequence of survival depending on the preservation of a single irreplaceable bud), palms have become vulnerable to extreme environmental conditions. Hence, their distribution is concentrated in those tropical and sub-tropical regions with constant conditions of (mild to high) temperature and moisture all year round.

Libellulidae (Insecta: Odonata) from Itapiracó reserve, Maranhão, Brazil: new records and species distribution information

In this work, I apply a simple protocol to species occurrence inventory of Odonata in a region of Maranhão state which has very few distributional records. Some relations between species occurrence and environmental characteristics are discussed, mainly in relation to the high occurrence of Erythemis. Eighteen new records are presented discussing the role of this approach to generate useful information for conservation purposes.

Species distribution models reveal apparent competitive and facilitative effects of a dominant species on the distribution of tundra plants

Abiotic factors are considered strong drivers of species distribution and assemblages. Yet these spatial patterns are also influenced by biotic interactions. Accounting for competitors or facilitators may improve both the fit and the predictive power of species distribution models (SDMs). We investigated the influence of a dominant species, Empetrum nigrum ssp. hermaphroditum, on the distribution of 34 subordinate species in the tundra of northern Norway. We related SDM parameters of those subordinate species to their functional traits and their co-occurrence patterns with E. hermaphroditum across three spatial scales. By combining both approaches, we sought to understand whether these species may be limited by competitive interactions and/or benefit from habitat conditions created by the dominant species. The model fit and predictive power increased for most species when the frequency of occurrence of E. hermaphroditum was included in the SDMs as a predictor. The largest increase was found for species that 1) co-occur most of the time with E. hermaphroditum, both at large (i.e. 750 m) and small spatial scale (i.e. 2 m) or co-occur with E. hermaphroditum at large scale but not at small scale and 2) have particularly low or high leaf dry matter content (LDMC). Species that do not co-occur with E. hermaphroditum at the smallest scale are generally palatable herbaceous species with low LDMC, thus showing a weak ability to tolerate resource depletion that is directly or indirectly induced by E. hermaphroditum. Species with high LDMC, showing a better aptitude to face resource depletion and grazing, are often found in the proximity of E. hermaphroditum. Our results are consistent with previous findings that both competition and facilitation structure plant distribution and assemblages in the Arctic tundra. The functional and co-occurrence approaches used were complementary and provided a deeper understanding of the observed patterns by refinement of the pool of potential direct and indirect ecological effects of E. hermaphroditum on the distribution of subordinate species. Our correlative study would benefit being complemented by experimental approaches.

Predicting the impacts of climate change on genetic diversity in an endangered lizard species.

Many endangered species persist as a series of isolated populations, with some populations more genetically diverse than others. If climate change disproportionately threatens the most diverse populations, the species' ability to adapt (and hence its long-term viability) may be affected more severely than would be apparent by its numerical reduction. In the present study, we combine genetic data with modelling of species distributions under climate change to document this situation in an endangered lizard (Eulamprus leuraensis) from montane southeastern Australia. The species is known from only about 40 isolated swamps. Genetic diversity of lizard populations is greater in some sites than others, presumably reflecting consistently high habitat suitability over evolutionary time. Species distribution modelling suggests that the most genetically diverse populations are the ones most at risk from climate change, so that global warming will erode the species' genetic variability faster than it curtails the species' geographic distribution.

Evaluating the influence of spatial uncertainty in locality points for species distributional modeling

1. Species distribution modelling is used increasingly in both applied and theoretical research to predict how species are distributed and to understand attributes of species' environmental requirements. In species distribution modelling, various statistical methods are used that combine species occurrence data with environmental spatial data layers to predict the suitability of any site for that species. While the number of data sharing initiatives involving species' occurrences in the scientific community has increased dramatically over the past few years, various data quality and methodological concerns related to using these data for species distribution modelling have not been addressed adequately. 2. We evaluated how uncertainty in georeferences and associated locational error in occurrences influence species distribution modelling using two treatments: (1) a control treatment where models were calibrated with original, accurate data and (2) an error treatment where data were first degraded spatially to simulate locational error. To incorporate error into the coordinates, we moved each coordinate with a random number drawn from the normal distribution with a mean of zero and a standard deviation of 5 km. We evaluated the influence of error on the performance of 10 commonly used distributional modelling techniques applied to 40 species in four distinct geographical regions. 3. Locational error in occurrences reduced model performance in three of these regions; relatively accurate predictions of species distributions were possible for most species, even with degraded occurrences. Two species distribution modelling techniques, boosted regression trees and maximum entropy, were the best performing models in the face of locational errors. The results obtained with boosted regression trees were only slightly degraded by errors in location, and the results obtained with the maximum entropy approach were not affected by such errors. 4. Synthesis and applications. To use the vast array of occurrence data that exists currently for research and management relating to the geographical ranges of species, modellers need to know the influence of locational error on model quality and whether some modelling techniques are particularly robust to error. We show that certain modelling techniques are particularly robust to a moderate level of locational error and that useful predictions of species distributions can be made even when occurrence data include some error.

What do we gain from simplicity versus complexity in species distribution models?

Species distribution models (SDMs) are widely used to explain and predict species ranges and environmental niches. They are most commonly constructed by inferring species' occurrence-environment relationships using statistical and machine-learning methods. The variety of methods that can be used to construct SDMs (e.g. generalized linear/additive models, tree-based models, maximum entropy, etc.), and the variety of ways that such models can be implemented, permits substantial flexibility in SDM complexity. Building models with an appropriate amount of complexity for the study objectives is critical for robust inference. We characterize complexity as the shape of the inferred occurrence-environment relationships and the number of parameters used to describe them, and search for insights into whether additional complexity is informative or superfluous. By building 'under fit' models, having insufficient flexibility to describe observed occurrence-environment relationships, we risk misunderstanding the factors shaping species distributions. By building 'over fit' models, with excessive flexibility, we risk inadvertently ascribing pattern to noise or building opaque models. However, model selection can be challenging, especially when comparing models constructed under different modeling approaches. Here we argue for a more pragmatic approach: researchers should constrain the complexity of their models based on study objective, attributes of the data, and an understanding of how these interact with the underlying biological processes. We discuss guidelines for balancing under fitting with over fitting and consequently how complexity affects decisions made during model building. Although some generalities are possible, our discussion reflects differences in opinions that favor simpler versus more complex models. We conclude that combining insights from both simple and complex SDM building approaches best advances our knowledge of current and future species ranges.