Predictive performance of presence‐only species distribution models: a benchmark study with reproducible code

Ecological Monographs, Год журнала: 2021, Номер 92(1)

Опубликована: Окт. 8, 2021

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

Язык: Английский

---

Want to model a species niche? A step-by-step guideline on correlative ecological niche modelling

Ecological Modelling, Год журнала: 2021, Номер 456, С. 109671 - 109671

Опубликована: Июль 19, 2021

Язык: Английский

---

Integrating citizen science and spatial ecology to inform management and conservation of the Italian seahorses

Ecological Informatics, Год журнала: 2023, Номер 79, С. 102402 - 102402

Опубликована: Дек. 1, 2023

Citizen science and spatial ecology analyses can inform species distributions, habitat preferences, threats in elusive endangered such as seahorses. Through a dedicated citizen survey submitted to the Italian diving centers, we collected 115 presence records of two seahorses occurring along coasts: Hippocampus hippocampus H. guttulatus. From this dataset, used 85 seahorse valitaded identify ecological features these poorly known quantify effects human activities on their suitability through geographic information systems distribution modelling. Our results indicated continuous suitable area for both coasts, with single major gap central Adriatic Sea (Emilia-Romagna Marche regions). They co-occurred most range, particularly southern Tyrrhenian niches resulted be significantly similar, although not equivalent. The least-cost paths were concentrated Italy (Apulia, Calabria, Sicily), suggesting that more data is needed improve resolution available information, especially northern Italy. Human influenced 35% 41% guttulatus, respectively, while only 25% 30% potential are protected by Italy's existing conservation system, accordance global average In particular, represents critical where occurrence lower anthropic impact higher. Considering all regions, fishing effort main activity impacting species. These findings will support implementation efficient actions. We encourage application interaction facilitate assessment sustainable management organisms.

Язык: Английский

---

Top ten hazards to avoid when modeling species distributions: a didactic guide of assumptions, problems, and recommendations

Ecography, Год журнала: 2024, Номер 2024(4)

Опубликована: Янв. 31, 2024

Species distribution models, also known as ecological niche models or habitat suitability have become commonplace for addressing fundamental and applied biodiversity questions. Although the field has progressed rapidly regarding theory implementation, key assumptions are still frequently violated recommendations inadvertently overlooked. This leads to poor being published used in real‐world applications. In a structured, didactic treatment, we summarize what our view constitute ten most problematic issues, hazards, negatively affecting implementation of correlative approaches species modeling (specifically those that model by comparing environments species' occurrence records with background pseudoabsence sample). For each hazard, state relevant assumptions, detail problems arise when violating them, convey straightforward existing recommendations. We discuss five major outstanding questions active current research. hope this contribution will promote more rigorous these valuable stimulate further advancements.

Язык: Английский

---

Coastal Wetland Mapping Using Ensemble Learning Algorithms: A Comparative Study of Bagging, Boosting and Stacking Techniques

Remote Sensing, Год журнала: 2020, Номер 12(10), С. 1683 - 1683

Опубликована: Май 25, 2020

Coastal wetlands are a critical component of the coastal landscape that increasingly threatened by sea level rise and other human disturbance. Periodically mapping wetland distribution is crucial to ecosystem management. Ensemble algorithms (EL), such as random forest (RF) gradient boosting machine (GBM) algorithms, now commonly applied in field remote sensing. However, performance potential EL methods, extreme (XGBoost) bagged trees, rarely compared tested for mapping. In this study, we three most widely used techniques (i.e., bagging, stacking) map highly modified catchment, Manning River Estuary, Australia. Our results demonstrated advantages using ensemble classifiers accurately types landscape. Enhanced bagging decision i.e., with additional methods increasing diversity RF weighted subspace forest, had comparably high predictive power. For stacking method evaluated our inconclusive, further comprehensive quantitative study encouraged. findings also suggested were less effective at discriminating minority classes comparison more common classes. Finally, variable importance indicated hydro-geomorphic factors, tidal depth distance water edge, among influential variables across top classifiers. vegetation indices derived from longer time series sensing data arrest full features land phenology likely improve type separation areas.

Язык: Английский

---

ClimateEU, scale-free climate normals, historical time series, and future projections for Europe

Scientific Data, Год журнала: 2020, Номер 7(1)

Опубликована: Дек. 4, 2020

Abstract Interpolated climate data have become essential for regional or local change impact assessments and the development of adaptation strategies. Here, we contribute an accessible, comprehensive database interpolated Europe that includes monthly, annual, decadal, 30-year normal last 119 years (1901 to 2019) as well multi-model CMIP5 projections 21 st century. The also variables relevant ecological research infrastructure planning, comprising more than 20,000 grids can be queried with a provided ClimateEU software package. In addition, 1 km 2.5 resolution gridded generated by are available download. quality estimates was evaluated against weather station representative subset variables. Dynamic environmental lapse rate algorithms employed generate scale-free specific locations lead improvements 10 50% in accuracy compared data. We conclude discussion applications limitations this database.

Язык: Английский

---

Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage

Scientific Reports, Год журнала: 2021, Номер 11(1)

Опубликована: Янв. 15, 2021

Abstract We examine how different datasets, including georeferenced hardcopy maps of extents and herbarium specimens (spanning the range from 100 to 85,000 km 2 ) influence ecological niche modeling. check 13 available environmental modeling algorithms, using 30 metrics score their validity evaluate which are useful for selection best model. The validation is made an independent dataset comprised presences absences collected in a range-wide field survey Carpathian endemic plant Leucanthemum rotundifolium (Compositae). Our analysis models’ predictive performances indicates that almost all datasets may be used construction species distributional range. Both very local general can produce predictions, more detailed than original ranges. Results also highlight possibility data manually archival sources reconstructions aimed at establishing species’ niches. discuss possible applications those associated problems. For evaluation models, we suggest employing AUC, MAE, Bias. show example AUC MAE combined select model with performance.

Язык: Английский

---

Sampling and modelling rare species: Conceptual guidelines for the neglected majority

Global Change Biology, Год журнала: 2022, Номер 28(12), С. 3754 - 3777

Опубликована: Янв. 31, 2022

Biodiversity conservation faces a methodological conundrum: measurement often relies on species, most of which are rare at various scales, especially prone to extinction under global change, but also the challenging sample and model. Predicting distribution change species using conventional models is because hardly captured by survey systems. When enough data available, predictions usually spatially biased towards locations where likely occur, violating assumptions many modelling frameworks. Workflows predict eventually map distributions imply important trade-offs between quantity, quality, representativeness model complexity that need be considered prior analysis. Our opinion study designs carefully integrate different steps, from sampling modelling, in accordance with types rarity available order improve our capacity for sound assessment prediction distribution. In this article, we summarize comment how categories lead occurrence depending choices made during process, namely spatial samples (where sample) protocol each selected location (how sample). We then clarify suitable model). Among others, forms, highlight insights systematic species-targeted coupled hierarchical allow correcting overdispersion sources bias. article provides scientists practitioners much-needed guide through ever-increasing diversity developments type data.

Язык: Английский

---

Forest tree species distribution for Europe 2000–2020: mapping potential and realized distributions using spatiotemporal machine learning

PeerJ, Год журнала: 2022, Номер 10, С. e13728 - e13728

Опубликована: Июль 25, 2022

This article describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species ( Abies alba Mill., Castanea sativa Corylus avellana L., Fagus sylvatica Olea europaea Picea abies L. H. Karst., Pinus halepensis nigra J. F. Arnold, pinea sylvestris Prunus avium Quercus cerris ilex robur suber and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data total of three million points was used train different algorithms: random forest, gradient-boosted trees, generalized linear models, k-nearest neighbors, CART an artificial neural network. A stack 305 coarse covariates representing spectral reflectance, biophysical conditions biotic competition as predictors realized distributions, while potential modelled with environmental only. Logloss computing time were select the best algorithms tune ensemble model stacking logistic regressor meta-learner. An trained each species: probability uncertainty produced using window 4 years six per species, distributions only one map produced. Results cross validation show that consistently outperformed or performed good individual in both tasks, models achieving higher predictive performances (TSS = 0.898, R 2 logloss 0.857) than ones average 0.874, 0.839). Ensemble Q. achieved 0.968, 0.952) 0.959, 0.949) distribution, P. 0.731, 0.785, 0.585, 0.670, respectively, distribution) 0.658, 0.686, 0.623, 0.664) worst. Importance predictor variables differed across green band summer Normalized Difference Vegetation Index (NDVI) fall diffuse irradiation precipitation driest quarter (BIO17) being most frequent important distribution. On average, fine-resolution (250 m) +6.5%, +7.5%). The shows how combining continuous consistent Earth Observation series state art can be derive dynamic maps. predictions quantify temporal trends forest degradation composition change.

Язык: Английский

---

Identifying climate refugia for high‐elevation Alpine birds under current climate warming predictions

Global Change Biology, Год журнала: 2022, Номер 28(14), С. 4276 - 4291

Опубликована: Апрель 20, 2022

Abstract Identifying climate refugia is key to effective biodiversity conservation under a changing climate, especially for mountain‐specialist species adapted cold conditions and highly threatened by warming. We combined distribution models (SDMs) with forecasts identify high‐elevation bird ( Lagopus muta , Anthus spinoletta Prunella collaris Montifringilla nivalis ) in the European Alps, where ecological effects of changes are particularly evident predicted intensify. considered future (2041–2070) (SSP585 scenario, four models) identified three types refugia: (1) in‐situ potentially suitable both current conditions, ex‐situ (2) only according all or (3) at least out conditions. SDMs were based on very large, high‐resolution occurrence dataset (2901–12,601 independent records each species) collected citizen scientists. fitted using different algorithms, balancing statistical accuracy, realism predictive/extrapolation ability. selected most reliable ones consistency between training testing data extrapolation over distant areas. Future predictions revealed that (with partial exception A. will undergo range contraction towards higher elevations, losing 17%–59% their (larger losses L. ). ~15,000 km 2 Alpine region as species, which 44% currently designated protected areas (PAs; 18%–66% among countries). Our findings highlight usefulness spatially accurate scientists, importance model extrapolating Climate refugia, partly included within PAs system, should be priority sites habitats, habitat degradation/alteration human activities prevented ensure suitability alpine species.

Язык: Английский

---