scholarly journals МОДЕЛИ МАКСИМАЛЬНОЙ ЭНТРОПИИ И ПРОСТРАНСТВЕННОЕ РАСПРЕДЕЛЕНИЕ ВИДОВ ДОННЫХ СООБЩЕСТВ НА ТЕРРИТОРИИ СРЕДНЕГО И НИЖНЕГО ПОВОЛЖЬЯ

2021 ◽  
pp. 10-16
Author(s):  
Владимир Кириллович Шитиков ◽  
Татьяна Дмитриевна Зинченко ◽  
Лариса Владимировна Головатюк
Keyword(s):  
Maximum Entropy ◽  
Species Distribution ◽  
Ecological Modelling ◽  
Geographical Information ◽  
Latitudinal Gradients ◽  
Ecological Niches ◽  
Distribution Models ◽  
Zonal Distribution ◽  
Cambridge University ◽  
Geographic Distributions

Представлены результаты применения метода максимальной энтропии (MaxEnt) для моделирования пространственного распределения видов макрозообентоса на территории Среднего и Нижнего Поволжья. Использовались данные гидробиологического мониторинга многолетних (1990-2019 гг.) исследований донных сообществ в 108 средних и малых реках. В качестве независимых переменных, отражающих условия среды, построенные модели включали климатические и ландшафтные показатели растрового типа, загружаемые с сервера WorldClim (средние температуры, количество осадков, высота и вертикальная расчлененность рельефа). Приводятся результаты тестирования качества и прогнозирующей силы моделей, а также статистические показатели относительной важности каждого из использованных абиотических факторов. Обсуждаются проблемы использования различных алгоритмов построения моделей пространственного распределения видов применительно к данным гидробиологических наблюдений пресноводных лотических экосистем. Библиографические ссылки 1. Зинченко Т.Д. Эколого-фаунистическая характеристика хирономид (Diptera, Chhironomidae) малых рек бассейна Cредней и Нижней Волги (Атлас). Тольятти: Кассандра, 2011. 258 с. 2. Лисовский А.А., Дудов С.В., Оболенская Е.В. Преимущества и ограничения использования методов экологического моделирования ареалов. 1. Общие подходы // Журнал общей биологии. 2020. Т. 81. №2. С. 123–134. 3. Лисовский А.А., Дудов С.В. Преимущества и ограничения использования методов экологического моделирования ареалов. 2. MaxEnt // Журнал общей биологии. 2020а. Т. 81. №2. С. 135–146. 4. Монаков А.В. Питание пресноводных беспозвоночных / Под ред. А.А. Стрелкова. М., 1998. 218 с. 5. Шитиков В.К., Зинченко Т.Д. Статистический анализ структурной изменчивости донных сообществ и проверка гипотезы речного континуума // Водные ресурсы. 2014. Т. 41, №5. С. 530–540. 6. Шитиков В.К., Мастицкий С.Э. Классификация, регрессия и другие алгоритмы Data Mining с использованием R. Электронная книга. 2017. 351 с. URL: https://stok1946.blogspot.com (Дата обращения 10.10.2020). 7. Franklin J. Mapping Species distributions: spatial inference and prediction. Cambridge: Cambridge University Press, 2009. 320 p. 8. García-Roselló E., Guisande C., Heine J., Pelayo-Villamil P., Manjarrés-Hernández A., González-Vilas L., González‐Dacosta J., Vaamonde A., Granado‐Lorencio C. Using MODESTR to download, import and clean species distribution records // Methods in ecology and evolution. 2014. V. 5. P. 703–713. DOI: 10.1111/2041-210X.12209 9. Golovatyuk L.V., Shitikov V.K., Zinchenko T.D. Estimation of the zonal distribution of species of bottom communities in lowland rivers of the middle and Lower Volga basin // Biology bulletin. 2018. V. 45 (10). Р. 1262–1268. 10. González-Vilas L., Guisande C., Vari R., Pelayo-Villamil P., Manjarrés-Hernández A., García-Roselló E., González-Dacostae J., Heinee J., Pérez-Costasa E., Granado-Lorenciof C., Palau-Ibarsg A., Loboh J.M. Geospatial data of freshwater habitats for macroecological studies: an example with freshwater fishes // International journal of geographical information science. 2015. V.30, Iss.1, P. 126-141. DOI: 10.1080/13658816.2015.1072629 11. Guisan A., Thuiller W., Zimmermann N.E. Habitat suitability and distribution models: with applications in R. Cambridge: Cambridge University Press, 2017. 478 p. 12. Guisande C., Garcia-Rosello E., Heine J., Gonzalez-Dacosta J., Gonzalez-Vilas L., Garcia-Perez B., Lobo J.M. SPEDInstabR: an algorithm based on a fluctuation index for selecting predictors in species distribution modeling // Ecological Informatics. 2017. V. 37. P. 18–23. 13. Harte J. Maximum entropy and ecology: a theory of abundance, distribution, and energetics. London: Oxford University Press, 2011. 257 p. 14. Hastie T., Fithian W. Inference from controversy // Ecography. 2013. V. 36. P. 864–867. 15. Hijmans R.J., Cameron S.E., Parra J.L., Jones P.G., JarvisA. Very high resolution interpolated climate surfaces for global land areas // International journal of climatology. 2005. V. 25. P. 1965‒1978. 16. Johnson D.H. The Comparison of usage and availability measurements for evaluating resource preference // Ecology. 1980. V. 61, N 1. P. 65‒71. 17. Koleff P., Gaston K.J. Latitudinal gradients in diversity: real patterns and random models // Ecography. 2001. V. 24. Р. 341–351. 18. Manni F., Guerard E., Heyer E. Geographic patterns of (genetic, morphologic, linguistic) variation: how barriers can be detected by using Monmonier’s algorithm // Human biology. 2004. V. 76, №2. Р. 173‒190. 19. Norberg A., Abrego N., Blanchet F.G., Adler F.R., Anderson B.J. et al. A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels // Ecological monographs. 2019. V. 89, №3. P. e01370. 20. Peterson A.T., Soberón J., Pearson R.G., Anderson R.P., Martínez-Meyer E, Nakamura M., Araújo M.B. Ecological niches and geographic distributions (MPB-49). Princeton: Princeton Univ. Press, 2011. 328 p. 21. Phillips S.J., Anderson R.P., Schapire R.E. Maximum entropy modeling of species geographic distributions // Ecological modelling. 2006. V. 190, №3–4. P. 231–259.

Introduction

2011 ◽  
Author(s):  
A. Townsend Peterson ◽  
Jorge Soberón ◽  
Richard G. Pearson ◽  
Robert P. Anderson ◽  
Enrique Martínez-Meyer ◽  
...  
Keyword(s):  
Conceptual Framework ◽  
Species Distribution ◽  
Ecological Niche ◽  
Ecological Niche Modeling ◽  
Species Distribution Modeling ◽  
Niche Modeling ◽  
Ecological Niches ◽  
Distribution Modeling ◽  
Geographic Distributions ◽  
Complex Relationships

This book deals with ecological niche modeling and species distribution modeling, two emerging fields that address the ecological, geographic, and evolutionary dimensions of geographic distributions of species. It provides a conceptual overview of the complex relationships between ecological niches and geographic distributions of species, both across space and (perhaps to a lesser degree) through time. The emphasis is on how that conceptual framework relates to ecological niche modeling and species distribution modeling, which the book argues are complementary and are most broadly applicable to diverse questions regarding the ecology and geography of biodiversity phenomena. Part I of the book introduces the conceptual framework for thinking about and discussing the distributional ecology of species, Part II is concerned with the data and tools that have been used in the early development of the field, and Part III focuses on real-world situations to which these tools have been applied.

Understanding the ecological niche to elucidate spatial strategies of the southernmost Tupinambis lizards

2013 ◽  
Vol 34 (4) ◽  
pp. 551-565 ◽  
Author(s):  
Sofía Lanfri ◽  
Valeria Di Cola ◽  
Sergio Naretto ◽  
Margarita Chiaraviglio ◽  
Gabriela Cardozo
Keyword(s):  
Species Distribution ◽  
Evolutionary Biology ◽  
Species Distribution Models ◽  
Regional Scale ◽  
Distribution Patterns ◽  
Niche Differentiation ◽  
Ecological Niches ◽  
Distribution Models ◽  
Interspecific Differences ◽  
Spatial Strategies

Understanding factors that shape ranges of species is central in evolutionary biology. Species distribution models have become important tools to test biogeographical, ecological and evolutionary hypotheses. Moreover, from an ecological and evolutionary perspective, these models help to elucidate the spatial strategies of species at a regional scale. We modelled species distributions of two phylogenetically, geographically and ecologically close Tupinambis species (Teiidae) that occupy the southernmost area of the genus distribution in South America. We hypothesized that similarities between these species might have induced spatial strategies at the species level, such as niche differentiation and divergence of distribution patterns at a regional scale. Using logistic regression and MaxEnt we obtained species distribution models that revealed interspecific differences in habitat requirements, such as environmental temperature, precipitation and altitude. Moreover, the models obtained suggest that although the ecological niches of Tupinambis merianae and T. rufescens are different, these species might co-occur in a large contact zone. We propose that niche plasticity could be the mechanism enabling their co-occurrence. Therefore, the approach used here allowed us to understand the spatial strategies of two Tupinambis lizards at a regional scale.

Niches and Geographic Distributions

2011 ◽  
Author(s):  
A. Townsend Peterson ◽  
Jorge Soberón ◽  
Richard G. Pearson ◽  
Robert P. Anderson ◽  
Enrique Martínez-Meyer ◽  
...  
Keyword(s):  
Population Growth ◽  
Spatial Resolution ◽  
Species Distribution ◽  
Growth Patterns ◽  
Venn Diagram ◽  
Ecological Niches ◽  
Abiotic Conditions ◽  
Geographic Space ◽  
Natural Connection ◽  
Geographic Distributions

This chapter considers a concept of niche that emphasizes multidimensional spaces of scenopoetic variables and provides a natural connection to the study of geographic distributions of species. It first explains the relations between environmental and geographic spaces before discussing the use of equations to link spatially explicit population growth patterns to variation in the ecological characteristics of species. It then describes the BAM diagram, a Venn diagram that displays the joint fulfillment in geographic space of three sets of conditions that together determine species distribution: biotic conditions, abiotic conditions, and movement of the species. The chapter also explores the spatial resolution of scenopoetic variables, estimation of the fundamental and existing fundamental niches, the biotically reduced niche, and caveats about reducing Grinnellian niches and the Eltonian Noise Hypothesis. Finally, it shows how distributional areas and ecological niches can be estimated.

scholarly journals Improving the interpretability of species distribution models by using local approximations

2018 ◽  
Author(s):  
Boyan Angelov
Keyword(s):  
Machine Learning ◽  
Species Distribution ◽  
Species Distribution Models ◽  
R Package ◽  
Ecological Niches ◽  
Distribution Models ◽  
Domain Experts ◽  
Applied Machine Learning ◽  
Black Boxes ◽  
Interpretable Model

ABSTRACTSpecies Distribution Models (SDMs) are used to generate maps of realised and potential ecological niches for a given species. As any other machine learning technique they can be seen as “black boxes”, due to a lack of interpretability. Advances in other areas of applied machine learning can be applied to remedy this problem. In this study we test a new tool relying on Local Interpretable Model-agnostic Explanations (LIME) by comparing its results of other known methods and ecological interpretations from domain experts. The findings confirm that LIME provides consistent and ecologically sound explanations of climate feature importance during the training of SDMs, and that the sdmexplain R package can be used with confidence.

scholarly journals Species Distribution Models and Niche Partitioning among Unisexual Darevskia dahli and Its Parental Bisexual (D. portschinskii, D. mixta) Rock Lizards in the Caucasus

Mathematics ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. 1329 ◽  
Author(s):  
Varos Petrosyan ◽  
Fedor Osipov ◽  
Vladimir Bobrov ◽  
Natalia Dergunova ◽  
Andrey Omelchenko ◽  
...  
Keyword(s):  
Species Distribution ◽  
Parental Species ◽  
Environmental Gradients ◽  
Niche Partitioning ◽  
Ecological Niches ◽  
Mountain Forests ◽  
Distribution Models ◽  
And Shifts ◽  
High Elevations ◽  
Geographical Parthenogenesis

Among vertebrates, true parthenogenesis is known only in reptiles. Parthenogenetic lizards of the genus Darevskia emerged as a result of the hybridization of bisexual parental species. However, uncertainty remains about the mechanisms of the co-existence of these forms. The geographical parthenogenesis hypothesis suggests that unisexual forms can co-exist with their parental species in the “marginal” habitats. Our goal is to investigate the influence of environmental factors on the formation of ecological niches and the distribution of lizards. For this reason, we created models of species distribution and ecological niches to predict the potential geographical distribution of the parthenogenetic and its parental species. We also estimated the realized niches breadth, their overlap, similarities, and shifts in the entire space of predictor variables. We found that the centroids of the niches of the three studied lizards were located in the mountain forests. The “maternal” species D. mixta prefers forest habitats located at high elevations, “paternal” species D. portschinskii commonly occurs in arid and shrub habitats of the lower belt of mountain forests, and D. dahli occupies substantially an intermediate or “marginal” position along environmental gradients relative to that of its parental species. Our results evidence that geographical parthenogenesis partially explains the co-existence of the lizards.

scholarly journals A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

2021 ◽  
Vol 13 (8) ◽  
pp. 1495
Author(s):  
Jehyeok Rew ◽  
Yongjang Cho ◽  
Eenjun Hwang
Keyword(s):  
Neural Networks ◽  
Species Distribution ◽  
Best Practice ◽  
Deep Neural Networks ◽  
Species Distribution Models ◽  
Species Distribution Model ◽  
Environmental Data ◽  
Distribution Model ◽  
Distribution Models ◽  
Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Sign in / Sign up

Export Citation Format

Share Document