| Issue № 1 |
Methods of ecological investigations |
pdf-version |
On the application of Max Ent algorithms in ecology
| Korosov Andrey Victorovich | DSc, professor, Petrozavodsk State University, 33, Lenin St., Petrozavodsk, 185910, Republic of Karelia, Russia, korosov@psu.karelia.ru |
|
Keywords: maximum entropy method MaxEnt ecology viper sexual dimorphism |
Summary: The article discusses the logical and computational foundations of the maximum entropy method, which the MaxEnt program uses. This program makes it possible to build models of the placement of different species of animals and plants. The subject of the analysis is the method of maximum entropy as a criterion for the success of the selection of model parameters. The principles of its work are shown in a series of increasingly complex quantitative examples from ecology. The calculations are illustrated by programs in the R language, which can be performed by readers for a deep understanding of the meaning of the procedure. The emphasis is placed on the difference between MaxEnt technology and other classifiers (discriminatory analysis, neural networks, etc.): instead of using contrast between groups of objects, MaxEnt strives to capture and enhance the uniformity of objects of the same group. This almost automatically leads to the separation of objects of one studied status from another. This technique makes it possible to effectively perform classification constructions in conditions of information scarcity. Some approaches for assigning a "break point", a threshold for binary classification, including elements of ROC analysis, the use of percentiles and quantiles are considered. The article serves as a practical introduction to the technology of constructing classifications using the principle of maximum entropy. © Petrozavodsk State University |
Published on: 02 May 2024 | |
References
A brief introduction to MaxEnt, GisLab. 2013. URL: https://gis-lab.info/qa/maxent.html (data obrascheniya: 20.09.2023). URL: https://www.microsoft.com/en-us/download/details.aspx?id=52427 (data obrascheniya: 20.09.2023).
Ansel'm A. I. Fundamentals of statistical physics and thermodynamics. M.: Nauka, 1973. 424 p.
Belashev B. Z. Suleymanov M. K. The entropy maximum method. Statistical description of systems, Fizika elementarnyh chastic i atomnogo yadra. Pis'ma v EChAYa. 2002. No. 6. P. 44–50. URL: http://www.jinr.ru/publish/ Pepan_letters/panl_6_2002/05_bel.pdf (data obrascheniya: 26.07.2023).
Belyaev A. M. Mihnin A. E. Rogachev M. V. ROC analysis and logistic regression in MedCalc: Uchebnoe posobie dlya vrachey i obuchayuschihsya v sisteme vysshego i dopolnitel'nogo professional'nogo obrazovaniya. SPb.: NMIC onkologii im. N. N. Petrova, 2023. 36 p.
Cherlin V. A. Improving the analysis of animal habitats and ecological niches (on the example of reptiles) using computer GIS programs, Uspehi sovremennoy biologii. 2020. T. 140, No. 1. P. 87–104. DOI: 10.31857/S0042132419060024. URL: https://sciencejournals.ru/cgi/getPDF.pl?jid=uspbio&year=2020&vol=140&iss=1&file=UspBio1906002Cherlin.pdf (data obrascheniya: 20.09.2023).
Dzheyns E. T. On the rationale justification of the maximumentropy methods, TIIER. 1982. T. 70, No. 9. P. 33–51.
Ecoinformatics. Theory. Practice. Methods and systems, Red. V. E. Sokolov. SPb.: Gidrometeoizdat, 1992. 520 p.
Entropy in the theory of information, Bol'shaya rossiyskaya enciklopediya. 2022. URL: https://bigenc.ru/c/entropiia-v-teorii-informatsii-8e42df (data obrascheniya: 20.09.2023).
Ivanova V. M. Kalinina V. N. Neshumova L. A. Reshetnikov I. O. Mathematical statistics. M.: Vysshaya shkola, 1981. 370 p.
Jaynes E. T. Information theory and statistical mechanics, Physical review. 1957. Vol. 106, No 4. P. 620–630.
Korosov A. V. Ecology of the common viper (Vipera berus L.) in the North (facts and models). Petrozavodsk: Izd-vo PetrGU, 2010. 264 p. URL: https://b.twirpx.link/file/4132514/ (data obrascheniya: 20.9.2023).
Lisovskiy A. A. Dudov S. V. Advantages and limitations of using methods of ecological modeling of habitats. 2. MaxEnt, Zhurnal obschey biologii. 2020. T. 81, No. 2. P. 135–146. URL: file:///C:/Users/koros/Downloads/OBB0135.pdf. (data obrascheniya: 20.09.2023).
Logistic regression and ROC analysis – mathematical apparatus, Loginom. 2020. URL: https://loginom.ru/blog/logistic-regression-roc-auc (data obrascheniya: 26.07.2023).
Maxent is now open source!, American Museum of Natural History. URL: https://biodiversityinformatics.amnh.org/open_source/maxent/ (data obrascheniya: 20.09.2023).
Maximum-entropy species distribution modeling tutorial, Microsoft Download Center. 2010. URL: https://www.microsoft.com/en-us/download/details.aspx?id=52427(data obrascheniya: 20.09.2023).
Nekrasova O. D. Titar V. M. Modeling and bioclimatic analysis of changes in the range of the water snake Natrix tessellata (Reptilia, Colubridae) in Ukraine, Pracі ukraїns'kogo gerpetologіchnogo tovaristva. 2014. No. 5. P. 80−83. URL: https://herpeto-volga.ru/literatura.html?task=download.send&id=922&catid=57&m=0 (data obrascheniya: 20.09.2023).
Olonova M. V. Gudkova P. D. Bioclimatic modeling: Tasks for practical work and methodological guidelines for their implementation. Tomsk: Izdatel'skiy Dom TGU, 2017. 50 p.
Phillips S. J. A brief tutorial on Maxent. Network of conservation educators and practitioners, center for biodiversity and conservation, American Museum of Natural History, Lessons in Conservation. 2009. Vol. 3. P. 108–135. URL: https://www.amnh.org/content/download/141371/2285439/file/LinC3_SpeciesDistModeling_Ex.pdf (data obrascheniya: 20.09.2023).
Phillips S. J., Anderson R. P., Schapire R. E. Maximum entropy modeling of species geographic distributions, Ecological Modelling. 2006. Vol. 190. P. 231–259.
Phillips S. J., Dudik M. Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation, Ecography. 2008. Vol. 31. P. 161–175. URL: https://onlinelibrary.wiley.com/doi/full/10.1111/j.0906-7590.2008.5203.x (data obrascheniya: 20.09.2023).
Schisterman E. F., Perkins N. J., Liu A., Bondell H. Optimal cut-point and its corresponding Youden index to discriminate individuals using pooled blood samples, Epidemiology. 2005. Vol. 16 (1). P. 73–81. DOI: 10.1097/01.ede.0000147512.81966.ba
Shitikov V. K. Mastickiy S. E. Classification, regression and other Data Mining algorithms using R. 2017. 351 p. URL: https://www.twirpx.org/file/2203014/, https://ranalytics.github.io/data-mining/ (data obrascheniya: 12.02.2021).
Shitikov V. K. Zinchenko T. D. Golovatyuk L. V. Models of maximum entropy and spatial distribution of species of bottom communities in the territory of the middle and lower Volga region, Rossiyskiy zhurnal prikladnoy ekologii 2021. No. 2. P. 10–16. DOI: 10.24852/2411-7374.2021.2.10.16. URL: http://www.ievbras.ru/ecostat/Kiril/R/Paper/ETAT_2021.pdf (data obrascheniya: 20.09.2023).
Shitikov V. K. Models SDM. 2020. URL: https://stok1946.blogspot.com/2020/11/sdm.html (data obrascheniya: 20.09.2023)
The R project for statistical computing. 2023. URL: https://www.r-project.org/ (data obrascheniya: 26.07.2023).
Theoretical foundations of the Maxent method, GisLab. URL: https://wiki.gis-lab.info/w/Teoreticheskie_osnovy_metoda_Maxent (data obrascheniya: 20.09.2023).
© 2011 - 2024
Petrozavodsk State University
technical support - RCNIT
The editor-in-chief - Andrey Korosov
ecopri@petrsu.ru