scholarly journals Species Distribution Modelling Using Deep Learning

Author(s):  
Rutger Vos ◽  
Mark Rademaker ◽  
Laurens Hogeweg

Species distribution modelling, or ecological niche modelling, is a collection of techniques for the construction of correlative models based on the combination of species occurrences and GIS data. Using such models, a variety of research questions in biodiversity science can be investigated, among which are the assessment of habitat suitability around the globe (e.g. in the case of invasive species), the response of species to alternative climatic regimes (e.g. by forecasting climate change scenarios, or by hindcasting into palaeoclimates), and the overlap of species in niche space. The algorithms used for the construction of such models include maximum entropy, neural networks, and random forests. Recent advances both in computing power and in algorithm development raise the possibility that deep learning techniques will provide valuable additions to these existing approaches. Here, we present our recent findings in the development of workflows to apply deep learning to species distribution modelling, and discuss the prospects for the large-scale application of deep learning in web service infrastructures to analyze the growing corpus of species occurrence data in biodiversity information facilities.

Author(s):  
Cemal Turan

The progress on species distribution modelling (SDM) methods has brought new insights into the field of biological invasion management. In particular, statistical niche modelling, for spatio-temporal predictions of marine species’ distribution, is an increasingly used tool, supporting efficient decision-making for prevention and conservation. Earth's climate has changed significantly in the last century and the number of alien species penetrating from Indo-Pacific Ocean and South part of the Atlantic in the Mediterranean will continue to increase over the next decades. The purpose of the present study was to predict the potential geographic distribution and expansion of invasive alien lionfish (Pterois miles and Pterois volitans) with ecological niche modelling along the Mediterranean Sea. Temporal and spatial occurrence data from the first occurrence of a species for each country with coast along the Mediterranean Sea, was used to develop robust predictions of species richness, since the capacity to predict spatial patterns of species richness remains largely unassessed in this region. Marine climatic data layers were collected from the Bio-ORACLE and MARSPEC global databases. Different statistical models were evaluated to establish if these could provide useful predictions of absolute and relative lionfish distribution and expansion. The findings are an important step towards validating the use of SDM for invasive alien lionfish in the Mediterranean Sea.


PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0248797
Author(s):  
Frederico Hintze ◽  
Ricardo B. Machado ◽  
Enrico Bernard

Species distribution modelling (SDM) gained importance on biodiversity distribution and conservation studies worldwide, including prioritizing areas for public policies and international treaties. Useful for large-scale approaches and species distribution estimates, it is a plus considering that a minor fraction of the planet is adequately sampled. However, minimizing errors is challenging, but essential, considering the uses and consequences of such models. In situ validation of the SDM outputs should be a key-step—in some cases, urgent. Bioacoustics can be used to validate and refine those outputs, especially if the focal species’ vocalizations are conspicuous and species-specific. This is the case of echolocating bats. Here, we used extensive acoustic monitoring (>120 validation points over an area of >758,000 km2, and producing >300,000 sound files) to validate MaxEnt outputs for six neotropical bat species in a poorly-sampled region of Brazil. Based on in situ validation, we evaluated four threshold-dependent theoretical evaluation metrics’ ability in predicting models’ performance. We also assessed the performance of three widely used thresholds to convert continuous SDMs into presence/absence maps. We demonstrated that MaxEnt produces very different outputs, requiring a careful choice on thresholds and modeling parameters. Although all theoretical evaluation metrics studied were positively correlated with accuracy, we empirically demonstrated that metrics based on specificity-sensitivity and sensitivity-precision are better for testing models, considering that most SDMs are based on unbalanced data. Without independent field validation, we found that using an arbitrary threshold for modelling can be a precarious approach with many possible outcomes, even after getting good evaluation scores. Bioacoustics proved to be important for validating SDMs for the six bat species analyzed, allowing a better refinement of SDMs in large and under-sampled regions, with relatively low sampling effort. Regardless of the species assessing method used, our research highlighted the vital necessity of in situ validation for SDMs.


2020 ◽  
Author(s):  
Rafael Schouten ◽  
Peter Anton Vesk ◽  
Michael Kearney

Climate is a major factor determining the distribution of plant species. Correlative models are frequently used to model the relationships between species distributions and climatic drivers but, increasingly, their use for prediction in novel scenarios such as climate change is being questioned. Mechanistic models, where processes limiting plant distribution are explicitly included, are regarded as preferable but more challenging.The availability of tools for simulating microclimates with high spatial and temporal definition has also opened new possibilities for simulating the limiting environmental stresses experienced by plant over their ontogeny. However, the field of mechanistic species distribution modelling is relatively new and the tools and theory for constructing these models are underdeveloped.In this paper we explore the potential for using a Dynamic Energy Budget model of organism growth integrated with microclimate and photosynthesis models. We model the interactions of plant growth and microclimatic stressors over the life stages of plant growth, and scale them up to demonstrate predictions of distribution at the continental scale. We develop the model using Julia, a new language for scientific computing, as a set of generic modelling packages. These have a modular, toolkit structure that has the potential to increase the efficiency and transparency of developing mechanistic SDMs.


2021 ◽  
Author(s):  
Frederico Hintze ◽  
Ricardo B. Machado ◽  
Enrico Bernard

AbstractSpecies distribution modelling (SDM) gained importance on biodiversity distribution and conservation studies worldwide, including prioritizing areas for public policies and international treaties. Useful for large-scale approaches and estimates, is a plus considering that a minor fraction of the planet is adequately sampled. However, SDM needs to be as reliable as possible. Minimizing errors is challenging, but essential, considering the uses and consequences of such models. In situ validation of the SDM outputs should be a key-step – in some cases, urgent. Bioacoustics can be used to validate and refine those outputs, especially if the focal species’ vocalizations are conspicuous and species-specific. This is the case of echolocating bats. Here, we used extensive acoustic monitoring (>120 validation points, covering >758,000 km2, and >300,000 sound files) to validate MaxEnt outputs for six neotropical bat species in a poorly-sampled region of Brazil. Based on in situ validation, we evaluated four threshold-dependent theoretical evaluation metrics’ ability in predicting models’ performance. We also assessed the performance of three widely used thresholds to convert continuous SDMs into presence/absence maps. We demonstrated that MaxEnt produces very different outputs, requiring a careful choice on thresholds and modeling parameters. Although all theoretical evaluation metrics studied were positively correlated with accuracy, we empirically demonstrated that metrics based on specificity-sensitivity and sensitivity-precision are better for testing models, considering that most SDMs are based on unbalanced data. Without independent field validation, we found that using an arbitrary threshold for modelling can be a precarious approach with many possible outcomes, even after getting good evaluation scores. Bioacoustics proved to be important for validating SDMs for the six bat species analyzed, allowing a better refinement of SDMs in large and under-sampled regions, with relatively low sampling effort. Regardless of species assessing method used, our research highlighted the vital necessity of in situ validation for SDMs.


Sign in / Sign up

Export Citation Format

Share Document