Forecasting species distributions: Correlation does not equal causation

Sirén, Alexej P. K.; Sutherland, Chris; Karmalkar, Ambarish V.; Duveneck, Matthew J.; Morelli, Toni Lyn

doi:10.1111/ddi.13480

Cited by 11 publications

(8 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our results have to be interpreted and analyzed carefully: contrary to process based models, correlative models describe the patterns, not the mechanisms, in the association between species occurrences and predictor variables; for this reason, correlative SDMs risk overlooking potentially important driving factors determining species distributions since they cannot distinguish between direct and indirect effects ( Sirén et al, 2022 ). A known issue in this sense is the masking effect of abiotic factors on competition and predation: SDMs could estimate abiotic predictors as the most important for species abundance, even in those cases when distribution is strongly affected by competition ( Godsoe, Franklin & Blanchet, 2017 ) or when biotic interactions are strictly correlated with abiotic factors ( Filazzola, Matter & Roland, 2020 ).…”

Section: Discussionmentioning

confidence: 95%

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

Bonannella

Hengl²,

Heisig

et al. 2022

PeerJ

View full text Add to dashboard Cite

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 Mill., Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., Prunus avium L., Quercus cerris L., Quercus ilex L., Quercus robur L., Quercus suber L. and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data for a total of three million of points was used to train different algorithms: random forest, gradient-boosted trees, generalized linear models, k-nearest neighbors, CART and an artificial neural network. A stack of 305 coarse and high resolution covariates representing spectral reflectance, different biophysical conditions and biotic competition was used as predictors for realized distributions, while potential distribution was modelled with environmental predictors only. Logloss and computing time were used to select the three best algorithms to tune and train an ensemble model based on stacking with a logistic regressor as a meta-learner. An ensemble model was trained for each species: probability and model uncertainty maps of realized distribution were produced for each species using a time window of 4 years for a total of six distribution maps per species, while for potential distributions only one map per species was produced. Results of spatial cross validation show that the ensemble model consistently outperformed or performed as good as the best individual model in both potential and realized distribution tasks, with potential distribution models achieving higher predictive performances (TSS = 0.898, R2logloss = 0.857) than realized distribution ones on average (TSS = 0.874, R2logloss = 0.839). Ensemble models for Q. suber achieved the best performances in both potential (TSS = 0.968, R2logloss = 0.952) and realized (TSS = 0.959, R2logloss = 0.949) distribution, while P. sylvestris (TSS = 0.731, 0.785, R2logloss = 0.585, 0.670, respectively, for potential and realized distribution) and P. nigra (TSS = 0.658, 0.686, R2logloss = 0.623, 0.664) achieved the worst. Importance of predictor variables differed across species and models, with the green band for summer and the Normalized Difference Vegetation Index (NDVI) for fall for realized distribution and the diffuse irradiation and precipitation of the driest quarter (BIO17) being the most frequent and important for potential distribution. On average, fine-resolution models outperformed coarse resolution models (250 m) for realized distribution (TSS = +6.5%, R2logloss = +7.5%). The framework shows how combining continuous and consistent Earth Observation time series data with state of the art machine learning can be used to derive dynamic distribution maps. The produced predictions can be used to quantify temporal trends of potential forest degradation and species composition change.

show abstract

Section: Discussionmentioning

confidence: 95%

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

Bonannella

Hengl²,

Heisig

et al. 2022

PeerJ

View full text Add to dashboard Cite

show abstract

“…However, our results have to be interpreted and analyzed carefully: contrary to process based models, correlative models describe the patterns, not the mechanisms, in the association between species occurrences and predictor variables; for this reason, correlative SDMs risk overlooking potentially important driving factors determining species distributions since they cannot distinguish between direct and indirect effects (Sirén et al, 2022). A known issue in this sense is the masking effect of abiotic factors on competition and predation: SDMs could estimate abiotic predictors as the most important for species abundance, even in those cases when distribution is strongly affected by competition (Godsoe et al, 2017) or when biotic interactions are strictly correlated with abiotic factors (Filazzola et al, 2020).…”

Section: Miguelmentioning

confidence: 90%

Forest tree species distribution for Europe 2000-2020: mapping potential and realized distributions using spatiotemporal Machine Learning

Bonannella¹,

Hengl²,

Heisig

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper describes a data-driven framework based on spatiotemporal machine learning to producedistribution maps for 16 tree species (Abies alba Mill., Castanea sativa Mill., Corylus avellana L., Fagussylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold,Pinus pinea L., Pinus sylvestris L., Prunus avium L., Quercus cerris L., Quercus ilex L., Quercus roburL., Quercus suber L. and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data for atotal of 3 million of points was used to train different algorithms: random forest, gradient-boosted trees,generalized linear models, k-nearest neighbors, CART and an artificial neural network. A stack of 305 coarseand high resolution covariates representing spectral reflectance, different biophysical conditions and bioticcompetition was used as predictors for realized distributions, while potential distribution was modelled withenvironmental predictors only. Logloss and computing time were used to select the three best algorithms totune and train an ensemble model based on stacking with a logistic regressor as a meta-learner. An ensemblemodel was trained for each species: probability and model uncertainty maps of realized distribution wereproduced for each species using a time window of 4 years for a total of 6 distribution maps per species, whilefor potential distributions only one map per species was produced. Results of spatial cross validation showthat the ensemble model consistently outperformed or performed as good as the best individual model inboth potential and realized distribution tasks, with potential distribution models achieving higher predictiveperformances (TSS = 0.898, R2logloss = 0.857) than realized distribution ones on average (TSS = 0.874,R2logloss = 0.839). Ensemble models for Q. suber achieved the best performances in both potential (TSS =0.968, R2logloss = 0.952) and realized (TSS = 0.959, R2logloss = 0.949) distribution, while P. sylvestris (TSS= 0.731, 0.785, R2logloss = 0.585, 0.670, respectively, for potential and realized distribution) and P. nigra(TSS = 0.658, 0.686, R2logloss = 0.623, 0.664) achieved the worst. Importance of predictor variables differedacross species and models, with the green band for summer and the Normalized Difference Vegetation Index(NDVI) for fall for realized distribution and the diffuse irradiation and precipitation of the driest quarter(BIO17) being the most frequent and important for potential distribution. On average, fine-resolutionmodels outperformed coarse resolution models (250 m) for realized distribution (TSS = +6.5%, R2logloss =+7.5%). The framework shows how combining continuous and consistent Earth Observation time seriesdata with state of the art machine learning can be used to derive dynamic distribution maps. The producedpredictions can be used to quantify temporal trends of potential forest degradation and species compositionchange.

show abstract

“…Predators of hares in the study area included generalist species (coyotes Canis latrans , bobcats Lynx rufus , red fox Vulpes vulpes , fisher Pekania pennanti , American marten Martes americana , weasels Mustela spp., northern goshawks Accipiter gentilis , and great‐horned owls Bubo virginianus ) and one specialist (Canada lynx Lynx canadensis ). Generalist predators typically were widespread, except for bobcats that occupied lower elevation and southern regions and martens that were primarily distributed in northern and high elevation regions (Sirén et al 2021, 2022). Lynx were common only in the northernmost region (Connecticut Lakes) of the study area (Sirén et al 2021, 2022) and occurred at low density.…”

Section: Methodsmentioning

confidence: 99%

A Great Escape: resource availability and density‐dependence shape population dynamics along trailing range edges

et al. 2023

Self Cite

View full text Add to dashboard Cite

Populations along geographical range limits are often exposed to unsuitable climate and low resource availability relative to core populations. As such, there has been a renewed focus on understanding the factors that determine range limits to better predict how species will respond to global change. Using recent theory on range limits and classical understanding of density dependence, we evaluated the influence of resource availability on the snowshoe hare Lepus americanus along its trailing range edge. We estimated variation in population density, habitat use, survival, and parasite loads to test the Great Escape Hypothesis (GEH), i.e. that density dependence determines, in part, a species' persistence along trailing edges. We found that variability in resource availability affected density and population fluctuations and led to trade‐offs in survival for snowshoe hare populations in the northeastern USA. Hares living in resource‐limited environments had lower and less variable population density, yet higher survival and lower parasitism compared to populations living in resource‐rich environments. We suggest that density‐dependent dynamics, elicited by resource availability, provide hares a unique survival advantage and partly explain persistence along their trailing edge. We hypothesize that this low‐density escape from predation and parasitism occurs for other prey species along trailing edges, but the extent to which it occurs is likely conditional on the quality of matrix habitat. Our work indicates that biotic factors play an important role in shaping species' trailing edges and more detailed examination of non‐climatic factors is warranted to better inform conservation and management decisions.

show abstract

Forecasting species distributions: Correlation does not equal causation

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 11 publications

References 84 publications

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

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

Forest tree species distribution for Europe 2000-2020: mapping potential and realized distributions using spatiotemporal Machine Learning

A Great Escape: resource availability and density‐dependence shape population dynamics along trailing range edges

Contact Info

Product

Resources

About