Biology subjects

van Tiel, N.

Publications and source records attributed to van Tiel, N..

5 recordsLinked to original sources

bioRxiv2025

Multi-scale neural networks enhance species distribution modelling across predictors and taxonomic groups

Ecological processes and patterns are scale-dependent, as reflected in how relationships between species occurrence and the environment vary across scales. In species distribution models (SDMs), spatial scale can strongly affect model predictions and performance. Despite this, the choice of scale is often overlooked. The development of SDMs using deep learning models has enabled spatially structured data, such as patches of environmental raster data, to be considered as model inputs, making the question of scale even more crucial. Here, we evaluate convolutional neural network-based multi-species SDMs considering different scales on a dataset from Switzerland, including more than 8 million observations for 2390 plant and 1006 animal species comprising amphibians, butterflies, beetles, and mammals. We investigate how scale affects model performance and compare single- and multi-scale models. Our results reveal stronger scale effects for remote sensing indices than for bioclimatic and edaphic variables. In single-scale models, we find that plant species perform better with smaller spatial scales, while the opposite is true for animal species. Multi-scale models consistently improve predictive performance and reduce sensitivity to arbitrary scale selection across all modalities and taxonomic groups. The effect of scale is nonetheless smaller than the increase in performance achieved by considering multiple predictor groups. To improve the interpretability of such complex models, we use attribution methods to compute the relative contribution of different scales and predictor groups. Our study demonstrates the importance of accounting for scale and the potential of deep learning methods to integrate ecological complexity with spatial data across scales. HighlightsO_LIDeep learning SDMs can use spatial environmental data as model predictors C_LIO_LIThe spatial extent of the predictors affects model performance C_LIO_LIMulti-scale models improve performance across predictors and taxonomic groups C_LIO_LIMulti-scale modelling reduces sensitivity to arbitrary scale selection C_LIO_LIExplainable AI methods provide contribution scores for scales and predictor groups C_LI

ecology↗

bioRxiv2025

Migrating in a warming world: A deep learning approach to predict pan-American seasonal shifts in the monarch butterfly niche

Climate change is driving biodiversity loss, disrupting ecosystem functioning, and altering species distributions. Migratory species, whose range varies across seasons depending on specific climatic conditions, are particularly sensitive to environmental changes and serve as indicators of ecosystem health. However, current species distribution models often fail to capture the temporal dynamics critical for migratory species, limiting their ability to provide accurate future range estimations. In this study, we address this gap by developing a time-aware deep learning species distribution model for the monarch butterfly (Danaus plexippus), an iconic species for biodiversity conservation. Using monarch occurrence records across the Americas gathered from scientific and citizen science sources, we embed the effect of monthly climatic variables in a sequential framework. We compare the performance of our seasonal model to conventional time-static baselines, showing not only better performance in the present, where the models have been trained and validated, but also in the past. Our findings show that climatic factors such as humidity, temperature, precipitation and cloud coverage strongly influence the ecological niche of the monarch butterfly, with notable seasonal and spatial variability. Applying our model under climate change scenarios, we predict a northwestward shift in the monarch range by the end of the XXI century, with expansion in Canada and significant contraction in California and Central America, key sites for overwintering that also host resident monarch populations. These changes could severely impact the species migratory cycle and population stability. Using Shapley values, an explainable AI technique, we identify the decrease in precipitation and humidity as important environmental drivers responsible for the contraction of overwintering sites. By focusing on a species of high ecological relevance through a time-aware modeling approach, this work brings novel insights for the conservation of migratory species in the face of the challenges posed by climate change.

ecology↗

bioRxiv2021

A geospatial mapping pipeline for ecologists

Geospatial modelling can give fundamental insights in the biogeography of life, providing key information about the living world in current and future climate scenarios. Emerging statistical and machine learning approaches can help us to generate new levels of predictive accuracy in exploring the spatial patterns in ecological and biophysical processes. Although these statistical models cannot necessarily represent the essential mechanistic insights that are needed to understand global biogeochemical processes under ever-changing environmental conditions, they can provide unparalleled predictive insights that can be useful for exploring the variation in biophysical processes across space. As such, these emerging tools can be a valuable approach to complement existing mechanistic approaches as we aim to understand the biogeography of Earths ecosystems. Here, we present a comprehensive methodology that efficiently handles large datasets to produce global predictions. This mapping pipeline can be used to generate quantitative, spatially explicit predictions, with a particular emphasis on spatially-explicit insights into the evaluation of model uncertainties and inaccuracies.

ecology↗

bioRxiv2021

Mapping tree species for restoration potential resilient to climate change

The restoration of forest ecosystems is associated with key benefits for biodiversity and ecosystem services. Where possible, ecosystem restoration efforts should be guided by a detailed knowledge of the native flora to regenerate ecosystems in a way that benefits natural biodiversity, ecosystem services, and natures contribution to people. Machine learning can map the ecological suitability of tree species globally, which then can guide restoration efforts, especially in regions where knowledge about the native tree flora is still insufficient. We developed an algorithm that combines ecological niche modelling and geographic distributions that allows for the high resolution (1km) global mapping of the native range and suitability of 3,987 tree species under current and future climatic conditions. We show that in most regions where forest cover could be potentially increased, heterogeneity in ecological conditions and narrow species niche width limit species occupancy, so that in several areas with reforestation potential, a large amount of potentially suitable species would be required for successful reforestation. Local tree planting efforts should consider a wide variety of species to ensure that the equally large variety of ecological conditions can be covered. Under climate change, a large fraction of the surface for restoration will suffer significant turnover in suitability, so that areas that are suitable for many species under current conditions will not be suitable in the future anymore. Such a turnover due to shifting climate is less pronounced in regions containing species with broader geographical distributions. This indicates that if restoration decisions are solely based on current climatic conditions, a large fraction of the restored area will become unsuitable in the future. Decisions on forest restoration should therefore take the niche width of a tree species into account to mitigate the risk of climate-driven ecosystem degradation.

ecology↗

bioRxiv2020

Ignoring fossil age uncertainty leads to inaccurate topology and divergence times in time calibrated tree inference

Time calibrated trees are challenging to estimate for many extinct groups of species due to the incompleteness of the rock and fossil records. Additionally, the precise age of a sample is typically not known as it may have occurred at any time during the time interval spanned by the rock layer. Bayesian phylogenetic approaches provide a coherent framework for incorporating multiple sources of evidence and uncertainty. In this study, we simulate datasets with characteristics typical of Palaeozoic marine invertebrates, in terms of character and taxon sampling. We use these datasets to examine the impact of different age handling methods on estimated topologies and divergence times obtained using the fossilized birth-death process. Our results reiterate the importance of modeling fossil age uncertainty, although we find that the overall impact of fossil age uncertainty depends on both fossil taxon sampling and character sampling. When character sampling is low, different approaches to handling fossil age uncertainty make little to no difference in the accuracy and precision of the results. However, when character sampling is high, sampling the fossil ages as part of the inference gives topology and divergence times estimates that are as good as those obtained by fixing ages to the truth, whereas fixing fossil ages to incorrect values results in higher error and lower coverage. Modeling fossil age uncertainty is thus critical, as fixing incorrect fossil ages will negate the benefits of improved fossil and character sampling.

evolutionary biology↗