arXiv subjects

Florian Hartig

Publications and source records attributed to Florian Hartig.

At least 19 recordsLinked to original sources

arXiv2026

Equivalence testing in pesticide risk assessment -- Evaluation and practical guidance for design, analysis and interpretation

Harmful pesticide effects exceeding specific protection goals (SPG) may go undetected in underpowered experimental designs. Regulatory honeybee field studies have consistently failed to reach the statistical power required under European Food Safety Authority (EFSA) guidance, which may have caused approval of high-risk substances. Therefore, EFSA advised a shift from testing the null hypothesis of 'no effect' to equivalence testing. Under this approach, a pesticide is classified as 'low risk' if the null hypothesis that its effect exceeds the SPG can be rejected. For honeybees, the recommended SPG is a colony size reduction below 10%. Critics have argued that this framework requires excessive site replication to demonstrate pesticide safety and proposed an alternative equivalence test defining treatment effects relative to the lower bound of the 90%-control-group confidence interval. Using simulations mimicking a regulatory honeybee field study, we show that although the two equivalence tests share the same trade-off between false 'low-risk' and false 'high-risk' classifications, only EFSA's original recommendation reliably identifies pesticides with effects > SPG at alpha = 0.2. Our results show that increasing site replication beyond the current practice is unavoidable for a reliable regulatory assessment. However, for pesticides with effect sizes of 5% or less, site requirements remain lower than those implied by the power requirement of the former EFSA guidance. Moreover, covariate adjustment through a model term or balanced colony allocation using anticlustering randomisation can reduce site requirements without losing power and thus save costs. Finally, we provide guidance and R functions for anticlustering randomisation and equivalence testing for pesticide risk assessment.

stat.ME↗

arXiv2026

Analyzing animal movement using deep learning

Understanding how animals move through heterogeneous landscapes is central to ecology and conservation. In this context, step selection functions (SSFs) have emerged as the main statistical framework to analyze how biotic and abiotic predictors influence movement paths observed by radio tracking, GPS tags, or similar sensors. A traditional SSF consists of a generalized linear model (GLM) that infers the animal's habitat preferences (selection coefficients) by comparing each observed movement step to random steps. Such GLM-SSFs, however, cannot flexibly consider non-linear or interacting effects, unless those have been specified a priori. To address this problem, generalized additive models have been integrated in the SSF framework, but those GAM-SSFs are still limited in their ability to represent complex habitat preferences and inter-individual variability. Here we explore the utility of deep neural networks (DNNs) to overcome these limitations. We find that DNN-SSFs, coupled with explainable AI to extract selection coefficients, offer many advantages for analyzing movement data. In the case of linear effects, they effectively retrieve the same effect sizes and p-values as conventional GLMs. At the same time, however, they can automatically detect complex interaction effects, nonlinear responses, and inter-individual variability if those are present in the data. We conclude that DNN-SSFs are a promising extension of traditional SSF. Our analysis extends previous research on DNN-SSF by exploring differences and similarities of GLM, GAM and DNN-based SSF models in more depth, in particular regarding the validity of statistical indicators that are derived from the DNN. We also propose new DNN structures to capture inter-individual effects that can be viewed as a nonlinear random effect. All methods used in this paper are available via the 'citoMove' R package.

stat.AP↗

arXiv2024

Is there a robust effect of mainland mutualism rates on species richness of oceanic islands?

In island biogeography, it is widely accepted that species richness on island depends on the area and isolation of the island as well as the species pool on the mainland. Delavaux et al. (2024) suggest that species richness on oceanic islands also depends on the proportion of mutualists on the mainland, based on the idea that mutualists require specific interaction partners for their survival and thus have lower chances of establishment after successful immigration. As the proportion of mutualists increases towards the tropics, this effect could explain a weaker latitudinal diversity gradient (LDG) for oceanic islands. However, after re-analyzing their data, we have doubts if these conclusions are supported by the available data.

q-bio.PE↗

arXiv2024

Novel community data in ecology -- properties and prospects

New technologies for acquiring biological information such as eDNA, acoustic or optical sensors, make it possible to generate spatial community observations at unprecedented scales. The potential of these novel community data to standardize community observations at high spatial, temporal, and taxonomic resolution and at large spatial scale ('many rows and many columns') has been widely discussed, but so far, there has been little integration of these data with ecological models and theory. Here, we review these developments and highlight emerging solutions, focusing on statistical methods for analyzing novel community data, in particular joint species distribution models; the new ecological questions that can be answered with these data; and the potential implications of these developments for policy and conservation.

q-bio.PE↗

arXiv2023

Can predictive models be used for causal inference?

Supervised machine learning (ML) and deep learning (DL) algorithms excel at predictive tasks, but it is commonly assumed that they often do so by exploiting non-causal correlations, which may limit both interpretability and generalizability. Here, we show that this trade-off between explanation and prediction is not as deep and fundamental as expected. Whereas ML and DL algorithms will indeed tend to use non-causal features for prediction when fed indiscriminately with all data, it is possible to constrain the learning process of any ML and DL algorithm by selecting features according to Pearl's backdoor adjustment criterion. In such a situation, some algorithms, in particular deep neural networks, can provide near unbiased effect estimates under feature collinearity. Remaining biases are explained by the specific algorithmic structures as well as hyperparameter choice. Consequently, optimal hyperparameter settings are different when tuned for prediction or inference, confirming the general expectation of a trade-off between prediction and explanation. However, the effect of this trade-off is small compared to the effect of a causally constrained feature selection. Thus, once the causal relationship between the features is accounted for, the difference between prediction and explanation may be much smaller than commonly assumed. We also show that such causally constrained models generalize better to new data with altered collinearity structures, suggesting generalization failure may often be due to a lack of causal learning. Our results not only provide a perspective for using ML for inference of (causal) effects but also help to improve the generalizability of fitted ML and DL models to new data.

stat.ML↗

arXiv2023

cito: An R package for training neural networks using torch

Deep Neural Networks (DNN) have become a central method in ecology. Most current deep learning (DL) applications rely on one of the major deep learning frameworks, in particular Torch or TensorFlow, to build and train DNN. Using these frameworks, however, requires substantially more experience and time than typical regression functions in the R environment. Here, we present 'cito', a user-friendly R package for DL that allows specifying DNNs in the familiar formula syntax used by many R packages. To fit the models, 'cito' uses 'torch', taking advantage of the numerically optimized torch library, including the ability to switch between training models on the CPU or the graphics processing unit (GPU) (which allows to efficiently train large DNN). Moreover, 'cito' includes many user-friendly functions for model plotting and analysis, including optional confidence intervals (CIs) based on bootstraps for predictions and explainable AI (xAI) metrics for effect sizes and variable importance with CIs and p-values. To showcase a typical analysis pipeline using 'cito', including its built-in xAI features to explore the trained DNN, we build a species distribution model of the African elephant. We hope that by providing a user-friendly R framework to specify, deploy and interpret DNN, 'cito' will make this interesting model class more accessible to ecological data analysis. A stable version of 'cito' can be installed from the comprehensive R archive network (CRAN).

cs.LG↗

arXiv2022

Machine Learning and Deep Learning -- A review for Ecologists

1. The popularity of Machine learning (ML), Deep learning (DL), and Artificial intelligence (AI) has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML and DL algorithms are often perceived as opaque, and their relationship to classical data analysis tools remains debated. 2. Although it is often assumed that ML and DL excel primarily at making predictions, ML and DL can also be used for analytical tasks traditionally addressed with statistical models. Moreover, most recent discussions and reviews on ML focus mainly on DL, missing out on synthesizing the wealth of ML algorithms with different advantages and general principles. 3. Here, we provide a comprehensive overview of the field of ML and DL, starting by summarizing its historical developments, existing algorithm families, differences to traditional statistical tools, and universal ML principles. We then discuss why and when ML and DL models excel at prediction tasks and where they could offer alternatives to traditional statistical methods for inference, highlighting current and emerging applications for ecological problems. Finally, we summarize emerging trends such as scientific and causal ML, explainable AI, and responsible AI that may significantly impact ecological data analysis in the future. 4. We conclude that ML and DL are powerful new tools for predictive modeling and data analysis. The superior performance of ML and DL algorithms compared to statistical models can be explained by their higher flexibility and automatic data-dependent complexity optimization. However, their use for causal inference is still disputed as the focus of ML and DL methods on predictions creates challenges for the interpretation of these models. Nevertheless, we expect ML and DL to become an indispensable tool in E&E, comparable to other traditional statistical tools.

q-bio.QM↗

arXiv2022

The evidence contained in the P-value is context dependent

In a recent opinion article, Muff et al. recapitulate well-known objections to the Neyman-Pearson Null-Hypothesis Significance Testing (NHST) framework and call for reforming our practices in statistical reporting. We agree with them on several important points: the significance threshold P<0.05 is only a convention, chosen as a compromise between type I and II error rates; transforming the p-value into a dichotomous statement leads to a loss of information; and p-values should be interpreted together with other statistical indicators, in particular effect sizes and their uncertainty. In our view, a lot of progress in reporting results can already be achieved by keeping these three points in mind. We were surprised and worried, however, by Muff et al.'s suggestion to interpret the p-value as a "gradual notion of evidence". Muff et al. recommend, for example, that a P-value > 0.1 should be reported as "little or no evidence" and a P-value of 0.001 as "strong evidence" in favor of the alternative hypothesis H1.

q-bio.QM↗

arXiv2021

A new method for faster and more accurate inference of species associations from big community data

1. Joint Species Distribution models (JSDMs) explain spatial variation in community composition by contributions of the environment, biotic associations, and possibly spatially structured residual covariance. They show great promise as a general analytical framework for community ecology and macroecology, but current JSDMs, even when approximated by latent variables, scale poorly on large datasets, limiting their usefulness for currently emerging big (e.g., metabarcoding and metagenomics) community datasets. 2. Here, we present a novel, more scalable JSDM (sjSDM) that circumvents the need to use latent variables by using a Monte-Carlo integration of the joint JSDM likelihood and allows flexible elastic net regularization on all model components. We implemented sjSDM in PyTorch, a modern machine learning framework that can make use of CPU and GPU calculations. Using simulated communities with known species-species associations and different number of species and sites, we compare sjSDM with state-of-the-art JSDM implementations to determine computational runtimes and accuracy of the inferred species-species and species-environmental associations. 3. We find that sjSDM is orders of magnitude faster than existing JSDM algorithms (even when run on the CPU) and can be scaled to very large datasets. Despite the dramatically improved speed, sjSDM produces more accurate estimates of species association structures than alternative JSDM implementations. We demonstrate the applicability of sjSDM to big community data using eDNA case study with thousands of fungi operational taxonomic units (OTU). 4. Our sjSDM approach makes the analysis of JSDMs to large community datasets with hundreds or thousands of species possible, substantially extending the applicability of JSDMs in ecology. We provide our method in an R package to facilitate its applicability for practical data analysis.

q-bio.QM↗

arXiv2020

Inferring species interactions using Granger causality and convergent cross mapping

Identifying directed interactions between species from time series of their population densities has many uses in ecology. This key statistical task is equivalent to causal time series inference, which connects to the Granger causality (GC) concept: $x$ causes $y$ if $x$ improves the prediction of $y$ in a dynamic model. However, the entangled nature of nonlinear ecological systems has led to question the appropriateness of Granger causality, especially in its classical linear Multivariate AutoRegressive (MAR) model form. Convergent-cross mapping (CCM), a nonparametric method developed for deterministic dynamical systems, has been suggested as an alternative. Here, we show that linear GC and CCM are able to uncover interactions with surprisingly similar performance, for predator-prey cycles, 2-species deterministic (chaotic) or stochastic competition, as well as 10- and 20-species interaction networks. There is no correspondence between the degree of nonlinearity of the dynamics and which method performs best. Our results therefore imply that Granger causality, even in its linear MAR($p$) formulation, is a valid method for inferring interactions in nonlinear ecological networks; using GC or CCM (or both) can instead be decided based on the aims and specifics of the analysis.

q-bio.PE↗

arXiv2019

Machine learning algorithms to infer trait-matching and predict species interactions in ecological networks

Ecologists have long suspected that species are more likely to interact if their traits match in a particular way. For example, a pollination interaction may be more likely if the proportions of a bee's tongue fit a plant's flower shape. Empirical estimates of the importance of trait-matching for determining species interactions, however, vary significantly among different types of ecological networks. Here, we show that ambiguity among empirical trait-matching studies may have arisen at least in parts from using overly simple statistical models. Using simulated and real data, we contrast conventional generalized linear models (GLM) with more flexible Machine Learning (ML) models (Random Forest, Boosted Regression Trees, Deep Neural Networks, Convolutional Neural Networks, Support Vector Machines, naive Bayes, and k-Nearest-Neighbor), testing their ability to predict species interactions based on traits, and infer trait combinations causally responsible for species interactions. We find that the best ML models can successfully predict species interactions in plant-pollinator networks, outperforming GLMs by a substantial margin. Our results also demonstrate that ML models can better identify the causally responsible trait-matching combinations than GLMs. In two case studies, the best ML models successfully predicted species interactions in a global plant-pollinator database and inferred ecologically plausible trait-matching rules for a plant-hummingbird network, without any prior assumptions. We conclude that flexible ML models offer many advantages over traditional regression models for understanding interaction networks. We anticipate that these results extrapolate to other ecological network types. More generally, our results highlight the potential of machine learning and artificial intelligence for inference in ecology, beyond standard tasks such as image or pattern recognition.

q-bio.PE↗

arXiv2018

Simulation Modeling

With the rise of computers, simulation models have emerged beside the more traditional statistical and mathematical models as a third pillar for ecological analysis. Broadly speaking, a simulation model is an algorithm, typically implemented as a computer program, which propagates the states of a system forward. Unlike in a mathematical model, however, this propagation does not employ the methods of calculus but rather a set of rules or formulae that directly prescribe the next state. Such an algorithmic model specification is particularly suited for describing systems that are difficult to capture or analyze with differential equations such as: (a) systems that are highly nonlinear or chaotic; (b) discrete systems, for example networks or groups of distinct individuals; (c) systems that are stochastic; and (d) systems that are too complex to be successfully treated with classical calculus. As these situations are frequently encountered in ecology, simulation models are now widely applied across the discipline. They have been instrumental in developing new insights into classical questions of species' coexistence, community assembly, population dynamics, biogeography, and many more. The methods for this relatively young field are still being actively developed, and practical work with simulation models requires ecologists to learn new skills such as coding, sensitivity analysis, calibration, validation, and forecasting uncertainties. Moreover, scientific inquiry with complex systems has led to subtle changes to the philosophical and epistemological views regarding simplicity, reductionism, and the relationship between prediction and understanding.

q-bio.PE↗

arXiv2017

An Extended Empirical Saddlepoint Approximation for Intractable Likelihoods

The challenges posed by complex stochastic models used in computational ecology, biology and genetics have stimulated the development of approximate approaches to statistical inference. Here we focus on Synthetic Likelihood (SL), a procedure that reduces the observed and simulated data to a set of summary statistics, and quantifies the discrepancy between them through a synthetic likelihood function. SL requires little tuning, but it relies on the approximate normality of the summary statistics. We relax this assumption by proposing a novel, more flexible, density estimator: the Extended Empirical Saddlepoint approximation. In addition to proving the consistency of SL, under either the new or the Gaussian density estimator, we illustrate the method using two examples. One of these is a complex individual-based forest model for which SL offers one of the few practical possibilities for statistical inference. The examples show that the new density estimator is able to capture large departures from normality, while being scalable to high dimensions, and this in turn leads to more accurate parameter estimates, relative to the Gaussian alternative. The new density estimator is implemented by the esaddle R package, which can be found on the Comprehensive R Archive Network (CRAN).

stat.ME↗

arXiv2014

On the sympatric evolution and evolutionary stability of coexistence by relative nonlinearity of competition

If two species exhibit different nonlinear responses to a single shared resource, and if each species modifies the resource dynamics such that this favors its competitor, they may stably coexist. This coexistence mechanism, known as relative nonlinearity of competition, is well understood theoretically, but less is known about its evolutionary properties and its prevalence in real communities. We address this challenge by using adaptive dynamics theory and individual-based simulations to compare community stabilization and evolutionary stability of species that coexist by relative nonlinearity. In our analysis, evolution operates on the species' density-compensation strategies, and we consider a trade-off between population growth rates at high and low resource availability. We confirm previous findings that, irrespective of the particular model of density dependence, there are many combinations of overcompensating and undercompensating density-compensation strategies that allow stable coexistence by relative nonlinearity. However, our analysis also shows that most of these strategy combinations are not evolutionarily stable and will be outcompeted by an intermediate density-compensation strategy. Only very specific trade-offs lead to evolutionarily stable coexistence by relative nonlinearity. As we find no reason why these particular trade-offs should be common in nature, we conclude that the sympatric evolution and evolutionary stability of relative nonlinearity, while possible in principle, seems rather unlikely. We speculate that this may, at least in part, explain why empirical demonstrations of this coexistence mechanism are rare, noting, however, that the difficulty to detect relative nonlinearity in the field [...]

q-bio.PE↗

arXiv2014

Technical Note: Approximate Bayesian parameterization of a process-based tropical forest model

Inverse parameter estimation of process-based models is a long-standing problem in many scientific disciplines. A key question for inverse parameter estimation is how to define the metric that quantifies how well model predictions fit to the data. This metric can be expressed by general cost or objective functions, but statistical inversion methods require a particular metric, the probability of observing the data given the model parameters, known as the likelihood. For technical and computational reasons, likelihoods for process-based stochastic models are usually based on general assumptions about variability in the observed data, and not on the stochasticity generated by the model. Only in recent years have new methods become available that allow the generation of likelihoods directly from stochastic simulations. Previous applications of these approximate Bayesian methods have concentrated on relatively simple models. Here, we report on the application of a simulation-based likelihood approximation for FORMIND, a parameter-rich individual-based model of tropical forest dynamics. We show that approximate Bayesian inference, based on a parametric likelihood approximation placed in a conventional Markov chain Monte Carlo (MCMC) sampler, performs well in retrieving known parameter values from virtual inventory data generated by the forest model. We analyze the results of the parameter estimation, examine its sensitivity to the choice and aggregation of model outputs and observed data (summary statistics), and demonstrate the application of this method by fitting the FORMIND model to field data from an Ecuadorian tropical forest. Finally, we discuss how this approach differs from approximate Bayesian computation (ABC), another method commonly used to generate simulation-based likelihood approximations. Our results demonstrate that simulation-based inference, [...]

q-bio.PE↗

arXiv2013

Does "model-free" forecasting really outperform the "true" model? A reply to Perretti et al

Estimating population models from uncertain observations is an important problem in ecology. Perretti et al. observed that standard Bayesian state-space solutions to this problem may provide biased parameter estimates when the underlying dynamics are chaotic. Consequently, forecasts based on these estimates showed poor predictive accuracy compared to simple "model-free" methods, which lead Perretti et al. to conclude that "Model-free forecasting outperforms the correct mechanistic model for simulated and experimental data". However, a simple modification of the statistical methods also suffices to remove the bias and reverse their results.

q-bio.PE↗

arXiv2010

Smart spatial incentives for market-based conservation

Market-based instruments such as payments, auctions or tradable permits have been proposed as flexible and cost-effective instruments for biodiversity conservation on private lands. Trading the service of conservation requires one to define a metric that determines the extent to which a conserved site adds to the regional conservation objective. Yet, while markets for conservation are widely discussed and increasingly applied, little research has been conducted on explicitly accounting for spatial ecological processes in the trading. In this paper, we use a coupled ecological economic simulation model to examine how spatial connectivity may be considered in the financial incentives created by a market-based conservation scheme. Land use decisions, driven by changing conservation costs and the conservation market, are simulated by an agent-based model of land users. On top of that, a metapopulation model evaluates the conservational success of the market. We find that optimal spatial incentives for agents correlate with species characteristics such as the dispersal distance, but they also depend on the spatio-temporal distribution of conservation costs. We conclude that a combined analysis of ecological and socio-economic conditions should be applied when designing market instruments to protect biodiversity.

q-bio.PE↗

arXiv2010

Stay by thy neighbor? Social organization determines the efficiency of biodiversity markets with spatial incentives

Market-based conservation instruments, such as payments, auctions or tradable permits, are environmental policies that create financial incentives for landowners to engage in voluntary conservation on their land. But what if ecological processes operate across property boundaries and land use decisions on one property influence ecosystem functions on neighboring sites? This paper examines how to account for such spatial externalities when designing market-based conservation instruments. We use an agent-based model to analyze different spatial metrics and their implications on land use decisions in a dynamic cost environment. The model contains a number of alternative submodels which differ in incentive design and social interactions of agents, the latter including coordinating as well as cooperating behavior of agents. We find that incentive design and social interactions have a strong influence on the spatial allocation and the costs of the conservation market.

physics.soc-ph↗