Fine scale prediction of ecological community composition using a two-step sequential Machine Learning ensemble

Prediction is one of the last frontiers in ecology. Indeed, predicting fine-scale species composition in natural systems is a complex challenge as multiple abiotic and biotic processes operate simultaneously to determine local species abundances. On the one hand, species intrinsic performance and their tolerance limits to different abiotic pressures modulate species abundances. On the other hand there is growing recognition that species interactions play an equally important role in limiting or promoting such abundances within ecological communities. Here, we present a joint effort between ecologists and data scientists to use data-driven models to predict species abundances using reasonably easy to obtain data. We propose a sequential data-driven modeling approach that in a first step predicts the potential species abundances based on abiotic variables, and in a second step uses these predictions to model the realized abundances once accounting for species competition. Using a curated data set over five years we predict fine-scale species abundances in a highly diverse annual plant community. Our models show a remarkable spatial predictive accuracy using only easy-to-measure variables in the field, yet such predictive power is lost when temporal dynamics are taken into account. This result suggests that predicting future abundances requires longer time series analysis to capture enough variability. In addition, we show that these data-driven models can also suggest how to improve mechanistic models by adding missing variables that affect species performance such as particular soil conditions (e.g. carbonate availability in our case). Robust models for predicting fine-scale species composition informed by the mechanistic understanding of the underlying abiotic and biotic processes can be a pivotal tool for conservation, especially given the human-induced rapid environmental changes we are experiencing. This objective can be achieved by promoting the knowledge gained with classic modelling approaches in ecology and recently developed data-driven models.

Download Full-text

Fine scale prediction of ecological community composition using a two-step sequential machine learning ensemble

10.1101/2021.03.24.436771 ◽

2021 ◽

Author(s):

Icíar Civantos ◽

Javier García-Algarra ◽

David García-Callejas ◽

Javier Galeano ◽

Oscar Godoy ◽

...

Keyword(s):

Species Composition ◽

Species Interactions ◽

Predictive Power ◽

Environmental Changes ◽

Temporal Dynamics ◽

Data Driven ◽

Series Data ◽

Soil Conditions ◽

Fine Scale ◽

Species Abundances

Prediction is one the last frontiers in ecology. Indeed, predicting fine scale species composition in natural systems is a complex challenge as multiple abiotic and biotic processes operate simultaneously to determine local species abundances. On the one hand, species intrinsic performance and their tolerance limits to different abiotic pressures modulate species abundances. On the other hand there is growing recognition that species interactions play an equally important role in limiting or promoting such abundances within ecological communities. Here, we present a joint effort between ecologists and data scientists to use data-driven models informed by ecological deterministic processes to predict species abundances using reasonably easy to obtain data. To overcome the classical procedure in ecology of parameterizing complex population models of multiple species interactions and poor predictive power, we followed instead a sequential data-driven modeling approach. We use this framework to predict species abundances over 5 years in a highly diverse annual plant community. Our models show a surprisingly high spatial predictive accuracy using only easy to measure variables in the field, yet such predictive power is lost when temporal dynamics are taken into account. This result suggest that predicting the temporal dimension of our system requires longer time series data. Such data would likely capture additional sources of variability that determine temporal patterns of species abundances. In addition, we show that these data-driven models can also inform back mechanistic models of important missing variables that affect species performance such as particular soil conditions (e.g. carbonate availability in our case). Being able to gain predictive power at fine-scale species composition while maintaining a mechanistic understanding of the underlying processes can be a pivotal tool for conservation, specially given the human induced rapid environmental changes we are experiencing. Here, we document how this objective can be achieved by promoting the interplay between classic modelling approaches in ecology and recently developed data-driven models.

Download Full-text

On the accuracy of paleodiversity reconstructions: a case study in Antarctic Neogene radiolarians

Paleobiology ◽

10.1666/12016 ◽

2013 ◽

Vol 39 (3) ◽

pp. 491-509 ◽

Cited By ~ 7

Author(s):

Johan Renaudie ◽

David B. Lazarus

Keyword(s):

Environmental Changes ◽

Ecological Change ◽

Significant Drop ◽

Data Set ◽

Species Abundances ◽

History Of ◽

Ecological Event ◽

Plankton Diversity ◽

Paleoceanographic Change ◽

Species Occurrences

The deep-sea Cenozoic planktonic microfossil record has the unique characteristics of continuously well-preserved populations of most species, with virtually unlimited sample size, and therefore constitutes, in principle, a major resource for macroevolutionary research. Antarctic Neogene radiolarians in particular, are diverse, abundant and consistently well-preserved and evolved rapidly. This fauna is, in theory, a near-perfect testing ground for paleodiversity reconstructions. In this study we determined the diversity history of these faunas from a new quantitative, taxonomically complete data set from Neogene and Quaternary sections at several Antarctic sites. The pattern retrieved by our whole-fauna data set shows a significant, largely extinctionless ecological change in faunal composition and decrease in the evenness of species' abundances during the late Miocene, followed 3 Myr later, at around 5 Ma, by a significant drop in diversity. We tentatively associate this ecological event with a synchronous, regional change in the composition of the primary producers, but as yet cannot identify any environmental changes associated with the later extinction. Further, our whole-fauna diversity history was compared to diversity computed from much less complete, biostratigraphically oriented studies of species' occurrences, compiled in the Neptune database and reconstructed by using subsampling methodologies. Comparison of our whole-fauna and subsampling-reconstructed diversity patterns shows that the first-order trends are the same in both, suggesting that, to some degree, such literature compilations can be used to explore diversity history of plankton. However, our results also highlight substantial errors and distortions in the reconstructed diversity which make it poorly suited to more-detailed studies (e.g., for comparison of diversity history with paleoenvironmental history). We conclude that detailed studies of plankton diversity, and particularly those attempting to understand the relation between diversity and paleoceanographic change, should be based on taxonomically comprehensive, quantitative data.

Download Full-text

Linking biotic homogenisation with large-scale changes of species associations

10.1101/2020.11.13.380956 ◽

2020 ◽

Author(s):

Stanislas Rigal ◽

Vincent Devictor ◽

Pierre Gaüzère ◽

Sonia Kéfi ◽

Jukka T. Forsman ◽

...

Keyword(s):

Spatial Distribution ◽

Global Change ◽

Species Composition ◽

Species Interactions ◽

Temporal Dynamics ◽

Temporal Changes ◽

Species Association ◽

Β Diversity ◽

Biotic Homogenisation ◽

Spatio Temporal

AbstractAimThe impact of global change on biodiversity is commonly assessed in terms of changes in species distributions, species richness and species composition across communities. Whether and how much interactions between species are also changing is much less documented and mostly limited to local studies of ecological networks. Moreover, we largely ignore how biotic homogenisation (i.e. the replacement of a set of diverse and mainly specialist species by a few generalists) is affecting or being affected by changes in the structure of species interactions. Here, we approximate species interactions with species associations based on the correlation in species spatial co-occurrence to understand the spatio-temporal changes of species interactions and their relationship to biotic homogenisation.LocationFrance.Time period2001-2017.Major taxa studiedCommon breeding birds.MethodsWe use network approaches to build three community-aggregated indices to characterise species associations and we compare them to changes in species composition in communities. We evaluate the spatial distribution and temporal dynamics of these indices in a dataset of bird co-abundances of more than 100 species monitored for 17 years (2001-2017) from 1,969 sites across France. We finally test whether spatial and temporal changes of species associations are related to species homogenisation estimated as the spatio-temporal dynamics of β-diversity.ResultsWe document a non-random spatial distribution of both structure and temporal changes in species association networks. We also report a directional change in species associations linked to β-diversity modifications in space and time, suggesting that biotic homogenisation affects not only species composition but also species associations.Main ConclusionsOur study highlights the importance of evaluating changes of species association networks, in addition to species turnover when studying biodiversity responses to global change.

Download Full-text

A Review and evaluation of Machine Translation methods for Lumasaaba

Journal of Digital Science ◽

10.33847/2686-8296.2.1_1 ◽

2020 ◽

pp. 3-17

Author(s):

Peter Nabende

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Machine Translation ◽

Language Processing ◽

Research Area ◽

Data Driven ◽

East African ◽

Data Set ◽

African Languages ◽

Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

Download Full-text

Langfristige Entwicklung von zwei Waldgesellschaften im Białowieża-Urwald

Schweizerische Zeitschrift fur Forstwesen ◽

10.3188/szf.2008.0080 ◽

2008 ◽

Vol 159 (4) ◽

pp. 80-90 ◽

Cited By ~ 3

Author(s):

Bogdan Brzeziecki ◽

Feliks Eugeniusz Bernadzki

Keyword(s):

Species Composition ◽

Tree Species ◽

Stand Structure ◽

Temporal Dynamics ◽

Structural Parameters ◽

Forest Communities ◽

Natural Forests ◽

Tree Species Composition ◽

Strong Trend ◽

Long Term Study

The results of a long-term study on the natural forest dynamics of two forest communities on one sample plot within the Białowieża National Park in Poland are presented. The two investigated forest communities consist of the Pino-Quercetum and the Tilio-Carpinetum type with the major tree species Pinus sylvestris, Picea abies, Betula sp., Quercus robur, Tilia cordata and Carpinus betulus. The results reveal strong temporal dynamics of both forest communities since 1936 in terms of tree species composition and of general stand structure. The four major tree species Scots pine, birch, English oak and Norway spruce, which were dominant until 1936, have gradually been replaced by lime and hornbeam. At the same time, the analysis of structural parameters indicates a strong trend towards a homogenization of the vertical stand structure. Possible causes for these dynamics may be changes in sylviculture, climate change and atmospheric deposition. Based on the altered tree species composition it can be concluded that a simple ≪copying≫ (mimicking) of the processes taking place in natural forests may not guarantee the conservation of the multifunctional character of the respective forests.

Download Full-text

Simultaneous spatiotemporal super-resolution and multi-parametric fluorescence microscopy

Nature Communications ◽

10.1038/s41467-021-22002-9 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Jagadish Sankaran ◽

Harikrushnan Balasubramanian ◽

Wai Hoh Tang ◽

Xue Wen Ng ◽

Adrian Röllin ◽

...

Keyword(s):

Single Molecule ◽

Temporal Dynamics ◽

Growth Factor Receptor ◽

Super Resolution ◽

Actin Binding ◽

Biological Knowledge ◽

Data Set ◽

Epidermal Growth ◽

Molecular Brightness ◽

Super Resolution Microscopy

AbstractSuper-resolution microscopy and single molecule fluorescence spectroscopy require mutually exclusive experimental strategies optimizing either temporal or spatial resolution. To achieve both, we implement a GPU-supported, camera-based measurement strategy that highly resolves spatial structures (~100 nm), temporal dynamics (~2 ms), and molecular brightness from the exact same data set. Simultaneous super-resolution of spatial and temporal details leads to an improved precision in estimating the diffusion coefficient of the actin binding polypeptide Lifeact and corrects structural artefacts. Multi-parametric analysis of epidermal growth factor receptor (EGFR) and Lifeact suggests that the domain partitioning of EGFR is primarily determined by EGFR-membrane interactions, possibly sub-resolution clustering and inter-EGFR interactions but is largely independent of EGFR-actin interactions. These results demonstrate that pixel-wise cross-correlation of parameters obtained from different techniques on the same data set enables robust physicochemical parameter estimation and provides biological knowledge that cannot be obtained from sequential measurements.

Download Full-text

A Data-Driven Surrogate Approach for the Temporal Stability Forecasting of Vegetation Covered Dikes

Water ◽

10.3390/w13010107 ◽

2021 ◽

Vol 13 (1) ◽

pp. 107

Author(s):

Elahe Jamalinia ◽

Faraz S. Tehrani ◽

Susan C. Steele-Dunne ◽

Philip J. Vardon

Keyword(s):

Numerical Simulation ◽

Water Flux ◽

Temporal Stability ◽

Synthetic Data ◽

Climatic Conditions ◽

Training Data ◽

Data Driven ◽

Data Set ◽

Surface Cracking ◽

Real Time Analysis

Climatic conditions and vegetation cover influence water flux in a dike, and potentially the dike stability. A comprehensive numerical simulation is computationally too expensive to be used for the near real-time analysis of a dike network. Therefore, this study investigates a random forest (RF) regressor to build a data-driven surrogate for a numerical model to forecast the temporal macro-stability of dikes. To that end, daily inputs and outputs of a ten-year coupled numerical simulation of an idealised dike (2009–2019) are used to create a synthetic data set, comprising features that can be observed from a dike surface, with the calculated factor of safety (FoS) as the target variable. The data set before 2018 is split into training and testing sets to build and train the RF. The predicted FoS is strongly correlated with the numerical FoS for data that belong to the test set (before 2018). However, the trained model shows lower performance for data in the evaluation set (after 2018) if further surface cracking occurs. This proof-of-concept shows that a data-driven surrogate can be used to determine dike stability for conditions similar to the training data, which could be used to identify vulnerable locations in a dike network for further examination.

Download Full-text

Repeated surveying over 6 years reveals that fine-scale habitat variables are key to tropical mountain ant assemblage composition and functional diversity

Scientific Reports ◽

10.1038/s41598-020-80077-8 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Mulalo M. Muluvhahothe ◽

Grant S. Joseph ◽

Colleen L. Seymour ◽

Thinandavha C. Munyai ◽

Stefan H. Foord

Keyword(s):

Climate Change ◽

Species Composition ◽

High Altitude ◽

Functional Diversity ◽

Large Scale ◽

Climate Models ◽

Spatial Scales ◽

Abiotic Factors ◽

Composition Analysis ◽

Fine Scale

AbstractHigh-altitude-adapted ectotherms can escape competition from dominant species by tolerating low temperatures at cooler elevations, but climate change is eroding such advantages. Studies evaluating broad-scale impacts of global change for high-altitude organisms often overlook the mitigating role of biotic factors. Yet, at fine spatial-scales, vegetation-associated microclimates provide refuges from climatic extremes. Using one of the largest standardised data sets collected to date, we tested how ant species composition and functional diversity (i.e., the range and value of species traits found within assemblages) respond to large-scale abiotic factors (altitude, aspect), and fine-scale factors (vegetation, soil structure) along an elevational gradient in tropical Africa. Altitude emerged as the principal factor explaining species composition. Analysis of nestedness and turnover components of beta diversity indicated that ant assemblages are specific to each elevation, so species are not filtered out but replaced with new species as elevation increases. Similarity of assemblages over time (assessed using beta decay) did not change significantly at low and mid elevations but declined at the highest elevations. Assemblages also differed between northern and southern mountain aspects, although at highest elevations, composition was restricted to a set of species found on both aspects. Functional diversity was not explained by large scale variables like elevation, but by factors associated with elevation that operate at fine scales (i.e., temperature and habitat structure). Our findings highlight the significance of fine-scale variables in predicting organisms’ responses to changing temperature, offering management possibilities that might dilute climate change impacts, and caution when predicting assemblage responses using climate models, alone.

Download Full-text

Genotyping of Two Mediterranean Trout Populations in Central-Southern Italy for Conservation Purposes Using a Rainbow-Trout-Derived SNP Array

Animals ◽

10.3390/ani11061803 ◽

2021 ◽

Vol 11 (6) ◽

pp. 1803

Author(s):

Valentino Palombo ◽

Elena De Zio ◽

Giovanna Salvatore ◽

Stefano Esposito ◽

Nicolaia Iaffaldano ◽

...

Keyword(s):

Rainbow Trout ◽

Genetic Structure ◽

Fishery Management ◽

Snp Array ◽

Fine Scale ◽

Principal Coordinates Analysis ◽

Data Set ◽

Management Actions ◽

Principal Coordinates ◽

Mediterranean Trout

Mediterranean trout is a freshwater fish of particular interest with economic significance for fishery management, aquaculture and conservation biology. Unfortunately, native trout populations’ abundance is significantly threatened by anthropogenic disturbance. The introduction of commercial hatchery strains for recreation activities has compromised the genetic integrity status of native populations. This work assessed the fine-scale genetic structure of Mediterranean trout in the two main rivers of Molise region (Italy) to support conservation actions. In total, 288 specimens were caught in 28 different sites (14 per basins) and genotyped using the Affymetrix 57 K rainbow-trout-derived SNP array. Population differentiation was analyzed using pairwise weighted FST and overall F-statistic estimated by locus-by-locus analysis of molecular variance. Furthermore, an SNP data set was processed through principal coordinates analysis, discriminant analysis of principal components and admixture Bayesian clustering analysis. Firstly, our results demonstrated that rainbow trout SNP array can be successfully used for Mediterranean trout genotyping. In fact, despite an overwhelming number of loci that resulted as monomorphic in our populations, it must be emphasized that the resulted number of polymorphic loci (i.e., ~900 SNPs) has been sufficient to reveal a fine-scale genetic structure in the investigated populations, which is useful in supporting conservation and management actions. In particular, our findings allowed us to select candidate sites for the collection of adults, needed for the production of genetically pure juvenile trout, and sites to carry out the eradication of alien trout and successive re-introduction of native trout.

Download Full-text

Mapping the Spatial-Temporal Dynamics of Vegetation Response Lag to Drought in a Semi-Arid Region

Remote Sensing ◽

10.3390/rs11161873 ◽

2019 ◽

Vol 11 (16) ◽

pp. 1873 ◽

Cited By ~ 6

Author(s):

Li Hua ◽

Huidong Wang ◽

Haigang Sui ◽

Brian Wardlow ◽

Michael J. Hayes ◽

...

Keyword(s):

Vegetation Index ◽

Temporal Dynamics ◽

Risk Mitigation ◽

Scientific Information ◽

Gaussian Function ◽

Drought Risk ◽

Severe Drought ◽

Similar Response ◽

Vegetation Types ◽

Data Set

Drought, as an extreme climate event, affects the ecological environment for vegetation and agricultural production. Studies of the vegetative response to drought are paramount to providing scientific information for drought risk mitigation. In this paper, the spatial-temporal pattern of drought and the response lag of vegetation in Nebraska were analyzed from 2000 to 2015. Based on the long-term Daymet data set, the standard precipitation index (SPI) was computed to identify precipitation anomalies, and the Gaussian function was applied to obtain temperature anomalies. Vegetation anomaly was identified by dynamic time warping technique using a remote sensing Normalized Difference Vegetation Index (NDVI) time series. Finally, multilayer correlation analysis was applied to obtain the response lag of different vegetation types. The results show that Nebraska suffered severe drought events in 2002 and 2012. The response lag of vegetation to drought typically ranged from 30 to 45 days varying for different vegetation types and human activities (water use and management). Grasslands had the shortest response lag (~35 days), while forests had the longest lag period (~48 days). For specific crop types, the response lag of winter wheat varied among different regions of Nebraska (35–45 days), while soybeans, corn and alfalfa had similar response lag times of approximately 40 days.

Download Full-text