“…Using the 'cforest' function in the R package 'party' (Version 1.3-5) (Hothorn et al 2013) the outcomes of 500 conditional inference tree models (Hothorn et al 2006) were compiled and the relative importance of explanatory variables were ranked across all models. The conditional inference algorithm is based on a random forest machine-learning algorithm (Breiman 2001) used in many ecological modeling contexts (e.g., (Fox et al 2017, Mi et al 2017, Mohapatra et al 2019, Shearman et al 2019).…”
Land-use history is the template upon which contemporary plant and tree populations establish and interact with one another and exerts a legacy on the structure and dynamics of species assemblages and ecosystems. We use the first census (2010-2014) of a 35-ha forest-dynamics plot at the Harvard Forest in central Massachusetts to explore such legacies. The plot includes 108,632 live stems ≥ 1 cm in diameter (2215 individuals/ha) and 7,595 dead stems ≥ 5 cm in diameter. Fifty-one woody plant species were recorded in the plot, but two tree species - Tsuga canadensis (eastern hemlock) and Acer rubrum (red maple) - and one shrub - Ilex verticillata (winterberry) -comprised 56% of all stems. Live tree basal area averaged 42.25 m2/ha, of which 84% was represented by T. canadensis (14.0 m2/ha), Quercus rubra (northern red oak; 9.6 m2/ha), A. rubrum (7.2 m2/ha) and Pinus strobus (eastern white pine; 4.4 m2/ha). These same four species also comprised 78% of the live aboveground biomass, which averaged 245.2 Mg/ha, and were significantly clumped at distances up to 50 m within the plot. Spatial distributions of A. rubrum and Q. rubra showed negative intraspecific correlations in diameters up to at least a 150-m spatial lag, likely indicative of competition for light in dense forest patches. Bivariate marked point-pattern analysis showed that T. canadensis and Q. rubra diameters were negatively associated with one another, indicating resource competition for light. Distribution and abundance of the common overstory species are predicted best by soil type, tree neighborhood effects, and two aspects of land-use history: when fields were abandoned in the late 19th century and the succeeding forest types recorded in 1908. In contrast, a history of intensive logging prior to 1950 and a damaging hurricane in 1938 appear to have had little effect on the distribution and abundance of present-day tree species.
“…Using the 'cforest' function in the R package 'party' (Version 1.3-5) (Hothorn et al 2013) the outcomes of 500 conditional inference tree models (Hothorn et al 2006) were compiled and the relative importance of explanatory variables were ranked across all models. The conditional inference algorithm is based on a random forest machine-learning algorithm (Breiman 2001) used in many ecological modeling contexts (e.g., (Fox et al 2017, Mi et al 2017, Mohapatra et al 2019, Shearman et al 2019).…”
Land-use history is the template upon which contemporary plant and tree populations establish and interact with one another and exerts a legacy on the structure and dynamics of species assemblages and ecosystems. We use the first census (2010-2014) of a 35-ha forest-dynamics plot at the Harvard Forest in central Massachusetts to explore such legacies. The plot includes 108,632 live stems ≥ 1 cm in diameter (2215 individuals/ha) and 7,595 dead stems ≥ 5 cm in diameter. Fifty-one woody plant species were recorded in the plot, but two tree species - Tsuga canadensis (eastern hemlock) and Acer rubrum (red maple) - and one shrub - Ilex verticillata (winterberry) -comprised 56% of all stems. Live tree basal area averaged 42.25 m2/ha, of which 84% was represented by T. canadensis (14.0 m2/ha), Quercus rubra (northern red oak; 9.6 m2/ha), A. rubrum (7.2 m2/ha) and Pinus strobus (eastern white pine; 4.4 m2/ha). These same four species also comprised 78% of the live aboveground biomass, which averaged 245.2 Mg/ha, and were significantly clumped at distances up to 50 m within the plot. Spatial distributions of A. rubrum and Q. rubra showed negative intraspecific correlations in diameters up to at least a 150-m spatial lag, likely indicative of competition for light in dense forest patches. Bivariate marked point-pattern analysis showed that T. canadensis and Q. rubra diameters were negatively associated with one another, indicating resource competition for light. Distribution and abundance of the common overstory species are predicted best by soil type, tree neighborhood effects, and two aspects of land-use history: when fields were abandoned in the late 19th century and the succeeding forest types recorded in 1908. In contrast, a history of intensive logging prior to 1950 and a damaging hurricane in 1938 appear to have had little effect on the distribution and abundance of present-day tree species.
“…For instance, GP has been used to project heat tolerance in diverse wheat lines ( Sukumaran et al, 2017 ; Juliana et al, 2019 ), and bovine genotypes ( Garner et al, 2016 ), in all cases more as a proof of concept. Similarly, ML approaches have not only deepened our understating on populations’ range shifts in the light of thermal variation ( Rippke et al, 2016 ; Garah and Bentouati, 2019 ; Mohapatra et al, 2019 ) but also assisted eGWAS of critical temperature thresholds ( Chen et al, 2018 ) and phylogenetic forecasting in plants ( Park et al, 2020 ). However, since GP and ML are both cutting-edge tools, there is still room and need for new developments.…”
Molecular evolution offers an insightful theory to interpret the genomic consequences of thermal adaptation to previous events of climate change beyond range shifts. However, disentangling often mixed footprints of selective and demographic processes from those due to lineage sorting, recombination rate variation, and genomic constrains is not trivial. Therefore, here we condense current and historical population genomic tools to study thermal adaptation and outline key developments (genomic prediction, machine learning) that might assist their utilization for improving forecasts of populations’ responses to thermal variation. We start by summarizing how recent thermal-driven selective and demographic responses can be inferred by coalescent methods and in turn how quantitative genetic theory offers suitable multi-trait predictions over a few generations via the breeder’s equation. We later assume that enough generations have passed as to display genomic signatures of divergent selection to thermal variation and describe how these footprints can be reconstructed using genome-wide association and selection scans or, alternatively, may be used for forward prediction over multiple generations under an infinitesimal genomic prediction model. Finally, we move deeper in time to comprehend the genomic consequences of thermal shifts at an evolutionary time scale by relying on phylogeographic approaches that allow for reticulate evolution and ecological parapatric speciation, and end by envisioning the potential of modern machine learning techniques to better inform long-term predictions. We conclude that foreseeing future thermal adaptive responses requires bridging the multiple spatial scales of historical and predictive environmental change research under modern cohesive approaches such as genomic prediction and machine learning frameworks.
“…A Random Forest algorithm, assuming non-parametric distribution, was employed to predict the potential distribution of Betula utilis niche in the Hindu-Kush Himalayan (HKH) region by Mohapatra et al (2019). The occurrence in the last interglacial, current and future scenarios suggest that it is more likely to occur at elevation ranges of 2601-2800 m, 3801-4000 m, and 4201-4400 m, respectively.…”
Biodiversity is continually transformed by a changing climate. Conditions change across the face of the planet at variable pace leading to rearrangements of biological associations. The carbon cycle and the water cycle, arguably the two most important large-scale processes for life on Earth; depend on biodiversity at genetic, species, and ecosystem levels and can yield feedbacks to climate change. India is no less affected through this feedback mechanism of climate change and had shown its cause and effect association in several studies. In this special issue we present 25 papers contributed by ca 90 authors from India and elsewhere those discuss wide-ranging aspects of biodiversity and climate change. These contributions are based on presentations made at the 2nd International Workshop on Biodiversity and Climate Change (BDCC-2018) held on 24-27-February 2018 at the Indian Institute of Technology Kharagpur, India. The papers are arranged in six sections: Plant (and lichen) Diversity and Climate; Plant Diversity Pattern and Environmental Heterogeneity; Forest Biomass and Carbon; Plant Diversity and Remote Sensing; Species Distribution Modelling; and Animal Diversity, Soil and Biotechnology. Included amongst the contributions are ones using a national database on plant diversity, describing vegetation carbon and biomass sequestration patterns, utilizing remote sensing to assess plant diversity proxies and conservation prioritization, employing species distribution models to analyze climate change scenarios, using acoustics indices for rapid assessment of biodiversity, addressing the soil micro-biome and environmental stress on medicinal plants.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.