Deep learning models map rapid plant species changes from citizen science and remote sensing data.

Anthropogenic habitat destruction and climate change are reshaping the geographic distribution of plants worldwide. However, we are still unable to map species shifts at high spatial, temporal, and taxonomic resolution. Here, we develop a deep learning model trained using remote sensing images from California paired with half a million citizen science observations that can map the distribution of over 2,000 plant species. Our model-Deepbiosphere-not only outperforms many common species distribution modeling approaches (AUC 0.95 vs. 0.88) but can map species at up to a few meters resolution and finely delineate plant communities with high accuracy, including the pristine and clear-cut forests of Redwood National Park. These fine-scale predictions can further be used to map the intensity of habitat fragmentation and sharp ecosystem transitions across human-altered landscapes. In addition, from frequent collections of remote sensing data, Deepbiosphere can detect the rapid effects of severe wildfire on plant community composition across a 2-y time period. These findings demonstrate that integrating public earth observations and citizen science with deep learning can pave the way toward automated systems for monitoring biodiversity change in real-time worldwide.

Predicting undetected native vascular plant diversity at a global scale.

Vascular plants are diverse and a major component of terrestrial ecosystems, yet their geographic distributions remain incomplete. Here, I present a global database of vascular plant distributions by integrating species distribution models calibrated to species' dispersal ability and natural habitats to predict native range maps for 201,681 vascular plant species into unsurveyed areas. Using these maps, I uncover unique patterns of native vascular plant diversity, endemism, and phylogenetic diversity revealing hotspots in underdocumented biodiversity-rich regions. These hotspots, based on detailed species-level maps, show a pronounced latitudinal gradient, strongly supporting the theory of increasing diversity toward the equator. I trained random forest models to extrapolate diversity patterns under unbiased global sampling and identify overlaps with modeled estimations but unveiled cryptic hotspots that were not captured by modeled estimations. Only 29% to 36% of extrapolated plant hotspots are inside protected areas, leaving more than 60% outside and vulnerable. However, the unprotected hotspots harbor species with unique attributes that make them good candidates for conservation prioritization.

Biodiversity and infrastructure interact to drive tourism to and within Costa Rica.

SignificanceTourism accounts for roughly 10% of global gross domestic product, with nature-based tourism its fastest-growing sector in the past 10 years. Nature-based tourism can theoretically contribute to local and sustainable development by creating attractive livelihoods that support biodiversity conservation, but whether tourists prefer to visit more biodiverse destinations is poorly understood. We examine this question in Costa Rica and find that more biodiverse places tend indeed to attract more tourists, especially where there is infrastructure that makes these places more accessible. Safeguarding terrestrial biodiversity is critical to preserving the substantial economic benefits that countries derive from tourism. Investments in both biodiversity conservation and infrastructure are needed to allow biodiverse countries to rely on tourism for their sustainable development.

Uncovering Broad Macroecological Patterns by Comparing the Shape of Species' Distributions along Environmental Gradients.

AbstractSpecies' distributions can take many different forms. For example, fat-tailed or skewed distributions are very common in nature, as these can naturally emerge as a result of individual variability and asymmetric environmental tolerances, respectively. Studying the basic shape of distributions can teach us a lot about the ways climatic processes and historical contingencies shape ecological communities. Yet we still lack a general understanding of how their shapes and properties compare to each other along gradients. Here, we use Bayesian nonlinear models to quantify range shape properties in empirical plant distributions. With this approach, we are able to distil the shape of plant distributions and compare them along gradients and across species. Studying the relationship between distribution properties, we revealed the existence of broad macroecological patterns along environmental gradients-such as those expected from Rapoport's rule and the abiotic stress limitation hypothesis. We also find that some aspects of the shape of observed ranges-such as kurtosis and skewness of the distributions-could be intrinsic properties of species or the result of their historical contexts. Overall, our modeling approach and results untangle the general shape of plant distributions and provide a mapping of how this changes along environmental gradients.

The influence of climate change on the future distribution of two Thymus species in Iran: MaxEnt model-based prediction.

Within a few decades, the species habitat was reshaped at an alarming rate followed by climate change, leading to mass extinction, especially for sensitive species. Species distribution models (SDMs), which estimate both present and future species distribution, have been extensively developed to investigate the impacts of climate change on species distribution and assess habitat suitability. In the West Asia essential oils of T. daenensis and T. kotschyanus include high amounts of thymol and carvacrol and are commonly used as herbal tea, spice, flavoring agents and medicinal plants. Therefore, this study aimed to model these Thymus species in Iran using the MaxEnt model under two representative concentration pathways (RCP 4.5 and RCP 8.5) for the years 2050 and 2070. The findings revealed that the mean temperature of the warmest quarter (bio10) was the most significant variable affecting the distribution of T. daenensis. In the case of T. kotschyanus, slope percentage was the primary influencing factor. The MaxEnt modeling also demonstrated excellent performance, as indicated by all the Area Under the Curve (AUC) values exceeding 0.9. Moreover, based on the projections, the two mentioned species are expected to undergo negative area changes in the coming years. These results can serve as a valuable achievement for developing adaptive management strategies aimed at enhancing protection and sustainable utilization in the context of global climate change.

Soil properties constrain predicted poleward migration of plants under climate change.

Many plant species are predicted to migrate poleward in response to climate change. Species distribution models (SDMs) have been widely used to quantify future suitable habitats, but they often neglect soil properties, despite the importance of soil for plant fitness. As soil properties often change along latitudinal gradients, higher-latitude soils might be more or less suitable than average conditions within the current ranges of species, thereby accelerating or slowing potential poleward migration. In this study, we built three SDMs - one with only climate predictors, one with only soil predictors, and one with both - for each of 1870 plant species in Eastern North America, in order to investigate the relative importance of soil properties in determining plant distributions and poleward shifts under climate change. While climate variables were the most important predictors, soil properties also had a substantial influence on continental-scale plant distributions. Under future climate scenarios, models including soil predicted much smaller northward shifts in distributions than climate-only models (c. 40% reduction). Our findings strongly suggest that high-latitude soils are likely to impede ongoing plant migration, and they highlight the necessity of incorporating soil properties into models and predictions for plant distributions and migration under environmental change.

Pushing the envelope: do narrowly and widely distributed Eucalyptus species differ in response to climate warming?

Contemporary climate change will push many tree species into conditions that are outside their current climate envelopes. Using the Eucalyptus genus as a model, we addressed whether species with narrower geographical distributions show constrained ability to cope with warming relative to species with wider distributions, and whether this ability differs among species from tropical and temperate climates. We grew seedlings of widely and narrowly distributed Eucalyptus species from temperate and tropical Australia in a glasshouse under two temperature regimes: the summer temperature at seed origin and +3.5°C. We measured physical traits and leaf-level gas exchange to assess warming influences on growth rates, allocation patterns, and physiological acclimation capacity. Warming generally stimulated growth, such that higher relative growth rates early in development placed seedlings on a trajectory of greater mass accumulation. The growth enhancement under warming was larger among widely than narrowly distributed species and among temperate rather than tropical provenances. The differential growth enhancement was primarily attributable to leaf area production and adjustments of specific leaf area. Our results suggest that tree species, including those with climate envelopes that will be exceeded by contemporary climate warming, possess capacity to physiologically acclimate but may have varying ability to adjust morphology.

Incorporating plant phenological responses into species distribution models reduces estimates of future species loss and turnover.

Anthropogenetic climate change has caused range shifts among many species. Species distribution models (SDMs) are used to predict how species ranges may change in the future. However, most SDMs rarely consider how climate-sensitive traits, such as phenology, which affect individuals' demography and fitness, may influence species' ranges. Using > 120 000 herbarium specimens representing 360 plant species distributed across the eastern United States, we developed a novel 'phenology-informed' SDM that integrates phenological responses to changing climates. We compared the ranges of each species forecast by the phenology-informed SDM with those from conventional SDMs. We further validated the modeling approach using hindcasting. When examining the range changes of all species, our phenology-informed SDMs forecast less species loss and turnover under climate change than conventional SDMs. These results suggest that dynamic phenological responses of species may help them adjust their ecological niches and persist in their habitats as the climate changes. Plant phenology can modulate species' responses to climate change, mitigating its negative effects on species persistence. Further application of our framework will contribute to a generalized understanding of how traits affect species distributions along environmental gradients and facilitate the use of trait-based SDMs across spatial and taxonomic scales.

Imperiled wanderlust lichens in steppe habitats of western North America comprise geographically structured mycobiont lineages and a reversal to sexual reproduction within this asexual clade.

The northern North American Cordillera is a globally significant center of endemism. In western North America, imperiled arid steppe habitats support a number of unique species, including several endemic lichens. However, processes driving diversification and endemism in this region remain unclear. In this study, we investigate diversity and phylogeography of the threatened wanderlust lichens (mycobiont = Rhizoplaca species) which occur unattached on calcareous soils in steppe habitats in western North America. Wanderlust lichens comprise three species of lichen-forming fungi (LFF) - Rhizoplaca arbuscula, R. haydenii, and R. idahoensis (endangered, IUCN Red List) - which occur in fragmented populations in Idaho and Wyoming, with more limited populations in southeastern Montana and northern Utah. These lichens reproduce almost exclusively via large, asexual vegetative propagules. Here, our aims were to (i) assess the evolutionary origin of this group and identify phylogeographic structure, (ii) infer ancestral geographic distributions for lineages within this clade, and (iii) use species distribution modeling to better understand the distribution of contemporary populations. Using a genome-skimming approach, we generated a 19.1 Mb alignment, spanning ca. half of the complete LFF genome, from specimens collected throughout the entire range of wanderlust lichens. Based on this phylogeny we investigated phylogeographic patterns using RASP. Finally, we used MaxEnt to estimate species distribution models for R. arbuscula and R. haydenii. We inferred a highly structured topology, with clades corresponding to distinct geographic regions and morphologies represented throughout the group's distribution. We found that R. robusta, a sexually reproducing taxon, is clearly nested within this asexual lineage. Phylogeographic analyses suggest that both dispersal and vicariance played a significant role throughout the evolutionary history of the vagrant Rhizoplaca clade, with most of the dispersal events originating from the Salmon Basin in eastern Idaho - the center of diversity for this group. Despite the fact that wanderlust lichens are dispersal limited due to large, unspecialized vegetative propagules, we inferred multiple dispersal events crossing the Continental Divide. Comparing herbarium records with SDMs suggests that wanderlust lichens don't fully occupy the areas of highest distribution probability. In fact, documented records often occur in areas predicted to be only marginally suitable. These data suggest a potential mismatch between contemporary habitats outside of the center of diversity in eastern Idaho with the most suitable habitat, adding to the vulnerability of this imperiled complex of endemic lichens.

Unravelling the role of tropical cyclones in shaping present species distributions.

Driven by climate change, tropical cyclones (TCs) are predicted to change in intensity and frequency through time. Given these forecasted changes, developing an understanding of how TCs impact insular wildlife is of heightened importance. Previous work has shown that extreme weather events may shape species distributions more strongly than climatic averages; however, given the coarse spatial and temporal scales at which TC data are often reported, the influence of TCs on species distributions has yet to be explored. Using TC data from the National Hurricane Center, we developed spatially and temporally explicit species distribution models (SDMs) to examine the role of TCs in shaping present-day distributions of Puerto Rico's 10 Anolis lizard species. We created six predictor variables to represent the intensity and frequency of TCs. For each occurrence of a species, we calculated these variables for TCs that came within 500 km of the center of Puerto Rico and occurred within the 1-year window prior to when that occurrence was recorded. We also included predictor variables related to landcover, climate, topography, canopy cover and geology. We used random forests to assess model performance and variable importance in models with and without TC variables. We found that the inclusion of TC variables improved model performance for the majority of Puerto Rico's 10 anole species. The magnitude of the improvement varied by species, with generalist species that occur throughout the island experiencing the greatest improvements in model performance. Range-restricted species experienced small, almost negligible, improvements but also had more predictive models both with and without the inclusion of TC variables compared to generalist species. Our findings suggest that incorporating data on TCs into SDMs may be important for modeling insular species that are prone to experiencing these types of extreme weather events.

Potential migration pathways of broadleaved trees across the receding boreal biome under future climate change.

Climate change has triggered poleward expansions in the distributions of various taxonomic groups, including tree species. Given the ecological significance of trees as keystone species in forests and their socio-economic importance, projecting the potential future distributions of tree species is crucial for devising effective adaptation strategies for both biomass production and biodiversity conservation in future forest ecosystems. Here, we fitted physiographically informed habitat suitability models (HSMs) at 50-m resolution across Sweden (55-68° N) to estimate the potential northward expansion of seven broadleaved tree species within their leading-edge distributions in Europe under different future climate change scenarios and for different time periods. Overall, we observed that minimum temperature was the most crucial variable for comprehending the spatial distribution of broadleaved tree species at their cold limits. Our HSMs projected a complex range expansion pattern for 2100, with individualistic differences among species. However, a frequent and rather surprising pattern was a northward expansion along the east coast followed by narrow migration pathways along larger valleys towards edaphically suitable areas in the north-west, where most of the studied species were predicted to expand. The high-resolution maps generated in this study offer valuable insights for our understanding of range shift dynamics at the leading edge of southern tree species as they expand into the receding boreal biome. These maps suggest areas where broadleaved tree species could already be translocated to anticipate forest and biodiversity conservation adaptation efforts in the face of future climate change.

Pushed waves, trailing edges, and extreme events: Eco-evolutionary dynamics of a geographic range shift in the owl limpet, Lottia gigantea.

As climatic variation re-shapes global biodiversity, understanding eco-evolutionary feedbacks during species range shifts is of increasing importance. Theory on range expansions distinguishes between two different forms: "pulled" and "pushed" waves. Pulled waves occur when the source of the expansion comes from low-density peripheral populations, while pushed waves occur when recruitment to the expanding edge is supplied by high-density populations closer to the species' core. How extreme events shape pushed/pulled wave expansion events, as well as trailing-edge declines/contractions, remains largely unexplored. We examined eco-evolutionary responses of a marine invertebrate (the owl limpet, Lottia gigantea) that increased in abundance during the 2014-2016 marine heatwaves near the poleward edge of its geographic range in the northeastern Pacific. We used whole-genome sequencing from 19 populations across >11 degrees of latitude to characterize genomic variation, gene flow, and demographic histories across the species' range. We estimated present-day dispersal potential and past climatic stability to identify how contemporary and historical seascape features shape genomic characteristics. Consistent with expectations of a pushed wave, we found little genomic differentiation between core and leading-edge populations, and higher genomic diversity at range edges. A large and well-mixed population in the northern edge of the species' range is likely a result of ocean current anomalies increasing larval settlement and high-dispersal potential across biogeographic boundaries. Trailing-edge populations have higher differentiation from core populations, possibly driven by local selection and limited gene flow, as well as high genomic diversity likely as a result of climatic stability during the Last Glacial Maximum. Our findings suggest that extreme events can drive poleward range expansions that carry the adaptive potential of core populations, while also cautioning that trailing-edge extirpations may threaten unique evolutionary variation. This work highlights the importance of understanding how both trailing and leading edges respond to global change and extreme events.

Projected climate and canopy change lead to thermophilization and homogenization of forest floor vegetation in a hotspot of plant species richness.

Mountain forests are plant diversity hotspots, but changing climate and increasing forest disturbances will likely lead to far-reaching plant community change. Projecting future change, however, is challenging for forest understory plants, which respond to forest structure and composition as well as climate. Here, we jointly assessed the effects of both climate and forest change, including wind and bark beetle disturbances, using the process-based simulation model iLand in a protected landscape in the northern Alps (Berchtesgaden National Park, Germany), asking: (1) How do understory plant communities respond to 21st-century change in a topographically complex mountain landscape, representing a hotspot of plant species richness? (2) How important are climatic changes (i.e., direct climate effects) versus forest structure and composition changes (i.e., indirect climate effects and recovery from past land use) in driving understory responses at landscape scales? Stacked individual species distribution models fit with climate, forest, and soil predictors (248 species currently present in the landscape, derived from 150 field plots stratified by elevation and forest development, overall area under the receiving operator characteristic curve = 0.86) were driven with projected climate (RCP4.5 and RCP8.5) and modeled forest variables to predict plant community change. Nearly all species persisted in the landscape in 2050, but on average 8% of the species pool was lost by the end of the century. By 2100, landscape mean species richness and understory cover declined (-13% and -8%, respectively), warm-adapted species increasingly dominated plant communities (i.e., thermophilization, +12%), and plot-level turnover was high (62%). Subalpine forests experienced the greatest richness declines (-16%), most thermophilization (+17%), and highest turnover (67%), resulting in plant community homogenization across elevation zones. Climate rather than forest change was the dominant driver of understory responses. The magnitude of unabated 21st-century change is likely to erode plant diversity in a species richness hotspot, calling for stronger conservation and climate mitigation efforts.

Environmental drivers behind the genetic differentiation in mountain chickadees (Poecile gambeli).

Anthropogenic climate change has a large impact on wildlife populations and the scale of the impacts has been increasing. In this study, we utilised 3dRAD sequence data to investigate genetic divergence and identify the environmental drivers of genetic differentiation between 12 populations of mountain chickadees, family Paridae, sampled across North America. To examine patterns of genetic variation across the range, we conducted a discriminant analysis of principal components (DAPC), admixture analysis, and calculated pairwise Fst values. The DAPC revealed four clusters: southern California, eastern Rocky Mountains, northwestern Rocky Mountains, and Oregon/northern California. We then used BayeScEnv to highlight significant outlier SNPs associated with the five environmental variables. We identified over 150 genes linked to outlier SNPs associated with more than 15 pathways, including stress response and circadian rhythm. We also found a strong signal of isolation by distance and local temperature was highly correlated with genetic distance. Maxent simulations showed a northward range shift over the next 50 years and a decrease in suitable habitat, highlighting the need for immediate conservation action.

A standard approach for including climate change responses in IUCN Red List assessments.

The International Union for Conservation of Nature (IUCN) Red List is a central tool for extinction risk monitoring and influences global biodiversity policy and action. But, to be effective, it is crucial that it consistently accounts for each driver of extinction. Climate change is rapidly becoming a key extinction driver, but consideration of climate change information remains challenging for the IUCN. Several methods can be used to predict species' future decline, but they often fail to provide estimates of the symptoms of endangerment used by IUCN. We devised a standardized method to measure climate change impact in terms of change in habitat quality to inform criterion A3 on future population reduction. Using terrestrial nonvolant tetrapods as a case study, we measured this impact as the difference between the current and the future species climatic niche, defined based on current and future bioclimatic variables under alternative model algorithms, dispersal scenarios, emission scenarios, and climate models. Our models identified 171 species (13% out of those analyzed) for which their current red-list category could worsen under criterion A3 if they cannot disperse beyond their current range in the future. Categories for 14 species (1.5%) could worsen if maximum dispersal is possible. Although ours is a simulation exercise and not a formal red-list assessment, our results suggest that considering climate change impacts may reduce misclassification and strengthen consistency and comprehensiveness of IUCN Red List assessments.

Una estrategia estándar para incluir las respuestas al cambio climático en las evaluaciones de la Lista Roja de la UICN Resumen La Lista Roja de la Unión Internacional para la Conservación de la Naturaleza (UICN) es una herramienta central para el monitoreo del riesgo de extinción e influye sobre las acciones y políticas para la biodiversidad. Para que esta herramienta sea efectiva, es crucial que tenga en cuenta de manera regular cada factor de extinción. El cambio climático se está convirtiendo rápidamente en un factor de extinción importante, pero considerar información sobre este factor todavía es un reto para la UICN. Se pueden usar varios métodos para predecir la declinación de una especie en el futuro, pero generalmente fallan en proporcionar estimaciones de los síntomas del peligro usados por la UICN. Diseñamos un método estandarizado para medir el impacto del cambio climático en términos del cambio en la calidad del hábitat para informar el criterio A3 sobre la reducción futura de las poblaciones. Usamos a los tetrápodos terrestres no voladores como estudio de caso para medir este impacto como la diferencia entre el nicho climático actual y futuro de las especies, definido con base en las variables bioclimáticas actuales y futuras con algoritmos de modelos alternativos, escenarios de dispersión y emisión y modelos climáticos. Nuestros modelos identificaron 171 especies (13% de las especies analizadas) para las que su categoría actual en la lista roja podría empeorar bajo el criterio A3 si no logran dispersarse más allá de su distribución actual en el futuro. Las categorías para 14 especies (1.5%) podrían empeorar si es posible la dispersión máxima. Aunque realizamos una simulación y no una evaluación formal para listas rojas, nuestros resultados sugieren que considerar los impactos del cambio climático podría reducir la clasificación incorrecta y fortalecer la coherencia y exhaustividad de las evaluaciones de la Lista Roja de la UICN.

The influence of scale-dependent geodiversity on species distribution models in a biodiversity hotspot.

Improving models of species' distributions is essential for conservation, especially in light of global change. Species distribution models (SDMs) often rely on mean environmental conditions, yet species distributions are also a function of environmental heterogeneity and filtering acting at multiple spatial scales. Geodiversity, which we define as the variation of abiotic features and processes of Earth's entire geosphere (inclusive of climate), has potential to improve SDMs and conservation assessments, as they capture multiple abiotic dimensions of species niches, however they have not been sufficiently tested in SDMs. We tested a range of geodiversity variables computed at varying scales using climate and elevation data. We compared predictive performance of MaxEnt SDMs generated using CHELSA bioclimatic variables to those also including geodiversity variables for 31 mammalian species in Colombia. Results show the spatial grain of geodiversity variables affects SDM performance. Some variables consistently exhibited an increasing or decreasing trend in variable importance with spatial grain, showing slight scale-dependence and indicating that some geodiversity variables are more relevant at particular scales for some species. Incorporating geodiversity variables into SDMs, and doing so at the appropriate spatial scales, enhances the ability to model species-environment relationships, thereby contributing to the conservation and management of biodiversity. This article is part of the Theo Murphy meeting issue 'Geodiversity for science and society'.

Shrinking suitable habitat of a sub-Arctic foundation kelp under future climate scenarios.

Climate change has profound effects on the distribution of kelp forests in the Arctic and sub-Arctic. However, studies on the responses of kelps to climate change, particularly along the sub-Arctic regions of the Alaska coast, are limited. Eualaria fistulosa is a foundational kelp species in the Aleutian Islands, with an east-west distribution that extends from Japan to southern southwest Alaska. In this study, we utilized a species distribution model (SDM) to explore changes in the future habitat suitability of E. fistulosa under contrasting Shared Socioeconomic Pathway (SSP) scenarios. Our model exhibited relatively high predictive performance, validating our SDM predictions. Notably, the SDM results indicate that minimum sea surface temperature, annual range in sea surface temperatures, and annual mean current velocities are the three most important predictor variables determining E. fistulosa's distribution. Furthermore, the projected geographic distribution of Eualaria is generally consistent with its observed occurrence records. However, under high emission scenarios (SSP5-8.5), E. fistulosa is predicted to contract its distribution range by 9.0% by 2100, with widespread disappearance along the southeast Alaskan coast and limited northward migration to Kamchatka Krai in Russia and Bristol Bay in Alaska. These findings contribute valuable insights for conservation strategies via addressing climate-induced alterations in sub-Arctic kelp distribution.

Evaluating effects of climate change on the spatial distribution of an atypical cavefish Onychostoma macrolepis.

Comprehending endangered species' spatial distribution in response to global climate change (GCC) is of great importance for formulating adaptive management, conservation, and restoration plans. However, it is regrettable that previous studies mainly focused on geoclimatic species, while neglected climate-sensitive subterranean taxa to a large extent, which clearly hampered the discovery of universal principles. In view of this, taking the endemic troglophile riverine fish Onychostoma macrolepis (Bleeker, 1871) as an example, we constructed a MaxEnt (maximum-entropy) model to predict how the spatial distribution of this endangered fish would respond to future climate changes (three Global Climate Models × two Shared Socio-economic Pathways × three future time nodes) based on painstakingly collected species occurrence data and a set of bioclimatic variables, including WorldClim and ENVIREM. Model results showed that variables related to temperature rather than precipitation were more important in determining the geographic distribution of this rare and endemic fish. In addition, the suitable areas and their distribution centroids of O. macrolepis would shrink (average: 20,901.75 km2) and move toward the northeast or northwest within the study area (i.e. China). Linking our results with this species' limited dispersion potential and unique habitat requirements (i.e. karst landform is essential), we thus recommended in situ conservation to protect this relict.

Active remote sensing data and dispersal processes improve predictions for an invasive aquatic plant during a climatic extreme in Great Lakes coastal wetlands.

Invasive aquatic plants pose a significant threat to coastal wetlands. Predicting suitable habitat for invasive aquatic plants in uninvaded yet vulnerable wetlands remains a critical task to prevent further harm to these ecosystems. The integration of remote sensing and geospatial data into species distribution models (SDMs) can help predict where new invasions are likely to occur by generating spatial outputs of habitat suitability. The objective of this study was to assess the efficacy of utilizing active remote sensing datasets (synthetic aperture radar (SAR) and light detection and ranging (LiDAR) with multispectral imagery and other geospatial data in predicting the potential distribution of an invasive aquatic plant based on its biophysical habitat requirements and dispersal dynamics. We also considered a climatic extreme (lake water levels) during the study period to investigate how these predictions may change between years. We compiled a time series of 1628 field records on the occurrence of Hydrocharis morsus-ranae (European frogbit; EFB) with nine remote sensing and geospatial layers as predictors to train and assess the predictive capacity of random forest models to generate habitat suitability in Great Lakes coastal wetlands in northern Michigan, USA. We found that SAR and LiDAR data were useful as proxies for key biophysical characteristics of EFB habitat (emergent vegetation and water depth), and that a vegetation index calculated from spectral imagery was one of the most important predictors of EFB occurrence. Our SDM using all predictors yielded the highest mean overall accuracy of 88.3% and a true skill statistic of 75.7%. Two of the most important predictors of EFB occurrence were dispersal-related: 1) distance to the nearest known EFB population (m), and 2) distance to nearest public boat launch (m). The area of highly suitable habitat (pixels assigned ≥0.8 probability) was 74% larger during a climatically extreme high water-level year compared to an average year. Our findings demonstrate that active remote sensing can be integrated into SDM workflows as proxies for important drivers of invasive species expansion that are difficult to measure in other ways. Moreover, the importance of a proxy variable for endogenous dispersal (distance to nearest known population) in these SDMs indicates that EFB is currently spreading, and thereby less influenced by within-site dynamics such as interspecific competition. Lastly, we found that extreme climatic conditions can dramatically change this species' niche, and therefore we recommend that future studies include dynamic climate conditions in SDMs to more accurately forecast the spread during early invasion stages.

Predicted distribution of Metaparasitylenchus hypothenemi (Tylenchida: Allantonematidae), parasite of the coffee berry borer.

Metaparasitylenchus hypothenemi is an endoparasitic nematode of the coffee berry borer Hypothenemus hampei. The nematode has only been recorded across a limited geographical range in coffee-growing areas of southeastern Mexico. Because of its confined geographical distribution, the effect of altitude, temperature, and mean annual precipitation on M. hypothenemi's presence/absence in the Soconusco region of Mexico was investigated. The geographical distribution of this parasite was predicted based on current data, using geographical information systems (GIS), the MaxEnt algorithm, and historical data to improve the prediction accuracy for other Neotropical regions. In Soconusco, the presence of this parasite is directly related to annual precipitation, especially in the areas with the highest annual rainfall (4000 - 4700 mm/year). Four species distribution models were generated for the Neotropical region with environmental variables for sites with parasite presence data, predicting a range of possible distribution with a high probability of occurrence in southeastern Mexico and southwestern Guatemala and a low probability in areas of Central and South America. Characterization of the abiotic habitat conditions suitable for M. hypothenemi development allows us to predict its distribution in the Neotropics and contributes to our understanding of its ecological relationship with environmental variables.