Implementation of species distribution models in Google Earth Engine

Land-cover change in Cuba and implications for the area of distribution of a specialist's host-plant

Changes in land cover directly affect biodiversity. Here, we assessed land-cover change in Cuba in the past 35 years and analyzed how this change may affect the distribution of Omphalea plants and Urania boisduvalii moths. We analyzed the vegetation cover of the Cuban archipelago for 1985 and 2020. We used Google Earth Engine to classify two satellite image compositions into seven cover types: forest and shrubs, mangrove, soil without vegetation cover, wetlands, pine forest, agriculture, and water bodies. We considered four different areas for quantifications of land-cover change: (1) Cuban archipelago, (2) protected areas, (3) areas of potential distribution of Omphalea, and (4) areas of potential distribution of the plant within the protected areas. We found that "forest and shrubs", which is cover type in which Omphalea populations have been reported, has increased significantly in Cuba in the past 35 years, and that most of the gained forest and shrub areas were agricultural land in the past. This same pattern was observed in the areas of potential distribution of Omphalea; whereas almost all cover types were mostly stable inside the protected areas. The transformation of agricultural areas into forest and shrubs could represent an interesting opportunity for biodiversity conservation in Cuba. Other detailed studies about biodiversity composition in areas of forest and shrubs gain would greatly benefit our understanding of the value of such areas for conservation.

Predictive ecological niche model for Cinnamomumparthenoxylon (Jack) Meisn. (Lauraceae) from Last Glacial Maximum to future in Vietnam

Cinnamomumparthenoxylon (Jack) Meisn. is a tree in genus Cinnamomum that has been facing global threats due to forest degradation and habitat fragmentation. Many recent studies aim to describe habitats and assess population and species genetic diversity for species conservation by expanding afforestation models for this species. Understanding their current and future potential distribution plays a major role in guiding conservation efforts. Using five modern machine-learning algorithms available on Google Earth Engine helped us evaluate suitable habitats for the species. The results revealed that Random Forest (RF) had the highest accuracy for model comparison, outperforming Support Vector Machine (SVM), Classification and Regression Trees (CART), Gradient Boosting Decision Tree (GBDT) and Maximum Entropy (MaxEnt). The results also showed that the extremely suitable ecological areas for the species are mostly distributed in northern Vietnam, followed by the North Central Coast and the Central Highlands. Elevation, Temperature Annual Range and Mean Diurnal Range were the three most important parameters affecting the potential distribution of C.parthenoxylon. Evaluation of the impact of climate on its distribution under different climate scenarios in the past (Last Glacial Maximum and Mid-Holocene), in the present (Worldclim) and in the future (using four climate change scenarios: ACCESS, MIROC6, EC-Earth3-Veg and MRI-ESM2-0) revealed that of C.parthenoxylon would likely expand to the northeast, while a large area of central Vietnam will gradually lose its adaptive capacity by 2100.

The Effects of Anthropogenic Disturbances on the Spatiotemporal Patterns of Medium-Large Mammals in Tropical Volcanic Landscapes

A comprehensive understanding of the consequences of human interactions with mammals is a critical factor in supporting and conserving species in landscapes dominated by humans, which are increasingly threatened. This study aimed to identify the spatial and temporal interactions between humans and mammals. A non-parametric statistical approach with kernel density was used to detect human-mammal temporal interactions. The species interaction factor (SIF) was applied to calculate the spatial overlap based on the two-species occupancy detection model. The activity patterns of medium mammals were nocturnal, diurnal, and cathemeral. The human-medium mammal pairs with SIF values that were <1 and statistically significant included the human-long-tailed macaque (Macaca fascicularis) pair, the human-leopard cat (Prionailurus bengalensis) pair, and the human-barking deer (Muntiacus muntjac) pair. Based on their SIF values and the high overlap in their activity times, the human-macaque pairings had a high risk of conflict. Barking deer and leopard cats displayed a coexistence with humans via time-sharing activities. Due to temporal niche variations with human activities, the existence of nocturnal mammals was relatively uninterrupted. This study showed that most mammals are able to adapt spatially and temporally to various human activities. Nonetheless, efforts to mitigate human-wildlife conflict must be maintained, particularly in the case of severely endangered species, such as the Sunda pangolin.

Beyond protected areas: The importance of mixed-use landscapes for the conservation of Sumatran elephants (Elephas maximus sumatranus)

Elephants were once widely distributed across the Indonesian island of Sumatra but now exist in small, isolated populations. Using the best data available on elephant occurrence, we aimed to (a) predict potential habitat suitability for elephants (Elephas maximus sumatranus) across the island of Sumatra and (b) model landscape connectivity among the extant elephant populations. We used direct sightings and indirect observations of elephant signs, as well as six remotely sensed proxies of surface ruggedness, vegetation productivity and structure, and human land use and disturbance, to model habitat suitability in a Google Earth Engine (GEE) environment. We validated the habitat suitability prediction using 10-fold spatial block cross validation and by calculating the area under the precision-recall curve (AUC-PR), sensitivity, and specificity for each model iteration. We also used a geolocation dataset collected from global positioning system (GPS) collars fitted on elephants as an independent validation dataset. Models showed good predictive performance with a mean AUC-PR of 0.73, sensitivity of 0.76, and specificity of 0.68. Greater than 83% of the independent GPS collar geolocations were located in predicted suitable habitat. We found human modification, surface ruggedness, and normalized difference vegetation index to be the most important variables for predicting suitable elephant habitat. Thirty-two percent, or 135,646 km2, of Sumatra's land area was predicted to be suitable habitat, with 43 patches of suitable habitat located across Sumatra. Areas with high connectivity were concentrated in the Riau and North Sumatra provinces. Though our analysis highlights the need to improve the quality of data collected on Sumatran elephants, more suitable habitat remains on Sumatra than is used by known populations. Targeted habitat conservation, especially of the suitable habitat in and around the Lamno, Balai Raja, Tesso Tenggara, Tesso Utara, Bukit Tigapuluh, Seblat, Padang Sugihan, and Bukit Barisan Selatan ranges, may improve the long-term viability of this critically endangered species.

Functional group analyses of herpetofauna in South Korea using a large dataset

Functional traits are characteristics of species that affect their fitness and ecosystem, and they greatly influence ecological niches. Thus, biodiversity assessment based on functional groups rather than species per se can more realistically reflect the ecological niche space. As essential players of ecosystem functions, herpetofauna are appropriate subjects of functional trait-based analyses. In this study, using a nationwide dataset and applying trait information and ecological niche modeling, the richness within each functional group, and the taxonomic and functional diversity indices of South Korean herpetofauna were visualized to identify and compare the geographic distributions. The results revealed that the reptile community seemed more locally diverse with more overlapping randomized patterns among groups than amphibians, while amphibians showed wider distributions and a higher within-grid occurrence ratio. Functional diversity indices of reptiles also showed more randomized geographic patterns with higher levels at Jejudo Island than amphibians. The findings of this study may help to identify biodiversity hot spots and understand its ecosystem health. Increasing survey data and trait information will improve the assessment.