Remote sensing variables improve species distribution models for alpine plant species

Mapping small mammal optimal habitats using satellite-derived proxy variables and species distribution models

Small mammal species play an important role influencing vegetation primary productivity and plant species composition, seed dispersal, soil structure, and as predator and/or prey species. Species which experience population dynamics cycles can, at high population phases, heavily impact agricultural sectors and promote rodent-borne disease transmission. To better understand the drivers behind small mammal distributions and abundances, and how these differ for individual species, it is necessary to characterise landscape variables important for the life cycles of the species in question. In this study, a suite of Earth observation derived metrics quantifying landscape characteristics and dynamics, and in-situ small mammal trapline and transect survey data, are used to generate random forest species distribution models for nine small mammal species for study sites in Narati, China and Sary Mogul, Kyrgyzstan. These species distribution models identify the important landscape proxy variables driving species abundance and distributions, in turn identifying the optimal conditions for each species. The observed relationships differed between species, with the number of landscape proxy variables identified as important for each species ranging from 3 for Microtus gregalis at Sary Mogul, to 26 for Ellobius tancrei at Narati. Results indicate that grasslands were predicted to hold higher abundances of Microtus obscurus, E. tancrei and Marmota baibacina, forest areas hold higher abundances of Myodes centralis and Sorex asper, with mixed forest-grassland boundary areas and areas close to watercourses predicted to hold higher abundances of Apodemus uralensis and Sicista tianshanica. Localised variability in vegetation and wetness conditions, as well as presence of certain habitat types, are also shown to influence these small mammal species abundances. Predictive application of the Random Forest (RF) models identified spatial hot-spots of high abundance, with model validation producing R2 values between 0.670 for M. gregalis transect data at Sary Mogul to 0.939 for E. tancrei transect data at Narati. This enhances previous work whereby optimal habitat was defined simply as presence of a given land cover type, and instead defines optimal habitat via a combination of important landscape dynamic variables, moving from a human-defined to species-defined perspective of optimal habitat. The species distribution models demonstrate differing distributions and abundances of host species across the study areas, utilising the strengths of Earth observation data to improve our understanding of landscape and ecological linkages to small mammal distributions and abundances.

Seeing from space makes sense: Novel earth observation variables accurately map species distributions over Himalaya

Topical advances in earth observation have enabled spatially explicit mapping of species' fundamental niche limits that can be used for nature conservation and management applications. This study investigates the possibility of applying functional variables of ecosystem retrieved from Moderate Resolution Imaging Spectroradiometer (MODIS) onboard sensor data to map the species distribution of two alpine treeline species, namely Betula utilis D.Don and Rhododendron campanulatum D.Don over the Himalayan biodiversity hotspot. In this study, we have developed forty-nine Novel Earth Observation Variables (NEOVs) from MODIS products, an asset to the present investigation. To determine the effectiveness and ecological significance of NEOVs combinations, we built and compared four different models, namely, a bioclimatic model (BCM) with bioclimatic predictor variables, a phenology model (PhenoM) with earth observation derived phenological predictor variables, a biophysical model (BiophyM) with earth observation derived biophysical predictor variables, and a hybrid model (HM) with a combination of selected predictor variables from BCM, PhenoM, and BiophyM. All models utilized topographical variables by default. Models that include NEOVs were competitive for focal species, and models without NEOVs had considerably poor model performance and explanatory strength. To ascertain the accurate predictions, we assessed the congruence of predictions by pairwise comparisons of their performance. Among the three machine learning algorithms tested (artificial neural networks, generalised boosting model, and maximum entropy), maximum entropy produced the most promising predictions for BCM, PhenoM, BiophyM, and HM. Area under curve (AUC) and true skill statistic (TSS) scores for the BCM, PhenoM, BiophyM, and HM models derived from maximum entropy were AUC ≥0.9 and TSS ≥0.6 for the focal species. The overall investigation revealed the competency of NEOVs in the accurate prediction of species' fundamental niches, but conventional bioclimatic variables were unable to achieve such a level of precision. A principal component analysis of environmental spaces disclosed that niches of focal species substantially overlapped each other. We demonstrate that the use of satellite onboard sensors' biotic and abiotic variables with species occurrence data can provide precision and resolution for species distribution mapping at a scale that is relevant ecologically and at the operational scale of most conservation and management actions.

Mapping breeding bird species richness at management-relevant resolutions across the United States

Human activities alter ecosystems everywhere, causing rapid biodiversity loss and biotic homogenization. These losses necessitate coordinated conservation actions guided by biodiversity and species distribution spatial data that cover large areas yet have fine-enough resolution to be management-relevant (i.e., ≤5 km). However, most biodiversity products are too coarse for management or are only available for small areas. Furthermore, many maps generated for biodiversity assessment and conservation do not explicitly quantify the inherent tradeoff between resolution and accuracy when predicting biodiversity patterns. Our goals were to generate predictive models of overall breeding bird species richness and species richness of different guilds based on nine functional or life-history-based traits across the conterminous United States at three resolutions (0.5, 2.5, and 5 km) and quantify the tradeoff between resolution and accuracy and, hence, relevance for management of the resulting biodiversity maps. We summarized 18 years of North American Breeding Bird Survey data (1992-2019) and modeled species richness using random forests, including 66 predictor variables (describing climate, vegetation, geomorphology, and anthropogenic conditions), 20 of which we newly derived. Among the three spatial resolutions, the percentage variance explained ranged from 27% to 60% (median = 54%; mean = 57%) for overall species richness and 12% to 87% (median = 61%; mean = 58%) for our different guilds. Overall species richness and guild-specific species richness were best explained at 5-km resolution using ~24 predictor variables based on percentage variance explained, symmetric mean absolute percentage error, and root mean square error values. However, our 2.5-km-resolution maps were almost as accurate and provided more spatially detailed information, which is why we recommend them for most management applications. Our results represent the first consistent, occurrence-based, and nationwide maps of breeding bird richness with a thorough accuracy assessment that are also spatially detailed enough to inform local management decisions. More broadly, our findings highlight the importance of explicitly considering tradeoffs between resolution and accuracy to create management-relevant biodiversity products for large areas.

A Neural Network-Based Spectral Approach for the Assignment of Individual Trees to Genetically Differentiated Subpopulations

Studying population structure has made an essential contribution to understanding evolutionary processes and demographic history in forest ecology research. This inference process basically involves the identification of common genetic variants among individuals, then grouping the similar individuals into subpopulations. In this study, a spectral-based classification of genetically differentiated groups was carried out using a provenance–progeny trial of Eucalyptus cladocalyx. First, the genetic structure was inferred through a Bayesian analysis using single-nucleotide polymorphisms (SNPs). Then, different machine learning models were trained with foliar spectral information to assign individual trees to subpopulations. The results revealed that spectral-based classification using the multilayer perceptron method was very successful at classifying individuals into their respective subpopulations (with an average of 87% of correct individual assignments), whereas 85% and 81% of individuals were assigned to their respective classes correctly by convolutional neural network and partial least squares discriminant analysis, respectively. Notably, 93% of individual trees were assigned correctly to the class with the smallest size using the spectral data-based multi-layer perceptron classification method. In conclusion, spectral data, along with neural network models, are able to discriminate and assign individuals to a given subpopulation, which could facilitate the implementation and application of population structure studies on a large scale.