Spatial Analysis For Conservation and Sustainability
Remote Sensing
Satellite images provide a wonderful record of the last fifty years of global change. We have pioneered new methods to map wildlife habitat and proxies for biodiversity and habitat, as well as agricultural abandonment and other types of land use change for large areas. We analyze MODIS/VIIRS data across the globe, Landsat and Sentinel-2 across continents, and high-resolution CORONA spy satellite imagery across countries.
Heterogeneous vegetation supports higher species richness than homogenous vegetation, which is why efficiently identifying heterogenous vegetation can be useful for biodiversity conservation. Satellite remote-sensing data provide an opportunity to generate vegetation heterogeneity metrics and to explore the phenology of vegetation patterns. Phenoclusters are vegetation types with similar phenological characteristics, and valuable for capturing vegetation habitat heterogeneity patterns. Our goal was to map phenoclusters for Wisconsin, USA, at 10-m spatial resolution based on land surface phenology metrics from EVI (Enhanced Vegetation Index) Sentinel-2 data. We characterized each phenocluster based on landcover composition and structure, phenology timing, and environmental factors, and compared them to bird species richness. We also calculated the diversity of phenoclusters at multiple spatial extents. We identified 14 phenoclusters in Wisconsin, each with distinct landcover composition and structure, and unique phenological characteristics. Our remotely-sensed phenoclusters effectively captured environmental gradients, with elevation and temperature emerging as the most important driving variables. Furthermore, the phenoclusters successfully captured bird biodiversity patterns, especially richness of forest and grassland specialist. Our results identified phenological patterns among Wisconsin’s forests, shrublands, and grasslands, capturing phenological timing both among and within the same tree species. Phenoclusters are a valuable tool for capturing vegetation habitat heterogeneity, phenology diversity and biodiversity patterns, as well as climate change effects.
Snow cover dynamics (i.e. depth, duration and variability) are dominant drivers of ecological processes during winter. For overwintering species, changes and gradients in snow cover may impact survival and population dynamics (e.g. facilitating survival via thermal refugia or limiting survival via reduced resource acquisition). However, snow cover dynamics are rarely used in species distribution modelling, especially for over-wintering birds. Currently, we lack understanding of how snow cover gradients affect overwintering bird distributions and which functional traits drive these associations at regional and continental scales. Using observations from eBird, a global community science network, we explored the effects of snow cover dynamics on continental pat-terns of occurrence and counts for 150 bird species. We quantified the relative impor-tance, species-specific responses and trait-based relationships of bird occurrence and abundance patterns to ecologically relevant snow cover dynamics across the United States. Snow cover dynamics were important environmental predictors in species dis-tributions models, ranking within the top three predictors for most species occurrence (> 90%) and count (> 79%) patterns across the contiguous United States. Species exhibited a gradient of responses to snow cover from snow association to snow avoid-ance, yet most birds were limited by long, persistent snow seasons. Duration of winter and percent frozen ground without snow structured species distributions in the east-ern USA, whereas snow cover variability was a stronger driver in the western USA. Birds associated with long, persistent snow seasons had traits associated with greater dispersal capacity and dietary diversity, whereas birds inhabiting regions with variable snow cover were generally habitat generalists. Our results suggest that various snow cover dynamics are important ecological filters of species distributions during winter. Global climate change is rapidly degrading key characteristics of seasonal snow cover. A changing cryosphere may elicit variable distributional changes for many overwinter-ing birds, potentially accelerating range shifts and novel community assemblages.
In this work, we propose a deep learning-based method to perform semiparametric regression analysis for spatially dependent data. To be specific, we use a sparsely connected deep neural network with rectified linear unit (ReLU) activation function to estimate the unknown regression function that describes the relationship between response and covariates in the presence of spatial dependence. Under some mild conditions, the estimator is proven to be consistent, and the rate of convergence is determined by three factors: (1) the architecture of neural network class, (2) the smoothness and (intrinsic) dimension of true mean function, and (3) the magnitude of spatial dependence. Our method can handle well large data set owing to the stochastic gradient descent optimization algorithm. Simulation studies on synthetic data are conducted to assess the finite sample performance, the results of which indicate that the proposed method is capable of picking up the intricate relationship between response and covariates. Finally, a real data analysis is provided to demonstrate the validity and effectiveness of the proposed method.
Global changes in climate and land use are threatening natural ecosystems, biodiversity, and the ecosystem services people rely on. This is why it is necessary to track and monitor spatiotemporal change at a level of detail that can inform science, management, and policy development. The current constellation of multiple Landsat and Sentinel-2 satellites collecting imagery at predominantly ≤30-m spatial resolution affords an opportunity for the generation of global medium- resolution products every few days. Our goal is to both identify the information needs and provide direction towards the generation of a suite of global, high-level, systematically-generated, medium-resolution products designed for both management and science. Our vision builds on the success of the NASA MODIS/VIIRS product suite, while recognizing the unique strengths of medium-resolution satellite data given their higher spatial resolution and longer time series. We propose a suite of 13 essential products that enable the characterization of the current state and changes in the biosphere, cryosphere, and hydrosphere, and would fill information needs identified by the Committee on Earth Observation Satellites for the Global Climate Observing System and the Global Terrestrial Observing System, by the National Research Council of the US National Academies in the decadal survey, and by others. These products are: land cover, land cover change, burned area, forest loss, vegetation indices, phenology, dynamic habitat indices, albedo, land surface temperature, snow cover, ice extent, surface water extent, and evapotranspiration. Furthermore, we provide a list of desirable products poised for addition to the essential products (e.g., crop type, emissivity, and ice sheet velocity). Lastly, we suggest aspirational products requiring further algorithm development (e.g., forest structure and crop yield). For the identified essential products, algorithms are in place, making it feasible to begin generating products systematically. These products should be accompanied by quality and accuracy assessments undertaken following consensus protocols. Five decades after the first Landsat satellite, and two decades after the MODIS products were first produced, it is time now for readily available, standardized, and consistent high-level products built upon medium-resolution imagery, thereby fulfilling the promise and the vision that inspired the Landsat program since its inception.
Socioeconomic shocks can cause regime shifts in land use, but even during shocks, and when land use change is widespread, some areas persist in their land use. The question is what makes these areas more resistant. Our research goal was to find out what explains where arable farming persisted despite a major socioeconomic shock of forced post-war displacements. Our study area were 291 villages in the Polish Carpathians where abandonment due to the forced displacement of the Ukrainian population after WWII was widespread. We compared prewar arable land with 1990 CORINE Land Cover data to quantify land-use change throughout the socialist period. We applied logistic regression with economically relevant environmental and access-related variables, and assessed the explanatory power of our models and relative importance of determinants. Forty years after forced displacements, arable farming persisted only in a small portion of what had been farmed in the 1940s (16 %), while the majority of former arable land converted to forests (54 %) or grasslands (22 %). Arable farming persisted mainly in areas with high accessibility that had oak-hornbeam forest as potential natural vegetation, on less steep slopes, and at lower elevations. Our models predicting agricultural abandonment leading to reforestation performed well (R2 = 0.57), but our model of persistent agriculture had low explanatory power (R2 = 0.26) as did models of conversion to grassland (R2 = 0.24). We therefore conclude that agricultural persistence is driven by different factors than agricultural land abandonment. In the long term, after arable farming ceases, areas can either be completely abandoned or convert to less intensive grassland use. These long-term changes have strong effects on biodiversity and ecosystem services, but are not well predicted by environmental and access-related determinants. Our findings can help to develop strategies and policies for areas affected by agricultural land abandonment caused by depopulation, and other socioeconomic shocks, and highlight the need to understand not only why arable land is abandoned, but also what determines its long-term fate.
Background: Wildland–urban interface (WUI) maps identify areas with wildfire risk, but they are often outdated owing to the lack of building data. Convolutional neural networks (CNNs) can extract building locations from remote sensing data, but their accuracy in WUI areas is unknown. Additionally, CNNs are computationally intensive and technically complex, making them challenging for end-users, such as those who use or create WUI maps, to apply.
Aims: We identified buildings pre- and post-wildfire and estimated building destruction for three California wildfires: Camp, Tubbs and Woolsey.
Methods: We evaluated a CNN-based building dataset and a CNN model from a separate commercial vendor to detect buildings from high-resolution imagery. This dataset and model represent to end-users the state of the art of what is readily available for potential WUI mapping.
Key results: We found moderate accuracies for the building dataset and the CNN model and a severe underestimation of buildings and their destruction rates where trees occluded buildings. The CNN model performed best post-fire with accuracies ≥73%.
Conclusions: Existing CNNs may be used with moderate accuracy for identifying individual buildings post-fire and mapping the extent of the WUI. The implications are, however, that CNNs are too inaccurate for post-fire damage assessments or building counts in the WUI.
Accurate maps of gains in tree cover are necessary to quantify carbon storage, wildlife habitat, and land use changes. Satellite-based mapping of emerging smallholder woodlots in heterogeneous landscapes of sub-Saharan Africa is challenging. Our goal was to evaluate the use of time series to detect and map small woodlots (<1 ha) in Tanzania. We distinguished woodlots from other land cover types by woodlots’ distinct multi-year spectral time series. Woodlots exhibit greening from planting to maturity followed by browning at harvest. We compared two time series approaches: 1) a linear model of Tasseled Cap Wetness (TCW) and other indices, and 2) LandTrendr temporal segmentation metrics. The approaches had equivalent woodlot detection accuracy, but LandTrendr segments had lower accuracy for characterizing woodlot age. We tested the effect of the following factors on woodlot detection and mapping accuracy: the length of the time series (2009–2019), frequency of observations (all Landsat vs. only Landsat-8), spatial resolution (30-m Landsat vs. 10-m Sentinel-2), and woodlot age and size. Woodlot mapping accuracies were higher with longer time series (54% at 3-yrs vs 77% at 7-yrs). The accuracies also improved with more observations, especially when the time series was short (3-yrs Landsat-8 only: 54% vs. all-Landsat: 64%, p-value <0.001). Sentinel-2’s higher spatial resolution minimized commission errors even for short time series. Finally, less than half of young and small (<0.4 ha) woodlots were detected, suggesting considerable omission errors in our and other woodlot maps. Our results suggest that the accurate detection of woodlots is possible by analyzing multi-year time series of Landsat and Sentinel-2 data. Given the region’s woodlot boom, accurate maps are needed to better quantify woodlots’ contribution to carbon sequestration, livelihoods enhancement, and landscape management.
Detailed maps of forest structure attributes are crucial for sustainable forest management, conservation, and forest ecosystem science at the landscape level. Mapping the structure of broad heterogeneous forests is challenging, but the integration of extensive field inventory plots with wall-to-wall metrics derived from synthetic aperture radar (SAR) and optical remote sensing offers a potential solution. Our goal was to map forest structure attributes (diameter at breast height, basal area, mean height, dominant height, wood volume and canopy cover) at 30-m resolution across the diverse 463,000 km2 of native forests of Argentina based on SAR Sentinel-1, vegetation metrics from Sentinel-2 and geographic coordinates. We modelled the forest structure attributes based on the latest national forest inventory, generated uncertainty maps, quantified the contribution of the predictors, and compared our height predictions with those from GEDI (Global Ecosystem Dynamics Investigation) and GFCH (Global Forest Canopy Height). We analyzed 3788 forest inventory plots (1000 m2 each) from Argentina’s Second Native Forest Inventory (2015–2020) to develop predictive random forest regression models. From Sentinel-1, we included both VV (vertical transmitted and received) and VH (vertical transmitted and horizontal received) polarizations and calculated 1st and 2nd order textures within 3 × 3 pixels to match the size of the inventory plots. For Sentinel-2, we derived EVI (enhanced vegetation index), calculated DHIs (dynamic habitat indices (annual cumulative, minimum and variation) and the EVI median, then generated 1st and 2nd order textures within 3 × 3 pixels of these variables. Our models including metrics from Sentinel-1 and 2, plus latitude and longitude predicted forest structure attributes well with root mean square errors (RMSE) ranging from 23.8% to 70.3%. Mean and dominant height models had notably good performance presenting relatively low RMSE (24.5% and 23.8%, respectively). Metrics from VH polarization and longitude were overall the most important predictors, but optimal predictors differed among the different forest structure attributes. Height predictions (r = 0.89 and 0.85) outperformed those from GEDI (r = 0.81) and the GFCH (r = 0.66), suggesting that SAR Sentinel-1, DHIs from Sentinel-2 plus geographic coordinates provide great opportunities to map multiple forest structure attributes for large areas. Based on our models, we generated spatially-explicit maps of multiple forest structure attributes as well as uncertainty maps at 30-m spatial resolution for all Argentina’s native forest areas in support of forest management and conservation planning across the country.
Habitat selection is a fundamental behavior of species that shapes a wide range of ecological processes, including species distribution, abundance, nutrient transfer, and tropic dynamics. The study of habitat selection is important to understand the interaction between species and environment. But it is a multivariate and hierarchical process, in which species are distinctively affected by several factors at multiple spatial scales. Therefore, it is important to understand how species select their habitat, what are the important spatial scales, and how the habitat selection process varies for different species.
Figure 1: Conceptual hierarchy of the decision-making process of habitat use by a migratory songbird (Stanley et al 2021).
Hierarchical habitat selection in birds varies greatly by species due to their ecological niches and behaviors. For instance, the Northern Spotted Owl specializes in old-growth conifers for nesting, forages in mature forests, and prefers undisturbed landscapes for its home range. Conversely, the Kirtland’s Warbler prefers, early to mid-successional jack pine forests, growing on sandy soil for nesting, these forests provide the specific vegetation structure and insect abundance that are essential for their foraging needs. Studying habitat selection is therefore crucial for effective conservation and ecosystem management, as it provides insights into their ecological requirements and aids in preserving their populations and the overall health of ecosystems.
Figure 2: Kirtland’s Warbler (left) Spotted Owl (right)
Despite notable advancements in the field, our understanding of the hierarchical aspects of habitat selection in birds remains limited. Habitat selection models typically rely on satellite data from a single sensor and scale, which limits their effectiveness in capturing spatial patterns of bird habitat.
Akash Anand is currently conducting a study aimed at modeling multiscale hierarchical habitat selection in birds and explaining the factors influencing individual species’ choices. His research investigates the crucial spatial scales for different species and identifies local environmental features that play a pivotal role in overall habitat selection decisions. To achieve this, he employs deep learning models to gain insights into the intricate interactions between species and their environments.
In conclusion, Akash’s research aims to determine the crucial spatial scales for individual species, providing valuable insights for conservationists and policymakers. Additionally, the findings will provide evidence of how the same species respond to varying environmental conditions and how their choices differ in different scenarios. This knowledge will inform more effective conservation and management strategies.
Halting biodiversity declines and promoting sustainable ecosystem usage are major conservation goals. To do so, it is necessary to understand the environmental correlates of biodiversity patterns.
Environmental variables used in biodiversity modelling come from a variety of sources and have varying levels of power to explain distributions of different species. Many environmental variables that have been used regularly for many years have shortcomings- they may not cover large areas, may not capture suitable habitat, or may not be able to capture changes in environmental conditions over time or space. Increasingly, novel remotely-sensed environmental data are being developed for modelling biodiversity patterns. Novel remotely sensed products may complement or even offer better results than environmental variables that have been used for many years.
Olah set out to identify sets of complementary variables, from among a set of standard variables and newly created variables, that can improve species distribution modelling. Olah used a combination of land cover, elevation, precipitation, and temperature variables, that are commonly used in species distribution modelling, and a set of novel-remotely sensed products to model distributions of forest affiliated bird species in Argentina.
Yungas forest in Calilegua National Park, Jujuy, Argentina
The set of novel environmental variables were created by SILVIS lab postdoctoral researcher Eduarda Silveira. These products measure spatial and interannual variation in the phenology of land surface temperature and forest vegetation greenness. Olah predicted that areas with more spatial variability in phenology and thermal conditions are more likely to host more species because there are a variety of resources and thermal conditions in close proximity, allowing many species to coexist in a small area. These areas may also buffer against high year-to-year variation in conditions because organisms are more likely to have access to refugia or resources that could allow them to persist. Temporal variation in forest greenness or temperature describes how consistent conditions are between years. High variability means that phenological events are not occurring at a predictable time, while low variability means that events are occurring predictably each year.
In another new product developed by Silveira, ground forest inventory data was combined with radar-based remotely-sensed data, resulting in modelled forest structure wall-to-wall across Argentina. Silveira also developed maps of forest phenoclusters and phenocluster diversity. Phenoclusters classify different forest types in Argentina, based on vegetation phenology, land surface temperature, and precipitation. Olah thinks phenoclusters are a more ecologically relevant way to characterize habitat important to bird species than typical land cover maps. Phenoclusters capture functional rather than only compositional or structural characteristics. By comparing how well these novel remotely-sensed products and traditionally used variables perform in species distribution modelling Olah assessed their usefulness for biodiversity mapping.
Polylepis forest in an Andean Mountain valley, Jujuy, Argentina.
Olah developed species distribution models for 152 forest bird species. She found that among three sets of models she constructed, those containing novel, traditional, or a mixed set of variables, performance was similar. However, models constructed from the mixed set of variables performed slightly better than models containing only one or the other set of data. The variables that were included in the greatest number of individual species’ distribution models included precipitation seasonality, precipitation of the driest quarter, as well as spatial heterogeneity in winter land surface temperature, which is a novel variable. Her results highlight how variables derived from different sources can offer complementary information for biodiversity modelling. Her models contribute to forest harvest planning in Argentina.
