Search USGS⌕ Search

SEARCH · Search USGS

Results for “Ecosystem Services”

Search indexed USGS publications on groundwater, aquifers, geologic maps, mineral resources and earthquakes. Explore source records by subject and place.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6Linked to original sources
USGS2005

Aggregate measures of ecosystem services: Can we take the pulse of nature?

National scale aggregate indicators of ecosystem services are useful for stimulating and supporting a broad public discussion about trends in the provision of these services. There are important considerations involved in producing an aggregate indicator, including whether the scientific and technological capacity exists, how to address varying perceptions of the societal importance of different services, and how to communicate information about these services to both decision makers and the general public. Although the challenges are formidable, they are not insurmountable. Quantification of ecosystem services and dissemination of information to decision makers and the public is critical for the responsible and sustainable management of natural resources.

Frontiers in Ecology and the Environment↗
USGS2019

Report on the workshop 'Global modelling of biodiversity and ecosystem services'

A three-day workshop on ‘Global Modelling of Biodiversity and Ecosystem Services’, was held in the Hague, Netherlands, from 24th to 26th June 2019. The workshop, attended by 35 modelling and scenario-building experts, was organised on behalf of the former IPBES1 expert group on scenarios and models of the first IPBES work programme by its interim technical support unit, and hosted by the PBL Netherlands Environmental Assessment Agency. The workshop drew on the ‘nature futures’ participatory scenario-building exercise initiated by the IPBES expert group on scenarios and models, and other biodiversity modelling initiatives such as the ISIMIP project2 working on adding biodiversity to the Shared Socioeconomic Pathways (SSPs) scenarios framework, the 'bending the curve' initiative3 led by IIASA4 and WWF5, and GEOBON6 working on modelling Essential Biodiversity Variables. The workshop was a step towards coordinating across biodiversity modelling initiatives, to build on each other’s work, and to seek synergies for the production of innovative scenarios on biodiversity and ecosystem services to inform the post-2020 agenda of the Convention on Biological Diversity, as well as the Sustainable Development Goals. The aims of the workshop were to: 1. Compile material as input for a first draft of the fifth Global Biodiversity Outlook (GBO-5) based on recent scenario work, including the ‘bending the curve’ scenarios and the newly developed PBL scenarios (modified from the Rio+20 scenarios), and existing models (to be completed by August 2019) 2. Develop a protocol for modelling trends and near term projections on indicators relevant to the Nature Futures Framework7 using models that are readily available (to be completed by early 2020) 3. Set the agenda and define the aims for a larger meeting at the end of 2019 to discuss the long term strategy towards the development of appropriate indicators and models to produce Nature Futures scenarios (to continue beyond Jan 2020)

Report↗
USGS2020

Quantifying interregional flows of multiple ecosystem services – A case study for Germany

Despite a growing number of national-scale ecosystem service (ES) assessments, few studies consider the impacts of ES use and consumption beyond national or regional boundaries. Interregional ES flows – ecosystem services “imported” from and “exported” to other countries – are rarely analyzed and their importance for global sustainability is little known. Here, we provide a first multi-ES quantification of a nation's use of ES from abroad. We focus on ES flows that benefit the population in Germany but are supplied outside German territory. We employ a conceptual framework recently developed to systematically quantify interregional ES flows. We address four types of interregional ES flows with: (i) biophysical flows of traded goods: cocoa import for consumption; (ii) flows mediated by migratory species: migration of birds providing pest control; (iii) passive biophysical flows: flood control along transboundary watersheds; and (iv) information flows: China's giant panda loan to the Berlin Zoo. We determined that: (i) Ivory Coast and Ghana alone supply around 53% of Germany's cocoa while major negative consequences for biodiversity occurred in Cameroon and Ecuador; (ii) Africa´s humid and sub-humid climate zones are important habitats for the majority of migratory bird species that provide natural pest control services in agricultural areas in Germany; (iii) Upstream watersheds outside the country add an additional 64% flood regulation services nationally, while Germany exports 40% of flood regulation services in neighboring, downstream countries; (iv) Information flows transported by the pandas were mainly related to political aspects and - contrary to our expectations - considerably less on biological and natural aspects. We discuss the implications of these results for international resource management policy and governance.

Global Environmental Change↗
USGS2017

Ecosystem services from transborder migratory species: Implications for conservation governance

This article discusses the conservation challenges of volant migratory transborder species and conservation governance primarily in North America. Many migratory species provide ecosystem service benefits to society. For example, insectivorous bats prey on crop pests and reduce the need for pesticides; birds and insects pollinate food plants; and birds afford recreational opportunities to hunters and birdwatchers. Migration is driven by the seasonal availability of resources; as resources in one area become seasonally scarce, individuals move to locations where resources have become seasonally abundant. The separation of the annual lifecycle means that species management and governance is often fractured across international borders. Because migratory species depend on habitat in different locations, their ability to provide ecosystem services in one area depends on the spatial subsidies, or support, provided by habitat and ecological processes in other areas. This creates telecouplings, or interconnections across geographic space, of areas such that impacts to the habitat of a migratory species in one location will affect the benefits enjoyed by people in other locations. Information about telecoupling and spatial subsidies can be used to craft new governance arrangements such as Payment for Ecosystem Services programs that target specific stakeholder groups and locations. We illustrate these challenges and opportunities with three North American case studies: the Duck Stamp Program, Mexican free-tailed bats ( Tadarida brasiliensis mexicana ), and monarch butterflies ( Danaus plexippus ).

Annual Review of Environment and Resources↗
USGS2009

Developing a Vision: Incorporating Ecosystem Services into Decision Making - Proceedings of a Workshop

The production, location, use, and value of ecosystem services have become an important factor in resource management. Decisions relating to resource conservation and restoration, as well as development, require an understanding of the services provided by natural systems and the response of these systems to natural and human-induced change. Increased demands for development and the resulting pressures on ecosystem services have lent urgency to the need for an improved understanding of the value of natural capital. However, resource management decisions are often made without considering the importance and value of services resulting from natural systems.

Open-File Report↗
USGS2020

Climate change effects on biodiversity, ecosystems, ecosystem services, and natural resource management in the United States

Climate change is a pervasive and growing global threat to biodiversity and ecosystems. Here, we present the most up-to-date assessment of climate change impacts on biodiversity, ecosystems, and ecosystem services in the U.S. and implications for natural resource management. We draw from the 4th National Climate Assessment to summarize observed and projected changes to ecosystems and biodiversity, explore linkages to important ecosystem services, and discuss associated challenges and opportunities for natural resource management. We find that species are responding to climate change through changes in morphology and behavior, phenology, and geographic range shifts, and these changes are mediated by plastic and evolutionary responses. Responses by species and populations, combined with direct effects of climate change on ecosystems (including more extreme events), are resulting in widespread changes in productivity, species interactions, vulnerability to biological invasions, and other emergent properties. Collectively, these impacts alter the benefits and services that natural ecosystems can provide to society. Although not all impacts are negative, even positive changes can require costly societal adjustments. Natural resource managers need proactive, flexible adaptation strategies that consider historical and future outlooks to minimize costs over the long term. Many organizations are beginning to explore these approaches, but implementation is not yet prevalent or systematic across the nation.

Science of the Total Environment↗
USGS2025

Constraints and enablers for meaningful consideration of plural values through integration of cultural ecosystem services (CES) in decision-making

This chapter presents and applies five constraint/enabler categories that influence integration of the plural values of cultural ecosystem services (CES) in decision-making, highlighting how diverse forms of CES knowledge can intersect with decision making contexts. CES make foundational contributions to human well-being, and yet they are consistently underrepresented in research products intended to inform decision-making. In particular, the relational and holistic values associated with CES categories such as cultural identity and maintenance of knowledge systems have been inadequately conveyed through existing instrumental approaches to ecosystem service assessment and ecosystem valuation. In this chapter we detail (1) a spectrum of forms in which CES knowledge may be conveyed to inform decision-making and (2) constraints and enabling factors that influence whether plural CES values are meaningfully considered in decision-making. This chapter considers how these constraints/enablers commonly influence integration of distinct CES knowledge forms in natural resource management decision contexts. Examples are then offered from case study research on Elwha River dam removal decision-making (Washington state, USA). These examples illustrate that factors commonly constraining integration of diverse CES knowledge forms can transform into enablers for meaningful consideration of relational values and holistic value perspectives, alongside instrumental values. The chapter concludes with takeaways for decision-makers, managers, and those who hold CES knowledge and seek to convey plural CES values to inform decision-making.

Book chapter↗
USGS2015

Integrated climate and land use change scenarios for California rangeland ecosystem services: wildlife habitat, soil carbon, and water supply

Context In addition to biodiversity conservation, California rangelands generate multiple ecosystem services including livestock production, drinking and irrigation water, and carbon sequestration. California rangeland ecosystems have experienced substantial conversion to residential land use and more intensive agriculture. Objectives To understand the potential impacts to rangeland ecosystem services, we developed six spatially explicit (250 m) climate/land use change scenarios for the Central Valley of California and surrounding foothills consistent with three Intergovernmental Panel on Climate Change emission scenario narratives. Methods We quantified baseline and projected change in wildlife habitat, soil organic carbon (SOC), and water supply (recharge and runoff). For six case study watersheds we quantified the interactions of future development and changing climate on recharge, runoff and streamflow, and precipitation thresholds where dominant watershed hydrological processes shift through analysis of covariance. Results The scenarios show that across the region, habitat loss is expected to occur predominantly in grasslands, primarily due to future development (up to a 37 % decline by 2100), however habitat loss in priority conservation errors will likely be due to cropland and hay/pasture expansion (up to 40 % by 2100). Grasslands in the region contain approximately 100 teragrams SOC in the top 20 cm, and up to 39 % of this SOC is subject to conversion by 2100. In dryer periods recharge processes typically dominate runoff. Future development lowers the precipitation value at which recharge processes dominate runoff, and combined with periods of drought, reduces the opportunity for recharge, especially on deep soils. Conclusion Results support the need for climate-smart land use planning that takes recharge areas into account, which will provide opportunities for water storage in dry years. Given projections for agriculture, more modeling is needed on feedbacks between agricultural expansion on rangelands and water supply.

California↗
USGS2012

Ecosystem services from converted land: the importance of tree cover in Amazonian pastures

Deforestation is responsible for a substantial fraction of global carbon emissions and changes in surface energy budgets that affect climate. Deforestation losses include wildlife and human habitat, and myriad forest products on which rural and urban societies depend for food, fiber, fuel, fresh water, medicine, and recreation. Ecosystem services gained in the transition from forests to pasture and croplands, however, are often ignored in assessments of the impact of land cover change. The role of converted lands in tropical areas in terms of carbon uptake and storage is largely unknown. Pastures represent the fastest-growing form of converted land use in the tropics, even in some areas of rapid urban expansion. Tree biomass stored in these areas spans a broad range, depending on tree cover. Trees in pasture increase carbon storage, provide shade for cattle, and increase productivity of forage material. As a result, increasing fractional tree cover can provide benefits land managers as well as important ecosystem services such as reducing conversion pressure on forests adjacent to pastures. This study presents an estimation of fractional tree cover in pasture in a dynamic region on the verge of large-scale land use change. An appropriate sampling interval is established for similar studies, one that balances the need for independent samples of sufficient number to characterize a pasture in terms of fractional tree cover. This information represents a useful policy tool for government organizations and NGOs interested in encouraging ecosystem services on converted lands. Using high spatial resolution remotely sensed imagery, fractional tree cover in pasture is quantified for the municipality of Rio Branco, Brazil. A semivariogram and devolving spatial resolution are employed to determine the coarsest sampling interval that may be used, minimizing effects of spatial autocorrelation. The coarsest sampling interval that minimizes spatial dependence was about 22 m. The area-weighted fractional tree cover for the study area was 1.85 %, corrected for a slight bias associated with the coarser sampling resolution. The pastures sampled for fractional tree cover were divided between ‘high’ and ‘low’ tree cover, which may be the result of intentional incorporation of arboreal species in pasture. Further research involving those ranchers that have a higher fractional tree cover may indicate ways to promote the practice on a broader scale in the region.

Urban Ecosystems↗
USGS2019

Modelling development of riparian ranchlands using ecosystem services at the Aravaipa Watershed, SE Arizona

This paper describes how subdivision and development of rangelands within a remote and celebrated semiarid watershed near the US-Mexico border might affect multiple ecohydrological services provided, such as recharge of the aquifer, water and sediment yield, water quality, flow rates and downstream cultural and natural resources. Specifically, we apply an uncalibrated watershed model and land-change forecasting scenario to consider the potential effects of converting rangelands to housing developments and document potential changes in hydrological ecosystem services. A new method to incorporate weather data in watershed modelling is introduced. Results of introducing residential development in this fragile arid environment portray changes in the water budget, including increases in surface-water runoff, water yield, and total sediment loading. Our findings also predict slight reductions in lateral soil water, a component of the water budget that is increasingly becoming recognized as critical to maintaining water availability in arid regions. We discuss how the proposed development on shrub/scrub rangelands could threaten to sever imperative ecohydrological interactions and impact multiple ecosystem services. This research highlights rangeland management issues important for the protection of open-space, economic valuation of rangeland ecosystem services, conservation easements, and incentives to develop markets for these.

Arizona↗
USGS2019

Toward ecosystem accounts for Rwanda: Tracking 25 years of change in potential supply and flows of ecosystem services

1. Rwanda, a small but rapidly developing central African nation, has undertaken development of natural capital accounts to better inform its economic development through the World Bank’s Wealth Accounting and Valuation of Ecosystem Services (WAVES) Partnership. In this paper, we develop ecosystem service (ES) models to quantify the physical supply components of ecosystem accounts in Rwanda from 1990 to 2015. 2. We applied the InVEST carbon storage, sediment delivery ratio, and annual and seasonal water yield models to map changes in potential ES supply nationwide. We also quantified flows of sediment and water to 96 hydroelectric dam, irrigation dam, and water treatment plant sites. 3. Over a 25-year period, we found declines in all ES, which were most strongly driven by conversion of forests to cropland. Declines were most pronounced from 1990 to 2000 and 2010 to 2015; ES were relatively stable from 2000 to 2010. From 2010 to 2015, over 42% of Rwanda’s water-use sites (representing 17% of the nation’s hydroelectric generation capacity and 69% of its water treatment capacity) had increases in sediment export and quick flow greater than the national average. 4. Our results quantify nationwide ES trends, their implications for key water-dependent industries, and the importance of protected areas in safeguarding ES potential supply and flows in Rwanda. They also provide data that can be integrated with existing land, water, and economic accounts for Rwanda, as well as a baseline to inform development strategies that better link economic and environmental goals.

People and Nature↗
USGS2010

The use of scenario analysis to assess water ecosystem services in response to future land use change in the Willamette River Basin, Oregon

Human pressures on the natural resources of the United States have resulted in many unintended changes in our ecosystems, e.g., loss of biodiversity, habitat degradation, increases in the number of endangered species, and increases in contamination and water pollution. Environmental managers are concerned about broad-scale changes in land use and landscape pattern and their cumulative impact on hydrologic and ecological processes that affect stream conditions. The type of land use and land cover has direct consequences for most ecosystem services, including water quantity and water quality, erosion control, and biodiversity. As human pressure continues to increase, ecosystem services worldwide are projected to suffer continued loss and degradation, thus reducing the capacity of ecosystems to provide essential goods and services that contribute to human well-being (MEA 2005). The ability to assess, report, and forecast the life support functions of ecosystems is absolutely critical to our capacity to make informed decisions which will maintain the sustainable nature of our environmental services and secure these resources into the future. This study presents an integrated approach to identify areas with potential water quality problems as a result of land cover change projected by stakeholders within a moderately large river basin in the Pacific Northwest (USA). A process-based hydrologic watershed model was used to examine the contribution of land use/land cover to sediment yield, and nitrate and phosphorous loadings, and identify subwatersheds within the Willamette River basin that would be most affected in the year 2050 relative to three possible future scenarios which include inherent differences related to conservation, existing planning trends, and open development. Thus, the objective of this study was to evaluate the effects of alternative future scenarios that describe varying degrees of urban development and human use on hydrological response related to water quality. Results of this study suggest that the amount of forest along streams and agriculture consistently explained a high percentage of variation in nutrients. The AGWA-SWAT model was used to simulate change in sediment yield, nitrate and phosphorus transported with surface runoff for the three future scenarios. With regard to nitrate, the greatest increase was associated with subwatersheds with agricultural land use and urban areas. Although the model predicted some improvement in basin headwaters for all scenarios, nitrate loadings are expected to decrease under the conservation scenario. The largest decrease was observed in the Coast Range. With regard to phosphorous loadings, the lowest reduction was observed in subwatersheds draining predominantly forest areas. The greatest increase was observed under the open development scenario in subwatersheds with agricultural land use. Urbanization and agriculture are presumed to be the major environmental stressors affecting watershed condition of the Willamette River Basin.

Oregon↗
USGS2019

Towards globally customizable ecosystem service models

Scientists, stakeholders and decision makers face trade-offs between adopting simple or complex approaches when modeling ecosystem services (ES). Complex approaches may be time- and data-intensive, making them more challenging to implement and difficult to scale, but can produce more accurate and locally specific results. In contrast, simple approaches allow for faster assessments but may sacrifice accuracy and credibility. The ARtificial Intelligence for Ecosystem Services (ARIES) modeling platform has endeavored to provide a spectrum of simple to complex ES models that are readily accessible to a broad range of users. In this paper, we describe a series of five “Tier 1” ES models that users can run anywhere in the world with no user input, while offering the option to easily customize models with context-specific data and parameters. This approach enables rapid ES quantification, as models are automatically adapted to the application context. We provide examples of customized ES assessments at three locations on different continents and demonstrate the use of ARIES' spatial multi-criteria analysis module, which enables spatial prioritization of ES for different beneficiary groups. The models described here use publicly available global- and continental-scale data as defaults. Advanced users can modify data input requirements, model parameters or entire model structures to capitalize on high-resolution data and context-specific model formulations. Data and methods contributed by the research community become part of a growing knowledge base, enabling faster and better ES assessment for users worldwide. By engaging with the ES modeling community to further develop and customize these models based on user needs, spatiotemporal contexts, and scale(s) of analysis, we aim to cover the full arc from simple to complex assessments, minimizing the additional cost to the user when increased complexity and accuracy are needed.

Science of the Total Environment↗
USGS2019

Social equity shapes zone-selection: Balancing aquatic biodiversity conservation and ecosystem services delivery in the transboundary Danube River Basin

Freshwater biodiversity is declining, despite national and international efforts to manage and protect freshwater ecosystems. Ecosystem-based management (EBM) has been proposed as an approach that could more efficiently and adaptively balance ecological and societal needs. However, this raises the question of how social and ecological objectives can be included in an integrated management plan. Here, we present a generic model-coupling framework tailored to address this question for freshwater ecosystems, using three components: biodiversity, ecosystem services (ESS), and a spatial prioritisation that aims to balance the spatial representation of biodiversity and ESS supply and demand. We illustrate this model-coupling approach within the Danube River Basin using the spatially explicit, potential distribution of (i) 85 fish species as a surrogate for biodiversity as modelled using hierarchical Bayesian models, and (ii) four estimated ESS layers produced by the Artificial Intelligence for Ecosystem Services (ARIES) platform (with ESS supply defined as carbon storage and flood regulation, and demand specified as recreation and water use). These are then used for (iii) a joint spatial prioritisation of biodiversity and ESS employing Marxan with Zones, laying out the spatial representation of multiple management zones. Given the transboundary setting of the Danube River Basin, we also run comparative analyses including the country-level purchasing power parity (PPP)-adjusted gross domestic product (GDP) and each country's percent cover of the total basin area as potential cost factors, illustrating a scheme for balancing the share of establishing specific zones among countries. We demonstrate how emphasizing various biodiversity or ESS targets in an EBM model-coupling framework can be used to cost-effectively test various spatially explicit management options across a multi-national case study. We further discuss possible limitations, future developments, and requirements for effectively managing a balance between biodiversity and ESS supply and demand in freshwater ecosystems.

Science of the Total Environment↗
USGS2022

Analysis of provisioning ecosystem services and perceptions of climate change for indigenous communities in the Western Himalayan Gurez Valley, Pakistan

Climate change is a significant threat to people living in mountainous regions. It is essential to understand how montane communities currently depend especially on the provisioning ecosystem services (ES) and the ways in which climate change will impact these services, so that people can develop relevant adaptation strategies. The ES in the Gurez Valley, in the Western Himalayas of Pakistan, provide a unique opportunity to explore these questions. This understudied area is increasingly exposed not only to climate change but also to the overexploitation of resources. Hence, this study aimed to (a) identify and value provisioning ES in the region; (b) delineate indigenous communities’ reliance on ES based on valuation; and (c) measure the perceptions of indigenous communities of the impact of climate change on the ES in Gurez Valley. Semi-structured interviews and focus group discussions were used to classify the provisioning ES by using the ‘Common International Classification on Ecosystem Services’ (CICES) table and applying the ‘Total Economic Valuation (TEV)’ Framework. Results indicate that the indigenous communities are highly dependent on ES, worth 6730 ± 520 USD/Household (HH)/yr, and perceive climate change as a looming threat to water, crops, and rearing livestock ESS in the Gurez Valley. The total economic value of the provisioning ES is 3.1 times higher than a household’s average income. Medicinal plant collection is a significant source of revenue in the Valley for some households, i.e., worth 766 ± 134.8 USD/HH/yr. The benefits of the sustainable use of ES and of climate change adaptation and mitigation, are culturally, economically, and ecologically substantial for the Western Himalayans.

Gurez Valley, Himalaya↗
USGS2015

Landscape prediction and mapping of game fish biomass, an ecosystem service of Michigan rivers

The increased integration of ecosystem service concepts into natural resource management places renewed emphasis on prediction and mapping of fish biomass as a major provisioning service of rivers. The goals of this study were to predict and map patterns of fish biomass as a proxy for the availability of catchable fish for anglers in rivers and to identify the strongest landscape constraints on fish productivity. We examined hypotheses about fish responses to total phosphorus (TP), as TP is a growth-limiting nutrient known to cause increases (subsidy response) and/or decreases (stress response) in fish biomass depending on its concentration and the species being considered. Boosted regression trees were used to define nonlinear functions that predicted the standing crops of Brook Trout Salvelinus fontinalis , Brown Trout Salmo trutta , Smallmouth Bass Micropterus dolomieu , panfishes (seven centrarchid species), and Walleye Sander vitreus by using landscape and modeled local-scale predictors. Fitted models were highly significant and explained 22–56% of the variation in validation data sets. Nonlinear and threshold responses were apparent for numerous predictors, including TP concentration, which had significant effects on all except the Walleye fishery. Brook Trout and Smallmouth Bass exhibited both subsidy and stress responses, panfish biomass exhibited a subsidy response only, and Brown Trout exhibited a stress response. Maps of reach-specific standing crop predictions showed patterns of predicted fish biomass that corresponded to spatial patterns in catchment area, water temperature, land cover, and nutrient availability. Maps illustrated predictions of higher trout biomass in coldwater streams draining glacial till in northern Michigan, higher Smallmouth Bass and panfish biomasses in warmwater systems of southern Michigan, and high Walleye biomass in large main-stem rivers throughout the state. Our results allow fisheries managers to examine the biomass potential of streams, describe geographic patterns of fisheries, explore possible nutrient management targets, and identify habitats that are candidates for species management.

Michigan↗
USGS2016

Modeling the effects of urban expansion on natural capital stocks and ecosystem service flows: A case study in the Puget Sound, Washington, USA

Urban expansion and its associated landscape modifications are important drivers of changes in ecosystem service (ES). This study examined the effects of two alternative land use-change development scenarios in the Puget Sound region of Washington State on natural capital stocks and ES flows. Land-use change model outputs served as inputs to five ES models developed using the Artificial Intelligence for Ecosystem Services (ARIES) platform. While natural capital stocks declined under managed (1.3–5.8%) and unmanaged (2.8–11.8%) development scenarios, ES flows increased by 18.5–56% and 23.2–55.7%, respectively. Human development of natural landscapes reduced their capacity for service provision, while simultaneously adding beneficiaries, particularly along the urban fringe. Using global and local Moran’s I, we identified three distinct patterns of change in ES due to projected landuse change. For services with location-dependent beneficiaries – open space proximity, viewsheds, and flood regulation – urbanization led to increased clustering and hot-spot intensities. ES flows were greatest in the managed land-use change scenario for open space proximity and flood regulation, and in the unmanaged land-use change scenario for viewsheds—a consequence of the differing ES flow mechanisms underpinning these services. We observed a third pattern – general declines in service provision – for carbon storage and sediment retention, where beneficiaries in our analysis were not location dependent. Contrary to past authors’ finding of ES declines under urbanization, a more nuanced analysis that maps and quantifies ES provision, beneficiaries, and flows better identifies gains and losses for specific ES beneficiaries as urban areas expand.

Washington↗
USGS2018

Machine learning for ecosystem services

Recent developments in machine learning have expanded data-driven modelling (DDM) capabilities, allowing artificial intelligence to infer the behaviour of a system by computing and exploiting correlations between observed variables within it. Machine learning algorithms may enable the use of increasingly available ‘big data’ and assist applying ecosystem service models across scales, analysing and predicting the flows of these services to disaggregated beneficiaries. We use the Weka and ARIES software to produce two examples of DDM: firewood use in South Africa and biodiversity value in Sicily, respectively. Our South African example demonstrates that DDM (64–91% accuracy) can identify the areas where firewood use is within the top quartile with comparable accuracy as conventional modelling techniques (54–77% accuracy). The Sicilian example highlights how DDM can be made more accessible to decision makers, who show both capacity and willingness to engage with uncertainty information. Uncertainty estimates, produced as part of the DDM process, allow decision makers to determine what level of uncertainty is acceptable to them and to use their own expertise for potentially contentious decisions. We conclude that DDM has a clear role to play when modelling ecosystem services, helping produce interdisciplinary models and holistic solutions to complex socio-ecological issues.

Ecosystem Services↗