Ecosystem Intelligence Platform

EcoMetrix Solutions Group, LLC

Ecosystem Intelligence Platform

Ecosystem Intelligence (EI) is a proven quantification platform that provides robust, system-level analysis of baseline, reference, and scenario change — for understanding ecosystems, ecosystem impacts, and ecosystem service benefit production. The ability of  the EI platform to support the specific TNFD use case is illustrated on the Ecosystem Intelligence website (https://www.ecosystemintelligence.com/tnfd-leap).

EI Platform Modules

The EI platform currently includes several modules, including a high-level Screening Module and a detailed Design Module (Risk Module coming in late 2023). EI modules enable users to characterize baseline site performance, model endless ‘what-if’ design and restoration scenarios and compare performance to reference site conditions for benchmarking and gap assessment purposes. In addition, the Design Module enables users to monitor and verify performance over time.

Screening Module

The Screening Module utilizes generalized datasets derived from field data to help users quickly (with no ecological expertise required) understand general site performance in comparison to biome-specific reference conditions. The purpose of EI’s Screening Module is to provide early decision-makers with an understanding of:

• Ecosystem services performance values associated with highly functioning reference landscapes in the local biome,
• Ecosystem services performance values associated with generalized land cover and land uses in the local biome,
• How generalized land cover performance values may be affected by development or thoughtful design intervention activities; and
• The type and rough spatial extent of intervention(s) required to improve site performance in response to reference conditions/targets, in support of early planning and rough-order-of magnitude cost-estimating needs.

The ultimate goal of the Screening Module is to provide an early due diligence tool to help organizations reduce negative impacts and quickly identify the potential benefits that may result from the inclusion of regenerative elements in project design. This approach helps get regenerative design, informed by a high-level, bottom-up contextual understanding, into project development conversations early, before preliminary designs are complete, and design and construction budgets are established.

Design Module

The EI Design Module is a powerful decision-support tool that enables site-specific data to be utilized for modeling baseline site performance, quantifying the impacts and benefits expected to result from design scenarios, and for generating location-specific reference site performance values for benchmarking and target setting purposes. The Design Module uses a combination of remotely sensed and on-the-ground, field collected data to provide a comprehensive understanding of site performance conditions. Users can create an infinite number of design scenarios and customized reference conditions to help optimize design solutions in response to site context. Using the Design Module and the field data collection App, existing site conditions and project outcomes can be field verified by Certified users to document impacts and uplift resulting from management activities and design decisions.

How is the EI Platform fit for TNFD’s Purpose?

In addition to addressing LEAP process needs (https://www.ecosystemintelligence.com/tnfd-leap), EI provides a solution that:

Is Tested and Credible – The underlying EI approach originated in the realm of U.S. regulatory compliance at the state and federal level, winning the 2005 FHWA Environmental Excellence Award for the Oregon Bridge Replacement Environmental Stewardship Program and the 2006 FHWA Exemplary Ecosystems Initiative Award for the ODOT Conservation and Mitigation Banking Program. A subsequent iteration of the methodology, known as EcoMetrix, was recognized as “an exemplar software tool for biodiversity and ecosystems decisions” in the President’s Council of Advisors on Science and Technology, “Sustaining Environmental Capital: Protecting Society and the Economy” Report in July of 2011. In 2013, EcoMetrix was customized for The Nature Conservancy (TNC) and the Dow Chemical Company and was made publicly available as the Ecosystem Services Identification and Inventory (ESII) Tool. ESII, the precursor to EI, was recognized in 2016 by the President’s Council of Environmental Quality as “a critical development” useful for helping agencies implement President Obama’s 2015 Executive Memorandum, which requires federal agencies to integrate ecosystem services into federal decision-making processes.

One of the many strengths of the EI platform is that it has been developed by SME practitioners, for SME practitioners, over more than a twenty-year period. During that time, over one hundred ecologists, fish and wildlife biologists, botanists, wetland, desert, and forestry scientists, soil scientists, hydrologists, water quality experts, fluvial geomorphologists, engineers, environmental toxicologists, chemists, spatial analysts, and policy experts have contributed to the body of work known today as the EI platform. This collaborative and multidisciplinary development approach, involving dedicated SME teams from academia, natural resource and regulatory agencies, NGOs, private corporations, and consulting firms is at the heart of what makes the EI platform an ideal tool for use in applied analyses that generate actionable outcomes.

Is Globally Relevant – The EI platform is globally relevant, enabling use of the same approach regardless of site location. Already used in over 45 countries, this consistent approach supports global results aggregation and presentation in support of organization-wide assessment and reporting. To date, EI models have been applied on every continent except the Antarctic, and within every biome capable of supporting vegetative attributes. When necessary, attributes and scoring considerations can be fine-tuned in response to geographically driven issues identified by SMEs participating in the EI Commons.

Includes a Broad Array of Customizable, Relevant Metrics – The EI platform includes biophysical function and process models, in addition to a broad suite of ecosystem service benefit production models. The ecosystem service models have been organized into categories including Air Quality, Biodiversity, Climate, Soil, Water Quality, Water Quantity, and Wellbeing to facilitate reporting, while the biophysical function and process models (e.g., interception, evaporation, carbon uptake, carbon storage, etc.) are presented as supplemental metrics for use in design optimization. Many additional models, including a suite of social and cultural metrics, are planned for upcoming releases. The diversity of metrics and the variety of reporting outputs available gives businesses a flexible suite of resources to use in both issue-specific analysis contexts, as well as in systems-based evaluations that look across media and regulatory silos.

Is Easy to Use, Balancing Complexity and Simplicity – Understanding impacts to ecosystem services requires an awareness of many diverse and complex relationships that occur in nature – and similarly, between nature and humans. However, this understanding must be democratized and made accessible to non-SMEs in order for positive ecological change to be achieved on the landscape. This creates a challenge for decision support tool developers, as they must strike a balance between complexity and simplicity in order to produce tools that are both credible and broadly useable. The EI approach to capturing the complexity and interconnectedness of the ecosystem provides scientific rigor and credibility, while limiting the burden placed on non-SME users. The goal of democratizing user access to the sophisticated EI decision-support resources has shaped everything from how the EI models are constructed to how the field data collection surveys have been designed. The EI platform offers users of all skill sets, regardless of sector or application, access to a range of tools that enable everything from rapid assessments to detailed analysis, modeling, and monitoring capabilities. Reporting formats can be customized upon request to meet the suite of emerging regulatory, ESG, and financial disclosure needs.

Utilizes Locally Attuned, Bottom-Up Data – EI models rely on a mix of data inputs derived from regional climate data, outputs from third-party remote sensing analysis, and field-collected data. Regional data and remote data are used where appropriate, relevant, and reliable. Field collected data are used, in support of the bottom-up approach, to provide an accurate reflection of site performance. EI users are encouraged to visit project sites and collect the required attribute data using the field data collection App. However, if field data collection is not possible in full or in part, remotely sensed data (or surrogate data from similar localities and habitat types) can be used with the understanding that output accuracy will be less certain. This is due in part to the fact that some key attribute data are sometimes not feasible to collect remotely. EI data collection protocols include guidance to help the user identify reasonable surrogate inputs and strategies for enabling field verification when surrogates have been used.

Emphasizes Repeatability and Addresses Uncertainty – Repeatability, a critical concern in regard to credibility, refers to the likelihood that multiple tool users analyzing a given site will collect consistent data and produce consistent results. This is especially important when outputs are used for ESG reporting or for compliance purposes. EI platform developers have addressed this need by:

• Performing systematic testing when developing new models to develop realistic data collection protocols and to structure data collection survey questions, help material, and input response options/formats in a manner that optimizes clarity and educational value.
• Testing input response options/formats to evaluate how precise the response options can be before errors or inconsistencies between data collectors are observed.
• Performing statistical repeatability testing, whereby user responses are collected in a test environment, analyzed, and used to improve question formats and answer options.
• Assessing the likelihood of any given user answering any given question incorrectly and accounting for any associated user uncertainty using Bayesian belief networks (BBN).

Uncertainty associated with user experience is also addressed by the EI platform, where user experience levels can be set in the user’s profile to adjust the tool’s confidence in user-collected data. Multiple layers of training are offered, including basic user training, Certified user training, and training offered for third-party Verifiers. User experience profiles are adjusted accordingly.

Provides Scalable Analyses in the Built and Natural Environments – Analysis scales, both spatial and temporal, have become increasingly important in the analysis and evaluation of ecosystem services. The EI platform models are designed to function at multiple scales, each offering a unique level of resolution. The modeling approach is based on using a digital twin to capture the change associated with impacts/benefits provided on any parcel of land, with no minimum or maximum size requirement. The basic premise behind EI’s bottom-up approach is that capturing change based on field-collected attribute data provides the greatest certainty regarding model output quality. However, the level of effort required to collect input data must align with the intended use of the outputs and therefore EI has been designed to offer users maximum flexibility.

For projects involving footprint level analyses (e.g., facility siting decisions, stream restoration design scenarios, infrastructure siting decisions, etc.), it is important to understand how a specific location on the ground performs and may be affected by land use/design change. In these cases, users are encouraged to create a digital twin as detailed  as necessary to accurately characterize the area of impact, both in terms of baseline condition and planned changes. Conversely, in the case of general landscape performance where programmatic decisions (e.g., high-level watershed management strategies) are driving the analysis rather than specific design footprints, users are encouraged to create a less detailed digital twin that still captures the general landscape characteristics and performance.

Is Designed to Foster Interoperability and Adapt to Advances in Artificial Intelligence and/or Machine Learning – The EI platform developers are well connected in the ecosystem of evolving tools and recognize the importance and value of enabling interoperability, as well as Artificial Intelligence (AI) and Machine Learning (ML). As data resources and tools evolve, EI will continue to adapt to ensure efficient use of the best resources available and collaborate with key partners in the evolution of fit-for-purpose decision support tools. The potential use of AI and/or ML applications in the development/refinement of EI models and field data collection is currently being tested.