Global Adaptation Layer
A hyper-local global adaptation dataset for building resilience
Overview
The Global Adaptation Layers are a set of globally consistent, hyperlocal geospatial data layers on the adaptation capacity of any coordinate on earth, enabling "ground truth” analysis of climate resilience down to the neighborhood or asset-level.
Our Approach: Engineering a Hyper-local Global Adaptation Dataset
Climate change is already here and will only continue to escalate - making adaptation all the more essential. Against this backdrop, organizations are looking to deepen their understanding of adaptation capacity, in order to strengthen resilience against climate challenges.
However, existing global climate adaptation datasets often lack sufficient resolution, typically offering only high-level societal resilience indicators such as income or education at city and county-levels. This in turn limits the ability of investors, corporations, and governments to gain the localized insights needed at the asset-level. This includes data on hazard-specific adaptations in the local environment, such as drainage capacity for floods, or fire response stations for wildfire. All these factors are equally crucial to explaining climate resilience.
AlphaGeo’s Global Adaptation Layer is our solution to this problem. Using proprietary AI techniques for data extraction and downscaling, we have engineered multiple layers of globally consistent, hyper local climate adaptation indices at up to 30 meters in resolution. Together with high-level societal resilience indicators, these datasets offer a true-to-the-ground portrayal of the resilience of any location in the world.
The Global Adaptation Layers are currently comprised of global scores and underlying features for:
Heat Stress Adaptation (e.g., Building Density, Urban Greenery)
Inland Flooding Adaptation (e.g., Porosity, Proximity to Drainage Systems)
Coastal Flooding Adaptation (e.g., Coastal Defenses, Proximity to Natural Buffers)
Hurricane Wind Adaptation (e.g., Building Strength, Proximity to Flood Storage)
Drought Adaptation (e.g., Proximity to Water Treatment, Proximity to Water Storage)
Wildfire Adaptation (e.g., Proximity to Fire Response, Proximity to Fire Prevention)
Societal Resilience (e.g., Local GNI, Vulnerable Population)
Methodology
The Global Climate Adaptation Layer aims to be a globally consistent, high-resolution climate adaptation dataset engineered from a diverse set of geospatial data sources that provide information on the built environment with up to 30 meters resolution for each type of climate hazard.
The overall methodology can be broken down into four steps as show in the flowchart below. The processes are iterative as any step in the process could help inform decision making in other steps.
Define adaptation themes from domain expertise
For each climate hazard, a throughout study on the best practices in hazard mitigation and adaptation is conducted. Then, we define the thematic areas that can be potentially quantified to explain the degree of adaptation.
For example, water treatment facilities—including filtration systems, wastewater treatment plants, and water storage solutions—play a critical role in managing dry spells. During prolonged periods of drought, a location’s proximity to these facilities and its access to their services become key indicators of drought resilience. Thus, we define the feature ‘Availability and Capacity of Water Works’ to indicate whether a location falls within the service area of water treatment facilities.
Collect required spatial attributes
After defining the features to be engineered, we then find the suitable data source to construct the proposed feature. The selected data sources need to meet at minimum one of the three criteria below:
Peer-reviewed - the data is published in academic journals that underwent a peer-review process. E.g. Local-climate zone data from World Urban Database and Access Portal Tools (WUDAPT)
Well-documented - the data is published with clear explanation of methodologies and/or code repositories for third parties to reproduce the results. E.g. OpenStreetMap.
Well-established - the data is published by reputable organizations and are widely used by the industry. E.g. 10m Global Land Cover by Impact Observatory.
In the case of the feature defined above, OpenStreetMap provides a global map of geospatial features containing water works, wastewater treatment plants, water access point, and other related vector features. Additionally, data from the Global Dam Watch Database provides the locations, capacity, and outlines of freshwater reservoirs, which complements the data from OpenStreetMap.
Construct thematic features using geospatial operations
In most situations, simply taking raw data from the source is insufficient in explaining the defined adaptation themes. The raw data need to be cleaned, processed, and engineered into the desired thematic features for better explainability and compatibility with other data layers. While each data source and adaptation theme require unique processing pipeline, the general workflow is as follows:
Clean and fix source data anomalies at native resolution
Enhance the resolution or complete missing areas of the source data if necessary
Convert raw data into structured data with spatial indexes
Apply spatial and statistical operations to obtain the targeted thematic feature
Rescale the thematic feature to a scale of 0 - 100, with 100 indicating the highest resilience in each theme. This can be achieved using min-max normalization or percentile ranking depending on the distribution of the thematic feature.
Using the drought resilience example, vector data from OpenStreetMap are first cleaned and buffered to determine the radius of coverage, and then aggregated into a unified spatial index. Similarly, data from reservoir datasets are processed by buffering reservoir polygons with a corresponding radius. By overlaying these layers, we can identify the number of services or adaptation features available at each location. A location that meets all criteria within the Water Treatment category would fall within the service radius of water infrastructure, benefit from high water capacity, and have access to multiple water access points, and thus score 100, indicating the highest resilience in terms of ‘Availability and Capacity of Water Works’.
Aggregate adaptation scores for each hazard
Finally, all adaptation features for a single hazard are aggregated to one distribution which is then used to adjust for the intensity of the hazard. As such, a location that scores 100 in all constituent themes enjoys the highest possible offset for the relevant hazard. This process is applied to each of the six climate hazards to obtain the Resilience-adjusted Risk using methods described in our Climate Risk and Resilience Framework.
Last updated
