Project Resilience launched its work in 2022 with coverage for one of the UN SDGs before expanding to other SDGs in 2023. The project has three working groups dedicated to delivering this work:
1. Minimum Viable Product (MVP) Working Group
This Working Group is composed of subject matter experts in machine learning modeling, UX development, Architecture and DevOps who are working towards the goal of creating an MVP for the machine learning ensemble model and supporting architecture for one of the SDG topics.
The MVP working group will work in two Tracks (Data and Architecture) to produce the following deliverables:
-
Develop architecture to pull input and output data hosted by third parties
- Develop code to compare both predictors and prescriptors in third party models and produce a set of performance metrics
- Build a portal to visualize assessment of predictors and prescriptors to include generations of key performance indicators (KPIs) and comparison across models
- Develop ensemble model for predictors and prescriptors
- Build API for third parties to submit models
MVP Demo Land Use Optimization demo, AI for Good Global Summit Workshop, 5 July 2023
2. Data Working Group
This Working Group is composed of subject matter experts in data science, data sharing, and data standardization. The goal of data working group is to provide guidelines for data contribution towards solutions that project resilience will create, and develop specifications and conduct case studies for data sharing in a standardized way with interoperable interfaces with the following specific objectives:
- To identify contributors and their roles (relationships) as data suppliers (sources)
- To convert collected data into publicly available data and/or datasets
-
To validate data quality with appropriate KPIs
- To support data clearing house as a platform to aggregate the data
- To curate data with common data models for shared taxonomy
- To support data features (context/action/ outcomes) and repositories (local storages)
- To support data life cycle management
- To ensure security, privacy, and trust as well as legal compliance including data ownership
The data working group plans to develop deliverables focusing on the areas of climate, water and energy in two phases as follows:
-
Phase 1:
- Guidelines for data contribution to Project Resilience (Version 1) covering data value chain and involved contributors, requirements analysis for publicly available data/datasets and security and privacy concerns and legal compliance
- Review of existing standards on data covering gap analysis of existing standards and identification of potential work items to be standardized
-
Phase 2:
- Guidelines for data contribution to Project Resilience (Version 2) covering more detailed guidelines based on the first deliverable on guidelines and identification of technical challenges, tools as well as potential risks
-
Specifications for interoperable data sharing for AI/ML covering in-depth analysis of technical choices and development of technical specifications, and relevant standardization activities in ITU-T collaborating with other SDOs
-
Case studies for creating publicly available data/datasets and sharing them in order to share experiences among contributors.
Data Working Group Lead Gyu Myoung Lee, Liverpool John Moores University, United Kingdom
3. Product Experience Working Group
This Working Group is composed of subject matter experts in in product management, user interaction, and usability. The goal of this working group is to identify types of users that will benefit from the AI Utility and ensure that each has an optimal user experience with the platform and will be able to provide feedback and insight into solution usage.
Product Experience Working Group Lead TBD