AI continues to foster the new collaborations needed to build the groundwork for the visions and applications.
FREMONT, CA: About 900 Earth-observing satellites presently peer down at us from space. Simultaneously, an evolving network of ground-based sensor technologies tracks water movement, the sounds of ecosystems, and the chemicals that permeate soils and the atmosphere above it. This latest generation of sensing technologies is attended by sophisticated physical models, from climate simulators to continental-scale hydrologic models. These expansive novel data streams and physical models present uncharted opportunities to leverage AI to address the requirements of a planet on life support. Read on to know more.
In sustainability management and decision-making, use cases of AI have been limited. Most work has depended on standard supervised learning methods to evaluate single dimensions of land use or climate risk-focused at scales that extend beyond those where decisions are made. Although the use of indicators allows remotely sensed data streams to serve as proxies for factors other than land leverage and climate, to the knowledge, very few studies have utilized mixed data streams, especially high-resolution human-centered data, due to the vast mismatches between spatial and temporal character. Thus, there is an immediate requirement to develop methods that can learn from diverse data streams and transfer that learning to community-based decision-making.
Using AI as a decision tool to guide sustainability efforts has also lagged behind uses in other areas. A substantial hindrance to the development of sustainable societies arises from the complexity of socio-economic-environmental systems. This complexity can surpass the potential for a human to understand all interactions and causations. A common method to make sense of this complexity is to develop indexes or collections of indicators. Although useful as a metric for evaluation, when applied as a tactic for decision making, a strong dependence on indices can lead to unintended impacts because a static index cannot fully account for uncertainty connected with human behavior and community-driven priorities.
Most important, indexes can be influenced by embedded social and cultural preferences and local political action. To address these challenges needs an intelligent system, human or machine, that can deeply understand multi-dimensional issues and solutions in complex socio-economic-environmental systems.