Celest Science develops high-resolution seasonal climate forecasts using deep learning and physics-informed AI models. The platform provides probabilistic predictions that quantify uncertainty for sub-seasonal to seasonal risk assessment. This enables better decision-making for clients in the insurance, energy, and agribusiness sectors facing climate volatility.
Funding
$2.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
AVPPFounders
Product
Problem
Traditional risk assessment methods often rely on historical climate data, failing to account for the increasing frequency and intensity of extreme weather events caused by climate change. This makes it difficult for organizations to accurately assess and prepare for future climate-related risks, leading to potential economic losses and operational disruptions.
Solution
Celest.Science provides AI-powered climate risk insights, offering sub-seasonal to decadal predictions to help organizations proactively adapt to changing climate conditions. By blending deep learning, generative models, and physics-informed AI, their platform bridges the gap between weather forecasting and long-term climate simulation. This enables users to anticipate extreme climate events, accurately assess physical risks, and diagnose the vulnerability of assets to climate change. The platform delivers probabilistic forecasts that quantify prediction uncertainty, providing a comprehensive view of possible outcomes for enhanced decision-making.
Target Audience
Celest.Science primarily serves organizations in the insurance, energy, and agribusiness industries, helping them manage climate-related risks, optimize resource allocation, and improve strategic decision-making.
Features
- Sub-seasonal to seasonal climate predictions, ranging from weeks to a decade ahead
- AI-driven models that leverage deep learning, generative models, and physics-informed approaches
- Integration of historical climate data, trends, and current conditions for dynamic risk assessment
- Probabilistic forecasts that quantify prediction uncertainty and estimate extreme event occurrences
- API access for easy integration into existing workflows
- Weekly forecast updates