AquaFHIR: Decentralized Climate Data

Inspiration

Climate data transparency is one of the most critical challenges in fighting climate change today. While citizen science and local environmental monitoring are highly effective, the data is often unstructured, fragmented, and vulnerable to manipulation by bad actors or careless record-keeping. We were inspired to build a system that bridges the gap between subjective human observation and rigorous, decentralized scientific data. We wanted to create an ecosystem where climate data is not only perfectly structured but mathematically impossible to alter.

What it does

AquaChain (AquaFHIR) is an AI-powered, decentralized interoperability bridge. It empowers everyday citizens to report on urban ecosystem health (like stream pollution or algae blooms) using plain, natural language.

When a report is submitted, our AI engine instantly analyzes the text, determines the risk level, and translates it into an HL7 FHIR standard digital observation. Crucially, the system then calculates a SHA-256 cryptographic hash of this data payload and anchors it to a simulated public blockchain ledger. The result is a real-time Environmental Data Ledger for policymakers—a dashboard of climate data that is strictly standardized by AI and immutably secured by Web3 cryptography.

How we built it

We focused on building a clean, "Web2-style" user experience that hides complex "Web3" mechanics under the hood:

Frontend: Next.js (React) and Tailwind CSS for a highly responsive, mobile-first Citizen Portal and an enterprise-grade Ledger Dashboard. Artificial Intelligence: We integrated the Fireworks AI API (utilizing the Llama-3-70B-Instruct model) to power the NLP backend. It intelligently parses unstructured text ("green scum and dead fish") into structured risk assessments. Blockchain & Cryptography: The backend utilizes Node's crypto modules to generate SHA-256 payload hashes and mock Web3 transaction hashes, simulating the minting of climate data onto an immutable public ledger.

Challenges we ran into

The biggest challenge was track alignment—specifically, marrying subjective human input with rigorous data standards (Track 4: Climate Data). Translating qualitative environmental observations into strict quantitative healthcare/environmental standards required careful prompt engineering to ensure the LLM did not hallucinate risk factors.

Accomplishments that we're proud of

We are incredibly proud to have built a system that proves decentralized environmental surveillance doesn't have to be complicated to use. By combining AI as a "translation layer" and Blockchain as a "trust layer", we created a seamless pipeline from a citizen's smartphone directly to an immutable climate ledger.

What we learned

We learned that the barrier to decentralized climate action isn't a lack of interest, but the friction of complex tools. By allowing users to simply type out what they see and letting AI and smart contracts handle the complex data structuring and cryptographic verification, we drastically increase the potential for high-quality, continuous environmental monitoring.

What's next for AquaFHIR: Decentralized Climate Data

Our immediate next steps are to transition our cryptographic simulation into live Smart Contracts deployed on a low-energy blockchain testnet (like Polygon or Ethereum Sepolia). We also plan to expand the AI model to ingest metadata from IoT water sensors, creating a hybrid ledger of both human and machine-generated climate data.

Built With

• artificial-intelligence
• blockchain
• climate-tech
• hl7-fhir
• next.js
• react
• tailwind-css
• web3