MangroveLens: AI Monitoring & On-Chain Proof of Restoration

[Proposal setup] Proposal title

Please provide your proposal title

MangroveLens: AI Monitoring & On-Chain Proof of Restoration

[Proposal Summary] Budget Information

Enter the amount of funding you are requesting in ADA

190000

[Proposal Summary] Time

Please specify how many months you expect your project to last

12

[Proposal Summary] Translation Information

Please indicate if your proposal has been auto-translated

No

Original Language

en

[Proposal Summary] Problem Statement

What is the problem you want to solve?

Coastal mangrove restoration lacks reliable, scalable monitoring. Field surveys are slow, costly and hard to verify, and there is no automated, blockchain-secured proof of restoration.

[Proposal Summary] Supporting Documentation

Supporting links

• https://www.bondy.earth/en
,
• https://dagshub.com/nelson.maillard/Bondy-Omdena
,
• https://www.omdena.com/blog/monitoring-reforestation-using-machine-learning
,
• https://ia.bondy.earth/Model_Prediction
,
• https://sites.google.com/bondy.earth/information-system/syst%C3%A8mes-dinformation?authuser=0

[Proposal Summary] Project Dependencies

Does your project have any dependencies on other organizations, technical or otherwise?

No

Describe any dependencies or write 'No dependencies'

No dependencies

[Proposal Summary] Project Open Source

Will your project's outputs be fully open source?

No

Please provide details on the intellectual property (IP) status of your project outputs, including whether they will be released as open source or retained under another licence.

MangroveLens will use a mixed IP model. The production platform will be mostly proprietary, because it hosts sensitive ecological and finance data. Selected analysis libraries, anonymised sample datasets and Cardano smart-contract interfaces will be published openly so other builders can reuse the Proof of Restoration pattern.

[Theme Selection] Theme

Please choose the most relevant theme and tag related to the outcomes of your proposal

Environment

[Campaign Category] Category Questions

Describe what makes your idea innovative compared to what has been previously launched in the market (whether by you or others).

MangroveLens is one of the first Cardano projects to link automated ecological monitoring directly with on-chain proofs of restoration.

It is innovative because it:

• Uses computer-vision models trained on a unique drone dataset of 15,000 ha of real mangrove sites, detecting seedlings, canopy recovery and biomass trends rather than only coarse land-use classes.

• Turns these indicators into structured digital attestations and hashes each validated report to Cardano, creating a verifiable “Proof of Restoration” trail that can underpin carbon sequestration, NFTs or impact-linked finance.

• Builds on a prior Machine Learning prototype developed with Omdena and hosted on DagsHub, so we extend proven data pipelines instead of starting from a pure idea.

For Cardano this provides a specialised blue-carbon MRV rail, complementary to general tree-tracking or NDVI-oracle projects already funded by Catalyst.

Describe what your prototype or MVP will demonstrate, and where it can be accessed.

The MVP demonstrates the full workflow from imagery to on-chain proof. Users will:

1. Upload or link drone and satellite scenes for selected mangrove plots;
2. Run AI models that segment mangroves, detect survival and estimate canopy and carbon proxies;
3. Explore indicators on a web map and generate monitoring reports;
4. Send a signed “Proof of Restoration" record to a Cardano testnet smart contract for each validated report.

The public will access a testnet dApp to inspect sample plots and their on-chain proofs.

Partner NGOs and researchers will use a secure workspace to upload real data and test the workflow during the pilot.

Describe realistic measures of success, ideally with on-chain metrics.

We define success using technical, adoption and on-chain metrics:

• AI performance: at least 85% precision and recall on validation data for mangrove detection and classification.

• Coverage: 15,000 ha of mangroves processed, with indicators generated for at least three restoration projects.

• User adoption: 5 active pilot users (NGO staff, scientists and project managers) using the dashboard during the pilot.

• On-chain usage: a minimum of 500 Proof of Restoration transactions on Cardano testnet across multiple monitoring cycles and plots.

•Mainnet readiness: a documented, smart-contract interface and at least one Letter of Intent from a finance or carbon partner to use the system after the fund.

[Your Project and Solution] Solution

Please describe your proposed solution and how it addresses the problem

MangroveLens is an AI-powered monitoring and verification platform dedicated to mangrove and blue-carbon projects and built on Cardano.

It ingests drone and satellite imagery, aligns it with plot boundaries and field observations, and runs computer-vision models to detect mangrove cover, seedling survival, canopy change and carbon proxies.

Results are stored in a geospatial database and presented through a web dashboard and APIs so project teams can track performance, compare sites and export reports.

When a monitoring report is validated, key metrics and metadata are hashed and recorded in a Cardano smart contract, creating a tamper-proof Proof of Restoration event linked to the project, plot and date.

This replaces spreadsheet-based monitoring with automated analytics, reduces verification costs and provides funders, registries and the Cardano community with independently verifiable evidence of ecological impact.

[Your Project and Solution] Impact

Please define the positive impact your project will have on the wider Cardano community

MangroveLens positions Cardano as a backbone for real-world climate and biodiversity action.

It gives the community a live example where network transactions represent verified restoration events, not just financial trades.

The project delivers a reusable Proof of Restoration contract pattern, open ecological analysis components and anonymised datasets that other builders can fork or extend for forests, wetlands or regenerative agriculture.

We will engage Cardano Impact, Cardano Africa and other community groups with testnet demos, feedback sessions and transparent reporting. This will seed collaborations with impact funds, NGOs and DeFi builders, leading to new nature-based applications and sustained on-chain activity.

[Your Project and Solution] Capabilities & Feasibility

What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?

Bôndy has run large-scale restoration and agroforestry programmes since 2019, managing millions of trees and long-term partnerships with NGOs, scientists and communities.

In 2022 we co-developed with Omdena a Machine Learning dashboard for reforestation monitoring, including vegetation indices, segmentation models and a dockerised web app; the code and data pipelines are stored in a public DagsHub repository.

This provides a strong technical foundation for MangroveLens.

Our team now includes a dedicated CIO for data architecture, two GIS and remote-sensing specialists, a sustainability and certification expert, and ZenGate Global as our blockchain and infrastructure engineering partner.

We will validate feasibility through three phases:

1. architecture and data pipeline set-up;

2. AI models and dashboard integrated with plot-level data;

3. with ZenGate, deployment of the solution on Cardano testnet, anchoring key monitoring indicators on-chain, and running a field pilot on a selected mangrove area.

[Milestones] Project Milestones

Milestone Title

Project setup and technical & data architecture defined

Milestone Outputs

Core team contracted; governance, risk and reporting processes defined. System architecture and data-flow diagrams produced, covering AI pipeline, geospatial database, backend, frontend and Cardano contracts. First test dataset (one mangrove site) ingested into a development database.

Acceptance Criteria

Architecture document reviewed and approved by the project lead and core technical team, including data flows, component responsibilities, and Cardano integration points. A tagged version of this document is stored in the shared.

Evidence of Completion

1. Link to PDF.

Notes: Documents and links will be hosted on a public Notion page. We may additionally consider providing the evidence in other mediums to facilitate milestone reviewer access, but this shall not be the basis of a milestone rejection unless the reviewer is unable to access the page.

Delivery Month

3

Cost

23000

Progress

20 %

Milestone Title

Data pipeline and baseline AI models for mangrove monitoring

Milestone Outputs

Operational ETL pipeline for drone and satellite imagery and field data. Baseline computer-vision models trained for mangrove segmentation, seedling detection and canopy/NDVI analysis, integrated into the pipeline. Evaluation report with metrics and recommended improvements.

Acceptance Criteria

Pipeline can process all datasets from at least two mangrove sites end-to-end. Models reach minimum agreed performance (around 85% precision/recall) on validation data and indicators are stored in the database.

Evidence of Completion

1. Link to PDF.

Notes: Documents and links will be hosted on a public Notion page. We may additionally consider providing the evidence in other mediums to facilitate milestone reviewer access, but this shall not be the basis of a milestone rejection unless the reviewer is unable to access the page.

Delivery Month

6

Cost

50000

Progress

40 %

Milestone Title

Web dashboard beta for restoration teams

Milestone Outputs

1. Functional web dashboard with login, plot selection on a map, time-series charts of key indicators and basic report export.
2. Role-based access implemented for at least two partner organisations. User testing sessions run and priority UX issues fixed.

Acceptance Criteria

1. At least two pilot users from partner organisations can use the dashboard to review their plots with assistance.
2. Bug list and UX issues tracked and resolved for the initial beta.

The version will be entirely in French or in English.

Evidence of Completion

1. Public or password-protected URL of the beta dashboard.
2. Link to a PDF

Please note that the dashboard will not be responsive at this stage and must be opened from a recent desktop or laptop computer.

Delivery Month

9

Cost

60000

Progress

70 %

Milestone Title

Cardano testnet integration and field pilot

Milestone Outputs

1. Smart contracts deployed on Cardano testnet implementing the Proof of Restoration record.
2. Backend integrated so that validated monitoring reports are hashed and submitted on-chain.
3. Pilot with at least two mangrove projects generating on-chain proofs through the dashboard.

Acceptance Criteria

1. Minimum of 200 Proof of Restoration transactions created on Cardano testnet across multiple plots and monitoring cycles.
2. Contracts and APIs documented and reviewed, with no critical security issues outstanding.

Evidence of Completion

1. Testnet contract addresses and example transaction IDs
2. Link to a PDF.

Notes: Documents and links will be hosted on a public Notion page. We may additionally consider providing the evidence in other mediums to facilitate milestone reviewer access, but this shall not be the basis of a milestone rejection unless the reviewer is unable to access the page.

Delivery Month

11

Cost

45000

Progress

90 %

Milestone Title

Project Close-out

Milestone Outputs

1. Hardened, production-ready codebase with resolved issues from the pilot and a clear mainnet deployment plan

2. Promotional content produced for the tool

3. Project Close-out Report and Project Close-out Video submitted created

Acceptance Criteria

1. The tool is fully deployed on the Cardano mainnet with no know bugs.

2. Communication materials, including case studies, social media content

3. Final closeout report is publicly available and final closeout video is publicly available

Evidence of Completion

1. Link to the prototype tools

2. Link to social media contents & case studies

3. Link to final closeout report & link to final closeout video

Delivery Month

12

Cost

22000

Progress

100 %

[Final Pitch] Budget & Costs

Please provide a cost breakdown of the proposed work and resources

• 51,000 ADA – AI and data engineering: model refinement, training, evaluation, and maintenance of the ETL/geodatabase pipeline.

• 43,000 ADA – Blockchain and backend: Plutus contracts, APIs, security reviews, testnet deployment and performance tuning.

• 33,000 ADA – Frontend and UX: web dashboard, maps, wallet integration, field-app components, accessibility and user testing.

• 38,000 ADA – Field pilot and scientific support: partner coordination, data acquisition, validation campaigns, travel and workshops.

• 25,000 ADA – Project management, accounting, legal and community engagement: coordination, reporting to Catalyst, legal review and ecosystem outreach.

[Final Pitch] Value for Money

How does the cost of the project represent value for the Cardano ecosystem?

This project turns 190,000 ADA into a reusable MRV infrastructure for many future nature-based solutions on Cardano. Since we are building on an existing prototype developed with Omdena and on a codebase already available on DagsHub, Catalyst funds are mainly devoted to engineering a robust, Cardano-native implementation and data processing rather than preliminary research.

The resulting AI pipelines, geospatial database design and “Proof of Restoration” smart contract pattern can be reused by other teams, reducing duplication and accelerating the launch of new climate projects. By enabling verifiable restoration records that can back carbon credits, impact tokens or green lending, MangroveLens can unlock much larger volumes of capital and long-term on-chain activity far beyond the cost of the prototype itself.

[Self-Assessment] Self-Assessment Checklist

I confirm that evidence of prior research, whitepaper, design, or proof-of-concept is provided.

Yes

I confirm that the proposal includes ecosystem research and uses the findings to either (a) justify its uniqueness over existing solutions or (b) demonstrate the value of its novel approach.

Yes

I confirm that the proposal demonstrates technical capability via verifiable in-house talent or a confirmed development partner (GitHub, LinkedIn, portfolio, etc.)

Yes

I confirm that the proposer and all team members are in good standing with prior Catalyst projects.

Yes

I confirm that the proposal clearly defines the problem and the value of the on-chain utility.

Yes

I confirm that the primary goal of the proposal is a working prototype deployed on at least a Cardano testnet.

Yes

I confirm that the proposal outlines a credible and clear technical plan and architecture.

Yes

I confirm that the budget and timeline (≤ 12 months) are realistic for the proposed work.

Yes

I confirm that the proposal includes a community engagement and feedback plan to amplify prototype adoption with the Cardano ecosystem.

Yes

I confirm that the budget is for future development only; excludes retroactive funding, incentives, giveaways, re-granting, or sub-treasuries.

Yes

[Required Acknowledgements] Consent & Confirmation

I Agree

Yes