Skip to content
View darlianecunha's full-sized avatar
🎯
🎯

Block or report darlianecunha

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
darlianecunha/README.md

Hi, I'm Darliane Cunha

Sustainability Data Scientist | PhD | Maritime decarbonisation, port emissions analytics, ESG text mining, SDG indicators | Python, ML, NLP, SQL

Website LinkedIn ORCID Google Scholar

Open to data science, sustainability analytics and research roles in ports, shipping and climate, in the Netherlands and across Europe.


About me

I turn raw port, ship and regulatory data into evidence, dashboards and open tools used by port authorities, regulators and researchers. Full Professor at the Federal University of Maranhão (Brazil), PhD in Accounting and Finance (Universidad de Zaragoza), postdoctoral research at Erasmus University Rotterdam (2024–2025).

  • What I work on: at-berth and anchorage CO₂ inventories, EU MRV and EU ETS analytics, onshore power supply business cases, text mining of sustainability reporting, SDG assessment frameworks for ports, computer vision for environmental monitoring.
  • Data I know well: EU MRV / THETIS, Copernicus Sentinel-5P, ANTAQ (Brazil's waterway regulator), port-call records, IMO GHG Study methods.
  • Stack: Python (pandas, scikit-learn, Streamlit), SQL (DuckDB), NLP, CLIP, React/TypeScript, Vercel, GitHub.

Featured projects

Competency Project What it is Links
Regulatory analytics shipping-methane-monitor Two-year observatory of verified CH₄ and N₂O from 16,664 ships (EU MRV 2024–2025): same ships cut CO₂ 5% and raised CH₄ 21% Live · Code · DOI
Carbon pricing shipping-carbon-costs 3,303 companies ranked by EU ETS carbon cost (€6.99 bn/yr) Live · Code
Remote sensing eu-ports-no2 NO₂ enhancement over 17 European ports and shipping lanes from Sentinel-5P Live · Code
Machine learning vessel-efficiency-ml Leakage-free scikit-learn pipeline predicting ships' CO₂ efficiency grades (A to E) Code · DOI
Port emissions Brazil_Vessel_Call_Intelligence 30,972 port calls, 8,506 vessels, at-berth CO₂ and OPS potential, benchmarked against the EU MRV fleet Code · DOI
Python library maritimeco2 Citable library for OPS-avoidable at-berth CO₂ (IMO method), behind decarbport.com Code · DOI
SQL / data engineering antaq-port-sql DuckDB star-schema warehouse of Brazilian port operations with documented queries Code · DOI
SDG analytics atributosods Peer-reviewed port sustainability framework, 84 indicators (Marine Policy 2025) Live · Code · DOI
NLP / text mining textmining PDFWords: PDFs to VOSviewer co-occurrence networks, in the browser Live · DOI
Data platform brazilportdata Research hub for the Brazilian port sector (ANTAQ data) Live
Computer vision blueport-ai2 Waste classification for ports, CLIP + linear probe, 94.6% cross-validated accuracy; runs in the browser Try it · Code · HF Space

Full portfolio with all tools: cunha-data-science.vercel.app


Recent peer-reviewed work

  • Cunha, D. R., & Pereira, N. N. (2026). Mapping ESG evolution in Brazilian ports: A text-mining approach to sustainability reporting. Marine Policy, 107287. doi:10.1016/j.marpol.2026.107287
  • Cunha, D. R., Porte, M. S., & Oliveira, C. B. M. (2026). A bibliometric analysis of port decarbonisation as a policy-driven transition. Discover Sustainability, accepted.
  • Cunha, D. R., Costa, M. D. C., Oliveira, C. B. M., & Pereira, N. N. (2025). SDG attributes: A sustainability assessment framework for Brazilian ports. Marine Policy, 181, 106841. doi:10.1016/j.marpol.2025.106841

20 peer-reviewed articles, 5 in Scopus Q1 journals; reviewer for 26 international journals. Full list on ORCID.


Tech stack

Python pandas scikit-learn DuckDB Streamlit React TypeScript Vercel

Pinned Loading

  1. maritimeco2 maritimeco2 Public

    Open Python library estimating OPS-avoidable at-berth CO2 for liquid bulk (tanker) vessels, IMO Fourth GHG Study 2020 method.

    Python

  2. shipping-methane-monitor shipping-methane-monitor Public

    Two-year observatory of verified CH₄ and N₂O emissions from ships calling at EU ports, from the EU MRV dataset (2024 to 2025). Tracks the CO₂-to-methane trade-off and the 2026 ETS methane bill. Liv…

    HTML 1

  3. vessel-efficiency-ml vessel-efficiency-ml Public

    ML pipeline predicting a ship's CO2 efficiency grade (A-E) from structural attributes using EU MRV data. Leakage-free features, scikit-learn models, stratified CV, permutation importance.

    Jupyter Notebook

  4. blueport-ai2 blueport-ai2 Public

    Built with Python, OpenAI CLIP (zero-shot image classification) and the Telegram Bot API. A port- specific image dataset is being curated to fine-tune and evaluate the model as the project matures.

    Python

  5. textmining textmining Public

    PDFWords: bibliometric text-mining tool that turns PDFs into word co-occurrence networks for VOSviewer. 100% in-browser, no upload.

    HTML

  6. port-emissions-mcp port-emissions-mcp Public

    CP server that lets Claude query Brazilian port statistics and estimate at-berth CO₂

    Python