Published May 16, 2025 | Version 1
Journal article Open

RETROFIT-LAT: A comprehensive dataset for energy efficiency investments in Latvia

Creators

  • 1. Decision Support Systems Lab, National Technical University of Athens, Zografou, Attica, Greece
  • 2. VIDES INVESTICIJU FONDS SIA, Riga, Latvia

Description

This article presents RETROFIT-LAT: a collection of data from 1010 residential building projects, funded by the Republic of Latvia's Environmental Investment Fund (LEIF). The first dataset analyses the energy performance and sustainability of buildings before and after retrofitting actions, including their energy consumption, CO 2 emissions, and energy classes. It spans projects implemented from 1870 to 2022, covering various building types and regions, with data on their energy use, heat loss coefficients, and both renewable and non-renewable energy contributions. The second dataset focuses on photovoltaic (solar panel) installations as part of energy efficiency measures. It documents electricity consumption, rimary energy use before and after installation, inverter power, and reductions in CO 2 emissions. Such a collection could offer a valuable foundation for developing machine learning models to evaluate and predict the impacts of retrofitting and solar panel installations on energy efficiency and sustainability. It could also be particularly relevant for researchers and policymakers who evaluate the effectiveness of energy-saving measures or planning similar interventions in other contexts.

Files

openreseurope-5-21678.pdf

Files (2.1 MB)

Name Size Download all
md5:3930821f590a866bfbb292cc42de78c7
2.1 MB Preview Download

Additional details

Cites
10.5281/zenodo.14697230 (DOI)
10.48550/arXiv.2412.04045 (DOI)
10.1016/j.enbuild.2022.111836 (DOI)
10.1016/j.erss.2015.11.006 (DOI)
10.1109/IISA56318.2022.9904353 (DOI)
10.1080/17512549.2022.2108142 (DOI)
10.1007/s12273-020-0630-5 (DOI)
10.3390/math12010019 (DOI)
10.56556/gssr.v1i2.327 (DOI)
10.48550/arXiv.2504.06055 (DOI)
10.1109/SusTech60925.2024.10553513 (DOI)
10.1016/j.softx.2024.101758 (DOI)
10.3390/su162310320 (DOI)
10.53022/oarjst.2024.11.2.0098 (DOI)

References

  • Tzortzis A, Rempi P (2025). epu-ntua/RETROFIT-LAT. Zenodo. doi:10.5281/zenodo.14697230
  • Tzortzis AM, Kormpakis G, Pelekis S (2024). AI4EF: Artificial Intelligence for energy efficiency in the building sector. doi:10.48550/arXiv.2412.04045
  • Sarmas E, Spiliotis E, Marinakis V (2022). A meta-learning classification model for supporting decisions on energy efficiency investments. Energy Build. doi:10.1016/j.enbuild.2022.111836
  • Palm J, Reindl K (2016). Understanding energy efficiency in Swedish residential building renovation: a practice theory approach. Energy Res Soc Sci. doi:10.1016/j.erss.2015.11.006
  • Karakolis E, Pelekis S, Mouzakitis S (2022). Artificial Intelligence for next generation energy services across Europe-the I-Nergy project.
  • Kormpakis G, Kapsalis P, Alexakis K (2022). An advanced visualisation engine with role-based access control for building energy visual analytics. doi:10.1109/IISA56318.2022.9904353
  • Senarathne LR, Nanda G, Sundararajan R (2022). Influence of building parameters on energy efficiency levels: a Bayesian network study. Adv Build Energy Res. doi:10.1080/17512549.2022.2108142
  • Du J, Yu C, Pan W (2020). Multiple influencing factors analysis of household energy consumption in high-rise residential buildings: evidence from Hong Kong. Build Simul. doi:10.1007/s12273-020-0630-5
  • Tzortzis AM, Pelekis S, Spiliotis E (2024). Transfer learning for day-ahead load forecasting: a case study on European national electricity demand time series. Mathematics. doi:10.3390/math12010019
  • Voumik LC, Islam MJ, Raihan A (2022). Electricity production sources and CO2 emission in OECD countries: static and dynamic panel analysis. Glob Sustain Res. doi:10.56556/gssr.v1i2.327
  • Rempi P, Pelekis S, Tzortzis AM (2025). Explainable AI for building energy retrofitting under data scarcity. doi:10.48550/arXiv.2504.06055
  • Michalakopoulos V, Pelekis S, Kormpakis G (2024). Data-driven building energy efficiency prediction using physics-informed neural networks. doi:10.1109/SusTech60925.2024.10553513
  • Pelekis S, Pountridis T, Kormpakis G (2024). DeepTSF: codeless machine learning operations for time series forecasting. SoftwareX. doi:10.1016/j.softx.2024.101758
  • He B, Zheng H, Zhang Q (2024). Toward a comprehensive economic comparison framework for solar projects: a case study of utility and residential scales. Sustainability. doi:10.3390/su162310320
  • Kishara KK, Obulinji HW, Ondimu KN (2024). Analysis of the spatial variations in the adoption of solar energy technologies among households in rural and urban areas of Konoin sub-County, Kenya. Open Access Res J Sci Technol. doi:10.53022/oarjst.2024.11.2.0098