Remote Sensing and GIS Applications in Environmental Sciences

Remote Sensing-Based Analysis of Residential Electricity Consumption Drivers in Tabriz’s Cold Semi-Arid Climate Using Machine Learning and Deep Learning

Document Type : Original Article

Authors

Department of urban and regional planning, Faculty of planning and environmental sciences, University of Tabriz, Tabriz, Iran.

10.22034/rsgi.2025.68899.1147

Abstract

This study investigates the climatic and urban factors influencing residential electricity consumption in Tabriz, Iran, a city with a cold semi-arid climate, using remote sensing data and machine learning (Random Forest, LightGBM) and deep learning (LSTM, CNN) models. Bi-monthly data from 2008 to 2023, including LST (day/night), NDVI, NDBI, NDWI, DMSP-OLS/VIIRS Nighttime Lights, Precipitation, Relative Humidity, Solar Radiation, Sunshine Hours, and AQI (NO₂, O₃, Aerosol), were used. Electricity consumption data were obtained from the Tabriz Electricity Distribution Company. Variables were Z-score normalized and processed in Google Earth Engine. Four models—Random Forest (RF), LightGBM, LSTM, and CNN—were implemented in Google Colab. Performance was evaluated using R², RMSE, and MAE, with feature importance assessed via SHAP analysis. Random Forest outperformed others (R²=0.91, RMSE=0.29, MAE=0.17), effectively capturing nonlinear relationships. Key drivers were NDWI (0.228), Night Light (0.211), and Solar Radiation (0.189), highlighting water scarcity, urbanization, and radiative heating impacts. LightGBM showed moderate performance (R²=0.64), emphasizing NDBI and Precipitation, while LSTM and CNN underperformed (R²<0) due to limited data and non-sequential variables. SHAP and residual analyses confirmed RF’s robust, stable predictions with minimal bias compared to LightGBM’s scale-dependent errors and deep models’ irregular residuals. In Tabriz’s cold semi-arid climate, residential electricity consumption is driven by NDWI, urbanization (Night Light), and solar radiation. These reflect increased heating/cooling needs due to low precipitation, urban heat islands, and rising temperatures. Green infrastructure and passive solar design are recommended to mitigate demand. This approach suits data-scarce regions, with potential enhancements via household behavioral data integration.

Keywords

Main Subjects

Objective: This study investigates the climatic and urban factors influencing residential electricity consumption in Tabriz, Iran, a city with a cold semi-arid climate, using remote sensing data and machine learning (Random Forest, LightGBM) and deep learning (LSTM, CNN) models.

Methods: Bi-monthly data from 2008 to 2023, including LST (day/night), NDVI, NDBI, NDWI, DMSP-OLS/VIIRS Nighttime Lights, Precipitation, Relative Humidity, Solar Radiation, Sunshine Hours, and AQI (NO₂, O₃, Aerosol), were used. Electricity consumption data were obtained from the Tabriz Electricity Distribution Company. Variables were Z-score normalized and processed in Google Earth Engine. Four models—Random Forest (RF), LightGBM, LSTM, and CNN—were implemented in Google Colab. Performance was evaluated using R², RMSE, and MAE, with feature importance assessed via SHAP analysis.

Results: Random Forest outperformed others (R²=0.91, RMSE=0.29, MAE=0.17), effectively capturing nonlinear relationships. Key drivers were NDWI (0.228), Night Light (0.211), and Solar Radiation (0.189), highlighting water scarcity, urbanization, and radiative heating impacts. LightGBM showed moderate performance (R²=0.64), emphasizing NDBI and Precipitation, while LSTM and CNN underperformed (R²<0) due to limited data and non-sequential variables. SHAP and residual analyses confirmed RF’s robust, stable predictions with minimal bias compared to LightGBM’s scale-dependent errors and deep models’ irregular residuals.

Conclusions: In Tabriz’s cold semi-arid climate, residential electricity consumption is driven by NDWI, urbanization (Night Light), and solar radiation. These reflect increased heating/cooling needs due to low precipitation, urban heat islands, and rising temperatures. Green infrastructure and passive solar design are recommended to mitigate demand. This approach suits data-scarce regions, with potential enhancements via household behavioral data integration.

Abulibdeh, A., Pirasteh, S., Mafi-Gholami, D., Kucukvar, M., Onat, N., & Zaidan, E. (2024). Unveiling the nexus between land use, land surface temperature, and carbon footprint: A multi-scale analysis of building+g energy consumption in arid urban areas. Earth Systems and Environment. https://doi.org/10.1007/s41748-024-00550-6
Akbarzadeh, A., & Bavali, F. (2024). Investigation of density factor in urban morphology on micro-climate parameters in cold and dry areas: Case study of Tabriz City, Iran. Power System Technology. https://doi.org/10.52783/pst.544
Al-Zayer, J., & Al-Ibrahim, A. (1996). Modelling the impact of temperature on electricity consumption in the eastern province of Saudi Arabia. Journal of Forecasting, 15(2), 97–106. https://doi.org/10.1002/(SICI)1099-131X(199603)15:2<97::AID-FOR609>3.0.CO;2-K
Auffhammer, M., & Aroonruengsawat, A. (2011). Simulating the impacts of climate change, prices and population on California’s residential electricity consumption. Climatic Change, 109(Suppl 1), 191–210. https://doi.org/10.1007/s10584-011-0299-y
Beyer, R., Franco-Bedoya, S., & Galdo, V. (2020). Examining the economic impact of COVID-19 in India through daily electricity consumption and nighttime light intensity. World Development, 140, 105287. https://doi.org/10.1016/j.worlddev.2020.105287
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In KDD’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
Choi, H.-M., Kim, M.-K., Yang, H., & Hsieh, W.-H. (2021). Abnormally high water temperature prediction using LSTM deep learning model. Journal of Intelligent & Fuzzy Systems, 40(4), 8013–8020. https://doi.org/10.3233/JIFS-189623
Da, Y., Zeng, B., Fan, J., Hu, J., & Li, L. (2023). Heterogeneous responses to climate: Evidence from residential electricity consumption. Climatic Change, 176(5), 1–19. https://doi.org/10.1007/s10584-023-03590-5
Diffenbaugh, N. S., Pal, J. S., Trapp, R. J., & Giorgi, F. (2007). Fine-scale processes regulate the response of extreme events to global climate change. Proceedings of the National Academy of Sciences, 102(44), 15774–15778. https://doi.org/10.1073/pnas.0501972102
Du, K., Yu, Y., & Wei, C. (2020). Climatic impact on China’s residential electricity consumption: Does the income level matter? China Economic Review, 63, 101520. https://doi.org/10.1016/j.chieco.2020.101520
Elshewey, A. M., Jamjoom, M. M., & Alkhammash, E. H. (2025). An enhanced CNN with ResNet50 and LSTM deep learning forecasting model for climate change decision making. Scientific Reports, 15(1), 1–32. https://doi.org/10.1038/s41598-025-97401-9
Emenekwe, C. C., & Emodi, N. V. (2022). Temperature and residential electricity demand for heating and cooling in G7 economies: A method of moments panel quantile regression approach. Climate, 10(10), 142. https://doi.org/10.3390/cli10100142
Ghazi, B., & Jeihouni, E. (2022). Projection of temperature and precipitation under climate change in Tabriz, Iran. Arabian Journal of Geosciences, 15(7), 641. https://doi.org/10.1007/s12517-022-09848-z
Heydari, H., & Movaghari, A. (2025). The change in weather types in two population centers in northwestern Iran (Urmia and Tabriz) around Lake Urmia with the Woś classification approach. Journal of Water and Climate Change, 16(2), 356–374. https://doi.org/10.2166/wcc.2025.356
Hu, Y., Dai, Z., & Guldmann, J.-M. (2020). Modeling the impact of 2D/3D urban indicators on the urban heat island over different seasons: A boosted regression tree approach. Journal of Environmental Management, 266, 110424. https://doi.org/10.1016/j.jenvman.2020.110424
Imani, M. (2021). Electrical load-temperature CNN for residential load forecasting. Energy, 227, 120480. https://doi.org/10.1016/j.energy.2021.120480
Imani, S., Dinpashoh, Y., Asadi, E., & Fakheri-Fard, A. (2024). Assessing the impact of climate change by using Mann–Kendall, Pettitt and statistical downscaling model: Case study of Tabriz station. Acta Geophysica, 72(4), 3047–3063. https://doi.org/10.1007/s11600-024-01464-7
Imran, H., Hossain, A., Islam, A., Rahman, A., Bhuiyan, M. A. M., Paul, S., & Alam, A. (2021). Impact of land cover changes on land surface temperature and human thermal comfort in Dhaka City of Bangladesh. Earth Systems and Environment, 5(3), 667–693. https://doi.org/10.1007/s41748-021-00243-4
Isaac, M., & van Vuuren, D. P. (2009). Modeling global residential sector energy demand for heating and air conditioning in the context of climate change. Energy Policy, 37(2), 507–521. https://doi.org/10.1016/j.enpol.2008.09.051
Joo, C., Park, H., Lim, J., Cho, H., & Kim, J. (2022). Development of physical property prediction models for polypropylene composites with optimizing random forest hyperparameters. International Journal of Intelligent Systems, 37(6), 3625–3653. https://doi.org/10.1002/int.22700
Karimimoshaver, M., & Shahrak, M. S. (2022). The effect of height and orientation of buildings on thermal comfort. Sustainable Cities and Society, 79, 103720. https://doi.org/10.1016/j.scs.2022.103720
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems (pp. 3149–3157). Curran Associates. https://dl.acm.org/doi/10.5555/3294996.3295074
Kooshesh Vatan, M. A., Asghari Zamani, A., Nemati, M., & Poormohammad, F. (2021). A comparison of multiple linear regression and random forest regression to evaluate the price of residential units: Case study of North Valiasr, Tabriz. Geography and Territorial Spatial Arrangement, 11(40), 57–82. https://doi.org/10.22111/gaij.2021.6486
Koushesh Vatan, M. A., Nemati, M., Şekertekin, A., & Aslkhiabani, M. Z. (2025). Time series trend detection and forecasting of SUHI in Tabriz, Iran. Urban Climate, 59, 102321. https://doi.org/10.1016/j.uclim.2025.102321
Koushesh Vatan, M. A., Nemati, M., Sekertekin, A., & Zehtabi Aslkhiabani, M. (2025). Time series trend detection and forecasting of SUHI in Tabriz, Iran. Urban Climate, 59, 102321. https://doi.org/10.1016/j.uclim.2025.102321
Li, L., Song, X., Li, J., Li, K., & Jiao, J. (2023). The impacts of temperature on residential electricity consumption in Anhui, China: Does the electricity price matter? Climatic Change, 176(5), 1–26. https://doi.org/10.1007/s10584-023-03500-9
Mastrucci, A., van Ruijven, B., & Byers, E. (2021). Global scenarios of residential heating and cooling energy demand and CO2 emissions. Climatic Change, 168(3–4), 14. https://doi.org/10.1007/s10584-021-03229-3
Mukherjee, S., & Nateghi, R. (2017). Climate sensitivity of end-use electricity consumption in the built environment: An application to the state of Florida, United States. Energy, 128, 688–700. https://doi.org/10.1016/j.energy.2017.04.034
Nourani, V., & Paknezhad, N. J. (2022). Application of PPIE method to assess the uncertainty and accuracy of multi-climate model-based temperature and precipitation downscaling. Theoretical and Applied Climatology, 147(1–2), 645–661. https://doi.org/10.1007/s00704-021-03884-7
Pablo-Romero, M. P., Sánchez-Braza, A., & Izquierdo, C. (2024). Income, extreme temperature, and residential electricity consumption in the Spanish provinces. Climate Change Economics, 15(3), 2450004. https://doi.org/10.1142/S2010007824500040
Patel, S., Indraganti, M., & Jawarneh, R. N. (2023). A comprehensive systematic review: Impact of land use/land cover (LULC) on land surface temperatures (LST) and outdoor thermal comfort. Building and Environment, 249, 111130. https://doi.org/10.1016/j.buildenv.2023.111130
Sailor, D. J., & Pavlova, A. A. (2003). Air conditioning market saturation and long-term response of residential cooling energy demand to climate change. Energy, 28(9), 941–951. https://doi.org/10.1016/S0360-5442(03)00033-1
Santamouris, M., Cartalis, C., Synnefa, A., & Kolokotsa, D. (2015). On the impact of urban heat island and global warming on the power demand and electricity consumption of buildings—A review. Energy and Buildings, 98, 119–124. https://doi.org/10.1016/j.enbuild.2014.09.052
Sarkodie, S. A., Ahmed, M. Y., & Owusu, P. A. (2021). Ambient air pollution and meteorological factors escalate electricity consumption. Science of the Total Environment, 795, 148841. https://doi.org/10.1016/j.scitotenv.2021.148841
Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306. https://doi.org/10.1016/j.physd.2019.132306
Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2019). The performance of LSTM and BiLSTM in forecasting time series. In 2019 IEEE International Conference on Big Data (Big Data) (pp. 3285–3292). IEEE. https://doi.org/10.1109/BigData47090.2019.9005482
Sreedevi, V., Adarsh, S., & Nourani, V. (2021). Multiscale coherence analysis of reference evapotranspiration of north-western Iran using wavelet transform. Journal of Water and Climate Change, 12(8), 3780–3794. https://doi.org/10.2166/wcc.2021.379
Su, Y., & Ullah, K. (2024). Exploring the correlation between rising temperature and household electricity consumption: An empirical analysis in China. Heliyon, 10(9), e30130. https://doi.org/10.1016/j.heliyon.2024.e30130
Wang, D., Li, L., & Zhao, D. (2022). Corporate finance risk prediction based on LightGBM. Information Sciences, 602, 259–268. https://doi.org/10.1016/j.ins.2022.04.058
Xia, C., Yao, T., Wang, W., & Hu, W. (2022). Effect of climate on residential electricity consumption: A data-driven approach. Energies, 15(9), 3355. https://doi.org/10.3390/en15093355
Zhang, M., Chen, Y., Hu, W., Deng, N., & He, W. (2021). Exploring the impact of temperature change on residential electricity consumption in China: The ‘crowding-out’ effect of income growth. Energy and Buildings, 245, 111040. https://doi.org/10.1016/j.enbuild.2021.111040
Zhang, S., Guo, Q., Smyth, R., & Yao, Y. (2022). Extreme temperatures and residential electricity consumption: Evidence from Chinese households. Energy Economics, 107, 105890. https://doi.org/10.1016/j.eneco.2022.105890
Zhao, K., Ning, Z., Xu, C., Zhao, X., & Huang, X. (2024). How do driving factors affect the diurnal variation of land surface temperature across different urban functional blocks? A case study of Xi’an, China. Sustainable Cities and Society, 110, 105738. https://doi.org/10.1016/j.scs.2024.105738
Zheng, S., Huang, G., Zhou, X., & Zhu, X. (2020). Climate-change impacts on electricity demands at a metropolitan scale: A case study of Guangzhou, China. Applied Energy, 261, 114295. https://doi.org/10.1016/j.apenergy.2019.114295
Remote Sensing and GIS Applications in Environmental Sciences
Volume 5, Issue 16
November 2025
Pages 113-95
  • Receive Date: 30 August 2025
  • Revise Date: 15 September 2025
  • Accept Date: 05 October 2025