Search

This article addresses the class imbalance problem in urban gain modelling (UGM) of Tabriz and Isfahan megacities in Iran by proposing novel cost-sensitive machine learning models, namely costsensitive support vector machine (CSVM), random forest (CRF) and artificial neural network (CANN). Random sampling, a frequently utilized method, fails to effectively tackle this issue by biasing models towards no change samples, which outnumber change samples. The results showed that CRF exhibited the highest accuracy (AUC = 0.560), followed by CANN (AUC = 0.557) and CSVM (AUC = 0.448) in Isfahan. In Tabriz, CRF (AUC = 0.809) and CANN (AUC = 0.818) excelled, outperforming balanced sampling models constructed with ANN, RF and SVM with the AUROC of ANN and RF boosted by 15% and 2% in validation. By emphasizing the significance of addressing class imbalance appropriately, this research highlights the improvement in modelling outcomes achievable through the cost-sensitive models especially in Tabriz case. [ABSTRACT FROM AUTHOR]

The integration of solar energy systems into buildings via photovoltaic (PV) and other technologies can curb the amount of greenhouse gas emissions produced by buildings. However, the performance of solar energy systems is highly dependent on climatic and economic conditions. In this regard, the techno‐economic feasibility of building attached PV systems are studied for three scenarios considering three cities of Iran namely Tehran, Tabriz, and Kish Island, which have different climatic conditions. The result shows that the PV systems can annually meet 4.5–20% of the electricity needs for Tehran, 3.0–13% for Tabriz and 2.0–11.5% for Kish Island. Moreover, roof mounted PV systems were found to be a better alternative to envelope attached systems in technical and economic terms. The payback period for the solar energy systems was found to be between 8.7 and 14.3 years for Tehran, 14.2 and 22.6 years for Tabriz, and 11.6 and 21.1 for Kish Island. [ABSTRACT FROM AUTHOR]