Medium-shallow borehole ground heat exchangers (BGHEs) utilize a burial depth ranging from 200 to 600 m. The heat exchange capacity of a single medium-shallow BGHE is higher than that of a single shallow BGHE. Compared to medium-deep BGHEs, the cost of medium-shallow BGHEs is lower, and both heating and cooling can be achieved, while the former can only be used for heating. However, there is a relative lack of research on the heat transfer characteristics of medium-shallow BGHEs, especially on the influence of the working fluid type on the heat transfer performance of BGHEs. This study aimed to investigate the impact of different working fluids on the performance of medium-shallow BGHEs. First, a heat transfer model for medium-shallow BGHEs was established considering the ground temperature gradient and geothermal heat flow, and its accuracy was validated using experimental test data. Second, the model was used to compare and analyze the effects of various working fluids on the heat transfer performance, pressure loss, and potential environmental benefits of BGHEs. Based on economic analysis, CO₂ was determined to be the most suitable working fluid among the organic fluids considered. Finally, the influence of the number of boreholes and the type of working fluid on the heat transfer performance of borehole clusters consisting of 2 and 4 boreholes was analyzed using the superposition principle. The results indicated that CO₂ could provide the highest heat transfer among the various working fluids selected in this study, as its heat extraction and heat dissipation were approximately 15% and 12% higher than those achieved by water. Isobutane (R600a) achieved the highest net heat and emission reduction, surpassing water by 66.7% and 73.6%, respectively. Regarding the four boreholes, the outlet temperature of the BGHEs gradually decreased at the end of each heating season. After 10 years of operation, the value decreased by approximately 2 °C. The results in this paper provide a theoretical basis and technical guidance for the rational selection of working fluids and improvements in the heat transfer performance of BGHEs, which could promote the development and application of medium-shallow geothermal energy sources.

Short-term building cooling load prediction is crucial for optimizing building energy management and promoting sustainability. While data-driven models excel in this task, their performance heavily depends on the input feature set. Feature selection must balance predictive accuracy (relevance) and model simplicity (minimal redundancy), a challenge that existing methods often address incompletely. This study proposes a novel feature optimization framework that integrates the Maximum Information Coefficient (MIC) to measure non-linear relevance and the Maximum Relevance Minimum Redundancy (MRMR) principle to control redundancy. The proposed MRMR-MIC method was evaluated against four benchmark feature selection methods using three predictive models in a simulated office building case study. The results demonstrate that MRMR-MIC significantly outperforms other methods: it reduces the feature dimensionality from over 170 to merely 40 variables while maintaining a prediction error below 5%. This represents a substantial reduction in model complexity without sacrificing accuracy. Furthermore, the selected features cover a more comprehensive and physically meaningful set of attributes compared to other redundancy-control methods. The study concludes that the MRMR-MIC framework provides a robust, systematic methodology for identifying essential feature variables, which can not only enhance the performance of prediction models, but also offer practical guidance for designing cost-effective data acquisition systems in real-building applications.