Due to insufficient records and limited number of weather stations, prediction models must be used to forecast local climate conditions. Accurate prediction is required in the case of emerging cities because rapid growth in urban development causes changes in the attributes of the urban environment, particularly the local microclimate. With the help of the Urban Weather Generator (UWG) and a locally established weather station, this research explores the validity of UWG processed open weather data (i.e., World Weather Online and Open Weather Map datasets). The Marina district in the city of Lusail near Doha, Qatar, saw a 26% increase in temperature prediction accuracy. A more detailed analysis of a representative residential building load prediction reveals that cooling estimate gaps are reduced by 2.7% to 7.3% when compared to the underestimated loads from the rural weather dataset. The impact of urban morphology on urban climate is further studied. The results show that increasing building construction, which results in increased building footprint density in the studied area, increases cooling consumption of the representative residential building by more than 11,000 kWh under certain conditions. Whereas, increase in greenery only results in savings of around 250 kWh. Additionally, a uniform random sensitivity analysis of 10 UWG characteristics showed that cooling consumption can vary between 10,000 kWh and 47,500 kWh compared to the predicted cooling consumption when the baseline weather dataset is used.

由于记录不足和气象站数量有限，必须使用预测模型来预测当地的气候条件。新兴城市需要准确预测，因为城市发展的快速增长会引起城市环境属性的变化，尤其是当地的小气候。在城市天气生成器 (UWG) 和当地建立的气象站的帮助下，这项研究探索了 UWG 处理过的开放天气数据（即 World Weather Online 和 Open Weather Map 数据集）的有效性。卡塔尔多哈附近的 Lusail 市 Marina 地区的温度预测准确度提高了 26%。对代表性住宅建筑负荷预测的更详细分析表明，冷却估计差距减少了 2.7% 至 7。与来自农村天气数据集的低估负荷相比，下降了 3%。进一步研究了城市形态对城市气候的影响。结果表明，在特定条件下，增加建筑物的建设，导致研究区域的建筑物占地面积密度增加，使代表性住宅建筑的冷却消耗增加超过 11,000 kWh。然而，增加绿化只会节省约 250 千瓦时。此外，对 10 个 UWG 特性的统一随机敏感性分析表明，与使用基线天气数据集时预测的冷却消耗相比，冷却消耗可能在 10,000 kWh 到 47,500 kWh 之间变化。结果表明，在特定条件下，增加建筑物的建设，导致研究区域的建筑物占地面积密度增加，使代表性住宅建筑的冷却消耗增加超过 11,000 kWh。然而，增加绿化只会节省约 250 千瓦时。此外，对 10 个 UWG 特性的统一随机敏感性分析表明，与使用基线天气数据集时预测的冷却消耗相比，冷却消耗可能在 10,000 kWh 到 47,500 kWh 之间变化。结果表明，在特定条件下，增加建筑物的建设，导致研究区域的建筑物占地面积密度增加，使代表性住宅建筑的冷却消耗增加超过 11,000 kWh。然而，增加绿化只会节省约 250 千瓦时。此外，对 10 个 UWG 特性的统一随机敏感性分析表明，与使用基线天气数据集时预测的冷却消耗相比，冷却消耗可能在 10,000 kWh 到 47,500 kWh 之间变化。