Scholarlink

<p>Accurate prediction of urban water consumption is of great significance for water resources management and the development of efficient decision-support systems. In this study, key influencing factors of water consumption are identified using causation entropy, and a randomly distributed embedding (RDE) model is established to forecast multiple categories of water consumption in data-scarce scenarios. The performance of the RDE model is validated using water consumption data from the Longdong Energy Base in China. The result shows that with only 15 training samples, the correlation coefficients of RDE for many water consumption categories exceed 0.9. In Pingliang, population, actual irrigation area, effective irrigation area, and GDP are the dominant driving factors of water consumption, whereas in Qingyang, GDP and industrial added value are the most influential factors. Finally, the RDE model is employed to predict water demand in the Longdong Energy Base. In brief, irrigation water demand shows an upward trend and total water consumption exhibits a clear decreasing trend in Qingyang. In Pingliang, irrigation water demand rises slightly. Overall, all categories of water demand in the Longdong Energy Base remain relatively stable, with total water demand projected to reach approximately 0.54 billion cubic meters by 2030. Therefore, the RDE model provides a novel and effective approach for water consumption prediction under small-sample conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Water Consumption based on Randomly Distributed Embedding under Small-sample Conditions

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Xiaojun Wang,
  • Longxia Qian,
  • Jianyun Zhang,
  • Song Chen,
  • Rui Zou,
  • Weihua Peng

摘要

Accurate prediction of urban water consumption is of great significance for water resources management and the development of efficient decision-support systems. In this study, key influencing factors of water consumption are identified using causation entropy, and a randomly distributed embedding (RDE) model is established to forecast multiple categories of water consumption in data-scarce scenarios. The performance of the RDE model is validated using water consumption data from the Longdong Energy Base in China. The result shows that with only 15 training samples, the correlation coefficients of RDE for many water consumption categories exceed 0.9. In Pingliang, population, actual irrigation area, effective irrigation area, and GDP are the dominant driving factors of water consumption, whereas in Qingyang, GDP and industrial added value are the most influential factors. Finally, the RDE model is employed to predict water demand in the Longdong Energy Base. In brief, irrigation water demand shows an upward trend and total water consumption exhibits a clear decreasing trend in Qingyang. In Pingliang, irrigation water demand rises slightly. Overall, all categories of water demand in the Longdong Energy Base remain relatively stable, with total water demand projected to reach approximately 0.54 billion cubic meters by 2030. Therefore, the RDE model provides a novel and effective approach for water consumption prediction under small-sample conditions.