Scholarlink

The increasing demand for food and climate change are challenges for the agricultural sector. The integration of IoT systems and the use of machine learning enable smart irrigation system and optimize the use of water. In this study, we use the L-moments statistical theory in an exploratory analysis aiming to extract distribution characteristics of variables related to evapotranspiration, specifically the ambient temperature, the atmospheric pressure, the soil moisture and the wind speed. In our analysis we use actual data collected between 2022 to 2025 by IoT sensors installed in 20 orchards located in different Spanish regions. Our results reveal the possibility for each considered variable to distinguish regions with different climatical conditions, which is crucial decision-making for irrigation plans and optimization problems.

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

Applying L-Moments Statistical Theory to Analyze Real-World Sensor Data from Orchards

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • José Ramón Torres-Martín,
  • Yolanda Carrión-García,
  • José Manuel Velarde-Gestera,
  • Inmaculada Mora-Jiménez,
  • Mihaela I. Chidean

摘要

The increasing demand for food and climate change are challenges for the agricultural sector. The integration of IoT systems and the use of machine learning enable smart irrigation system and optimize the use of water. In this study, we use the L-moments statistical theory in an exploratory analysis aiming to extract distribution characteristics of variables related to evapotranspiration, specifically the ambient temperature, the atmospheric pressure, the soil moisture and the wind speed. In our analysis we use actual data collected between 2022 to 2025 by IoT sensors installed in 20 orchards located in different Spanish regions. Our results reveal the possibility for each considered variable to distinguish regions with different climatical conditions, which is crucial decision-making for irrigation plans and optimization problems.