Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

What is Weather?01:07

What is Weather?

18.1K
Overview
18.1K
Temperature Measurement Sites01:14

Temperature Measurement Sites

1.5K
A thermometer measures body temperature. The common sites for measuring body temperature are the oral cavity, axillary region, temporal artery, and skin surface, such as the forehead, abdomen, and axilla. True core body temperature is assessed in the rectum, tympanic membrane, pulmonary artery, esophagus, and urinary bladder.
Oral: When assessing oral temperature, the thermometer tip should be placed under the tongue in the posterior sublingual pocket. It offers accurate readings and can be...
1.5K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Mast cell-derived IL-13 as a driver of Crohn disease-associated intestinal fibrosis.

Inflammatory bowel diseases·2026
Same author

Salicylic acid and silicon cross talk influence physiological and biochemical attributes of sorghum under salinity stress.

Scientific reports·2026
Same author

Microplastics across marine food webs: bioaccumulation, exposome interactions, and emerging oncogenic risks.

Environmental geochemistry and health·2026
Same author

Stable dry reforming of methane over Ni-Pt bimetallic catalysts supported on KIT-5 in a continuous flow system.

RSC advances·2026
Same author

Correction: Phytotoxicity and metal mobility in soils contaminated with mine tailings.

Environmental geochemistry and health·2026
Same author

Mescaline Alters Cerebellar Function, Global Connectivity, and Frequency-Selective Acoustic Gating: A BOLD fMRI Study in Awake Rats.

Neuroscience bulletin·2026

相关实验视频

Updated: Jun 4, 2025

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors
08:49

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors

Published on: December 21, 2019

9.2K

使用基于气象数据的机器学习范式,对不同深度的土壤温度进行估计.

Anurag Malik1, Gadug Sudhamsu2, Manjinder Kaur Wratch3

  • 1Punjab Agricultural University, Regional Research Station, Bathinda, 151001, Punjab, India. amalik19@pau.edu.

Environmental monitoring and assessment
|December 26, 2024
PubMed
概括

准确的土壤温度 (ST) 估计对于环境分析和作物生长至关重要. 协作神经模糊推断系统 (CANFIS) 模型在使用气象数据在各种深度预测每日ST时表现出卓越的准确性.

关键词:
浴室 浴室 浴室玛测试测试测试 玛测试测试机器学习范式的ML模式绩效指标是指性能指标.土壤温度 土壤温度.

更多相关视频

Simulating Temperature in a Soil Incubation Experiment
08:39

Simulating Temperature in a Soil Incubation Experiment

Published on: October 28, 2022

2.8K
In Situ Soil Moisture Sensors in Undisturbed Soils
08:20

In Situ Soil Moisture Sensors in Undisturbed Soils

Published on: November 18, 2022

6.1K

相关实验视频

Last Updated: Jun 4, 2025

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors
08:49

Manufacturing Simple and Inexpensive Soil Surface Temperature and Gravimetric Water Content Sensors

Published on: December 21, 2019

9.2K
Simulating Temperature in a Soil Incubation Experiment
08:39

Simulating Temperature in a Soil Incubation Experiment

Published on: October 28, 2022

2.8K
In Situ Soil Moisture Sensors in Undisturbed Soils
08:20

In Situ Soil Moisture Sensors in Undisturbed Soils

Published on: November 18, 2022

6.1K

科学领域:

  • 环境科学 环境科学
  • 农业科学 农业科学
  • 数据科学数据科学数据科学

背景情况:

  • 土壤温度 (ST) 对于了解环境条件,气候变化影响和农业生产率至关重要,影响作物生长和种子发芽.
  • 准确的ST监测对于有效的土地管理和气候建模至关重要.

研究的目的:

  • 使用机器学习 (ML) 模型,在多个深度 (5,15和30厘米) 估计每日土壤温度 (ST).
  • 为了比较四个ML范式的性能:随机森林 (RF),辐射基神经网络 (RBNN),多层感知神经网络 (MLPNN) 和协作神经模糊推理系统 (CANFIS).

主要方法:

  • 使用的气象数据包括平均空气温度 (Tmean),相对湿度 (RH),风速 (WS) 和明亮的阳光小时 (SSH).
  • 采用了马测试 (GT) 来选择每个土壤深度的输入变量的最佳组合.
  • 使用诸如平均绝对误差 (MAE),根平均平方误差 (RMSE),分散指数 (SI),效率系数 (COE),皮尔森相关系数 (PCC) 和协议指数 (IOA) 等指标评估模型性能.

主要成果:

  • 在所有土壤深度中,CANFIS模型实现了最高的准确性.
  • 在CANFIS中,错误率很低 (MAE:0.788-0.806°C,RMSE:0.854-1.074°C) 和一致度很高 (COE:0.985-0.986,PCC:0.993-0.995,IOA:0.996-0.998).在CANFIS中,错误率也很低,但也很高.
  • 该研究证实了气象参数作为ST估计模型输入的有效性.

结论:

  • 使用Tmean,RH,WS和SSH的CANFIS模型具有很高的能力,可以在各种深度准确地估计每天的土壤温度.
  • 这些发现为土壤温度预测提供了可靠的方法,支持农业和环境监测工作.
  • 机器学习方法为分析复杂的环境数据和提高预测准确性提供了强大的工具.