A Neural Network Model to Predict Temperature and Relative Humidity in a Greenhouse

被引:4
作者
Salazar, R. [1 ]
Lopez, I. [1 ]
Rojano, A. [1 ]
机构
[1] Autonomous Univ Chapingo, Edo Mexico 56230, Mexico
来源
PROCEEDINGS OF THE INTERNATIONAL SYMPOSIUM ON HIGH TECHNOLOGY FOR GREENHOUSE SYSTEM MANAGEMENT, VOLS 1 AND 2 | 2008年 / 801期
关键词
temperature; relative humidity; greenhouse; neural networks;
D O I
10.17660/ActaHortic.2008.801.60
中图分类号
S6 [园艺];
学科分类号
0902 ;
摘要
This research was developed in a interconnected polyethylene greenhouse with tomato, located in Chapingo State of Mexico, in which temperature and relative humidity were measured every five minute from January 23 to February 02 2007. During this period temperature variations were between 5 degrees C and 40 degrees C and RH oscillated between 22 -98% both of which are not within the optimal ranges, therefore a good environmental control tool is necessary to keep these variables inside of the optimal levels. Artificial Neural Network (ANN) technology was applied to predict temperature and relative humidity inside of the greenhouse because it often offers a superior alternative to traditional physical-based models, and excels at uncovering patterns or relationships in data. It is also a powerful non-linear estimator which is recommended when the functional form between input and output is unknown or it is not well understood but believed to be nonlinear. Three neural network models were implemented in the Matlab Neural Networks Toolbox, all of them with the same inputs: outside temperature (degrees C), relative humidity solar radiation (Wm-2) and wind speed (ms(-1)). The first model considered only temperature as an output with a mean square error (MSE) of 3.03 between real and predicted temperature values. The second model took into account relative humidity as an output with a MSE of 22.41 between real and predicted relative humidity values. Finally the third model considered two outputs temperature and relative humidity at the same time and produces an MSE equal to 3.39 for temperature and MSE equal to 29.23 for relative humidity. This feasibility study demonstrates that ANN technology has the potential to serve as a highly accurate forecasting tool. Moreover, ANN technology can continuously be updated, as new data become available, increasing its forecasting ability.
引用
收藏
页码:539 / 545
页数:7
相关论文
共 50 条
  • [31] Temperature and Relative Humidity Prediction in Swine Livestock Buildings
    Molano-Jimenez, Andres
    Orjuela-Canon, Alvaro D.
    Acosta-Burbano, Wilmer
    2018 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2018,
  • [32] Evaluation and Correction of PurpleAir Temperature and Relative Humidity Measurements
    Couzo, Evan
    Valencia, Alejandro
    Gittis, Phoebe
    ATMOSPHERE, 2024, 15 (04)
  • [33] Effect of temperature and relative humidity on yellowing rate of paddy
    Soponronnarit, S
    Srisubati, N
    Yoovidhya, T
    JOURNAL OF STORED PRODUCTS RESEARCH, 1998, 34 (04) : 323 - 330
  • [34] Coupled effects of the temperature and the relative humidity on gecko adhesion
    Peng, Zhilong
    Yang, Yazheng
    Chen, Shaohua
    JOURNAL OF PHYSICS D-APPLIED PHYSICS, 2017, 50 (31)
  • [35] Improved numerical model for steel reinforcement corrosion in concrete considering influences of temperature and relative humidity
    Yu, Bo
    Liu, Jianbo
    Li, Bing
    CONSTRUCTION AND BUILDING MATERIALS, 2017, 142 : 175 - 186
  • [36] Greenhouse Temperature and Humidity Intelligent Control System
    Sun Rong-Gao
    Wan Zhong
    Sun De-Chao
    CISST'09: PROCEEDINGS OF THE 3RD WSEAS INTERNATIONAL CONFERENCE ON CIRCUITS, SYSTEMS, SIGNAL AND TELECOMMUNICATIONS, 2009, : 120 - 125
  • [37] Performance Analysis of a Greenhouse Fan-Pad Cooling System: Gradients of Horizontal Temperature and Relative Humidity
    Dayioglu, Mehmet Ali
    Silleli, Hasan Huseyin
    JOURNAL OF AGRICULTURAL SCIENCES-TARIM BILIMLERI DERGISI, 2015, 21 (01): : 132 - 143
  • [38] Recurrent Neural Network Model for Prediction of Microclimate in Solar Greenhouse
    Wang Hongkang
    Li Li
    Wu Yong
    Meng Fanjia
    Wang Haihua
    Sigrimis, N. A.
    IFAC PAPERSONLINE, 2018, 51 (17): : 790 - 795
  • [39] Effects of ambient temperature, relative humidity and absolute humidity on risk of nasopharyngeal carcinoma in China
    Di, Wenyi
    Yu, Jiamin
    Zong, Dan
    Ge, Yizhi
    Zhang, Yujie
    Chen, Xin
    He, Xia
    INTERNATIONAL JOURNAL OF CANCER, 2024, 155 (04) : 646 - 653
  • [40] Estimation of relative humidity based on artificial neural network approach in the Aegean Region of Turkey
    Yasar, Abdulkadir
    Simsek, Erdogan
    Bilgili, Mehmet
    Yucel, Ahmet
    Ilhan, Ilhami
    METEOROLOGY AND ATMOSPHERIC PHYSICS, 2012, 115 (1-2) : 81 - 87