American Journal Of Biomedical Science & Pharmaceutical Innovation
1
https://theusajournals.com/index.php/ajbspi
VOLUME
Vol.05 Issue01 2025
PAGE NO.
1-3
Enhancements in modeling greenhouse microclimate and
evapotranspiration: an overview of recent progress
Afram Boamah
Department Of Water Resources Development, School Of Sustainable Development, University Of Environment And Sustainable
Development, Pmb Somanya, Eastern Region, Ghana
Received:
18 October 2024;
Accepted:
20 December 2024;
Published:
01 January 2025
Abstract:
This overview examines the recent advancements in modeling techniques for greenhouse microclimate
and evapotranspiration, which are crucial for optimizing agricultural production in controlled environments.
Accurate models are essential for understanding the dynamic interactions between environmental variables such
as temperature, humidity, light, and soil moisture, and their effects on plant growth and water usage. This review
highlights the latest progress in both physical-based and data-driven models, focusing on their applications,
benefits, and limitations in greenhouse settings. The integration of advanced technologies, including machine
learning, IoT sensors, and climate control systems, has improved the precision and real-time adaptability of
microclimate and evapotranspiration models. Additionally, the development of hybrid models combining
simulation and empirical data has enhanced predictive accuracy, contributing to better resource management
and sustainability. This paper aims to provide an updated perspective on the state-of-the-art modeling
approaches, offering valuable insights for researchers and practitioners in the field of greenhouse agriculture.
Keywords:
Greenhouse microclimate, Evapotranspiration modelling, Climate control systems, Machine learning,
Data-driven models, Physical-based models, Agricultural sustainability, Water management, Environmental
variables.
Introduction:
Greenhouses
provide
controlled
environments for plant growth, allowing year-round
production and protection against adverse weather
conditions. The microclimate within a greenhouse,
including factors such as temperature, humidity, and
airflow, significantly influences plant development,
yield, and quality. Understanding and accurately
predicting the greenhouse microclimate is vital for
optimizing
cultivation
practices,
resource
management, and ensuring crop success. Similarly,
estimating
evapotranspiration
rates
within
greenhouses is crucial for efficient water usage and
irrigation scheduling. Over the years, various modelling
techniques have been developed to simulate and
predict
the
greenhouse
microclimate
and
evapotranspiration accurately. This paper aims to
provide an overview of recent advances in modelling
techniques
for
greenhouse
microclimate
and
evapotranspiration, highlighting their advantages,
limitations, and applications.
METHOD
To compile this overview, a comprehensive literature
review was conducted. Relevant research articles,
conference papers, and books were reviewed, focusing
on modelling techniques specifically designed for
greenhouse microclimate and evapotranspiration. The
search was performed using various academic
databases and search engines, using keywords such as
"greenhouse
microclimate
modelling,"
"evapotranspiration modelling," "computational fluid
dynamics in greenhouses," "machine learning for
greenhouse microclimate," and "empirical models for
greenhouse evapotranspiration." The selected articles
were thoroughly analyzed to identify the key modelling
techniques and their respective applications in
greenhouse research. Additionally, emerging trends,
such as the integration of remote sensing data and
Internet of Things (IoT) technologies, were explored.
The collected information was then synthesized and
organized to provide a comprehensive overview of the
recent advances in modelling techniques for
greenhouse microclimate and evapotranspiration.
American Journal of Applied Science and Technology
2
https://theusajournals.com/index.php/ajast
American Journal of Applied Science and Technology (ISSN: 2771-2745)
RESULTS
The review of literature revealed several notable
advancements in modelling techniques for greenhouse
microclimate and evapotranspiration. Three main
approaches emerged: computational fluid dynamics
(CFD), machine learning algorithms, and empirical
models.
CFD models simulate the fluid flow, heat transfer, and
mass transfer within the greenhouse environment.
These models provide detailed spatial and temporal
information,
allowing
for
a
comprehensive
understanding of airflow patterns, temperature
distribution, and humidity levels. CFD models have
been widely used to optimize greenhouse designs,
evaluate ventilation strategies, and investigate the
impact of various factors on the microclimate.
Machine learning algorithms, including artificial neural
networks, support vector machines, and random
forests, have gained popularity in modelling
greenhouse microclimate. These techniques have the
ability to learn complex relationships between input
variables and output parameters, enabling accurate
predictions of temperature, humidity, and other
microclimate variables.
Machine learning models have demonstrated
promising results in forecasting and control
applications, aiding in decision-making processes for
greenhouse management.
Empirical models, based on statistical relationships and
experimental data, offer a simpler and more
computationally efficient approach to greenhouse
microclimate modelling. These models derive
correlations between input variables and output
parameters, often using regression analysis. Empirical
models are valuable for quick estimations and can be
useful when computational resources are limited.
Additionally, emerging trends in greenhouse modelling
include the integration of remote sensing data and IoT
technologies. Remote sensing provides valuable
information
on
vegetation
indices,
canopy
temperature, and water stress, which can be
incorporated into models to improve accuracy. IoT
technologies, such as sensor networks and automated
control systems, enable real-time data acquisition and
feedback, facilitating adaptive management strategies.
DISCUSSION
Each modelling technique has its advantages and
limitations. CFD models offer high spatial resolution but
require significant computational resources and
expertise to implement. Machine learning models excel
at capturing complex relationships but may suffer from
the black-box nature of their predictions. Empirical
models are computationally efficient but rely heavily
on the availability and quality of experimental data.
Understanding these trade-offs is crucial for selecting
the most appropriate modelling approach based on the
specific objectives and resources of the greenhouse
operation.
Furthermore, the applications of modelling techniques
in greenhouse research and practical implementation
are diverse. Modelling can aid in optimizing
greenhouse designs, improving ventilation strategies,
and assessing the impact of environmental factors on
crop performance. It can also support decision-making
processes related to irrigation scheduling, energy
management, and pest control. By accurately
estimating evapotranspiration rates, models contribute
to efficient water usage and conservation.
CONCLUSION
Advances in modelling techniques have significantly
contributed to our understanding and management of
greenhouse microclimate and evapotranspiration.
Computational fluid dynamics, machine learning
algorithms, and empirical models offer valuable tools
for simulating, predicting, and optimizing greenhouse
environments. The integration of remote sensing data
and IoT technologies further enhances the accuracy
and real-time capabilities of these models. By
leveraging these modelling techniques, greenhouse
operators can make informed decisions, improve
resource management, and enhance crop productivity
while minimizing environmental impacts. However, it is
important to consider the limitations and trade-offs
associated with each modelling approach, and further
research is needed to address challenges such as model
validation and parameter estimation. Overall,
modelling techniques continue to evolve and play a
crucial role in the sustainable development of
greenhouse agriculture.
REFERENCES
Zhang M Q, Zhang W, Chen X Y, Wang F, Wang H, Zhang
J S, et al. Modeling and simulation of temperature
control system in plant factory using energy balance.
Int J Agric & Biol Eng, 2021; 14(3): 55
–
61.
Yan H, Acquah S J, Zhang C, Huang S, Zhang H, Zhao B,
et al. Energy bpartitioning of greenhouse cucumber
based on the application of Penman-Monteith and Bulk
Transfer models. Agricultural Water Management,
2019; 217: 201
–
211.
Papadopoulos A P. Growing greenhouse tomatoes in
soil and soilless media. Agriculture Canada Publication,
1991; 79p.
Soria T, Cuartero J. Tomato fruit yield and water
consumption with salty water irrigation. ISHS Acta
American Journal of Applied Science and Technology
3
https://theusajournals.com/index.php/ajast
American Journal of Applied Science and Technology (ISSN: 2771-2745)
Horticulture, 1998; 458: 215
–
220.
Abou-Hadid A F, El-Shinawy M Z, El-Oksh I, Gomaa H,
El-Beltagy A S. Studies on water consumption of sweet
pepper plant under plastic houses. ISHS Acta
Horticulturae, 1994; 366: 365
–
372.
Tuzel Y, Ui M A, Tuzel I H. Effects of different irrigation
intervals and rates on Spring season glasshouse tomato
production: II, Fruit quality. ISHS Acta Horticulturae,
1994; 366: 389
–
396.
Harmanto, Salokhe V M, Babel M S, Tantau H J. Water
requirement of drip irrigated tomatoes grown in
greenhouse in tropical environment. Agricultural
Water Management, 2005; 71(3): 225
–
242.
Stanghellini C. Transpiration of greenhouse crops: An
aid to climate management. PhD dissertation.
Wageningen, the Netherlands: Agricultural University
of Wageningen, 1987; 150p.
Medrano E, Lorenzo P, Sanchez-Guerrero M C,
Montero J I. Evaluation and modelling of greenhouse
cucumber-crop transpiration under high and low
radiation conditions. Scientia Horticulturae, 2005;
105(2): 163
–
175.
Jolliet O, Bailey B J. The effect of climate on tomato
transpiration in greenhouse: measurements and
models comparison. Agricultural and Forestry
Meteorology, 1992; 58(1-2): 43
–
62
