A Comprehensive Simulation Model for Evaluating the Thermal and Energy Performance of Greenhouses in Thailand Using Machine Learning Techniques

Greenhouse crop production systems are deployed globally across diverse climatic zones.To maintain optimal environmental conditions for plant growth, greenhouses are constructed with various structural and technological components.However, greenhouses are inherently complex, nonlinear systems that regulate climate variables to promote plant productivity.In today's context, reducing energy consumption in built agricultural environments is crucial.Accurate modeling of plant growth and yield is essential for greenhouse operators and the broader agricultural sector.This study proposes a comprehensive simulation model for evaluating the thermal and energetic performance of greenhouses in Thailand.The model incorporates artificial intelligence (AI) techniques to enhance performance prediction.Specifically, a deep recurrent neural network using long short-term memory (LSTM) architecture is deployed.A comparative analysis is conducted to assess the accuracy and efficiency of various modeling approaches.The outcomes support improved greenhouse design and energy optimization strategies.