Chiang Mai Journal of Science

     Morchella (morels) are rare edible fungi with high economic value but challenging cultivation requirements. Traditional yield prediction methods rely on manual records and statistics, which are time-consuming and yield low accuracy due to morels' long growth cycles, complex environmental factors, and insufficient documentation. This study presents a novel machine learning approach for predicting wild morel yields in Gannan Prefecture, China, using ten years (2013-2023) of monthly meteorological data. Random Forest was applied for feature selection, and Gradient Boosting Machine (GBM) was used to address zero-yield data. The resulting datasets were then employed to develop predictive models with six machine learning algorithms, namely Random Forest, Support Vector Machines (SVM), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), Transformer, and Convolutional Neural Network (CNN). Comparative analysis revealed that the GBM-LSTM hybrid model achieved superior performance (MSE: 8047.40, RMSE: 90.43, MAE: 60.90, R2: 0.81). Feature importance analysis identified air humidity (0.298) as the most critical factor affecting morel yields, followed by oxygen concentration, rainfall, light intensity, air quality, CO2 concentration, and average low temperature. Climate trend analysis over the past decade indicates that environmental deterioration, including an increase in temperature (+1.2 °C), a decrease in rainfall (-8.3%), and a reduction in humidity (-6.7%), has been accompanied by a decline in wild morel production, highlighting the vulnerability of this valuable species to climate change. These findings provide scientific guidance for optimizing cultivation strategies and developing climate-adaptive management practices for sustainable morel production.