Morchella mushroom is a nutritionally rich and rare edible fungus. The traditional cultivation model, which relies on expanding the cultivation area to meet market demand, is no longer sufficient to address the rapidly growing market demand. Enhancing the yield and quality of Morchella without increasing the cultivation area is an intractable challenge in the development of the Morchella mushroom industry. Against this backdrop, this study investigates the effects of different amounts of wood ash (WA) application on the yield and quality of Morchella, and conducts an in-depth analysis in conjunction with soil physicochemical properties and microbial communities. The results indicate that the application of WA improves both the yield and quality of Morchella, with the highest yield increase observed in the WA2 treatment (4000 kg/hm²), which showed a 118.36% increase compared to the control group (CK). The application of WA also modified the physicochemical properties of the soil, significantly improving the integrated fertility index of the soil (IFI, p < 0.05). The soil microbial community structure was altered by the addition of WA. Redundancy analysis (RDA) revealed that pH and total potassium (TK) were the main environmental factors influencing the bacterial community, while pH, TK, and total nitrogen (TN) were the main factors influencing the fungal community structure. In addition, bacterial community diversity tended to increase with higher WA application rates, whereas fungal community diversity generally showed a decreasing trend. Furthermore, the relative abundance of beneficial microbial communities, such as Acidobacteriota, which promote the growth of Morchella, increased with higher WA application, while the relative abundance of detrimental microbial communities, such as Xanthomonadaceae, decreased. Partial least squares path model (PLS-PM) analysis of external factors affecting Morchella yield and quality indicated that WA application can alter soil physicochemical properties and soil microbial communities, thereby improving Morchella yield and quality. Among these factors, soil fertility was identified as the most important determinant of Morchella yield and quality.

The severe continuous cropping obstacles in Morchella cultivation, driven primarily by soil microecological imbalance, critically constrain the sustainable development of the industry. To address this challenge, this study evaluated the efficacy of rotary tillage, calcium cyanamide (CaCN₂), and organic fertilizer, applied individually and in combination, in mitigating these obstacles and explored the underlying microbial mechanisms. The soil was treated on 5 August 2024, and soil samples were collected on 5 October 2024. Four treatments were established: continuous cropping control (CK), rotary tillage (XGX), rotary tillage combined with calcium cyanamide (MPD), and rotary tillage combined with calcium cyanamide and organic fertilizer (MPX). Soil chemical properties were analyzed in conjunction with metagenomic sequencing to characterize the responses of soil properties and microbial communities, including both eukaryotic and bacterial taxa. The results indicated that the MPD treatment showed a relatively pronounced effect in enhancing key soil fertility indicators, including soil organic matter (OM), total nitrogen (TN), available nitrogen (AN), available potassium (AK), and total phosphorus (TP). All amendments significantly altered microbial community structures. Specifically, the integrated MPX treatment effectively reduced the relative abundance of the pathogenic fungus Olpidium while maintaining higher overall microbial diversity. It also significantly promoted the abundance of Morchella itself and beneficial bacterial phyla such as Actinomycetota and Pseudomonadota. Redundancy analysis identified AN and AK as the primary drivers of eukaryotic community variation, whereas Availa-ble phosphorus (AP) and potential of hydrogen (pH) were the key factors shaping the bacterial community. The results indicated that MPD was the showed relatively pronounced effectiveness in rapidly improving soil fertility and suppressing pathogenic fungi. In contrast, MPX showed relatively better performance in optimizing microbial community structure, enhancing microbial diversity, and strengthening overall ecological stability. These two treatments exhibited distinct advantages in soil chemical improvement and microbial community regulation, respectively, thereby providing alternative practical strategies and a theoretical basis for the ecological management of continuous-cropping obstacles in Morchella cultivation. It should be noted that this study did not include treatments with calcium cyanamide alone, organic fertilizer alone, or their combined application without rotary tillage. This is primarily because rotary tillage is a standard land preparation practice in Morchella cultivation, and the use of soil amendments without accompanying tillage is rarely adopted under practical production conditions.

Accurate prediction of the internal temperature of mushroom bags is essential but remains challenging owing to the complex nonlinear coupling between ambient conditions and the bag’s thermal state. This study proposes a physics-guided machine learning framework that translates thermodynamic prior knowledge into a set of interpretable engineered features. Specifically, we construct features that capture temporal thermal lags via cross-correlation optimal lag analysis, represent integrative thermal memory through cumulative moving averages and exponentially weighted moving averages (EWMAs) with a physically calibrated half-life, and quantify the interaction between evaporative cooling and ventilation using a vapor pressure deficit-gated temperature gradient. The engineered features are combined with standard environmental variables and supplied to several machine learning algorithms. Four paradigms—a physics model, a one-step physics model, a purely data-driven model, and the proposed physics-guided model—are systematically compared across four representative cultivation scenarios. The physics-guided XGBoost achieves the highest predictive accuracy, with R² values of 0.996, 0.993, 0.997, and 0.973 for the four datasets, significantly outperforming all baselines. SHAP and Accumulated Local Effects analyses reveal that EWMA dominates predictions and that the learned feature–response relationships align with established thermodynamic principles, confirming physical consistency. The framework provides a practical, interpretable solution for feedforward environmental control in edible mushroom cultivation.