Fengyu Li

Price volatility in fresh food commodities can weaken supply-chain coordination, disturb market expectations, and increase short-term risks to food availability and affordability. This issue is more pronounced for specialty crops with seasonal production, concentrated supply, limited storability, and high sensitivity to climate, trade, energy, and online-attention shocks. This study develops a trajectory-regularized physics-informed multi-source forecasting framework for daily wholesale prices of garlic, scallion, and ginger in China from 2014 to 2024. The framework, denoted as STL–ETO–EMA–PILSTM, integrates Seasonal-Trend decomposition using LOESS (STL), Efficient Multi-scale Attention (EMA), Long Short-Term Memory (LSTM), an economically motivated physics-informed trajectory residual constraint, and Exponential-Trigonometric Optimization (ETO), using production, climate, macroeconomic, trade, crude-oil, and online-attention indicators. In this framework, the physics-informed component is implemented as a trajectory residual constraint inspired by price-adjustment inertia and local continuity, rather than as a conventional PINN based on strict governing physical equations. In one-step-ahead forecasting, the model outperformed conventional machine learning baselines and additional time-series baselines, including naive persistence, Transformer Encoder, and PatchTST, with MAE values of 0.0853, 0.0581, and 0.1409 for garlic, scallion, and ginger, respectively, and R² values above 0.996. Leakage-prevention procedures, walk-forward validation, multi-horizon forecasting, and Diebold–Mariano tests were used to strengthen result credibility. Multi-step forecasting showed clear performance degradation as the horizon increased, supporting the positioning of the framework as a short-term market-monitoring tool rather than a long-horizon structural projection model. Permutation-based feature-importance and interaction analyses revealed crop-specific price drivers. The framework provides an interpretable tool for fresh food price forecasting, market stability monitoring, and short-term operational risk monitoring in fresh food supply chains.

Constructing a temperature and humidity prediction model for greenhouse-grown tomatoes is of great significance for achieving resource-efficient and sustainable greenhouse environmental control and promoting healthy tomato growth. However, traditional models often struggle to simultaneously capture long-term temporal trends, short-term local dynamic variations, and the coupling relationships among multiple variables. To address these issues, this study develops an iT-LSTM-CA multi-step prediction model, in which the inverted Transformer (iTransformer, iT) is employed to capture global dependencies across variables and long temporal scales, the Long Short-Term Memory (LSTM) network is utilized to extract short-term local variation patterns, and a cross-attention (CA) mechanism is introduced to dynamically fuse the two types of features. Experimental results show that, compared with models such as Gated Recurrent Unit (GRU), Temporal Convolutional Network (TCN), Recurrent Neural Network (RNN), LSTM, and Bidirectional Long Short-Term Memory (Bi-LSTM), the iT-LSTM-CA achieves the best performance in multi-step forecasting tasks at 3 h, 6 h, 12 h, and 24 h horizons. For temperature prediction, the R² ranges from 0.96 to 0.98, with MAE between 0.42 °C and 0.79 °C and RMSE between 0.58 °C and 1.06 °C; for humidity prediction, the R² ranges from 0.95 to 0.97, with MAE between 1.21% and 2.49% and RMSE between 1.78% and 3.42%. These results indicate that the iT-LSTM-CA model can effectively capture greenhouse environmental variations and provide a scientific basis for environmental control and management in tomato greenhouses.

The aim of this paper is to propose an improved lightweight YOLOv11 detection method in response to the difficulty of extracting tomato fruit features in greenhouse environments and the need for lightweight picking equipment. Firstly, the conventional step convolution is substituted by the Average pooling Downsampling (ADown) module with multi-path fusion; Gated Convolution (gConv) is incorporated in the C3K2 module, which considerably reduces the number of parameters and computation of the model. Concurrently, the Lightweight Shared Convolutional Detection (LSCD) is incorporated into the detection head component with to the aim of further reducing the computational complexity. Finally, the Wise–Powerful intersection over Union (Wise-PIoU) loss function is employed to optimise the model accuracy, and the effectiveness of each improvement module is verified by means of ablation experiments. The experimental results demonstrate that the precision of ACLW-YOLO (A stands for ADown, C stands for C3K2_gConv, L stands for LSCD, and W stands for Wise-PIoU) reaches 94.2%, the recall (R) is 92.0%, and the mean average precision (mAP) is 95.2%. Meanwhile, the model size is only 3.3 MB, the number of parameters is 1.6 M, and the floating-point computation is 3.9 GFLOPs. The ACLW-YOLO model enhances the precision of detection through its lightweight design, while concurrently achieving a substantial reduction in computational complexity and memory utilisation. The study demonstrates that the enhanced model exhibits superior recognition performance for various tomato fruits, thereby providing a robust theoretical and technical foundation for the automation of greenhouse tomato picking processes.

In order to ensure the price stability of niche agricultural products and enhance farmers' income, the study delves into the pattern of ginger price fluctuation rule and its main influencing factors. By combining seasonal decomposition STL, long and short-term memory network LSTM, attention mechanism ATT and Kolmogorov-Arnold network, a combined STL-LSTM-ATT-KAN prediction model is developed, and the model parameters are finely tuned by using multi-population adaptive particle swarm optimization algorithm (AMP-PSO). Based on an in-depth analysis of actual data on ginger prices over the past decade, the STL-LSTM-ATT-KAN model demonstrated excellent performance in terms of prediction accuracy: its mean absolute error (MAE) was 0.111, mean squared error (MSE) was 0.021, root mean squared error (RMSE) was 0.146, and the coefficient of determination (R²) was 0.998.This study provides the Ginger Industry, agricultural trade, farmers and policy makers with digitalized and intelligent aids, which are important for improving market monitoring, risk control, competitiveness and guaranteeing the stability of supply and price.