Related Experiment Videos
A Trajectory-Regularized Physics-Informed Hybrid Framework for Specialty Fresh Food Commodity Price Forecasting and
Fengyu Li1,2,3, Yujie Li1,2,3, Xingyu Gao1,2,3
1College of Information Science and Engineering, Shandong Agricultural University, Tai'an 271018, China.
Foods (Basel, Switzerland)
|July 15, 2026
Summary
This study introduces a new AI framework (STL-ETO-EMA-PILSTM) for forecasting daily wholesale prices of fresh produce like garlic, scallion, and ginger. It accurately predicts short-term price fluctuations, aiding market stability and risk monitoring.
Area of Science:
- Agricultural Economics
- Time Series Forecasting
- Machine Learning
Background:
- Fresh food commodity price volatility poses risks to supply chains and food security.
- Specialty crops are particularly vulnerable due to seasonal production and sensitivity to various shocks.
- Accurate short-term price forecasting is crucial for market stability and operational risk management.
Purpose of the Study:
- To develop an advanced forecasting framework for daily wholesale prices of garlic, scallion, and ginger in China.
- To integrate multiple data sources and advanced machine learning techniques for improved price prediction.
- To provide an interpretable tool for monitoring fresh food market dynamics and short-term risks.
Main Methods:
- Developed the STL-ETO-EMA-PILSTM framework, integrating Seasonal-Trend decomposition (STL), Efficient Multi-scale Attention (EMA), Long Short-Term Memory (LSTM), physics-informed trajectory residual constraints, and Exponential-Trigonometric Optimization (ETO).
- Utilized production, climate, macroeconomic, trade, crude-oil, and online-attention indicators as input features.
- Employed leakage-prevention, walk-forward validation, and Diebold-Mariano tests to ensure result credibility.
Main Results:
- The STL-ETO-EMA-PILSTM framework achieved high accuracy in one-step-ahead forecasting for garlic, scallion, and ginger, with R² values exceeding 0.996.
- Outperformed conventional machine learning and time-series baselines in forecasting accuracy (e.g., MAE of 0.0581 for scallions).
- Feature importance analysis identified crop-specific price drivers, enhancing model interpretability.
Conclusions:
- The developed framework is effective for short-term fresh food price forecasting and market monitoring.
- Performance degradation in multi-step forecasting confirms its utility as a short-term operational tool.
- The interpretable nature of the framework supports market stability analysis and risk management in fresh food supply chains.
Related Concept Videos
01:26Orthogonal Trajectories
Orthogonal trajectories describe the geometric relationship between two families of curves that intersect each other at right angles. One illustrative case involves a family of parabolas that open sideways along the x-axis. These curves share a common shape but differ by a scaling parameter, resulting in a set of curves that all pass through the origin and widen at different rates.Determining Orthogonal TrajectoriesTo identify the orthogonal trajectories for these parabolas, the first step...
01:25First Derivative Test: Problem Solving
Imagine an asset price that crashes to a low point, rebounds sharply as bargain-hunters step in, and then gradually declines. Such behavior can be modeled with a smooth function whose turning points represent locally overvalued and undervalued regions. A convenient example that captures rebound followed by decay is:The high and low points of this curve are identified using the first derivative test, which determines where the function changes from increasing to decreasing or vice versa. To...
01:29Application of Differentiation to Business
Calculus offers essential techniques for businesses seeking to optimize pricing strategies and revenue. In this case, a bakery wants to determine the ideal price and daily sales volume to maximize revenue. By modeling how changes in price affect demand and revenue, the bakery can apply calculus to make data-driven decisions.The demand function relates the price per cupcake to the number of cupcakes sold and captures how lower prices increase sales. Based on market data, the demand function can...
01:24Pole and System Stability
The transfer function is a fundamental concept representing the ratio of two polynomials. The numerator and denominator encapsulate the system's dynamics. The zeros and poles of this transfer function are critical in determining the system's behavior and stability.
Simple poles are unique roots of the denominator polynomial. Each simple pole corresponds to a distinct solution to the system's characteristic equation, typically resulting in exponential decay terms in the system's response.
Simple poles are unique roots of the denominator polynomial. Each simple pole corresponds to a distinct solution to the system's characteristic equation, typically resulting in exponential decay terms in the system's response.
01:16Precipitate Formation and Particle Size Control
In precipitation gravimetry, the precipitating agent should react specifically or selectively with the analyte. While a specific reagent reacts with the analyte alone, a selective reagent can react with a limited number of chemical species.
The obtained precipitate should be either a pure substance of known composition or easily converted to one by a simple process, such as ignition or drying. In addition, the precipitate should be insoluble and easily filterable. In general, filterability...
The obtained precipitate should be either a pure substance of known composition or easily converted to one by a simple process, such as ignition or drying. In addition, the precipitate should be insoluble and easily filterable. In general, filterability...
01:25Distribution Reliability and Automation
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...