Enhancing corn future price prediction through multi-modal data fusion: a comparative analysis of LSTM, sLSTM, mLSTM, and xLSTM models

This repository contains the code and datasets used in the study: "Multi-source Deep Learning Models for Agricultural Futures Price Prediction". Contents: - timeₚrediction. py: main prediction script- fourₘodelscomparison. py: model comparison- dataset. csv: processed dataset- googleₑarthₑngine. txt: remote sensing notesThis file provides the Google Earth Engine (GEE) script link used for remote sensing data processing. Google Earth Engine does not allow direct export of the full computational environment or interactive scripts as standalone files. Therefore, the reproducible script is shared via a permanent GEE link. All remote sensing indices (e. g. , NDVI/EVI) used in this study were generated based on the provided GEE script. Requirements: Python 3. 9+PyTorchpandasnumpy To reproduce results: Runpython timeₚrediction. py