A Deep Learning Model for Heterogeneous Dataset Analysis -- Application to Winter Wheat Crop Yield Prediction
This work addresses yield prediction for wheat crops, which is crucial for Western countries, but it appears incremental as it builds on existing LSTM methods by adding heterogeneous data handling.
The paper tackled the problem of predicting winter wheat crop yield by developing a deep learning model that handles heterogeneous datasets, combining time-varying and static data, and demonstrated it outperforms existing machine learning models.
Western countries rely heavily on wheat, and yield prediction is crucial. Time-series deep learning models, such as Long Short Term Memory (LSTM), have already been explored and applied to yield prediction. Existing literature reported that they perform better than traditional Machine Learning (ML) models. However, the existing LSTM cannot handle heterogeneous datasets (a combination of data which varies and remains static with time). In this paper, we propose an efficient deep learning model that can deal with heterogeneous datasets. We developed the system architecture and applied it to the real-world dataset in the digital agriculture area. We showed that it outperforms the existing ML models.