# Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS

## TL;DR

This study uses satellite images and deep learning to predict wheat yields in Hebei Province with high accuracy and resolution over 20 years.

## Contribution

A novel deep learning model combining LSTM and NIRv for high-resolution wheat yield prediction at county and pixel levels.

## Key findings

- The model combining LSTM and NIRv achieved the best prediction performance and stability.
- Synthesized Landsat and MODIS images improved the completeness and quality of yield prediction data.
- April was identified as the optimal time for prediction due to performance and lead time considerations.

## Abstract

To obtain seasonable and precise crop yield information with fine resolution is very important for ensuring the food security. However, the quantity and quality of available images and the selection of prediction variables often limit the performance of yield prediction. In our study, the synthesized images of Landsat and MODIS were used to provide remote sensing (RS) variables, which can fill the missing values of Landsat images well and cover the study area completely. The deep learning (DL) was used to combine different vegetation index (VI) with climate data to build wheat yield prediction model in Hebei Province (HB). The results showed that kernel NDVI (kNDVI) and near-infrared reflectance (NIRv) slightly outperform normalized difference vegetation index (NDVI) in yield prediction. And the regression algorithm had a more prominent effect on yield prediction, while the yield prediction model using Long Short-Term Memory (LSTM) outperformed the yield prediction model using Light Gradient Boosting Machine (LGBM). The model combining LSTM algorithm and NIRv had the best prediction effect and relatively stable performance in single year. The optimal model was then used to generate 30 m resolution wheat yield maps in the past 20 years, with higher overall accuracy. In addition, we can define the optimum prediction time at April, which can consider simultaneously the performance and lead time. In general, we expect that this prediction model can provide important information to understand and ensure food security.