Wheat Crop Yield Prediction Using Deep LSTM Model

TL;DR

This paper presents a deep LSTM model that predicts wheat crop yields using raw satellite imagery, outperforming existing methods and incorporating contextual geographic information for improved accuracy.

Contribution

The paper introduces a novel deep learning approach that directly models raw satellite images for crop yield prediction without feature extraction, achieving significant performance gains.

Findings

Outperforms existing methods by over 50% in accuracy.

Incorporating geographic context improves yield estimates.

Works effectively across multiple states in India.

Abstract

An in-season early crop yield forecast before harvest can benefit the farmers to improve the production and enable various agencies to devise plans accordingly. We introduce a reliable and inexpensive method to predict crop yields from publicly available satellite imagery. The proposed method works directly on raw satellite imagery without the need to extract any hand-crafted features or perform dimensionality reduction on the images. The approach implicitly models the relevance of the different steps in the growing season and the various bands in the satellite imagery. We evaluate the proposed approach on tehsil (block) level wheat predictions across several states in India and demonstrate that it outperforms existing methods by over 50\%. We also show that incorporating additional contextual information such as the location of farmlands, water bodies, and urban areas helps in improving the yield estimates.