MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer

作者：Fudong Lin, Summer Crawford, Kaleb Guillot, Yihe Zhang, Yan Chen, Xu Yuan, Li Chen, Shelby Williams, Robert Minvielle, Xiangming Xiao, Drew M. Gholson, Nicolas Quintana Ashwell, Tri Setiyono, Brenda Tubaña, Lu Peng, Magdy Bayoumi, Nian-Feng Tzeng · 年份：2023 · DOI：10.1109/iccv51070.2023.00531 · 被引用次数：63 · 研究领域：Remote Sensing in Agriculture、Smart Agriculture and AI、Urban Heat Island Mitigation

Precise crop yield prediction provides valuable information for agricultural planning and decision-making processes. However, timely predicting crop yields remains challenging as crop growth is sensitive to growing season weather variation and climate change. In this work, we develop a deep learning-based solution, namely Multi-Modal Spatial-Temporal Vision Transformer (MMST-ViT), for predicting crop yields at the county level across the United States, by considering the effects of short-term meteorological variations during the growing season and the long-term climate change on crops. Specifically, our MMST-ViT consists of a Multi-Modal Transformer, a Spatial Transformer, and a Temporal Transformer. The Multi-Modal Transformer leverages both visual remote sensing data and short-term meteorological data for modeling the effect of growing season weather variations on crop growth. The Spatial Transformer learns the high-resolution spatial dependency among counties for accurate agricultural tracking. The Temporal Transformer captures the long-range temporal dependency for learning the impact of long-term climate change on crops. Meanwhile, we also devise a novel multi-modal contrastive learning technique to pre-train our model without extensive human supervision. Hence, our MMST-ViT captures the impacts of both short-term weather variations and long-term climate change on crops by leveraging both satellite images and meteorological data. We have conducted extensive experiments o...