Deep learning maps California tomatoes using AlphaEarth embeddings

Researchers have developed a new method for mapping tomato cropping systems in California using Google DeepMind's AlphaEarth geospatial embeddings and a deep learning U-Net model. This approach eliminates the need for manual feature engineering, which was common in previous remote-sensing workflows. The model achieved high accuracy, with over 99% in pixel accuracy, precision, recall, and F1 score on an independent test set. Uncertainty maps generated by the model were highest near field edges, indicating reliable predictions within field interiors. AI

IMPACT Enables more accurate and efficient agricultural monitoring by leveraging advanced AI embeddings and models.

RANK_REASON Academic paper detailing a novel application of geospatial embeddings and deep learning for agricultural mapping. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• AlphaEarth
• AWS SageMaker
• California
• Google DeepMind
• Mohammadreza Narimani
• U-Net

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →