{
  "id": 9357180,
  "title": "Detection of Red Crown Rot of Soybean in Illinois Fields Using High-Resolution Satellite Imagery and Machine Learning",
  "url": "https://urgent.news/2026/09/23/detection-of-red-crown-rot-of-soybean-in-illinois-fields-using-high",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-23T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.09.22.753594v1?rss=1"
  },
  "original_language": "en",
  "account": "Red crown rot (RCR), caused by the pathogen Calonectria ilicicola, is an emerging soybean disease in the U.S. Midwest that currently lacks reliable methods for mapping its distribution within individual fields. This study investigated the use of high-resolution PlanetScope satellite imagery for this purpose, analyzing 15 commercial soybean fields across Illinois in both 2024 and 2025 growing seasons. The research involved classifying 2,921 georeferenced canopy plots as either asymptomatic or RCR-affected, using six multispectral bands and seven vegetation indices for each plot. Linear mixed-effects models were employed to analyze spectral differences between the two canopy classes, and seven distinct machine learning classifiers were evaluated using spatially independent leave-one-field-out cross-validation. RCR-affected canopies displayed notable spectral changes compared to healthy canopies, including higher reflectance in the visible and red-edge regions, lower near-infrared reflectance, and reduced vegetation-index values. Across all tested classifiers, the ROC-AUC values ranged from 0.963 to 0.982, indicating strong discriminatory power. Regularized logistic regression emerged as the best-performing model, achieving an accuracy of 0.945, balanced accuracy of 0.945, F1-score of 0.948, and ROC-AUC of 0.982 at its optimized decision threshold. The study identified Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and red reflectance as the most significant predictors of RCR presence in the machine learning models. While satellite-derived probability and classification maps largely aligned with observed symptoms in high-resolution UAV imagery, mixed pixels near disease patch boundaries reduced overall precision. These findings suggest that satellite-derived imagery holds promise for accurately mapping RCR-associated symptoms within soybean fields, offering a scalable approach for disease monitoring and management across commercial soybean operations.",
  "summary": "Red crown rot (RCR), caused by Calonectria ilicicola, is an emerging soybean disease in the U.S. Midwest for which scalable approaches to characterize within-field disease distribution are lacking. This study evaluated high-resolution PlanetScope satellite imagery for mapping RCR-affected soybean canopies across 15 commercial fields in Illinois surveyed during the 2024 and 2025 growing seasons. A…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}