Drones can now read a cotton field's thirst from the air
Crop Improvement
If you've ever hand-watered a garden bed and guessed wrong, this points to a future where a quick aerial scan tells you exactly which plants are stressed before they wilt.
Scientists flew a drone equipped with several types of cameras over cotton fields and fed the images into a computer model trained to guess how much water was inside the plants' leaves and stems. Instead of clipping samples and weighing them by hand, a common and slow method, the drone data let the model predict plant moisture quickly across a whole field. This kind of tool could eventually help farmers spot thirsty crops early and water more precisely.
Key Findings
Combined multiple UAV data types (multimodal sensing, likely including multispectral, thermal, and/or RGB imagery) to estimate cotton plant water content
Machine learning models were trained to translate aerial sensor readings into moisture predictions without destructive sampling
The approach targets faster, field-scale monitoring compared to traditional manual sampling methods
chevron_right Technical Summary
Researchers used drone cameras and machine learning to estimate how much water is inside cotton plants without touching a single leaf, which could help farmers water fields only where and when it's actually needed.
Species Mentioned
Was this useful?
Want to tell us more? (optional)
Thanks for the note!
Something went wrong — please try again.
Too many submissions. Try again in an hour.
Gene editing removes 97% of celiac-triggering proteins from bread wheat
It could mean that people with celiac disease — roughly 1 in 100 worldwide — may one day safely eat bread made from real wheat, without sacrificing the taste...
Cotton is a soft, fluffy staple fiber that grows in a boll, or protective case, around the seeds of the cotton plants of the genus Gossypium in the mallow family Malvaceae. The fiber is almost pure cellulose and may contain minor percentages of waxes, fats, pectins, and water. Under natural condi...