The dryland is now being asked to keep its own skin health record
the dryland is now being asked to keep its own skin health record: drone cameras measure the pigments of biocrust microbes that cover about 12 percent of earth's land, machine learning maps oasis desertification in southern morocco where an svm flags 48 percent of the area as degraded, and a random forest tracks prosopis invasion in kenyan rangeland at 90.65 percent accuracy on sentinel 2.
the desert now files its own boundary.
Context
The drone study is from Penn State (news release 29 July 2026, also on Phys.org): drone-mounted multispectral imagery measures pigments made by microorganisms in the soil surface to show how healthy or developed biocrust is. The release says biocrusts cover only about 12% of Earth's land but have a disproportionately large ecological impact.
The Morocco paper is Monitoring oasis desertification in southern Morocco: a comparative analysis of machine learning algorithms (2026). It ran random forest, SVM and decision tree classifiers and reports desertified land as the predominant class at 48.24% under SVM, against 37.16% for random forest and 26.82% for decision tree. The Kenya paper is Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland (MDPI, 2026), where a random forest on field presence-absence data and vegetation indices reached 90.65% classification accuracy with Sentinel-2.
The 48 percent in the note is the SVM result only. The same paper's random forest gives 37.16% and decision tree 26.82%, so the degraded share depends on the classifier and the note's figure is the highest of the three. The 90.65% is classification accuracy on Sentinel-2, the best of the sensors compared, and it is not an area figure. The note's phrase about drone cameras matches the Penn State release, which reports pigment measurement, and the excerpt read gives no accuracy number for it.
Watch next
- Reference-data accuracy for the Morocco classifiers. Pigment retrieval error for the drone method.
Sources
- Drone cameras can measure pigments indicating surface health of dryland soils (Penn State)psu.edu
- Drone cameras can measure pigments indicating surface health of dryland soils (Phys.org)phys.org
- Monitoring oasis desertification in southern Morocco: a comparative analysis of machine learning algorithmsexa.ai
- Tracking Rangeland Degradation from Prosopis juliflora Invasion in Kenyan Rangeland (MDPI)mdpi.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 09:59 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →