Eurasia Natural History Association
PalyFacies
Eurasia Natural History Association · Avrasya Doğa Tarihi Derneği
Open source

Try PalyFacies in your browser

dotader.com/paly

PaperAgbulut & Józsa (2026), Review of Palaeobotany and Palynology
doi.org/10.1016/j.revpalbo.2026.105731
Codegithub.com/borax9/-APAQ-Automated-Palynofacies-Area-Ratio-Quantification-for-the-Toarcian-Oceanic-Anoxic-Event

All contributions are welcome, especially images from slide scanners.
Introducing

PalyFacies

Free, open-source web app for automated palynofacies analysis of microscope images.

✓ Detects AOM, palynomorphs and phytoclasts
✓ Calibrated areas in µm² (10x, 20x, 40x)
✓ Tyson ternary plot, TAI and stratigraphic logs
✓ Single image or batch upload
✓ Runs in any browser, desktop or mobile

How it works

Two phases: AI, then analysis

1 · Deep learning: a YOLOv26 instance-segmentation model finds and masks every particle.
2 · Python engine: turns the masks into numbers, a Tyson plot, a TAI score and CSV/XLSX reports.

How it works · Step 1

Detect and mask each particle

The image is processed at 640 × 640 px. The model draws a pixel-level mask for every particle and labels it AOM, phytoclast or palynomorph, so background pixels are not counted.

94.1%
mAP@0.5 on segmentation masks
How it works · Step 2

Set the confidence threshold

Higher confidence keeps fewer but surer detections; lower keeps more. The curves show the precision–recall balance per class. Best mask F1 (0.92) was at 0.357.

98.7%
palynomorph mAP@0.5 (AOM 85.4%)
How it works · Step 3

Know where errors come from

The confusion matrix shows what is mixed up. Most AOM errors are particles blending into the slide background or hidden by opaque phytoclasts.

93.1% · 92.1%
mask precision · recall
How it works · Step 4

Measure areas, not just counts

Pixel areas are converted with Area (µm²) = pixels × (µm/pixel)², calibrated per objective. Relative area % = group area ÷ total area of the three groups × 100.

Area %
plus object counts per class
How it works · Step 5

Place the sample on the Tyson plot

The three percentages are projected onto the ternary triangle. The nearest of Tyson’s nine facies fields (I–IX) is assigned by Euclidean distance.

I–IX
facies fields
How it works · Step 6

Estimate thermal maturity (TAI)

The engine averages Hue and Value of the pixels inside each palynomorph mask. Darker colour means higher maturity, from immature (yellow) to overmature (black).

HSV
objective, no visual matching
How it works · Step 7

Build a stratigraphic log

Name files with a depth number (e.g. sample_12.jpg). Paly reads it, sorts the images by depth and plots AOM, palynomorph and phytoclast curves.

Batch
many images, one log
Source: 10.1016/j.revpalbo.2026.105731

🔬 Try PalyFacies now

↗ Open in new tab

⚠️ Important notice

Free Demo Version before Launching a Mobile App and you must increase threshold confidence to get better precision.

We do not claim that palynofacies analysis can be fully automated without error. PalyFacies is designed primarily to accelerate the second stage of the workflow, the quantitative analyses performed by our Palynofacies Engine. It is conceived as a fast, real-time screening tool that can be used at the wellsite, even during mudlogging operations. Rather than serving academic purposes, it has been developed to support petroleum exploration operations.

Get Data Annotation & Labeling Service