Update README.md

README.md

@@ -1,14 +1,47 @@
+# README.md için
 ---
-title: Ai Georeferencer
-emoji: 📈
-colorFrom: gray
-colorTo: blue
+title: AI Geo-Referencing System
+emoji: 🗺️
+colorFrom: blue
+colorTo: green
 sdk: gradio
-sdk_version: 5.49.1
+sdk_version: 4.0.0
 app_file: app.py
 pinned: false
-license: agpl-3.0
-short_description: Aİ Georeferencer
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🗺️ Advanced AI Geo-Referencing System
+
+Professional-grade geolocation prediction from aerial and satellite imagery using state-of-the-art AI models.
+
+## Features
+
+- 📍 Single image coordinate prediction
+- 📊 Batch processing with statistical analysis  
+- 🗺️ Interactive maps with uncertainty visualization
+- 📈 Regional classification and confidence scoring
+- 📤 Multiple export formats (GeoJSON, CSV, Excel)
+- 🤖 Multi-model ensemble (DINOv2, EuroSAT, EarthView, S2-NAIP)
+
+## Models Used
+
+- **DINOv2 Base**: Vision transformer backbone
+- **EarthView Dataset**: High-resolution satellite imagery
+- **EuroSAT Dataset**: Sentinel-2 satellite images  
+- **S2-NAIP Dataset**: Paired Sentinel-2 and NAIP images
+
+## Usage
+
+1. Upload an aerial/satellite image
+2. Click "Predict Coordinates" 
+3. View results on interactive map
+4. Export results in preferred format
+
+## Technical Details
+
+- PyTorch backend with transformer architecture
+- Multi-head attention for feature fusion
+- Uncertainty estimation and confidence scoring
+- GPU-accelerated inference
+- Production-ready API endpoints