10 Free GIS Data Source

A nice collection of free #GIS data sources "10 𝐅𝐫𝐞𝐞 𝐆𝐈𝐒 𝐃𝐚𝐭𝐚 𝐒𝐨𝐮𝐫𝐜𝐞𝐬: 𝐁𝐞𝐬𝐭 𝐆𝐥𝐨𝐛𝐚𝐥 𝐑𝐚𝐬𝐭𝐞𝐫 𝐚𝐧𝐝 𝐕𝐞𝐜𝐭𝐨𝐫 𝐃𝐚𝐭𝐚𝐬𝐞𝐭𝐬":

1. 𝐍𝐚𝐭𝐮𝐫𝐚𝐥 𝐄𝐚𝐫𝐭𝐡 𝐃𝐚𝐭𝐚: https://lnkd.in/diZSdcKt
2. 𝐔𝐒𝐆𝐒 𝐄𝐚𝐫𝐭𝐡 𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫: https://lnkd.in/daNe97jE
3. 𝐎𝐩𝐞𝐧𝐒𝐭𝐫𝐞𝐞𝐭𝐌𝐚𝐩: https://lnkd.in/dRECBK7q
4. 𝐄𝐬𝐫𝐢 𝐎𝐩𝐞𝐧 𝐃𝐚𝐭𝐚 𝐇𝐮𝐛: https://hub.arcgis.com/
5. 𝐍𝐀𝐒𝐀’𝐬 𝐒𝐨𝐜𝐢𝐨𝐞𝐜𝐨𝐧𝐨𝐦𝐢𝐜 𝐃𝐚𝐭𝐚 𝐚𝐧𝐝 𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬 𝐂𝐞𝐧𝐭𝐞𝐫 (𝐒𝐄𝐃𝐀𝐂): https://lnkd.in/d3YfbMiP
6. 𝐎𝐩𝐞𝐧 𝐓𝐨𝐩𝐨𝐠𝐫𝐚𝐩𝐡𝐲: https://opentopography.org
7. 𝐔𝐍𝐄𝐏 𝐄𝐧𝐯𝐢𝐫𝐨𝐧𝐦𝐞𝐧𝐭𝐚𝐥 𝐃𝐚𝐭𝐚 𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫: https://lnkd.in/dXN9gMgD
8. 𝐍𝐀𝐒𝐀 𝐄𝐚𝐫𝐭𝐡 𝐎𝐛𝐬𝐞𝐫𝐯𝐚𝐭𝐢𝐨𝐧𝐬 (𝐍𝐄𝐎): https://neo.gsfc.nasa.gov
9. 𝐒𝐞𝐧𝐭𝐢𝐧𝐞𝐥 𝐒𝐚𝐭𝐞𝐥𝐥𝐢𝐭𝐞 𝐃𝐚𝐭𝐚: https://lnkd.in/dJmAy47y
10. 𝐓𝐞𝐫𝐫𝐚 𝐏𝐨𝐩𝐮𝐥𝐮𝐬: https://terra.ipums.org 𝐑𝐞𝐚𝐝 𝐭𝐡𝐞 𝐟𝐮𝐥𝐥 𝐚𝐫𝐭𝐢𝐜𝐥𝐞 𝐡𝐞𝐫𝐞: https://lnkd.in/dFbCFwcK

𝐓𝐨𝐨𝐥𝐬 𝐭𝐨 𝐦𝐚𝐢𝐧𝐥𝐲 𝐯𝐢𝐬𝐮𝐚𝐥𝐢𝐳𝐞 𝐧𝐞𝐭𝐰𝐨𝐫𝐤𝐬:

• Geph - https://gephi.org
• Gephisto- https://lnkd.in/diSp3BWN
• VOSviewer - https://www.vosviewer.com
• Cytoscape - https://cytoscape.org
• Kumu - https://kumu.io
• GraphInsight - https://lnkd.in/d5XnkWJr
• NodeXL - https://nodexl.com
• Orange - https://lnkd.in/dZU8Zx3D
• Graphia - https://graphia.app
• Graphistry - https://www.graphistry.com
• SocNetV - https://socnetv.org
• Tulip - https://lnkd.in/dtc_BD33

𝐍𝐞𝐭𝐰𝐨𝐫𝐤 𝐥𝐢𝐛𝐫𝐚𝐫𝐢𝐞𝐬 𝐢𝐧 𝐏𝐲𝐭𝐡𝐨𝐧:

• networkx - https://lnkd.in/dKCCXjif
• graphviz - https://lnkd.in/dtrTeqRv
• pydot - https://lnkd.in/dA46YZvy
• python-igraph - https://lnkd.in/dCGsRXh2
• pyvis - https://lnkd.in/dVrQ64nN
• ipycytoscape - https://lnkd.in/d-hJjDdG
• pygsp - https://lnkd.in/dS7s-A_v
• graph-tool - https://lnkd.in/dvytUzdu
• nxviz - https://lnkd.in/duHbKGPN
• py2cytoscape - https://lnkd.in/dWUU8TZH
• ipydagred3 - https://lnkd.in/diXgFWMD
• ipysigma - https://lnkd.in/dP55J5et
• Py3Plex - https://lnkd.in/dhwe7f_g
• net wulf - https://lnkd.in/dxrHAm2P

9 use cases of Deep Learning with Imagery and tips on how to get started.

1. Extracting building footprints Instance Segmentation Models: MaskRCNN

2. Identifying new construction Change Detection Models: STA-Net ChangeDetector

3. Classifying homes as damaged or not after a forest fire Object Classification Models: FeatureClassifier with ResNet, Inception, VGG backbones

4. Detecting swimming pools Object Detection Models: SingleShotDetector(SSD), RetinaNet, YOLO, FasterRCNN, MMDetection

5. Road extraction Road Extraction Models: MultiTaskRoadExtractor

6. Crop Classification Imagery Time Series Classification Models: PSETAE

7. Land cover classification Pixel Classification Models: UNetClassifier, PSPNetClassifier, DeepLab, MMSegmentation

8. Mapping residential parcels Edge Detection Models: BDCNEdgeDetector, HEDEdgeDetector, ConnectNet

9. Increasing (upscaling) image resolution Image Enhancement Models: SuperResolution

How to start?

1. Prepear your input imagery data, and generate true-ortho with ArcGIS Reality for best accuracy.
2. ArcGIS API for Python + arcgis.learn module - Functions for calling the Deep Learning Tools https://lnkd.in/dCfsifZh
3. Explore and test pre-trained models - ArcGIS Living Atlas https://lnkd.in/dQsE5FXp
4. Use ArcGIS tools to improve or train your own models (see guide in each DLPK)
5. Build own Apps & Solutions

Application of AI in Agriculture

1. Crop and soil monitoring
2. Insect and plant disease detection
3. Livestock health monitoring
4. Intelligent spraying
5. Automatic weeding
6. Aerial survey and imaging
7. Produce grading and sorting
8. The future of AI in Agriculture: Farmers as AI engineers?