![\"\"](\"https:\/\/binus.ac.id\/humanitarian-ai\/wp-content\/uploads\/2025\/05\/waqar-mujahid-NU_s4KI_zME-unsplash-300x169.jpg\")
<\/p>\n<\/p>\n
Syllabus<\/strong><\/p>\n Pelatihan ini bertujuan meningkatkan kapasitas peserta dalam menerapkan teknologi Geospatial Artificial Intelligence (GeoAI)<\/strong> untuk melakukan penghitungan jumlah pohon kelapa sawit<\/strong> dan penilaian kesehatan tanaman<\/strong> secara akurat, efisien, dan berbasis data spasial guna mendukung pengelolaan perkebunan yang berkelanjutan dan berbasis presisi. Download Syllabus<\/a>.<\/p>\n Topics:<\/strong><\/p>\n Overview of GeoAI and Its Role in the Oil Palm Industry.<\/p>\n<\/li>\n Remote Sensing for Agriculture: UAV, Satellite, and Multispectral Data.<\/p>\n<\/li>\n Introduction to Monitoring Needs in Oil Palm Plantations.<\/p>\n<\/li>\n<\/ul>\n Learning Objectives:<\/strong><\/p>\n Understand basic concepts of GeoAI and its applications in the palm oil sector.<\/p>\n<\/li>\n Identify geospatial data sources (UAV, Sentinel-2, PlanetScope, etc.).<\/p>\n<\/li>\n Explain business and technical requirements for monitoring oil palm plantations.<\/p>\n<\/li>\n<\/ul>\n Topics:<\/strong><\/p>\n UAV Mission Planning and Data Collection.<\/p>\n<\/li>\n Orthomosaic Generation and Georeferencing.<\/p>\n<\/li>\n Satellite Imagery Preprocessing.<\/p>\n<\/li>\n Annotation and Labeling Techniques for AI Training.<\/p>\n<\/li>\n<\/ul>\n Learning Objectives:<\/strong><\/p>\n Conduct UAV data acquisition for oil palm plantations.<\/p>\n<\/li>\n Generate orthomosaic maps and perform geometric corrections.<\/p>\n<\/li>\n Prepare imagery datasets for AI model training.<\/p>\n<\/li>\n Use QGIS and LabelImg\/Roboflow for data annotation and labeling.<\/p>\n<\/li>\n<\/ul>\n Topics:<\/strong><\/p>\n Deep Learning Fundamentals for Object Detection.<\/p>\n<\/li>\n CNN and YOLOv5\/YOLOv8 for Tree Counting.<\/p>\n<\/li>\n Transfer Learning and Model Evaluation.<\/p>\n<\/li>\n Practice: Train a Model Using Oil Palm Dataset.<\/p>\n<\/li>\n<\/ul>\n Learning Objectives:<\/strong><\/p>\n Understand object detection algorithms (YOLO, Faster R-CNN) for palm tree identification.<\/p>\n<\/li>\n Train and evaluate AI models using UAV or satellite datasets.<\/p>\n<\/li>\n Perform automated tree counting and validate results with field data.<\/p>\n<\/li>\n<\/ul>\n Topics:<\/strong><\/p>\n Vegetation Indices (NDVI, GNDVI, SAVI) and Tree Health Indicators<\/p>\n<\/li>\n Semantic Segmentation with U-Net\/DeepLab<\/p>\n<\/li>\n Integrating Spectral and Textural Features<\/p>\n<\/li>\n Case Study: Health Mapping in Oil Palm Plantations<\/p>\n<\/li>\n<\/ul>\n Learning Objectives:<\/strong><\/p>\n Utilize vegetation indices to assess oil palm tree health.<\/p>\n<\/li>\n Train image segmentation models for classifying healthy\/unhealthy areas.<\/p>\n<\/li>\n Analyze classification results and validate with field or high-resolution data.<\/p>\n<\/li>\n<\/ul>\n Topics:<\/strong><\/p>\n Spatial Analysis with Python (geopandas, rasterio, shapely)<\/p>\n<\/li>\n Building a Simple GeoAI Dashboard (Streamlit or Dash)<\/p>\n<\/li>\n Model Deployment and GIS Platform Integration<\/p>\n<\/li>\n Group Project Presentation & Evaluation<\/p>\n<\/li>\n<\/ul>\n Learning Objectives:<\/strong><\/p>\n Integrate AI output with spatial data and map visualization.<\/p>\n<\/li>\n Develop a dashboard prototype for monitoring oil palm plantations.<\/p>\n<\/li>\n Design an end-to-end workflow from data acquisition to actionable insights.<\/p>\n<\/li>\n Present project results and receive feedback from instructors.<\/p>\n<\/li>\n<\/ul>\n Daily quizzes<\/p>\n<\/li>\n Mini-project (individual or group)<\/p>\n<\/li>\n Certificate awarded to participants with \u226580% attendance and who pass the final evaluation<\/p>\n<\/li>\n<\/ul>\n By the end of the training, participants will be able to:<\/p>\n Understand the foundational concepts and benefits of GeoAI in the oil palm industry<\/p>\n<\/li>\n Perform data acquisition, preprocessing, and analysis from UAVs, satellite imagery, and multispectral sensors<\/p>\n<\/li>\n Apply deep learning models (YOLO, U-Net) to automatically count palm trees and assess their health<\/p>\n<\/li>\n Integrate AI analysis with Geographic Information Systems (GIS)<\/p>\n<\/li>\n Evaluate and validate model results using field data or high-resolution images<\/p>\n<\/li>\n Apply an end-to-end pipeline from UAV mission planning to reporting insights for plantation management<\/p>\n<\/li>\n<\/ul>\nGeospatial Artificial Intelligence (GeoAI) for Oil Palm Tree Counting and Health Assessment<\/strong><\/h3>\n
\ud83d\udd58\u00a0Duration:<\/strong> 2 Days (16 Hours)<\/h4>\n
\ud83d\udc65 Level:<\/strong> Intermediate to Advanced<\/h4>\n
\ud83d\udcbc\u00a0Target Participants:<\/strong><\/h4>\n
\n
\ud83d\udccbMethod:<\/strong> Combination of lectures, hands-on practices, and case studies.<\/h4>\n
\n\ud83d\udcda\u00a0Day 1 \u2013 Session 1: Introduction and Fundamentals of GeoAI<\/strong><\/h3>\n
\n
\n
\n\ud83d\udcda\u00a0Day 1 \u2013 Session 2: Data Acquisition and Preprocessing<\/strong><\/h3>\n
\n
\n
\n\ud83d\udcda\u00a0Day 2 \u2013 Session 1: AI for Oil Palm Tree Counting<\/strong><\/h3>\n
\n
\n
\n\ud83d\udcda\u00a0Day 2 \u2013 Session 2: Tree Health Assessment and Classification<\/strong><\/h3>\n
\n
\n
\n\ud83d\udcdaDay 2 \u2013 Session 3: GeoAI Dashboard & Deployment<\/strong><\/h3>\n
\n
\n
\nEvaluation and Certification<\/strong><\/h3>\n
\n
\nLearning Outcomes:<\/strong><\/h3>\n
\n
\n