Remote SensingScientist Academy
Menu
Apply for cohort

One professional pathway

Remote sensing curriculum

Move from scientific programming foundations through geospatial data science to defensible remote sensing modelling. Every lesson contributes evidence to a portfolio project.

Module 1

Thinking Like a Scientific Programmer

Learn Python from zero and become capable of inspecting, organising and explaining scientific ecological data.

Portfolio project
Vegetation Data Explorer
Learning resources
12
  1. 1.1Welcome to Scientific Programming
  2. 1.2Variables and Scientific Data
  3. 1.3Collections for Ecological Information
  4. 1.4Conditions and Data-Quality Rules
  5. 1.5Repetition, Loops and Vectorised Thinking
  6. 1.6Functions, Errors and Debugging
  7. 1.7NumPy and Numerical Arrays
  8. 1.8Open the Published Dataset with pandas
  9. 1.9Missing Values, Types and Data Quality
  10. 1.10Filter, Group and Summarise
  11. 1.11Join, Reshape and Visualise
  12. 1.12Vegetation Data Explorer Project
Module 2

Geospatial Data Science

Turn vector, raster, UAV and satellite data into reproducible spatial analyses by learning spatial reasoning before software operations.

Portfolio project
UAV and Satellite Analysis Pipeline
Learning resources
66
  1. 2.1What Makes Data Geospatial?
  2. 2.2Coordinate Reference Systems
  3. 2.3Scale, Resolution and Spatial Support
  4. 2.4Geospatial Formats and Metadata
  5. 2.P1Accept, Review or Reject?
  6. 2.5GeoPandas and Spatial Tables
  7. 2.6Geometry with Shapely
  8. 2.7Spatial Joins, Overlay and Nearest Neighbours
  9. 2.8Spatial Indexing and Performance
  10. 2.9Topology, Geometry Cleaning and Data Integrity
  11. 2.10QGIS for Professional Spatial QA
  12. 2.P2Vector Handover Review
  13. 2.11What Is a Raster Really?
  14. 2.12Rasterio: Read, Inspect and Write Spatial Grids
  15. 2.13Crop, Mask, Reproject and Resample
  16. 2.14Raster Alignment and Grid Integrity
  17. 2.15Raster–Vector Integration
  18. 2.16Large Raster Processing
  19. 2.17Terrain Analysis with DEM and DSM
  20. 2.P3Build an Analysis-Ready Raster Stack
  21. 2.18UAV Remote Sensing Fundamentals
  22. 2.19Mission Design: Altitude, GSD and Overlap
  23. 2.20Sensors, Illumination and Radiometric Quality
  24. 2.21Georeferencing: GNSS, GCP, RTK and PPK
  25. 2.22Structure from Motion and Photogrammetric Reconstruction
  26. 2.23Point Clouds, DSM, DTM and Orthomosaics
  27. 2.24UAV Product QA and Error Diagnosis
  28. 2.25UAV Multispectral Processing Pipeline
  29. 2.P4Evaluate a UAV Survey Before Scientific Analysis
  30. 2.26Optical Remote Sensing
  31. 2.27Vegetation and Spectral Indices
  32. 2.28SAR Fundamentals
  33. 2.29Hyperspectral Remote Sensing
  34. 2.30LiDAR and Point Clouds
  35. 2.P5Build a Defensible Satellite Evidence Package
  36. 2.31Spatial Autocorrelation
  37. 2.32Spatial Sampling and Bias
  38. 2.33Interpolation and Geostatistics
  39. 2.34Spatial Regression Concepts
  40. 2.P6Design and Defend a Spatial Inference Plan
  41. 2.35SQL for Geospatial Scientists
  42. 2.36PostGIS Fundamentals
  43. 2.37Managing Large Spatial Data
  44. 2.P7Build a Governed Spatial Database Handover
  45. 2.38Xarray and Rioxarray
  46. 2.39EO Data Cubes
  47. 2.40Dask and Lazy Computation
  48. 2.41COG, Zarr and Cloud-Native Formats
  49. 2.42STAC
  50. 2.P8Build a Reproducible Cloud-Native EO Evidence Cube
  51. 2.43Web Maps and Spatial Services
  52. 2.44Interactive Mapping
  53. 2.45OGC Standards and Interoperability
  54. 2.P9Deliver an Accessible Environmental Monitoring Map
  55. 2.46ArcGIS Professional Ecosystem
  56. 2.P10Design a Portable Coastal-Meadow GIS Architecture
  57. 2.47Image Segmentation Fundamentals
  58. 2.48Deep Learning for Geospatial Images
  59. 2.49Geospatial Deep Learning QA
  60. 2.P11Audit a Meadow Segmentation Product
  61. 2.50APIs and Automated Data Acquisition
  62. 2.51Command-Line Geospatial Tools
  63. 2.52Docker for Geospatial Reproducibility
  64. 2.53Workflow Automation and CI
  65. 2.P12Productionise the Coastal-Meadow Pipeline
  66. CapstoneUAV and Satellite Analysis Pipeline
Module 3

Remote Sensing Modelling

Turn remote-sensing observations into defensible predictions by making the scientific claim, training evidence, validation design, uncertainty and operational domain explicit.

Portfolio project
Environmental Monitoring Project
Learning resources
31
  1. 3.1Prediction, Inference and Explanation
  2. 3.2Define the Target and Prediction Unit
  3. 3.3Design Predictors and Modelling Hypotheses
  4. 3.4Build the Modelling Dataset and Pre-register the Experiment
  5. 3.5What Does a Useful Model Need to Beat?
  6. 3.6Trees, Ensembles and Boosting
  7. 3.7XGBoost from First Principles
  8. 3.8Train the First Defensible XGBoost Model
  9. 3.9Validation Is Part of the Model
  10. 3.10Spatial, Grouped and Leave-Location-Out Validation
  11. 3.11Temporal and Spatiotemporal Validation
  12. 3.12Nested Model Selection and Leakage Prevention
  13. 3.13Hyperparameter Optimisation
  14. 3.14Early Stopping, Regularisation and Learning Dynamics
  15. 3.15Feature Selection, Redundancy and Stability
  16. 3.16Imbalanced Classification and Decision Thresholds
  17. 3.17Regression Evaluation
  18. 3.18Classification Evaluation and Probability Quality
  19. 3.19Residual Geography and Structured Failure
  20. 3.20Model Interpretation Without Causal Overclaiming
  21. 3.21Domain of Applicability and Extrapolation
  22. 3.22What Uncertainty Means in Predictive EO
  23. 3.23Prediction Intervals and Quantile Approaches
  24. 3.24Conformal Prediction and Empirical Coverage
  25. 3.25Uncertainty and Applicability Maps
  26. 3.26Raster Inference at Scale
  27. 3.27Google Earth Engine for Modelling Workflows
  28. 3.28Local ML versus Earth Engine ML
  29. 3.29Monitoring Through Repeated Predictions
  30. 3.30Reproducibility, Model Cards and Operational QA
  31. CapstoneEnvironmental Monitoring Project