Apply now
Postgraduate DiplomaData, AI, Simulation & Analytics Applications open

Diploma in Geo-Temporal Predictive Models

Online postgraduate diploma of 800 hours in geo-temporal predictive models. 8 modules covering spatial and temporal dependence, classical statistical models, geospatial machine learning, spatio-temporal deep learning, event and trajectory prediction, evaluation and uncertainty, and deployment, with an assigned technical tutor.

Duration800 hours · 6–8 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Characterise the spatial and temporal dependence of data.

02

Fit classical spatio-temporal statistical models.

03

Apply machine learning with appropriate spatial validation.

04

Train deep models on graphs and raster fields.

05

Predict events and trajectories with dedicated models.

06

Evaluate predictions and quantify their uncertainty.

07

Deploy and maintain geo-temporal models in production.

Profile

Who it's for

  • Spatial data scientists building forecasting models.
  • Forecasting analysts who need to account for location.
  • Geospatial machine learning engineers.
  • Environmental statisticians.
  • Mobility analysts predicting demand and traffic.
  • Climate data engineers.
  • Engineering or science graduates seeking to enter the energy sector.
Standards & tools

What you'll work with

  • ISO 19123-1:2023 (geographic information coverages)
  • ISO 19108:2002 (geographic information temporal schema)
  • ISO 19115-1:2014 (geographic information metadata)
  • ISO 19111:2019 (referencing by coordinates)
  • CF conventions for netCDF (climate and forecast metadata conventions)
  • Directive 2007/2/EC (INSPIRE) (EU spatial data infrastructure)
  • ISO/IEC 23053:2022 (framework for AI systems using machine learning)
  • R (gstat, sf, INLA)
  • Python xarray
  • PyTorch Geometric Temporal
  • LightGBM
  • QGIS
Syllabus

8 modules

  1. 1.1Spatio-temporal autocorrelation functions
  2. 1.2Stationarity and anisotropy
  3. 1.3Spatial weight matrices
  4. 1.4Variograms and covariograms
  5. 1.5Trend and seasonality components
  6. 1.6Areal, point and field data
  7. 1.7Coverages according to ISO 19123
  8. 1.8netCDF format and CF conventions
  9. 1.9Spatial and temporal cross-validation
  10. 1.10Workshop: spatio-temporal variogram of pollution data
  1. 2.1ARIMA and SARIMA models
  2. 2.2SAR and CAR spatial autoregressive models
  3. 2.3Universal and spatio-temporal kriging
  4. 2.4STARIMA models for spatial series
  5. 2.5Generalised linear mixed models
  6. 2.6Generalised additive models
  7. 2.7Hierarchical Bayesian models with INLA
  8. 2.8Model selection and information criteria
  9. 2.9Residual diagnostics
  10. 2.10Lab: spatio-temporal kriging with gstat
  1. 3.1Spatial feature engineering
  2. 3.2Spatial and temporal lags
  3. 3.3Spatial random forest and gradient boosting
  4. 3.4Spatial block validation
  5. 3.5Interpretability with spatial SHAP
  6. 3.6Satellite data as predictors
  7. 3.7Imputation of missing data
  8. 3.8Imbalance in rare events
  9. 3.9Transfer between regions
  10. 3.10Lab: demand prediction with LightGBM and block validation
  1. 4.1LSTM and GRU recurrent networks
  2. 4.2ConvLSTM for raster fields
  3. 4.3Spatio-temporal graph networks
  4. 4.4STGCN and DCRNN models
  5. 4.5Transformers for spatial series
  6. 4.6Geospatial foundation models
  7. 4.7Probabilistic forecasting with deep networks
  8. 4.8Training on large volumes
  9. 4.9Comparison with classical models
  10. 4.10Lab: traffic forecasting with an STGCN
  1. 5.1Hawkes point processes
  2. 5.2Predicting occurrences in grid cells
  3. 5.3Next-destination prediction
  4. 5.4Fleet movement models
  5. 5.5ETA arrival prediction
  6. 5.6Risks of feedback loops
  7. 5.7Probability calibration
  8. 5.8Early detection metrics
  9. 5.9Prospective real-time evaluation
  10. 5.10Practical exercise: Hawkes model for network failures
  1. 6.1Spatial MAE, RMSE and MAPE metrics
  2. 6.2CRPS and interval scores
  3. 6.3Temporal out-of-sample validation
  4. 6.4Error and uncertainty maps
  5. 6.5Spatial conformal prediction
  6. 6.6Biases due to sensor coverage
  7. 6.7Comparison with baseline models
  8. 6.8Robustness to regime changes
  9. 6.9Communicating uncertainty on maps
  10. 6.10Case study: evaluating an air quality model
  1. 7.1Pipelines with xarray and Dask
  2. 7.2Zarr storage and Cloud Optimized GeoTIFF
  3. 7.3Serving predictions as an API
  4. 7.4Updating and retraining
  5. 7.5Spatial drift monitoring
  6. 7.6Integration with corporate GIS
  7. 7.7Model governance
  8. 7.8Open data regulations
  9. 7.9Ethics in territorial predictions
  10. 7.10Case study: operational energy demand forecasting by zone
  1. 8.1Defining the problem and scale
  2. 8.2Integrating data sources
  3. 8.3Spatio-temporal exploratory analysis
  4. 8.4Baseline statistical model
  5. 8.5Machine learning model
  6. 8.6Evaluation with spatial validation
  7. 8.7Uncertainty quantification
  8. 8.8Operational deployment plan
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

Training is 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme fits alongside your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is R (gstat, sf, INLA), Python xarray, PyTorch Geometric Temporal, LightGBM and QGIS, in free, academic or evaluation versions. Case studies are based on real procedures: pollution prediction with monitoring station data, traffic forecasting on road graphs and demand models over spatial cells. Assessment is continuous by module, plus the final integrating project.

Standards covered: ISO 19123-1:2023, ISO 19108:2002, ISO 19115-1:2014, ISO 19111:2019, CF conventions for netCDF, Directive 2007/2/EC (INSPIRE), ISO/IEC 23053:2022

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO 19123-1, ISO 19108 and ISO 19115-1 applied to real cases, not as a theoretical annex.
Industry software:R (gstat, sf, INLA), Python xarray, PyTorch Geometric Temporal, LightGBM and QGIS, in free, academic or evaluation versions.
Final project:a geo-temporal predictive model for a real problem, from data integration and a statistical baseline to a machine learning model with spatial validation, uncertainty quantification and a deployment plan, reviewed by your tutor.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Problem and data integration
Define the problem and its scale and integrate the data sources.
Exploratory analysis and baseline
Explore the data spatio-temporally and fit a baseline statistical model.
Machine learning model
Train a machine learning model and evaluate it with spatial validation.
Uncertainty and deployment
Quantify prediction uncertainty and draw up an operational deployment plan.
Final project
The complete geo-temporal model, written up in a report and presentation reviewed by your tutor.
Career opportunities

Where this takes you

Spatial data scientistForecasting analystGeospatial machine learning engineerEnvironmental statisticianMobility analystClimate data engineer
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. A university degree is not required.
  • An internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with R (gstat, sf, INLA), Python xarray, PyTorch Geometric Temporal, LightGBM and QGIS, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.

Prior technical training or professional experience in the sector (no university degree required), a computer able to run the programme software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Routing and Scheduling with Real-World Constraints

Online postgraduate diploma of 800 hours in routing and scheduling with real-world constraints. 8 modules covering VRP variants, distance matrices, operational and legal constraints, exact methods,…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Policy Design with Monte Carlo Simulation

Online postgraduate diploma of 800 hours in policy design with Monte Carlo simulation. 8 modules covering Monte Carlo fundamentals, uncertainty modelling, variance reduction, policy evaluation, simulation-based…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,440 $

Diploma in Scenarios, Trade-offs and Sensitivity Analysis

Online postgraduate diploma of 800 hours in scenarios, trade-offs and sensitivity analysis. 8 modules covering multi-criteria decision structuring, scenario planning, AHP, TOPSIS and PROMETHEE, multi-objective optimisation,…

6–8 monthsOnlineData, AI, Simulation & Analytics
Diploma in Geo-Temporal Predictive ModelsEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Diploma in Uncertainty Quantification and PropagationView programme →Diploma in Classical and Deep RL for Dynamic SystemsView programme →Diploma in Stateful and Exactly-Once Pipeline DesignView programme →Diploma in Mobility Policy and KPI EvaluationView programme →Diploma in V&V of Critical Models and Safety CasesView programme →Diploma in Robust and Stochastic OptimizationView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.