The course runs from 4 to 8 August 2025 (daily timetable: 09.00-12.00 and 13.30-16.30).

PRELIMINARY PROGRAM

Monday 4 August 2025 – Introduction to the Course and training objectives (school directors).  Student self presentation.

Statistical models and sampling design. Prof. Acutis, Prof. Perego, Prof. Stellacci, Dr. Barca.

First class: General linear model and regression (linear, non linear and multiple).

Second class: Sampling size, number of replications, and sampling design. Spatial mixed models.

Practical: Regression, general linear and spatial mixed models. Sample size determination and power analysis. 

Tuesday 5 August 2025 –Conducting a meta-analysis in agro-environmental science”. Dr. Valkama.

First class: Literature search, data collection and database creation.
Second class: Meta-analysis. 

Practical: Database creation and running a meta-analysis.

Wednesday 6 August 2025 – Topography for agro-environmental modelling. Prof. Märker.

First class: Fundamentals of Terrain analysis (TA). From soil catena to 3D landscape

Second class: Environmental process modelling with emphasis on soil erosion and storm flow.

Practical: Examples and applications of TA. GIS-based assessment models for soil erosion.

Thursday 7 August 2025 – Management and spatial assessment of the agro-environmental data. Dr. Schillaci, Prof. Saia, Dr. Ceccherini.

First class: Acquisition of reference databases, land cover, soil databases (e.g., LUCAS), weather and climate data), data processing and harmonization.

Second class: remote sensing with Google Earth Engine

Practical: Examples and applications of Soil Organic Carbon modelling using R and GIS.

Friday 8 August 2025 – Machine learning for environmental modelling. Prof. Lipani, Dr. Schillaci.

First class: Machine learning (random forest, neural network) as a tool for agro-environmental modelling, land cover mapping, vegetation indices.

Second Class: Deep learning classification of satellite images using convolutional neural networks, examples and applications using Pyton, R and GIS.

Practical: Examples and applications of machine and deep learning

.