Remote Sensing for Agricultural Water Management
This course will be offered in an online/remote teaching format due to Covid-19 restrictions. The course's content and learning objectives will remain unchanged, while the duration may be extended. You can contact the course coordinator for more information about the new -temporary- format of the course.
For whom?
Young and mid-career professionals, engineers and technicians and academics involved in irrigation system management in various government and non-government organizations.
Prerequisites
General knowledge about remote sensing and GIS and their application in water related issues.
Dates, Fee, ECTS
Start: 04 July 2022
End: 22 July 2022
Deadline IHE application: 03 June 2022 - 23.59 (CET)
Course fee: € 3000
VAT is not included in the course fee
Learning objectives
- The students will be able to explain RS theory, technology, typical applications of earth observation data
- The students will be able to acquire pre-process satellite data (Landsat 8 / Sentinel 2), extract biophysical features, derive and analyse vegetation indices in agricultural systems
- The students will be able to map crop types using time series of big satellite data through application of machine learning algorithms in cloud based platforms
- The students will be able to explain the theory and implement surface energy balance model to estimate Evapotranspiration (ET), biomass production, and Water Productivity (WP)
- The students will be able to conduct irrigation performance assessment using remote sensing data, to identify gaps, diagnose issues and propose improvements
Course content
Topic 1: Introduction to Earth observation and remote sensing techniques Basics of RS and spatial big data; introduction to common RS data portal; earth observation satellites; typical application of RS and existing products; hands-on exercises on need analysis and acquiring of relevant data.
Topic 2: Remote Sensing data analysis Overview of RS data processing flow; satellite data pre-processing; mapping and visualizing spatial data; image analysis; hands-on exercise on deriving vegetation indices, zonal statistics using open source software and libraries.
Topic 3: Remote sensing and big data for mapping crop types Classification algorithms; machine learning approaches in crop classification from bigdata; ground truthing methods; accuracy assessment; hands-on exercises on crop type classification using open source libraries and cloud based Google Earth Engine (GEE)
Topic 4: Remote sensing for Evapotransipration, yield and WP assessment (SEBAL) Theory of SEBAL, Introduction to pySEBAL model, hands-on exercise on running pySEBAL to estimate ET, biomass, and WP. The skills acquired will be applied to the case study/assignment in progress during the class.
Topic 5: Remote sensing for irrigation water accounting and performance assessment Assessment of the irrigation performance using remote sensing based indicators for productivity, adequacy, reliability, and equity; interpreting results to identify gaps, diagnose water management problems, and attribute to relevant factors for improvements; perform irrigation scheme level water accounting
Key lecturers
- Dr. Poolad Karimi
- Dr. Sajid Pareeth
- Mr. Tim Busker