ID: 2.2/05.A
This webinar introduces the MLMapper, an open source QGIS plugin for predictive mapping that can provide calibrated predictions for any water-related variable. MLMapper uses machine learning algorithms to establish statistically significant patterns between a point-source binary target variable and a series of potentially explanatory variables. The tutorial presents how the MLMapper works and how it can help us in practice.
Learning Objectives
- What MLMapper is and the problems it can tackle
- What you need to run MLMapper
- How MLMapper can be used in practice
Target Audience
- Decision makers, modellers, researchers
Keywords
machine learning, GIS, data-driven predictions, water management modeling, open source
Related Resources
Publication: Martínez-Santos, P.: MLMapper: a versatile AI tool for spatial mapping, Virtual Exchange on “Artificial Intelligence for Integrated Drought Risk Management”, 26 November 2024.
Publication: Gómez-Escalonilla, et al.: GIS-Based Machine Learning Applications as Decision Support Systems to Enhance Groundwater Monitoring Networks, HIC2024, Beijing, China, 27-30 May 2024, https://doi.org/10.3850/iahr-hic2483430201-3, 2024.
Publication: Gómez-Escalonilla, et al.: A machine learning application for the development of groundwater vulnerability studies, HIC2024, Beijing, China, 27-30 May 2024, https://doi.org/10.3850/iahr-hic2483430201-378, 2024.
Publication: Martinez-Santos, P., et al.: A Surrogate Approach to Model Groundwater Level in Time and Space Based on Tree Regressors, SSRN, http://dx.doi.org/10.2139/ssrn.4890332, 2024.
Deliverable 3.1: Gap analysis of existing tools in the RBs
Deliverable 3.2: Improved modelling frameworks for better understanding of water resources at the river basin scale
[Category: 2.2 / Level: 1]
Presenter:
Dr. Pedro Martinez-Santos, Universidad Complutense de Madrid (UCM)
For further questions please contact us via this form https://stars4water.eu/contact/