Vitali Diaz Mercado graduated on 24 November 2021. Find his story and link to the thesis here.
Vitali Diaz Mercado (Vitali Diaz) is a civil engineer, passionate programmer, data analyst, modeler, and remote-sensing-based approaches developer to overcome water challenges. Vitali is originally from Mexico. He holds a BSc degree in Civil Engineering and an MSc degree in Water Science from the Faculty of Engineering at the Autonomous University of Mexico State. He received his PhD from IHE Delft and the Delft University of Technology. His BSc thesis, MSc and PhD studies were financed and supported by the National Council for Science and Technology of Mexico.
He has collaborated on various projects with case studies in Mexico, Colombia, Ecuador, Dominican Republic, El Salvador, Honduras, Costa Rica, Mauritania, Senegal, Mali, Cote d'Ivoire, Burkina Faso, Tanzania, Greece, India and Vietnam. The Prince Albert II of Monaco Foundation supported the last stage of his PhD through the project "Uncertainty aware intervention design for Mediterranean aquifer recharge".
His research interests include extreme hydrological events (drought and flood), machine learning, data visualization, data analysis, data management, hydrological modeling, integration of models and remote sensing data, development of GIS-based applications and water accounting. These lines of research have arisen during different stages of Vitali's academic and professional journey.
Vitali is currently doing a postdoc at the Delft University of Technology in the research group led by Prof. Peter van Oosterom. The postdoc is within the project “nD-PointCloud continuous level representation for spatio-temporal phenomena in Open Point Cloud Maps”, which is awarded by the Netherlands eScience Center. The project aims to make point clouds the primary representation of spatio-temporal features throughout the entire processing chain (data acquisition, storage, analysis, visualization and dissemination). Based on a novel use of high-resolution nD space-filling curves, the project will realize a deep integration of space, time and scale as the basis for data organization, enabling High Performance/Throughput Computing for enormous point clouds. A distributed Open Point Cloud Map (OPCM) infrastructure will be developed that supports the sharing of big data nD-PointCloud, and enables interactive real-time visualizations using perspective views without data density shocks, continuous zoom-in/out and progressive data streaming between the server and client. Applications from the water management domain will be used as Proof-of-Principle.
TopicSpatio-temporal analysis of hydrological drought: integration of data-driven and process-based models
Studies of drought have increased in light of new data availability and advances in spatio-temporal analysis. However, the following gaps still need to be filled: 1) methods to characterise drought that explicitly consider its spatio-temporal features, such as spatial extent (area) and pathway; 2) methods to monitor and predict drought that include the above-mentioned characteristics and 3) approaches for visualising and analysing drought characteristics to facilitate interpretation of its variation. This research aims to explore, analyse and propose improvements to the spatio-temporal characterisation of drought. Outcomes provide new perspectives towards better prediction.
The following research objectives were proposed. 1) Improve the methodology for characterising drought based on the phenomenon’s spatial features. 2) Develop a visual approach to analysing drought variations. 3) Develop a methodology for spatial drought tracking. 4) Explore machine learning (ML) techniques to predict crop-yield responses to drought. The four objectives were addressed and results are presented in his dissertation and publications.
Finally, a scope was formulated for integrating ML and the spatio-temporal analysis of drought. The proposed scope opens a new area of potential for drought prediction (i.e. predicting spatial drought tracks and areas). It is expected that the drought tracking and prediction method will help populations cope with drought and its severe impacts.
More details on the development of this research can be found at (Spatio-Temporal ANalysis of Drought) STAND project
A complete listing via ResearchGate
Diaz, V., Corzo Perez, G. A., Van Lanen, H. A. J., Solomatine, D., and Varouchakis, E. A. (2020). An approach to characterise spatio-temporal drought dynamics. Advances in Water Resources, 137, 103512. https://doi.org/10.1016/j.advwatres.2020.103512 [pdf] [html]
Diaz, V., Corzo Perez, G. A., Van Lanen, H. A. J., Solomatine, D., and Varouchakis, E. A. (2020). Characterisation of the dynamics of past droughts. Science of The Total Environment, 134588. https://doi.org/10.1016/j.scitotenv.2019.134588 [pdf] [html]
Diaz, V., Corzo, G., and Perez, J. R. (2019). 3 - Large-scale exploratory analysis of the spatiotemporal distribution of climate projections: applying the STRIVIng toolbox. In G. Corzo and E. A. Varouchakis (Eds.), Spatiotemporal Analysis of Extreme Hydrological Events (pp. 59–76). Elsevier. https://doi.org/10.1016/B978-0-12-811689-0.00003-3 [pdf] [html]
Diaz, V., Corzo, G., Lanen, H. A. J. Van, and Solomatine, D. P. (2019). 4 - Spatiotemporal drought analysis at country scale through the application of the STAND toolbox. In G. Corzo and E. A. Varouchakis (Eds.), Spatiotemporal Analysis of Extreme Hydrological Events (pp. 77–93). Elsevier. https://doi.org/10.1016/B978-0-12-811689-0.00004-5 [pdf] [html]
Le, H. M., Corzo, G., Medina, V., Diaz, V., Nguyen, B. L., and Solomatine, D. P. (2019). 7 - A comparison of spatial–temporal scale between multiscalar drought indices in the South Central Region of Vietnam. In G. Corzo and E. A. Varouchakis (Eds.), Spatiotemporal Analysis of Extreme Hydrological Events (pp. 143–169). Elsevier. https://doi.org/10.1016/B978-0-12-811689-0.00007-0 [pdf] [html]
Diaz, V., Corzo Perez, G. A., Van Lanen, H. A. J., and Solomatine, D. (2018). Intelligent drought tracking for its use in Machine Learning: implementation and first results. (G. La Loggia, G. Freni, V. Puleo, and M. De Marchis, Eds.), HIC 2018. 13th International Conference on Hydroinformatics (Vol. 3). Palermo: EasyChair. https://doi.org/10.29007/klgg link
Diaz Mercado, V., Corzo Perez, G., Solomatine, D., and Van Lanen, H. A. J. (2016). Spatio-temporal analysis of hydrological drought at catchment scale using a spatially-distributed hydrological model. Procedia Engineering, 154, 738–744. https://doi.org/10.1016/j.proeng.2016.07.577 link
Diaz, V., Corzo Perez, G. A., Van Lanen, H. A. J., and Solomatine, D. (2018). Comparative analysis of two evaporation-based drought indicators for large-scale drought monitoring. Geophysical Research Abstracts Vol. 20, EGU2018-18728. EGU General Assembly. Vienna. link
Osman, A., Diaz, V., Corzo Perez, G. A., Varouchakis, E., Solomatine, D. (2018). Finding negative response of crop yield to drought: a spatiotemporal approach over East India. International Conference on Water, Environment, Energy and Society (ICWEES), Tunisia. Based on Ahmed's MSc Thesis
Diaz, V., Corzo G., Van Lanen H.A.J., Solomatine D. (2017). On the visualization of water-related big data: extracting insights from drought proxies’ datasets. Geophysical Research Abstracts Vol. 19, EGU2017-10718-1. EGU General Assembly, Vienna link
Diaz, V., Corzo Perez G., Van Lanen H.A.J., Solomatine D. (2016). Spatio-temporal analysis of large-scale meteorological drought: helping to achieve the SDGs 6.A and 11.5. 12th Kovacs Colloquium, Paris, France. DOI: 10.13140/RG.2.1.2595.2888 link
#followme on Twitter
Co-supervisor of MSc research
Spatiotemporal analysis and prediction of crop yield using data-driven models and drought areas. Case study of India. Ahmed Abdelmoneim Ahmed Osman. MSc Thesis. WSE-HERBD.18-17, IHE-Delft, March 2018. Delft, Netherlands link
Integrated spatial precipitation drought index by combining remotely sensed information and local stations. Case study Guerrero State, Mexico. Yousra Omer Elfaroug Mohammed Khair. MSc Thesis. WSE-HI. 16-03, IHE-Delft, April 2016. Delft, Netherlands