<
 
 
 
 
×
>
You are viewing an archived web page, collected at the request of United Nations Educational, Scientific and Cultural Organization (UNESCO) using Archive-It. This page was captured on 17:22:35 Aug 02, 2016, and is part of the UNESCO collection. The information on this web page may be out of date. See All versions of this archived page.
Loading media information hide

Gerald Corzo Perez PhD, MSc

Lecturer / Researcher in Hydroinformatics

Biography

Gerald A. Corzo has extensive experience in modelling water resources using advanced ICT technology.  Since the last four year he has been working on the use of global hydrological models ensemble and their uncertainty for climate change analysis. In 2012 he won the Tison award as young scientist from the IAHR association. His work cover extreme natural events like the research in forecasting and analyzing flood and drought by the development of hydroinformatics technologies. In general, Artificial intelligence, Machine learning and Pattern Recognition have been applied in his thesis to solve problems in the water resources area. He has worked on different international institution like Wageningen University in the Netherlands and the Technologic of Monterrey in Mexico. He has coordinated the statistics of the Climate change inventory of adaptation and mitigation actions for Latin-America, presented at the WWF in 2012.  

He is the chair of the session in Geo-statistics at the EGU conference and reviewer of multiple journals like the Environmental Software and Modelling, the Journal of Hydrology and the Hydrology and Earth System Science, and some conferences like international joint conference in Neural Computation (IJCNN - IEEE). He have been awarded the researcher level one at the Mexican Academy of science (CONACYT). He is also an international Accredited Assessors for the RCEA and CONACYT. He belongs to different associations such as IAHR, IAHS, and the IEEE computational intelligent association as well as the Colombian civil engineer Society.

Dr Corzo is a civil engineer by training with a strong background on computational science. The subject of his Hydroinformatics doctoral work was developing modular models and hybrid methods on integrating computational intelligent algorithms and hydrological conceptual models. This work was tested inside the prototype of the operational Flood Early Warning System (Delft-FEWS) for the Meuse river basin. He has developed scripts for areas of computational intelligence, optimization of water resources and fluid dynamics simulation.
Recent Hydroinformatics Reseach cover exploring the use of mobile phone antennas for measuring precipitation.

Results of his work applied to a Colombian case study have been published in a number of conferences and in many international peer reviewed journals. He have participated on research projects with different international institutions like the North China University for Water Conservancy and Electric Power in China, CINARA in Colombia, Technologic of Monterrey in Mexico, CEH in England, University of Oslo in Norway and others. Since 2011 he have been involved with research on climate impacts on hydrological extremes around the world and he has proposed new methodologies for analysing spatio-temporal variations of extreme droughts from global hydrological models. From 2011 to 2012 he created and leaded the LatinAqua network for water research scientist in Latin-America.

Publications

On the spatio-temporal analysis of hydrological droughts from global hydrological models, Hydrology and Earth System Sciences, July 2011

This paper presents two methodologies that extend the tools to analyze spatio-temporal drought development and characteristics using large scale gridded time series of hydrometeorological data. The methodologies are distinguished and defined as non-contiguous and contiguous drought area analyses (i.e. NCDA and CDA). The NCDA presents time series of percentages of areas in drought at the global

Authors: Gerald Corzo Perez, Henny van Lanen, M. H. J. van Huijgevoort,F. Voss

Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - part 1Hydrology and Earth System Sciences, April 2010

A comprehensive data driven modeling experiment is presented in a two-part paper. In this first part, an extensive data-driven modeling experiment is proposed. The most important concerns regarding the way data driven modeling (DDM) techniques and data were handled, compared, and evaluated, and the basis on which findings and conclusions were drawn are discussed. A concise review of key articles

Authors: Gerald Corzo Perez, Dimitri Solomatine, A. Elshorbagy, S. Srinivasulu.

Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 2: ApplicationHydrology and Earth System Sciences, 2010

Inputs for the five case studies (half-hourly actual evapotranspiration, daily peat soil moisture, daily till soil moisture, and two daily rainfall-runoff datasets) are identified, either based on previous studies or using the mutual information content. Twelve groups (realizations) were randomly generated from each dataset by randomly sampling without replacement from the original dataset. Neural

Authors: Gerald Corzo Perez, Dimitri Solomatine, A. Elshorbagy, S. Srinivasulu.

Rainfall-interception-evaporationrunoff relationships in a semi-arid catchment, northern limpopo basin, zimbabwe. Hydrological Sciences Journal, 2010

The ephemeral Zhulube catchment (30 km2) in the northern Limpopo basin was instrumented and modelled in order to elucidate the dominant hydrological processes. Discharge events were disconnected, with short recession curves, probably caused by the shallow soils in the Tshazi sub-catchment, which dry out rapidly, and the presence of a dambo in the Gobalidanke sub-catchment. Two different flow event

Authors: Gerald Corzo Perez, Stefan Uhlenbrook, D. Love, S. Twomlow

River flow forecasting with artificial neural networks using satellite observed precipitation pre-processed with flow length and travel time information: case study of the ganges river basin. Hydrology and Earth System Sciences, 2009

This paper explores the use of flow length and travel time as a pre-processing step for incorporating spatial precipitation information into Artificial Neural Network models used for river flow forecasting. Spatially distributed precipitation is commonly required when modelling large basins, and it is usually incorporated in distributed physically-based hydrological modelling approaches. However

Authors: Gerald Corzo Perez, M. K. Akhtar, S. J. van Andel, and A. Jonoski.

Comprehensive flood mitigation and management in the Chi River BasinLowland Technology International, June 2011

Severe flooding of the flat downstream area of the Chi River Basin occurs frequently. This flooding is causing catastrophic loss of human lives, damage and economic loss. Effective flood management requires a broad and practical approach. Although flood disasters cannot completely be prevented, major part of potential loss of lives and damages can be reduced by comprehensive mitigation measures....more

Authors: Gerald Corzo Perez, K. Kuntiyawichai , B. Schultz , S. Uhlenbrook, Suryadi

Combining semi-distributed process-based and data-driven models in flow simulation: a case study of the Meuse river basinHydrology and Earth System Sciences, 2009

One of the challenges in river flow simulation modelling is increasing the accuracy of forecasts. This paper explores the complementary use of data-driven models, e.g. artificial neural networks (ANN) to improve the flow simulation accuracy of a semi-distributed process-based model. The IHMS-HBV model of the Meuse river basin is used in this research. Two schemes are tested. 

Authors: Gerald Corzo Perez, D. P. Solomatine, Hidayat, M. de Wit, M. Werner S. Uhlenbrook, and R. K. Price

Knowledge-based modularization and global optimization of artificial neural network models in hydrological forecastingJournal Neural Networks, 2007

Natural phenomena are multistationary and are composed of a number of interacting processes, so one single model handling all processes often suffers from inaccuracies. A solution is to partition data in relation to such processes using the available domain knowledge or expert judgment, to train separate models for each of the processes, and to merge them in a modular model (committee). 

Authors: Gerald Corzo PerezDimitri Solomatine

Baseflow separation techniques for modular artificial neural networks modelling in flow forecasting. Hydrological Sciences Journal, 2007, 

In hydrological sciences there is an increasing tendency to explore and improve artificial neural network (ANN) and other data-driven forecasting models. Attempts to improve such models relate, to a large extent, to the recognized problems of their physical interpretation. The present paper deals with the problem of incorporating hydrological knowledge into the modelling process through the use of 

Authors: Gerald Corzo PerezDimitri Solomatine

Self-Learning Cellular Automata for Forecasting Precipitation from Radar Images ASCE, January 2013

This paper presents a new forecasting methodology that uses self-learning cellular automata (SLCA) for including variables that consider the spatial dynamics of the mass of precipitation in a radar forecast model. Because the meteorological conditions involve nonlinear dynamic behavior, an automatic learning model is used to aid the cellular automata rules (SLCA). 

Authors: Arthur Mynett