Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

This study presents an approach to combine uncertainties of the hydrological model outputs predicted from a number of machine learning models. The machine learning based uncertainty prediction approach is very useful for estimation of hydrological models' uncertainty in particular hydro-metrological situation in real-time application [1]. In this approach the hydrological model realizations from Monte Carlo simulations are used to build different machine learning uncertainty models to predict uncertainty (quantiles of pdf) of the a deterministic output from hydrological model . Uncertainty models are trained using antecedent precipitation and streamflows as inputs. The trained models are then employed to predict the model output uncertainty which is specific for the new input data. We used three machine learning models namely artificial neural networks, model tree, locally weighted regression to predict output uncertainties. These three models produce similar verification results, which can be improved by merging their outputs dynamically. We propose an approach to form a committee of the three models to combine their outputs. The approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model in the Brue catchment in UK and the Bagmati catchment in Nepal. The verification results show that merged output is better than an individual model output. [1] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press, 2013.

Informe de la Reunión Regional Latinoamericana Preparatoria de la Conferencia Internacional sobre Población, realizada en el marco del Séptimo Período de Sesiones del Comité de Expertos Gubernamentales de Alto Nivel = Report of the Latin American Regional Preparatory Meeting for the International Conference on Population, held within the Seventh Session of the Committee of High-Level Government Experts

Incluye Bibliografía

Informe del Noveno Período de Sesiones del Comité de Expertos Gubernamentales de Alto Nivel, dedicado a la ciencia y la tecnología para el desarrollo = Report of the Ninth Session of the Committee of High-Level Government Experts: science and technology for development

Presenta la organizacion de los trabajos y el resumen de los debates de la reunion del CEGAN, realizada en Montevideo entre el 23 y el 24 de enero de 1984 en la cual se trataron la evaluacion de la aplicacion del Programa de Accion de Viena sobre ciencia y tecnologia para el desarrollo en America Latina, las propuestas de medidas y acciones futuras y las recomendaciones a los organos internacionales y regionales.

Informe del Undécimo Período de Sesiones del Comité de Expertos Gubernamentales de Alto Nivel (CEGAN), Bogotá, Colombia, 3-6 marzo 1986 = Report of the Eleventh Session of the Committee of High-Level Government Experts (CEGAN), Bogota, Colombia, 3-6 March 1986

Contiene la organizacion de los trabajos, resumen de los debates y conclusiones de la reunion que tuvo por objetivo analizar, por una parte, la instrumentacion de la Estrategia Internacional del Desarrollo (EID) y las perspectivas de America Latina y el Caribe para el fin del decenio de 1980, teniendo presente la evolucion de la crisis y, por la otra, la deuda externa de America Latina y el Caribe.