Publicaciones

Permanent URI for this collectionhttps://dspace.ucuenca.edu.ec/handle/123456789/45860

Browse

Now showing 1 - 20 of 1163

12th IFDC 2017 special issue – seasonal variations in nutrient composition of plant-based foods produced at the southern highlands of Ecuador
(2019) Ortiz Ulloa, Silvia Johana; Astudillo Rubio, Gabriela Cristina; Castro Arteaga, Evelyn Michelle; Castro Nube, Cecilia; Astudillo Astudillo, Sonia Cecilia; Donoso Moscoso, Silvana Patricia
Changes in environmental conditions may influence the biosynthesis of several food nutrients. This study aimed to compare macronutrient and mineral composition over several seasons in 25 fresh plant-based foods that are highly consumed and locally produced in the southern Ecuadorian highlands. Samples were collected during the rainy season (October 2015–March 2016) and dry season (April–September 2016) from main local markets and supermarkets. Analyses of composite samples were carried out in triplicate following AOAC methods, determining moisture by desiccation, ash by calcination, total fat by Weibull, total nitrogen by Kjeldahl, total carbohydrates by difference, phosphorus by colorimetry, and minerals (Na, K, Mg, Ca, Fe, Se, Cu and Zn) by atomic absorption spectroscopy. Overall, during the rainy season, significantly higher moisture content was observed (86.7 ± 9.0% vs. 85.9 ± 8.9%, p < 0.001), whereas fat (0.21 ± 0.21% vs. 0.31 ± 0.24%, p = 0.001), Fe (0.79±1.31 vs. 0.61 ± 0.98 mg/100 g, p < 0.001), Ca (50.4±68.0 vs. 23.0 ± 37.3 mg/100 g, p < 0.001), Mg (18.0 ± 11.4 vs. 15.2 ± 10.8 mg/100 g, p < 0.001) and Zn (0.35±0.69 vs. 0.2 ± 0.16 mg/100 g, p = 0.026 were significantly lower. This study demonstrates the influence of the season in the composition of vegetables cultivated in Ecuador. This factor, along with other sources of variability, should be defined, so as to be included in the quality assessments of representative food composition data. © 2019 Elsevier Inc.
A century of trends in adult human height
(2016-07-26) Donoso Moscoso, Silvana Patricia
Being taller is associated with enhanced longevity, and higher education and earnings. We reanalysed 1472 population-based studies, with measurement of height on more than 18.6 million participants to estimate mean height for people born between 1896 and 1996 in 200 countries. The largest gain in adult height over the past century has occurred in South Korean women and Iranian men, who became 20.2 cm (95% credible interval 17.5-22.7) and 16.5 cm (13.3- 19.7) taller, respectively. In contrast, there was little change in adult height in some sub-Saharan African countries and in South Asia over the century of analysis. The tallest people over these 100 years are men born in the Netherlands in the last quarter of 20th century, whose average heights surpassed 182.5 cm, and the shortest were women born in Guatemala in 1896 (140.3 cm; 135.8- 144.8). The height differential between the tallest and shortest populations was 19-20 cm a century ago, and has remained the same for women and increased for men a century later despite substantial changes in the ranking of countries.
A Comparative evaluation of preprocessing techniques for short texts in spanish
(Springer, 2020) Orellana Cordero, Marcos Patricio; Trujillo, Andrea; Cedillo Orellana, Irene Priscila
Natural Language Processing (NLP) is used to identify key information, generating predictive models, and explaining global events or trends. Also, NLP is supported during the process to create knowledge. Therefore, it is important to apply refinement techniques in major stages such as preprocessing, when data is frequently produced and processed with poor results. This document analyzes and measures the impact of combinations of preprocessing techniques and libraries for short texts that have been written in Spanish. These techniques were applied in tweets for analysis of sentiments considering evaluation parameters in its analysis, the processing time and characteristics of the techniques for each library. The performed experimentation provides readers insights for choosing the appropriate combination of techniques during preprocessing. The results show improvement of up to 5% to 9% in the performance of the classification.
A comparative study of black-box models for cement fineness prediction using SCADA measurements of a closed circuit grinding
(IEEE COMPUTER SOCIETY, 2016-02-01) Minchala Ávila, Luis Ismael; Mata, J. P.; Sanchez, C.; Yungaicela, N. M.
This paper presents a comparative study of three different modeling techniques for predicting cement fineness using input-output SCADA measurements of the closed circuit grinding in a cement plant. The modeling approaches used are the following: statistical, artificial neural networks (ANN), and adaptive neuro-fuzzy inference system (ANFIS). The data set for generating the predictive models are obtained from a database of the operation of the cement plant, UCEM-Guapan located in Azogues, Ecuador. Online validations of the proposed models allow the selection of the best approach and the most accurate models for cement fineness prediction, Blaine and percentage passing the sieve No. 325.
A comparative study of black-box models for cement quality prediction using input-output measurements of a closed circuit grinding
(INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS INC., 2016-04-18) Minchala Ávila, Luis Ismael; Sanchez, C; Yungaicela, M
This paper presents the methodology of design of three different modeling techniques for predicting cement quality using input-output measurements of the closed circuit grinding in a cement plant. The modeling approaches used are: statistical, artificial neural networks (ANN), and adaptive neuro-fuzzy inference systems (ANFIS). The data set for generating the predictive models are obtained from a database of the operation of the cement plant, UCEM-Guapan. An OPC (OLE for process control) network configuration in the SCADA system allows online validations of the proposed models in order to select the best approach for real-time prediction of cement quality.
A comparative study of water quality using two quality indices and a risk index in a drinking water distribution network
(2022) García Ávila, Fausto Fernando; Cadme Galabay, Manuel Remigio; Valdiviezo Gonzales, Lorgio; Gutierrez Ortega, Fausto Horacio; Flores del Pino, Lisveth Flores del Pino; Zhindón Arévalo, César
This study compares the Canadian Council Water Quality Index (CCME WQI) and the Arithmetic Water Quality Index (WAWQI) methodologies for determining the quality of water in the city of Azogues (Ecuador). Additionally, a drinking water quality risk index (IRCA) was determined to evaluate the degree of risk of disease occurrence related to water consumption. The data generated came from the analyses of twelve physicochemical parameters (pH, turbidity, colour, total dissolved solids, electrical conductivity, total hardness, alkalinity, nitrates, phosphates, sulfates, chlorides, residual chlorine) from 172 samples of water over six months. The calculated average value of CCME WQI (97.59 ± 1.08) indicates that 100% of the drinking system was of ‘excellent’ quality. The WAWQI average value was calculated to be 26.36 ± 1.13 indicating that 16.67% of the distribution system was of ‘excellent’ quality and 83.33% of the distribution water was of ‘good’ quality. The IRCA calculated in all the distribution zones is between 0 and 5% and therefore, the distributed water is considered suitable for human consumption and is rated at the no-risk level. Furthermore, WAWQI is influenced by parameters with low maximum allowed concentration (for example, turbidity value 1 NTU in the Ecuadorian standard was used instead of 5 NTU recommended by the WHO); conversely, CCME-WQI is influenced by parameters with a high maximum allowed concentration (no parameter exceeded the norm in this study). The IRCA is a support instrument to guarantee that the water supplied by the provider companies complies with the characteristics established for drinking water.
A Comparative Study on Time Series Prediction of Photovoltaic-Power Production Through Classic Statistical Techniques and Short-Term Memory Networks
(IEEE, 2023) Duran Nicholls, Juan Francisco; Minchala Ávila, Luis Ismael; Minchala Ávila, Luis Ismael
The inherent variability in the power production of renewable energy sources (RES) limits the effectiveness of energy management systems (EMS) since optimal dispatch on power networks highly depends on the accuracy of predictors associated with the energy output and load demand. Consequently, power prediction tools for variable time horizons allow for improving energy management decisions. In this context, this work presents a detailed methodology for the deployment of predictive models for the photovoltaic (PV) power output of a small solar farm. The prediction models process a PV power dataset's time series using statistical techniques and neural networks with long-short term memory (LSTM). Before the data fitting, we develop a data preprocessing system, which involves evaluating missing data in the time series and getting descriptive analysis of the data set to either complete portions or delete atypical data. The results strongly suggest that the LSTM network performs better than the statistical model in exchange for more considerable computation times for long-term predictions
A comparison of cephalometric measurements with conventional lateral cephalic 2D and reconstructed lateral cephalic of CBCT
(2022) Morocho Llivizaca, Karina Viviana; Bernal Pinos, Marco Vinicio; Bravo Calderón, Manuel Estuardo
Lateral cephalic radiography is mainly used to describe the morphology and growth of the craniofacial skeleton. It is considered a valuable diagnostic aid in orthodontics to plan treatment and evaluate the results. (1)(2) Cephalometric analyses requires identifying specific reference points and calculating various angular and linear dimensions. (3) Because cephalometry has been one of the most important diagnostic tools available to orthodontists for more than seven decades, different cephalometric norms have been published by leading physicians and researchers and it is used for: diagnosis, treatment progress, post-treatment evaluation, and research. (4) According to the orthodontic literature, other reconstructions such as lateral cephalic are known from more recent 3D cone beam computed tomography images. The attempt to develop 3D analysis and diagnosis is more interesting today. (4) (15) (23) Lateral cephalic radiographs are two-dimensional (2D) images that are used to represent three-dimensional (3D) structures. (5) Due to the different disadvantages of a 2D lateral cephalic X-ray: geometric distortion and the superposition of anatomical structures, 3D imaging has overcome the hurdle of 2D imaging by allowing orthodontists to visualize craniofacial structures without overlap or distortion.(6)(7)
A compartmental model to describe hydraulics in a full-scale waste stabilization pond
(2012-02-01) Alvarado Martínez, Andrés Omar
The advancement of experimental and computational resources has facilitated the use of computational fluid dynamics (CFD) models as a predictive tool for mixing behaviour in full-scale waste stabilization pond systems. However, in view of combining hydraulic behaviour with a biokinetic process model, the computational load is still too high for practical use. This contribution presents a method that uses a validated CFD model with tracer experiments as a platform for the development of a simpler compartmental model (CM) to describe the hydraulics in a full-scale maturation pond (7 ha) of a waste stabilization ponds complex in Cuenca (Ecuador). 3D CFD models were validated with experimental data from pulse tracer experiments, showing a sufficient agreement. Based on the CFD model results, a number of compartments were selected considering the turbulence characteristics of the flow, the residence time distribution (RTD) curves and the dominant velocity component at different pond locations. The arrangement of compartments based on the introduction of recirculation flow rate between adjacent compartments, which in turn is dependent on the turbulence diffusion coefficient, is illustrated. Simulated RTD's from a systemic tanks-in-series (TIS) model and the developed CM were compared. The TIS was unable to capture the measured RTD, whereas the CM predicted convincingly the peaks and lags of the tracer experiment using only a minimal fraction of the computational demand of the CFD model. Finally, a biokinetic model was coupled to both approaches demonstrating the impact an insufficient hydraulic model can have on the outcome of a modelling exercise. TIS and CM showed drastic differences in the output loads implying that the CM approach is to be used when modelling the biological performance of the full-scale system. © 2011 Elsevier Ltd.
A Comprehensive Ceiling Analysis of the Physical Layer Performance of the 5G NR
(Association for Computing Machinery, Inc, 2023) Belesaca Mendieta, Juan Diego; Vázquez Rodas, Andrés Marcelo; Vázquez Rodas, Andres Marcelo
Modern mobile communication systems, such as Fifth-Generation (5G) technology and beyond 5G, need to exhibit increased capacity, high level of efficiency, improved performance, low end-To-end delay, support to massive number of connections, quality of service and experience, among other requirements. A suboptimal configuration and/or operation of any component of the 5G network can significantly degrade the overall system performance. The physical layer of the radio access network plays a crucial role in the performance of the 5G system. Within this layer, three of the main components that have a significant impact are the characteristics of the propagation channels in which they operate, the synchronization scheme, and the channel estimation accuracy. These components directly influence the system performance and effectiveness. Therefore, this paper presents a comprehensive ceiling analysis of the physical layer of the 5G implemented according to the 3GPP standard. The evaluation of the system encompasses different and standardized channel conditions, synchronization schemes, and channel estimation methods. Rigorous and extensive simulations were conducted using the Matlab 5G NR toolbox for the PDSCH (Physical Downlink Shared Channel). The nodes were configured to operate in both macro-urban and indoor environments. The Clustered Delay Line (CDL) and Tapped Delay Line (TDL) channel models are evaluated under ideal channel estimation and synchronization conditions in each case. Subsequently, more realistic and practical configurations were considered. The simulation results provide quantitative insights of the maximum achievable throughput under various channel environments, including line-of-sight and nonline-of-sight conditions. These results help identify the specific physical layer components that have a greater impact on the throughput of the system. By pinpointing these components, researchers can focus their efforts on developing techniques aimed at enhancing the efficiency of the future beyond 5G networks.
A Data as a Service Metamodel for Managing Information of Healthcare and Internet of Things Applications
(Springer Science and Business Media Deutschland GmbH, 2020) Cedillo Orellana, Irene Priscila; Valdez Solis, Wilson Fernando; Cárdenas Delgado, Paúl; Prado Cabrera, Katerine Daniela
Internet of Things (IoT) applications nowadays generate a large amount of data, which are continually requiring adequate treatment and services on the Cloud to be available to stakeholders. Healthcare applications manage critical data from different sources as patient charts, Electronic Health Record (EHR), and devices which need security levels, data formatting, and quality of data due to their importance and sensitivity. Data as a Service (DaaS) is a data management framework provided though services on Cloud to bring data storage, integration, processing, analysis services, security, availability, elasticity, and quality characteristics to the data concerning the stakeholders. In this context, this paper proposes a data management solution deployed as DaaS for the healthcare domain presented through a metamodel focused on the federation pattern of data based on an Extract-Transform-Load (ETL) model for data classification; and considering a brief analysis of the non-functional characteristics proper of the DaaS domain as the security, confidentiality, priority, and availability. The metamodel is validated through an instantiation process using the MOntreal Cognitive Assessment (MOCA) test as the entry. Finally, it is presented a discussion from four stakeholder perspectives (e.g., data engineer, IoT solution developer, data quality analyst, health professional) about the solution.
A data infrastructure for managing information obtained from ambient assisted living
(Institute of Electrical and Electronics Engineers Inc., 2019) Valdez Solis, Wilson Fernando; Cedillo Orellana, Irene Priscila; Trujillo Orellana, Andrea Alexandra; Orellana Cordero, Marcos Patricio
The Internet of Things (IoT) is a current paradigm which can be part of several fields of application, and Healthcare is one of the most important. Ambient Assisted Living (AAL) is an important subfield in Healthcare. Also, services demand and network requirements of IoT systems due to the increase of connected devices and data flow overcharges Cloud. Fog Computing represents a new paradigm that lightens the network. Some applications use Fog Computing in order to reduce costs and improve performance of IoT applications. Healthcare is one of them and the implementation of Fog Computing architectures inside those systems is a new trend nowadays. The importance of having a data infrastructure in this kind of IoT systems is evident because of the relevance of the data. In this paper is presented a Data Infrastructure for Managing Information Obtained from Ambient Assisted Living. The model provides the data flow starting in the data reading in the IoT devices and ending in the Cloud by crossing Fog Computing Layer. The model considers communication protocols, security features and relationship between elements which take part in an AAL system. Moreover, the model was developed using Eclipse Modeling Tool and validated in the same tool by using an instantiation of the main classes of the model.
A data quality model for AAL systems
(Springer Nature Switzerland AG 2020, 2020) Erazo Garzón, Lenin Xavier; Erráez Jumbo, Jean Gabriel; Illescas Peña, Lourdes Eugenia; Cedillo Orellana, Irene Priscila
Ambient Assisted Living (AAL) aims to improve the quality of life of people, supporting them in their daily activities by the use of information technologies. The AAL systems are preferably focused on vulnerable groups (e.g., elderly people, people with special needs, children, patients with chronic diseases) to increase their independence in their natural living environment. These systems work in real time and their correct operation depends on the inferred knowledge of the data collected from sensors or other sources, thus the assurance of the quality of data is a priority aspect, especially in those systems that can put in risk the life of people. Currently, the research in this line is limited, there are not data quality models with a complete set of attributes and metrics adjusted to the AAL domain. This work proposes a data quality model for AAL systems conformed by the following characteristics: accuracy, completeness, currentness, confidentiality, accessibility, understandability and compliance; and their corresponding metrics. Finally, the application of the model to an intelligent pillbox, showed that it is a complete and valuable tool to evaluate the degree to which the quality of data is reached and preserved by an AAL system.
A data-driven optimization computational tool design for bike-sharing station distribution in small to medium-sized cities: a case study for Cuenca, Ecuador
(Springer Science and Business Media Deutschland GmbH, 2022) Shi, Pengcheng; Cueva Vera, Wilson Fernando; Cedillo Orellana, Irene Priscila
Faced with heavy vehicular traffic at present, the strategic implementation of Bike Sharing Systems (BSSs) in cities as an alternative means of transport for users is increasingly being adopted. These solutions reduce the environmental burden posed by other means of transportation, decrease costs for citizens, improves people's health due to physical activity, among other advantages. However, aspects such as the definition of bike stations’ locations represent a challenge when these solutions are being implemented. Therefore, this paper presents a software tool design that supports a method that defines the location and number of stations within a BSS. Also, the tool uses a data-driven optimization model to establish the location of stations. Finally, a case study carried out in Cuenca—Ecuador, demonstrates the proposal's feasibility, showing a significant concordance with the consulting firms-consortia results (70–90% of coincidence) at a lower cost
A domain-specific language for modeling IoT system architectures that support monitoring
(2022) Cedillo Orellana, Irene Priscila; Rossi, Gustavo; Moyano Dután, José Alfredo; Erazo Garzón, Lenin Xavier
The Internet of Things (IoT) is a technological paradigm involved in a diversity of domains with favorable impacts on people's daily lives and the development of industry and cities. Nowadays, one of the most critical challenges is developing software for IoT systems since the traditional Software Engineering methodologies and tools are unproductive in the face of the complex requirements resulting from the highly distributed, heterogeneous, and dynamic scenarios in which these systems operate. Model-Driven Engineering (MDE) emerges as an appropriate approach to abstract the complexity of IoT systems. However, there are no domain-specific languages (DSLs) aligned to standardized reference architectures for IoT. Furthermore, existing DSLs have an incomplete language to represent the IoT entities that may be needed at the edge, fog, and cloud layers to monitor IoT environments. Therefore, this paper proposes a domain-specific language named Monitor-IoT, which supports developers in designing multi-layer monitoring architectures for IoT systems with high abstraction, expressiveness, and flexibility. Monitor-IoT consists of a high-level visual modeling language and a metamodel aligned with the ISO/IEC 30141:2018 reference architecture. In addition, it provides a language capable of modeling architectures with a wide variety of digital entities and dataflows (synchronous and asynchronous) between them across the edge, fog, and cloud layers to support the monitoring of a diversity of IoT scenarios. The empirical evaluation of Monitor-IoT through the application of an experiment, which contemplates the use of the Technology Acceptance Model (TAM), demonstrates the intention of the participants to use this tool in the future since they consider it easy to use and useful.
A field, laboratory, and literature review evaluation of the water retention curve of volcanic ash soils: How well do standard laboratory methods reflect field conditions?
(2021) Jan, Feyen; Marin Molina, Franklin Geovanny; Mosquera Rojas, Giovanny Mauricio; Crespo Sánchez, Patricio Javier; Windhorst, David; Lutz, Breuer; Célleri Alvear, Rolando Enrique
Accurate determination of the water retention curve (WRC) of a soil is essential for the understanding and modelling of the subsurface hydrological, ecological, and biogeochemical processes. Volcanic ash soils with andic properties (Andosols) are recognized as important providers of ecological and hydrological services in mountainous regions worldwide due to their large fraction of small size particles (clay, silt, and organic matter) that gives them an outstanding water holding capacity. Previous comparative analyses of in situ (field) and standard laboratory methods for the determination of the WRC of Andosols showed contrasting results. Based on an extensive analysis of laboratory, experimental, and field measured WRCs of Andosols in combination with data extracted from the published literature we show that standard laboratory methods using small soil sample volumes (?300 cm3) mimic the WRC of these soils only partially. The results obtained by the latter resemble only a small portion of the wet range of the Andosols' WRC (from saturation up to ?5 kPa, or pF 1.7), but overestimate substantially their water content for higher matric potentials. This discrepancy occurs irrespective of site-specific land use and cover, soil properties, and applied method. The disagreement limits our capacity to infer correctly subsurface hydrological behaviour, as illustrated through the analysis of long-term soil moisture and matric potential data from an experimental site in the tropical Andes. These findings imply that results reported in past research should be used with caution and that future research should focus on determining laboratory methods that allow obtaining a correct characterization of the WRC of Andosols. For the latter, a set of recommendations and future directions to solve the identified methodological issues is proposed.
A general process for the semantic annotation and enrichment of electronic program guides
(Springer Verlag, 2019) Gonzalez Toral, Hernan Santiago; Espinoza Mejía, Jorge Mauricio; Palacio Baus, Kenneth Samuel; Saquicela Galarza, Víctor Hugo
Electronic Program Guides (EPGs) are usual resources aimed to inform the audience about the programming being transmitted by TV stations and cable/satellite TV providers. However, they only provide basic metadata about the TV programs, while users may want to obtain additional information related to the content they are currently watching. This paper proposes a general process for the semantic annotation and subsequent enrichment of EPGs using external knowledge bases and natural language processing techniques with the aim to tackle the lack of immediate availability of related information about TV programs. Additionally, we define an evaluation approach based on a distributed representation of words that can enable TV content providers to verify the effectiveness of the system and perform an automatic execution of the enrichment process. We test our proposal using a real-world dataset and demonstrate its effectiveness by using different knowledge bases, word representation models and similarity measures. Results showed that DBpedia and Google Knowledge Graph knowledge bases return the most relevant content during the enrichment process, while word2vec and fasttext models with Words Mover’s Distance as similarity function can be combined to validate the effectiveness of the retrieval task.
A holistic approach to supporting academic libraries in resource allocation processes
(University of Chicago Press, 2015-07-02) Sigüenza Guzmán, Lorena Catalina
E-content revolution, technological advances, and ever-shrinking budgets oblige libraries to efficiently allocate their limited resources between collection and services. Unfortunately, resource allocation is a complex process due to the diversity of data sources and formats required to be analyzed prior to decision making, as well as the lack of efficient methods of integration. The contribution of this article is twofold. We first propose an evaluation framework to holistically assess academic libraries. To do so, a four-pronged theoretical framework is used in which the library system and collection are analyzed from the perspective of users and internal stakeholders. Second, we present a data warehouse architecture that integrates, processes, and stores the holistically based collected data. By proposing this holistic approach, we aim to provide an integrated solution that assists library managers to make economic decisions based on a perspective of the library situation that is as realistic as possible.
A hybrid algorithm for supply chain optimization of assembly companies
(IEEE, 2019) Cevallos Tapia, Carlos Patricio; Sigüenza Guzmán, Lorena Catalina; Peña Ortega, Mario Patricio; Peña Ortega, Mario Patricio
A fundamental goal of any system is to get an optimal state. These optimal states can be found in different areas, such as medicine, engineering, or architecture. In the field of industrial engineering, one of its objectives is improving or optimizing company processes in order to increase benefits while reducing costs. In this context, an essential component is the supply chain, which is a network in that different entities, such as manufacturers, suppliers, distributors, retailers, transporters, and customers or end-users, are associated. Several optimization algorithms with different approaches have been developed to optimize the supply chain. Nevertheless, they still have problems to fulfill some requirements at once. This research aims to develop a hybrid optimization algorithm that leverages the capabilities of different approaches. This algorithm, which presents a multi-objective optimization schema, meets a tradeoff between the optimization results quality and the runtime. To this end, a manufacturing and assembly company is used as a case study to prove the algorithm. The results are also compared with other state-of-the-art algorithms using the same execution environment and general settings. Findings indicate that the hybrid algorithm converges in less time and in most cases, it could reach the global optimal.
A hybrid neural network based technique to improve the flow forecasting of physical and data driven models: methodology and case studies in andean watersheds
(2020) Farfan Duran, Juan Fernando; Ulloa, Jacinto; Avilés Añazco, Alex Manuel; Palacios Garate, Karina Fernanda
The present study was conducted in the Machángara Alto and Chulco rivers, which belong to the Paute basin in the provinces of Azuay and Cañar in southern Ecuador. Study focus: Andean watersheds are important providers of water supply for human consumption, food supply, energy generation, industrial water use, and ecosystem services and functions for many cities in Ecuador and in the rest of South America. In these regions, accurate quantification and prediction of water flow is challenging, mainly due to significant climatic variability and sparse monitoring networks. In the context of flow forecasting, this work evaluates the accuracy of two physical models (WEAP and GR2M) and two models based on artificial neural networks (ANN) that use meteorological data as input variables. Then, a hybrid technique is proposed, using the time series generated by the individual models as inputs of a new ANN. This approach aims to increase the accuracy of the simulated flow by combining and exploiting the information provided by physical and data-driven models. To assess the performance of the proposed methodology, statistical analyses are conducted for two case studies in the Andean region, where comparative analyses are performed for the individual models and the hybrid technique. New hydrological insights: The results indicate that the proposed technique is able to improve the individual performance of physical and ANN-based models, yielding good results in the calibration and validation stages for the two case studies. Specifically, increases in NSE were observed from 0.64 to 0.99 in the MachÁngara Alto river, and from 0.88 to 0.99 in the Chulco river. Higher accuracy of the hybrid technique was observed for all evaluation criteria considered in the analyses. The performance of the hybrid technique was also reflected in terms of water supply and demand, suggesting possible applications for the regional management of water resources, where accurate flow predictions are of utmost importance.

Browse

Browsing Publicaciones by Title