Abstract.Using numerical models which require large meteorological data sets is sometimes difficult and problems can often be traced back to the Input/Output functionality. Complex models are usually developed by the environmental sciences community with a focus on the core modelling issues. As a consequence, the I/O routines that are costly to properly implement are often error-prone, lacking flexibility and robustness. With the increasing use of such models in operational applications, this situation ceases to be simply uncomfortable and becomes a major issue.The MeteoIO library has been designed for the specific needs of numerical models that require meteorological data. The whole task of data preprocessing has been delegated to this library, namely retrieving, filtering and resampling the data if necessary as well as providing spatial interpolations and parameterizations. The focus has been to design an Application Programming Interface (API) that (i) provides a uniform interface to meteorological data in the models, (ii) hides the complexity of the processing taking place, and (iii) guarantees a robust behaviour in the case of format errors, erroneous or missing data. Moreover, in an operational context, this error handling should avoid unnecessary interruptions in the simulation process.A strong emphasis has been put on simplicity and modularity in order to make it extremely easy to support new data formats or protocols and to allow contributors with diverse backgrounds to participate. This library is also regularly evaluated for computing performance and further optimized where necessary. Finally, it is released under an Open Source license and is available at http://models.slf.ch/p/meteoio. This paper gives an overview of the MeteoIO library from the point of view of conceptual design, architecture, features and computational performance. A scientific evaluation of the produced results is not given here since the scientific algorithms that are used have already been published elsewhere.

No abstract

Abstract. Using numerical models which require large meteorological data sets is sometimes difficult and problems can often be traced back to the Input/Output functionality. Complex models are usually developed by the environmental sciences community with a focus on the core modelling issues. As a consequence, the I/O routines that are costly to properly implement are often error-prone, lacking flexibility and robustness. With the increasing use of such models in operational applications, this situation ceases to be simply uncomfortable and becomes a major issue. The MeteoIO library has been designed for the specific needs of numerical models that require meteorological data. The whole task of data preprocessing has been delegated to this library, namely retrieving, filtering and resampling the data if necessary as well as providing spatial interpolations and parametrizations. The focus has been to design an Application Programming Interface (API) that (i) provides a uniform interface to meteorological data in the models; (ii) hides the complexity of the processing taking place; and (iii) guarantees a robust behaviour in case of format errors, erroneous or missing data. Moreover, in an operational context, this error handling should avoid unnecessary interruptions in the simulation process. A strong emphasis has been put on simplicity and modularity in order to make it extremely easy to support new data formats or protocols and to allow contributors with diverse backgrounds to participate. This library can also be used in the context of High Performance Computing in a parallel environment. Finally, it is released under an Open Source license and is available at http://models.slf.ch/p/meteoio. This paper gives an overview of the MeteoIO library from the point of view of conceptual design, architecture, features and computational performance. A scientific evaluation of the produced results is not given here since the scientific algorithms that are used have already been published elsewhere.

Abstract. As numerical model developers, we have experienced first hand how most users struggle with the configuration of the models, leading to numerous support requests. Such issues are usually mitigated by offering a graphical user interface (GUI) that flattens the learning curve. Developing a GUI, however, requires a significant investment for the model developers, as well as a specific skill set. Moreover, this does not fit with the daily duties of model developers. As a consequence, when a GUI has been created – usually within a specific project and often relying on an intern – the maintenance either constitutes a major burden or is not performed. This also tends to limit the evolution of the numerical models themselves, since the model developers try to avoid having to change the GUI. In this paper we describe an approach based on an XML description of the required numerical model configuration elements (i.e., the data model of the configuration data) and a C++/Qt tool (Inishell) that populates a GUI based on this description on the fly. This makes the maintenance of the GUI very simple and enables users to easily get an up-to-date GUI for configuring the numerical model. The first version of this tool was written almost 10 years ago and showed that the concept works very well for our own surface process models. A full rewrite offering a more modern interface and extended capabilities is presented in this paper.

Abstract. As numerical model developers, we have experienced first hand how most users struggle with the configuration of the models, leading to numerous support requests. Such issues are usually mitigated by offering a Graphical User Interface (GUI) that flattens the learning curve. This requires however a significant investment for the model developer as well as a specific skill set. Moreover, this does not fit with the daily duties of model developers. As a consequence, when a GUI has been created, usually within a specific project and often relying on an intern, the maintenance either constitutes a major burden or is not performed. This also tends to limit the evolution of the numerical models themselves, since the model developers try to avoid having to change the GUI. In this paper we describe an approach based on an XML description of the required numerical model configuration elements and a C++/Qt tool (Inishell) that creates a GUI based on this description on the fly. This makes maintenance of the GUI very simple and enables users to easily get an up-to-date GUI for configuring the numerical model. The first version of this tool was written almost ten years ago and showed that the concept works very well for our own surface processes models. A full rewrite offering a more modern interface and extended capabilities is presented in this paper.