Enhancing environmental data imputation: A physically-constrained machine learning framework.

In water resources management, new computational capabilities have made it possible to develop integrated models to jointly analyze climatic conditions and water quantity/quality of the entire watershed system. Although the value of this integrated approach has been demonstrated so far, the limited availability of field data may hinder its applicability by causing high uncertainty in the model response. In this context, before collecting additional data, it is recommended first to recognize what improvement in model performance would occur if all available records could be well exploited. This work proposes a novel machine learning framework with physical constraints capable of successfully imputing a high percentage of missing data belonging to several environmental domains (meteorology, water quantity, water quality), yielding satisfactory results. In particular, the minimum NSE computed for meteorologic variables is 0.72. For hydrometric variables, NSE is always >0.97. More than 78 % of the physical-water-quality variables is characterized by NSE > 0.45, and >66 % of the chemical-water quality variables reaches NSE > 0.35. This work's results demonstrate the proposed framework's effectiveness as a data augmentation tool to improve the performance of integrated environmental modeling.

Managing Devices of a One-to-One Computing Educational Program Using an IoT Infrastructure.

Plan Ceibal is the name coined in Uruguay for the local implementation of the One Laptop Per Child (OLPC) initiative. Plan Ceibal distributes laptops and tablets to students and teachers, and also deploys a nationwide wireless network to provide Internet access to these devices, provides video conference facilities, and develops educational applications. Given the scale of the program, management in general, and specifically device management, is a very challenging task. Device maintenance and replacement is a particularly important process; users trigger such kind of replacement processes and usually imply several days without the device. Early detection of fault conditions in the most stressed hardware parts (e.g., batteries) would permit to prompt defensive replacement, contributing to reduce downtime, and improving the user experience. Seeking for better, preventive and scalable device management, in this paper we present a prototype of a Mobile Device Management (MDM) module for Plan Ceibal, developed over an IoT infrastructure, showing the results of a controlled experiment over a sample of the devices. The prototype is deployed over a public IoT infrastructure to speed up the development process, avoiding, in this phase, the need for local infrastructure and maintenance, while enforcing scalability and security requirements. The presented data analysis was implemented off-line and represents a sample of possible metrics which could be used to implement preventive management in a real deployment.