Toward sustainability and resilience in Chilean cities: Lessons and recommendations for air, water, and soil issues.

Achieving sustainability and resilience depends on the conciliation of environmental, social, and economic issues integrated into a long-term perspective to ensure communities flourish. Many nations are transitioning toward both objectives, while at the same time addressing structural concerns that have not allowed them to look after the environment in the past. Chile is one of these nations dealing with such challenges within a particular administrative context, an increasing environmental awareness, and a set of unique and complex geophysical boundaries that impose a plethora of hazards for cities, ecosystems, and human health. This paper presents recent accomplishments and gaps, mostly from an environmental perspective, on issues related to air pollution, the urban water cycle, and soil contamination, in the path being followed by Chile toward urban sustainability and resilience. The focus is on the bonds between cities and their geophysical context, as well as the relationships between environmental issues, the built environment, and public health. The description and diagnosis are illustrated using two cities as case studies, Temuco and Copiapó, whose socioeconomic, geographical, and environmental attributes differ considerably. Particulate matter pollution produced by the residential sector, drinking water availability, wastewater treatment, stormwater management, and soil contamination from the mining industry are discussed for these cities. Overall, the case studies highlight how tackling these issues requires coordinated actions in multiple areas, including regulatory, information, and financial incentive measures. Finally, the policy analysis discusses frameworks and opportunities for Chilean cities, which may be of interest when conceiving transitional paths toward sustainability and resilience for other cities elsewhere.

Attribute selection impact on linear and nonlinear regression models for crop yield prediction.

Efficient cropping requires yield estimation for each involved crop, where data-driven models are commonly applied. In recent years, some data-driven modeling technique comparisons have been made, looking for the best model to yield prediction. However, attributes are usually selected based on expertise assessment or in dimensionality reduction algorithms. A fairer comparison should include the best subset of features for each regression technique; an evaluation including several crops is preferred. This paper evaluates the most common data-driven modeling techniques applied to yield prediction, using a complete method to define the best attribute subset for each model. Multiple linear regression, stepwise linear regression, M5' regression trees, and artificial neural networks (ANN) were ranked. The models were built using real data of eight crops sowed in an irrigation module of Mexico. To validate the models, three accuracy metrics were used: the root relative square error (RRSE), relative mean absolute error (RMAE), and correlation factor (R). The results show that ANNs are more consistent in the best attribute subset composition between the learning and the training stages, obtaining the lowest average RRSE (86.04%), lowest average RMAE (8.75%), and the highest average correlation factor (0.63).