Search

Environmental impacts analysis in urban areas is a fundamental task for society's development since support environmental preservation is a key to help society from its own disorderly land use and unplanned occupied areas that lead various urban environmental problems. The main strategy in Brazil for protecting and preserving the ecosystems remains in the adoption of some protected areas such as Permanent Preservation Areas (PPA). The objective of this study is to perform a temporal assessment of environmental law violations related to PPA interventions and spatially identify hot spots areas using data visualization techniques and geographical information systtem (GIS). The analysis of spatial-temporal patterns was based on field data registered by 17th department of civil police from Minas Gerais state. The spatial data were processed in the Quantum GIS (QGIS) software, including SpatiaLite database plugin for SQL query perform, and RStudio. A total of 2.839 environmental violations were reported between 2011 and 2019. A spatial positive autocorrelation was found in data, according to Moran's Test. Our temporal analysis indicated reduction of reported violations in 2012 with respect to 2011 from the three police-regionals studied. One possible reason for this is that new revisions to Brazil's Forest Code were adopted in this period, which may have law differentiates between conservation and restoration requirements related to PPAs areas. The lowest occurrence rate was found in 3rd regional of Itajubá, which reached up to 66% in 2018. Our findings indicated higher violation occurrence very close to the regional's headquarters. This demonstrated that environmental law violations have occurred in natural resource destination areas likely due to the urban expansion process since headquarter are located in urban and populated areas, as noted by G statistic and clusters analysis. We hope that the knowledge and spatial insights developed in this paper can support civil police actions and public preservation policies. [ABSTRACT FROM AUTHOR]

Solar radiation prediction is necessary for designing photovoltaic systems, assessment of regional climate and crop growth modeling. However, this estimate depends on expensive devices, namely pyranometer and pyranometer. Considering the difficulty of acquiring these devices, predicting such values through mathematical and computational models is a convenient approach where costs can be reduced. In particular, machine learning methods have been successfully and widely applied for this task. However, the choice of the correct machine learning model, its parameters sets, and the variables used influence obtained results. This work presents a methodology that optimizes the aforementioned points to efficiently predict solar radiation in the state of Minas Gerais, Brazil. Currently, no work presents a computational model for the entire state. For this, data from 51 cities in Minas Gerais are used, obtained by the automatic weather stations of the National Institute of Meteorology. Two machine learning models, Artificial Neural Network and Multivariate Adaptive Regression Spline, were optimized through a Simple Genetic Algorithm, and the results compared to those available in the literature. The best results were found at the Guanhães station, with R 2 of 0.867 and RMSE of 1.68 MJ m - 2 day - 1 , and at the Muriaé station, with R 2 of 0.864 and RMSE of 1.64 MJ m - 2 day - 1 . The models had their metrics compared to each other through the methodology of performance profiles, where the Multivariate Adaptive Regression Spline model proved to be more efficient. The results demonstrate that computational models perform better than the empirical models currently used. [ABSTRACT FROM AUTHOR]