RESUMO
COVID-19 pandemic has had a major impact on our society, environment and public health, in both positive and negative ways. The main aim of this study is to monitor the effect of COVID-19 pandemic lockdowns on urban cooling. To do so, satellite images of Landsat 8 for Milan and Rome in Italy, and Wuhan in China were used to look at pre-lockdown and during the lockdown. First, the surface biophysical characteristics for the pre-lockdown and within-lockdown dates of COVID-19 were calculated. Then, the land surface temperature (LST) retrieved from Landsat thermal data was normalized based on cold pixels LST and statistical parameters of normalized LST (NLST) were calculated. Thereafter, the correlation coefficient (r) between the NLST and index-based built-up index (IBI) was estimated. Finally, the surface urban heat island intensity (SUHII) of different cities on the lockdown and pre-lockdown periods was compared with each other. The mean NLST of built-up lands in Milan (from 7.71 °C to 2.32 °C), Rome (from 5.05 °C to 3.54 °C) and Wuhan (from 3.57 °C to 1.77 °C) decreased during the lockdown dates compared to pre-lockdown dates. The r (absolute value) between NLST and IBI for Milan, Rome and Wuhan decreased from 0.43, 0.41 and 0.16 in the pre-lockdown dates to 0.25, 0.24, and 0.12 during lockdown dates respectively, which shows a large decrease for all cities. Analysis of SUHI for these cities showed that SUHII during the lockdown dates compared to pre-lockdown dates decreased by 0.89 °C, 1.78 °C, and 1.07 °C respectively. The results indicated a high and substantial impact of anthropogenic activities and anthropogenic heat flux (AHF) on the SUHI due to the substantial reduction of huge anthropogenic pressure in cities. Our conclusions draw attention to the contribution of COVID-19 lockdowns (reducing the anthropogenic activities) to creating cooler cities.
RESUMO
The accuracy of land crop maps obtained from satellite images depends on the type of feature selection algorithm and classifier. Each of these algorithms have different efficiency in different conditions; therefore, developing a suitable strategy for combining the capabilities of different algorithms in preparing a land crop map with higher accuracy can be very useful. The objective of this study was to develop a fusion-based framework for improving land crop mapping accuracy. First, the features were retrieved using the Sentinel 1, Sentinel 2, and Landsat-8 imagery. Then, training data and various feature selection algorithms including recursive feature elimination (RFE), random forest (RF), and Boruta were used for optimal feature selection. Various classifiers, including artificial neural network (ANN), support vector machine (SVM), and RF, were implemented to create maps of land crops relying on optimal features and training data. After that, in order to increase the result accuracy, maps of land crops derived from several scenarios were fused using a fusion-based voting strategy at the level of decision, and new maps of land crops and classification uncertainty maps were prepared. Subsequently, the performance of different scenarios was evaluated and compared. Among the feature selection algorithms, RF accuracy was higher than RFE and Boruta. Moreover, the efficiency of RF was higher than SVM and ANN. The overall accuracy of the voting scenario was higher than all other scenarios. The finding of this research demonstrated that combining the features' capabilities extracted from sensors in different spectral ranges, different feature selection algorithms, and classifiers improved the land crop classification accuracy.
