Forests suffer from heavy losses due to the occurrence of fires. A prediction model based on environmental condition, such as meteorological and vegetation indexes, is considered a promising tool to control forest fires. The construction of prediction models can be challenging due to (i) the requirement of selection of features most relevant to the prediction task, and (ii) heavily imbalanced data distribution where the number of large-scale forest fires is much less than that of small-scale ones. In this paper, we propose a forest fire prediction method that employs a sparse autoencoder-based deep neural network and a novel data balancing procedure. The method was tested on a forest fire dataset collected from the Montesinho Natural Park of Portugal. Compared to the best prediction results of other state-of-the-art methods, the proposed method could predict large-scale forest fires more accurately, and reduces the mean absolute error by 3–19.3 and root mean squared error by 0.95–19.3. The proposed method can better benefit the management of wildland fires in advance and the prevention of serious fire accidents. It is expected that the prediction performance could be further improved if additional information and more data are available.

Rapid urbanization causes the accumulation of large amounts of pollutants, including heavy metals, organic pollutants, and black carbon (BC). BC is the carbonaceous residue generated from the incomplete combustion of fossil fuels and biomass. It plays an important role on the migration of heavy metals and organic pollutants, as well as soil carbon sequestration. BC accumulation due to human activities greatly affects the global carbon budget, helps to drive climate change, and damages human health. To date, few studies have examined how the intensity of urbanization affects the distribution of BC in soils in urban areas. Therefore, the objective of this study is to determine the effects of urbanization intensity on the spatial distribution and content of BC in urban surface soil. We collected samples from 55 sites in South China and used a multi-scale geographical regression model to evaluate the impact of the interference intensity of urbanization on the amount and distribution of BC. Our results showed that the BC content was significantly higher in urban areas (9.74 ± 1.18 g kg⁻¹) than in rural areas (2.94 ± 0.89 g kg⁻¹) and that several urban parks with a higher interference intensity were hotspots of BC accumulation, suggesting that urbanization promoted BC accumulation. Our model revealed that road density was significantly and positively correlated with BC accumulation. Because there are more cars driving in areas with high road density, vehicle emissions may be one of the causes of BC accumulation. Our results also indicated that the impact of urbanization intensity on the BC distribution was sensitive to sampling density.

In order to effectively identify the shortcomings and potential health risks in the construction of healthy cities and achieve sustainable development, relevant improvement strategies have been formulated. According to the National Healthy City Evaluation Index System, with the concept of “Making improvements is more important than reaching standards”, the healthy city construction levels of the first batch of 13 cities in East China were evaluated by combining entropy weight and linear coefficient weighting from the five dimensions of environment, population, society, service, and culture, based on the data of statistical yearbooks, bulletins, and government websites. The results show that Suzhou, Jiading, Wuxi, Hangzhou, Ningbo, Tongxiang, and Zhenjiang are in the first-grade group, Xiamen, Yantai, Jinan, and Weihai are in the second-grade group, and Yichun and Ma’anshan are in the third-grade group. There is also more significant heterogeneity in the healthy environment indicator among the 13 cities; at the same time, there are specific differences in the healthy culture indicator, and there are slight differences in the indicators of healthy population, society, and service. The study reveals the gaps and problems in the construction of healthy cities. It proposes constructive ideas for promoting follow-up improvement of “making up for shortcomings and strengthening the weaknesses”.